Merging debian version 1.65.0+dfsg1-2.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

34 files changed, 7196 insertions, 443 deletions

diff --git a/library/stdarch/CONTRIBUTING.md b/library/stdarch/CONTRIBUTING.md
index ebccd73ea..4212abcd7 100644
--- a/library/stdarch/CONTRIBUTING.md
+++ b/library/stdarch/CONTRIBUTING.md
@@ -9,7 +9,7 @@ $ cd stdarch
 $ TARGET="<your-target-arch>" ci/run.sh
 ```
 
-Where `<your-target-arch>` is the target triple as used by `rustup`, e.g. `x86_x64-unknown-linux-gnu` (without any preceding `nightly-` or similar).
+Where `<your-target-arch>` is the target triple as used by `rustup`, e.g. `x86_64-unknown-linux-gnu` (without any preceding `nightly-` or similar).
 Also remember that this repository requires the nightly channel of Rust!
 The above tests do in fact require nightly rust to be the default on your system, to set that use `rustup default nightly` (and `rustup default stable` to revert).
 
diff --git a/library/stdarch/ci/docker/aarch64-unknown-linux-gnu/Dockerfile b/library/stdarch/ci/docker/aarch64-unknown-linux-gnu/Dockerfile
index 49464dacf..2f99999da 100644
--- a/library/stdarch/ci/docker/aarch64-unknown-linux-gnu/Dockerfile
+++ b/library/stdarch/ci/docker/aarch64-unknown-linux-gnu/Dockerfile
@@ -1,4 +1,4 @@
-FROM ubuntu:21.10
+FROM ubuntu:22.04
 RUN apt-get update && apt-get install -y --no-install-recommends \
   gcc \
   g++ \
diff --git a/library/stdarch/ci/docker/armv7-unknown-linux-gnueabihf/Dockerfile b/library/stdarch/ci/docker/armv7-unknown-linux-gnueabihf/Dockerfile
index 74181a4cb..b4cd0a68a 100644
--- a/library/stdarch/ci/docker/armv7-unknown-linux-gnueabihf/Dockerfile
+++ b/library/stdarch/ci/docker/armv7-unknown-linux-gnueabihf/Dockerfile
@@ -1,4 +1,4 @@
-FROM ubuntu:21.10
+FROM ubuntu:22.04
 RUN apt-get update && apt-get install -y --no-install-recommends \
   gcc \
   g++ \
diff --git a/library/stdarch/ci/docker/riscv64gc-unknown-linux-gnu/Dockerfile b/library/stdarch/ci/docker/riscv64gc-unknown-linux-gnu/Dockerfile
index 1618db22f..b9b3c682e 100644
--- a/library/stdarch/ci/docker/riscv64gc-unknown-linux-gnu/Dockerfile
+++ b/library/stdarch/ci/docker/riscv64gc-unknown-linux-gnu/Dockerfile
@@ -1,4 +1,4 @@
-FROM ubuntu:21.10
+FROM ubuntu:22.04
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
         gcc libc6-dev qemu-user ca-certificates \
diff --git a/library/stdarch/ci/dox.sh b/library/stdarch/ci/dox.sh
index e70a32b2d..3e507b456 100755
--- a/library/stdarch/ci/dox.sh
+++ b/library/stdarch/ci/dox.sh
@@ -22,9 +22,6 @@ dox() {
   rm -rf "target/doc/${arch}"
   mkdir "target/doc/${arch}"
 
-  export RUSTFLAGS="--cfg core_arch_docs"
-  export RUSTDOCFLAGS="--cfg core_arch_docs"
-
   cargo build --verbose --target "${target}" --manifest-path crates/core_arch/Cargo.toml
   cargo build --verbose --target "${target}" --manifest-path crates/std_detect/Cargo.toml
 
@@ -32,16 +29,14 @@ dox() {
           -o "target/doc/${arch}" crates/core_arch/src/lib.rs \
           --edition=2018 \
           --crate-name core_arch \
-          --library-path "target/${target}/debug/deps" \
-          --cfg core_arch_docs
+          --library-path "target/${target}/debug/deps"
   rustdoc --verbose --target "${target}" \
           -o "target/doc/${arch}" crates/std_detect/src/lib.rs \
           --edition=2018 \
           --crate-name std_detect \
           --library-path "target/${target}/debug/deps" \
           --extern cfg_if="$(ls target/"${target}"/debug/deps/libcfg_if-*.rlib)" \
-          --extern libc="$(ls target/"${target}"/debug/deps/liblibc-*.rlib)" \
-          --cfg core_arch_docs
+          --extern libc="$(ls target/"${target}"/debug/deps/liblibc-*.rlib)"
 }
 
 dox i686 i686-unknown-linux-gnu
diff --git a/library/stdarch/crates/core_arch/Cargo.toml b/library/stdarch/crates/core_arch/Cargo.toml
index 14b5479d1..e2b332af2 100644
--- a/library/stdarch/crates/core_arch/Cargo.toml
+++ b/library/stdarch/crates/core_arch/Cargo.toml
@@ -13,7 +13,6 @@ readme = "README.md"
 keywords = ["core", "simd", "arch", "intrinsics"]
 categories = ["hardware-support", "no-std"]
 license = "MIT OR Apache-2.0"
-build = "build.rs"
 edition = "2018"
 
 [badges]
diff --git a/library/stdarch/crates/core_arch/build.rs b/library/stdarch/crates/core_arch/build.rs
deleted file mode 100644
index 4d65e9ddc..000000000
--- a/library/stdarch/crates/core_arch/build.rs
+++ /dev/null
@@ -1,3 +0,0 @@
-fn main() {
-    println!("cargo:rustc-cfg=core_arch_docs");
-}
diff --git a/library/stdarch/crates/core_arch/src/aarch64/crc.rs b/library/stdarch/crates/core_arch/src/aarch64/crc.rs
index 6e8128534..ac3f8d815 100644
--- a/library/stdarch/crates/core_arch/src/aarch64/crc.rs
+++ b/library/stdarch/crates/core_arch/src/aarch64/crc.rs
@@ -10,6 +10,8 @@ extern "unadjusted" {
 use stdarch_test::assert_instr;
 
 /// CRC32 single round checksum for quad words (64 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32d)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(test, assert_instr(crc32x))]
@@ -18,6 +20,8 @@ pub unsafe fn __crc32d(crc: u32, data: u64) -> u32 {
 }
 
 /// CRC32-C single round checksum for quad words (64 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32cd)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(test, assert_instr(crc32cx))]
diff --git a/library/stdarch/crates/core_arch/src/aarch64/neon/generated.rs b/library/stdarch/crates/core_arch/src/aarch64/neon/generated.rs
index 74ea2963c..ac05a0c23 100644
--- a/library/stdarch/crates/core_arch/src/aarch64/neon/generated.rs
+++ b/library/stdarch/crates/core_arch/src/aarch64/neon/generated.rs
@@ -10,6 +10,8 @@ use super::*;
 use stdarch_test::assert_instr;
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_s8)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -23,6 +25,8 @@ pub unsafe fn veor3q_s8(a: int8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
 }
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_s16)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -36,6 +40,8 @@ pub unsafe fn veor3q_s16(a: int16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t
 }
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_s32)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -49,6 +55,8 @@ pub unsafe fn veor3q_s32(a: int32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t
 }
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_s64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -62,6 +70,8 @@ pub unsafe fn veor3q_s64(a: int64x2_t, b: int64x2_t, c: int64x2_t) -> int64x2_t
 }
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_u8)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -75,6 +85,8 @@ pub unsafe fn veor3q_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16
 }
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_u16)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -88,6 +100,8 @@ pub unsafe fn veor3q_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x
 }
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_u32)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -101,6 +115,8 @@ pub unsafe fn veor3q_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x
 }
 
 /// Three-way exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor3q_u64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(eor3))]
@@ -114,6 +130,8 @@ pub unsafe fn veor3q_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> uint64x
 }
 
 /// Absolute difference between the arguments of Floating
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fabd))]
@@ -128,6 +146,8 @@ pub unsafe fn vabd_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Absolute difference between the arguments of Floating
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fabd))]
@@ -142,6 +162,8 @@ pub unsafe fn vabdq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point absolute difference
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabds_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fabd))]
@@ -151,6 +173,8 @@ pub unsafe fn vabds_f32(a: f32, b: f32) -> f32 {
 }
 
 /// Floating-point absolute difference
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fabd))]
@@ -160,6 +184,8 @@ pub unsafe fn vabdd_f64(a: f64, b: f64) -> f64 {
 }
 
 /// Unsigned Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uabdl))]
@@ -171,6 +197,8 @@ pub unsafe fn vabdl_high_u8(a: uint8x16_t, b: uint8x16_t) -> uint16x8_t {
 }
 
 /// Unsigned Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uabdl))]
@@ -182,6 +210,8 @@ pub unsafe fn vabdl_high_u16(a: uint16x8_t, b: uint16x8_t) -> uint32x4_t {
 }
 
 /// Unsigned Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uabdl))]
@@ -193,6 +223,8 @@ pub unsafe fn vabdl_high_u32(a: uint32x4_t, b: uint32x4_t) -> uint64x2_t {
 }
 
 /// Signed Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sabdl))]
@@ -205,6 +237,8 @@ pub unsafe fn vabdl_high_s8(a: int8x16_t, b: int8x16_t) -> int16x8_t {
 }
 
 /// Signed Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sabdl))]
@@ -217,6 +251,8 @@ pub unsafe fn vabdl_high_s16(a: int16x8_t, b: int16x8_t) -> int32x4_t {
 }
 
 /// Signed Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sabdl))]
@@ -229,6 +265,8 @@ pub unsafe fn vabdl_high_s32(a: int32x4_t, b: int32x4_t) -> int64x2_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -238,6 +276,8 @@ pub unsafe fn vceq_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -247,6 +287,8 @@ pub unsafe fn vceqq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -256,6 +298,8 @@ pub unsafe fn vceq_s64(a: int64x1_t, b: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -265,6 +309,8 @@ pub unsafe fn vceqq_s64(a: int64x2_t, b: int64x2_t) -> uint64x2_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -274,6 +320,8 @@ pub unsafe fn vceq_p64(a: poly64x1_t, b: poly64x1_t) -> uint64x1_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -283,6 +331,8 @@ pub unsafe fn vceqq_p64(a: poly64x2_t, b: poly64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmeq))]
@@ -292,6 +342,8 @@ pub unsafe fn vceq_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmeq))]
@@ -301,6 +353,8 @@ pub unsafe fn vceqq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare bitwise equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -310,6 +364,8 @@ pub unsafe fn vceqd_s64(a: i64, b: i64) -> u64 {
 }
 
 /// Compare bitwise equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -319,6 +375,8 @@ pub unsafe fn vceqd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Floating-point compare equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -328,6 +386,8 @@ pub unsafe fn vceqs_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point compare equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -337,6 +397,8 @@ pub unsafe fn vceqd_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -347,6 +409,8 @@ pub unsafe fn vceqz_s8(a: int8x8_t) -> uint8x8_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -357,6 +421,8 @@ pub unsafe fn vceqzq_s8(a: int8x16_t) -> uint8x16_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -367,6 +433,8 @@ pub unsafe fn vceqz_s16(a: int16x4_t) -> uint16x4_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -377,6 +445,8 @@ pub unsafe fn vceqzq_s16(a: int16x8_t) -> uint16x8_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -387,6 +457,8 @@ pub unsafe fn vceqz_s32(a: int32x2_t) -> uint32x2_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -397,6 +469,8 @@ pub unsafe fn vceqzq_s32(a: int32x4_t) -> uint32x4_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -407,6 +481,8 @@ pub unsafe fn vceqz_s64(a: int64x1_t) -> uint64x1_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -417,6 +493,8 @@ pub unsafe fn vceqzq_s64(a: int64x2_t) -> uint64x2_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -427,6 +505,8 @@ pub unsafe fn vceqz_p8(a: poly8x8_t) -> uint8x8_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -437,6 +517,8 @@ pub unsafe fn vceqzq_p8(a: poly8x16_t) -> uint8x16_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -447,6 +529,8 @@ pub unsafe fn vceqz_p64(a: poly64x1_t) -> uint64x1_t {
 }
 
 /// Signed compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -457,6 +541,8 @@ pub unsafe fn vceqzq_p64(a: poly64x2_t) -> uint64x2_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -467,6 +553,8 @@ pub unsafe fn vceqz_u8(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -477,6 +565,8 @@ pub unsafe fn vceqzq_u8(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -487,6 +577,8 @@ pub unsafe fn vceqz_u16(a: uint16x4_t) -> uint16x4_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -497,6 +589,8 @@ pub unsafe fn vceqzq_u16(a: uint16x8_t) -> uint16x8_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -507,6 +601,8 @@ pub unsafe fn vceqz_u32(a: uint32x2_t) -> uint32x2_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -517,6 +613,8 @@ pub unsafe fn vceqzq_u32(a: uint32x4_t) -> uint32x4_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -527,6 +625,8 @@ pub unsafe fn vceqz_u64(a: uint64x1_t) -> uint64x1_t {
 }
 
 /// Unsigned compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmeq))]
@@ -537,6 +637,8 @@ pub unsafe fn vceqzq_u64(a: uint64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmeq))]
@@ -547,6 +649,8 @@ pub unsafe fn vceqz_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmeq))]
@@ -557,6 +661,8 @@ pub unsafe fn vceqzq_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqz_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmeq))]
@@ -567,6 +673,8 @@ pub unsafe fn vceqz_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmeq))]
@@ -577,6 +685,8 @@ pub unsafe fn vceqzq_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -586,6 +696,8 @@ pub unsafe fn vceqzd_s64(a: i64) -> u64 {
 }
 
 /// Compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -595,6 +707,8 @@ pub unsafe fn vceqzd_u64(a: u64) -> u64 {
 }
 
 /// Floating-point compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -604,6 +718,8 @@ pub unsafe fn vceqzs_f32(a: f32) -> u32 {
 }
 
 /// Floating-point compare bitwise equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqzd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -613,6 +729,8 @@ pub unsafe fn vceqzd_f64(a: f64) -> u64 {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmtst))]
@@ -624,6 +742,8 @@ pub unsafe fn vtst_s64(a: int64x1_t, b: int64x1_t) -> uint64x1_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmtst))]
@@ -635,6 +755,8 @@ pub unsafe fn vtstq_s64(a: int64x2_t, b: int64x2_t) -> uint64x2_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmtst))]
@@ -646,6 +768,8 @@ pub unsafe fn vtst_p64(a: poly64x1_t, b: poly64x1_t) -> uint64x1_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmtst))]
@@ -657,6 +781,8 @@ pub unsafe fn vtstq_p64(a: poly64x2_t, b: poly64x2_t) -> uint64x2_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmtst))]
@@ -668,6 +794,8 @@ pub unsafe fn vtst_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmtst))]
@@ -679,6 +807,8 @@ pub unsafe fn vtstq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Compare bitwise test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(tst))]
@@ -688,6 +818,8 @@ pub unsafe fn vtstd_s64(a: i64, b: i64) -> u64 {
 }
 
 /// Compare bitwise test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(tst))]
@@ -697,6 +829,8 @@ pub unsafe fn vtstd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Signed saturating accumulate of unsigned value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuqadds_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(suqadd))]
@@ -711,6 +845,8 @@ pub unsafe fn vuqadds_s32(a: i32, b: u32) -> i32 {
 }
 
 /// Signed saturating accumulate of unsigned value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuqaddd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(suqadd))]
@@ -725,6 +861,8 @@ pub unsafe fn vuqaddd_s64(a: i64, b: u64) -> i64 {
 }
 
 /// Signed saturating accumulate of unsigned value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuqaddb_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(suqadd))]
@@ -734,6 +872,8 @@ pub unsafe fn vuqaddb_s8(a: i8, b: u8) -> i8 {
 }
 
 /// Signed saturating accumulate of unsigned value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuqaddh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(suqadd))]
@@ -743,6 +883,8 @@ pub unsafe fn vuqaddh_s16(a: i16, b: u16) -> i16 {
 }
 
 /// Floating-point absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabs_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fabs))]
@@ -752,6 +894,8 @@ pub unsafe fn vabs_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabsq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fabs))]
@@ -761,6 +905,8 @@ pub unsafe fn vabsq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -770,6 +916,8 @@ pub unsafe fn vcgt_s64(a: int64x1_t, b: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -779,6 +927,8 @@ pub unsafe fn vcgtq_s64(a: int64x2_t, b: int64x2_t) -> uint64x2_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhi))]
@@ -788,6 +938,8 @@ pub unsafe fn vcgt_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhi))]
@@ -797,6 +949,8 @@ pub unsafe fn vcgtq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -806,6 +960,8 @@ pub unsafe fn vcgt_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -815,6 +971,8 @@ pub unsafe fn vcgtq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -824,6 +982,8 @@ pub unsafe fn vcgtd_s64(a: i64, b: i64) -> u64 {
 }
 
 /// Compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -833,6 +993,8 @@ pub unsafe fn vcgtd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Floating-point compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgts_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -842,6 +1004,8 @@ pub unsafe fn vcgts_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -851,6 +1015,8 @@ pub unsafe fn vcgtd_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -860,6 +1026,8 @@ pub unsafe fn vclt_s64(a: int64x1_t, b: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -869,6 +1037,8 @@ pub unsafe fn vcltq_s64(a: int64x2_t, b: int64x2_t) -> uint64x2_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhi))]
@@ -878,6 +1048,8 @@ pub unsafe fn vclt_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhi))]
@@ -887,6 +1059,8 @@ pub unsafe fn vcltq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -896,6 +1070,8 @@ pub unsafe fn vclt_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -905,6 +1081,8 @@ pub unsafe fn vcltq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -914,6 +1092,8 @@ pub unsafe fn vcltd_s64(a: i64, b: i64) -> u64 {
 }
 
 /// Compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -923,6 +1103,8 @@ pub unsafe fn vcltd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Floating-point compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclts_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -932,6 +1114,8 @@ pub unsafe fn vclts_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -941,6 +1125,8 @@ pub unsafe fn vcltd_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -950,6 +1136,8 @@ pub unsafe fn vcle_s64(a: int64x1_t, b: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -959,6 +1147,8 @@ pub unsafe fn vcleq_s64(a: int64x2_t, b: int64x2_t) -> uint64x2_t {
 }
 
 /// Compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcged_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -968,6 +1158,8 @@ pub unsafe fn vcged_s64(a: i64, b: i64) -> u64 {
 }
 
 /// Compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcged_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -977,6 +1169,8 @@ pub unsafe fn vcged_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Floating-point compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcges_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -986,6 +1180,8 @@ pub unsafe fn vcges_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcged_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -995,6 +1191,8 @@ pub unsafe fn vcged_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhs))]
@@ -1004,6 +1202,8 @@ pub unsafe fn vcle_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhs))]
@@ -1013,6 +1213,8 @@ pub unsafe fn vcleq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1022,6 +1224,8 @@ pub unsafe fn vcle_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1031,6 +1235,8 @@ pub unsafe fn vcleq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcled_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -1040,6 +1246,8 @@ pub unsafe fn vcled_s64(a: i64, b: i64) -> u64 {
 }
 
 /// Compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcled_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -1049,6 +1257,8 @@ pub unsafe fn vcled_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Floating-point compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcles_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1058,6 +1268,8 @@ pub unsafe fn vcles_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcled_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1067,6 +1279,8 @@ pub unsafe fn vcled_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1076,6 +1290,8 @@ pub unsafe fn vcge_s64(a: int64x1_t, b: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1085,6 +1301,8 @@ pub unsafe fn vcgeq_s64(a: int64x2_t, b: int64x2_t) -> uint64x2_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhs))]
@@ -1094,6 +1312,8 @@ pub unsafe fn vcge_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmhs))]
@@ -1103,6 +1323,8 @@ pub unsafe fn vcgeq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1112,6 +1334,8 @@ pub unsafe fn vcge_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1121,6 +1345,8 @@ pub unsafe fn vcgeq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgez_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1131,6 +1357,8 @@ pub unsafe fn vcgez_s8(a: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1141,6 +1369,8 @@ pub unsafe fn vcgezq_s8(a: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgez_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1151,6 +1381,8 @@ pub unsafe fn vcgez_s16(a: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1161,6 +1393,8 @@ pub unsafe fn vcgezq_s16(a: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgez_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1171,6 +1405,8 @@ pub unsafe fn vcgez_s32(a: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1181,6 +1417,8 @@ pub unsafe fn vcgezq_s32(a: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgez_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1191,6 +1429,8 @@ pub unsafe fn vcgez_s64(a: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmge))]
@@ -1201,6 +1441,8 @@ pub unsafe fn vcgezq_s64(a: int64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgez_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1211,6 +1453,8 @@ pub unsafe fn vcgez_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1221,6 +1465,8 @@ pub unsafe fn vcgezq_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgez_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1231,6 +1477,8 @@ pub unsafe fn vcgez_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmge))]
@@ -1241,6 +1489,8 @@ pub unsafe fn vcgezq_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare signed greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(eor))]
@@ -1250,6 +1500,8 @@ pub unsafe fn vcgezd_s64(a: i64) -> u64 {
 }
 
 /// Floating-point compare greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1259,6 +1511,8 @@ pub unsafe fn vcgezs_f32(a: f32) -> u32 {
 }
 
 /// Floating-point compare greater than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgezd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1268,6 +1522,8 @@ pub unsafe fn vcgezd_f64(a: f64) -> u64 {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtz_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1278,6 +1534,8 @@ pub unsafe fn vcgtz_s8(a: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1288,6 +1546,8 @@ pub unsafe fn vcgtzq_s8(a: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtz_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1298,6 +1558,8 @@ pub unsafe fn vcgtz_s16(a: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1308,6 +1570,8 @@ pub unsafe fn vcgtzq_s16(a: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtz_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1318,6 +1582,8 @@ pub unsafe fn vcgtz_s32(a: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1328,6 +1594,8 @@ pub unsafe fn vcgtzq_s32(a: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtz_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1338,6 +1606,8 @@ pub unsafe fn vcgtz_s64(a: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1348,6 +1618,8 @@ pub unsafe fn vcgtzq_s64(a: int64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtz_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -1358,6 +1630,8 @@ pub unsafe fn vcgtz_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -1368,6 +1642,8 @@ pub unsafe fn vcgtzq_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtz_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -1378,6 +1654,8 @@ pub unsafe fn vcgtz_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmgt))]
@@ -1388,6 +1666,8 @@ pub unsafe fn vcgtzq_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare signed greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -1397,6 +1677,8 @@ pub unsafe fn vcgtzd_s64(a: i64) -> u64 {
 }
 
 /// Floating-point compare greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1406,6 +1688,8 @@ pub unsafe fn vcgtzs_f32(a: f32) -> u32 {
 }
 
 /// Floating-point compare greater than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtzd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1415,6 +1699,8 @@ pub unsafe fn vcgtzd_f64(a: f64) -> u64 {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclez_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1425,6 +1711,8 @@ pub unsafe fn vclez_s8(a: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1435,6 +1723,8 @@ pub unsafe fn vclezq_s8(a: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclez_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1445,6 +1735,8 @@ pub unsafe fn vclez_s16(a: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1455,6 +1747,8 @@ pub unsafe fn vclezq_s16(a: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclez_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1465,6 +1759,8 @@ pub unsafe fn vclez_s32(a: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1475,6 +1771,8 @@ pub unsafe fn vclezq_s32(a: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclez_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1485,6 +1783,8 @@ pub unsafe fn vclez_s64(a: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmgt))]
@@ -1495,6 +1795,8 @@ pub unsafe fn vclezq_s64(a: int64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclez_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmle))]
@@ -1505,6 +1807,8 @@ pub unsafe fn vclez_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmle))]
@@ -1515,6 +1819,8 @@ pub unsafe fn vclezq_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclez_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmle))]
@@ -1525,6 +1831,8 @@ pub unsafe fn vclez_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmle))]
@@ -1535,6 +1843,8 @@ pub unsafe fn vclezq_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmp))]
@@ -1544,6 +1854,8 @@ pub unsafe fn vclezd_s64(a: i64) -> u64 {
 }
 
 /// Floating-point compare less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1553,6 +1865,8 @@ pub unsafe fn vclezs_f32(a: f32) -> u32 {
 }
 
 /// Floating-point compare less than or equal to zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclezd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1562,6 +1876,8 @@ pub unsafe fn vclezd_f64(a: f64) -> u64 {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltz_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1572,6 +1888,8 @@ pub unsafe fn vcltz_s8(a: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1582,6 +1900,8 @@ pub unsafe fn vcltzq_s8(a: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltz_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1592,6 +1912,8 @@ pub unsafe fn vcltz_s16(a: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1602,6 +1924,8 @@ pub unsafe fn vcltzq_s16(a: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltz_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1612,6 +1936,8 @@ pub unsafe fn vcltz_s32(a: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1622,6 +1948,8 @@ pub unsafe fn vcltzq_s32(a: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltz_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1632,6 +1960,8 @@ pub unsafe fn vcltz_s64(a: int64x1_t) -> uint64x1_t {
 }
 
 /// Compare signed less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(cmlt))]
@@ -1642,6 +1972,8 @@ pub unsafe fn vcltzq_s64(a: int64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point compare less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltz_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmlt))]
@@ -1652,6 +1984,8 @@ pub unsafe fn vcltz_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmlt))]
@@ -1662,6 +1996,8 @@ pub unsafe fn vcltzq_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltz_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmlt))]
@@ -1672,6 +2008,8 @@ pub unsafe fn vcltz_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point compare less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmlt))]
@@ -1682,6 +2020,8 @@ pub unsafe fn vcltzq_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Compare less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(asr))]
@@ -1691,6 +2031,8 @@ pub unsafe fn vcltzd_s64(a: i64) -> u64 {
 }
 
 /// Floating-point compare less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1700,6 +2042,8 @@ pub unsafe fn vcltzs_f32(a: f32) -> u32 {
 }
 
 /// Floating-point compare less than zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltzd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcmp))]
@@ -1709,6 +2053,8 @@ pub unsafe fn vcltzd_f64(a: f64) -> u64 {
 }
 
 /// Floating-point absolute compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcagt_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1723,6 +2069,8 @@ pub unsafe fn vcagt_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point absolute compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcagtq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1737,6 +2085,8 @@ pub unsafe fn vcagtq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point absolute compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcagts_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1751,6 +2101,8 @@ pub unsafe fn vcagts_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point absolute compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcagtd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1765,6 +2117,8 @@ pub unsafe fn vcagtd_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Floating-point absolute compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcage_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1779,6 +2133,8 @@ pub unsafe fn vcage_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point absolute compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcageq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1793,6 +2149,8 @@ pub unsafe fn vcageq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point absolute compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcages_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1807,6 +2165,8 @@ pub unsafe fn vcages_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point absolute compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaged_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1821,6 +2181,8 @@ pub unsafe fn vcaged_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Floating-point absolute compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcalt_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1830,6 +2192,8 @@ pub unsafe fn vcalt_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point absolute compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaltq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1839,6 +2203,8 @@ pub unsafe fn vcaltq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point absolute compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcalts_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1848,6 +2214,8 @@ pub unsafe fn vcalts_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point absolute compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaltd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facgt))]
@@ -1857,6 +2225,8 @@ pub unsafe fn vcaltd_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Floating-point absolute compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcale_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1866,6 +2236,8 @@ pub unsafe fn vcale_f64(a: float64x1_t, b: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point absolute compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaleq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1875,6 +2247,8 @@ pub unsafe fn vcaleq_f64(a: float64x2_t, b: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point absolute compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcales_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1884,6 +2258,8 @@ pub unsafe fn vcales_f32(a: f32, b: f32) -> u32 {
 }
 
 /// Floating-point absolute compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaled_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(facge))]
@@ -1893,6 +2269,8 @@ pub unsafe fn vcaled_f64(a: f64, b: f64) -> u64 {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -1915,6 +2293,8 @@ pub unsafe fn vcopy_lane_s8<const LANE1: i32, const LANE2: i32>(a: int8x8_t, b:
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -1945,6 +2325,8 @@ pub unsafe fn vcopyq_laneq_s8<const LANE1: i32, const LANE2: i32>(a: int8x16_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -1963,6 +2345,8 @@ pub unsafe fn vcopy_lane_s16<const LANE1: i32, const LANE2: i32>(a: int16x4_t, b
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -1985,6 +2369,8 @@ pub unsafe fn vcopyq_laneq_s16<const LANE1: i32, const LANE2: i32>(a: int16x8_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2001,6 +2387,8 @@ pub unsafe fn vcopy_lane_s32<const LANE1: i32, const LANE2: i32>(a: int32x2_t, b
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2019,6 +2407,8 @@ pub unsafe fn vcopyq_laneq_s32<const LANE1: i32, const LANE2: i32>(a: int32x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2035,6 +2425,8 @@ pub unsafe fn vcopyq_laneq_s64<const LANE1: i32, const LANE2: i32>(a: int64x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2057,6 +2449,8 @@ pub unsafe fn vcopy_lane_u8<const LANE1: i32, const LANE2: i32>(a: uint8x8_t, b:
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2087,6 +2481,8 @@ pub unsafe fn vcopyq_laneq_u8<const LANE1: i32, const LANE2: i32>(a: uint8x16_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2105,6 +2501,8 @@ pub unsafe fn vcopy_lane_u16<const LANE1: i32, const LANE2: i32>(a: uint16x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2127,6 +2525,8 @@ pub unsafe fn vcopyq_laneq_u16<const LANE1: i32, const LANE2: i32>(a: uint16x8_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2143,6 +2543,8 @@ pub unsafe fn vcopy_lane_u32<const LANE1: i32, const LANE2: i32>(a: uint32x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2161,6 +2563,8 @@ pub unsafe fn vcopyq_laneq_u32<const LANE1: i32, const LANE2: i32>(a: uint32x4_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2177,6 +2581,8 @@ pub unsafe fn vcopyq_laneq_u64<const LANE1: i32, const LANE2: i32>(a: uint64x2_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2199,6 +2605,8 @@ pub unsafe fn vcopy_lane_p8<const LANE1: i32, const LANE2: i32>(a: poly8x8_t, b:
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2229,6 +2637,8 @@ pub unsafe fn vcopyq_laneq_p8<const LANE1: i32, const LANE2: i32>(a: poly8x16_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2247,6 +2657,8 @@ pub unsafe fn vcopy_lane_p16<const LANE1: i32, const LANE2: i32>(a: poly16x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2269,6 +2681,8 @@ pub unsafe fn vcopyq_laneq_p16<const LANE1: i32, const LANE2: i32>(a: poly16x8_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2285,6 +2699,8 @@ pub unsafe fn vcopyq_laneq_p64<const LANE1: i32, const LANE2: i32>(a: poly64x2_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2301,6 +2717,8 @@ pub unsafe fn vcopy_lane_f32<const LANE1: i32, const LANE2: i32>(a: float32x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2319,6 +2737,8 @@ pub unsafe fn vcopyq_laneq_f32<const LANE1: i32, const LANE2: i32>(a: float32x4_
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2335,6 +2755,8 @@ pub unsafe fn vcopyq_laneq_f64<const LANE1: i32, const LANE2: i32>(a: float64x2_
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2358,6 +2780,8 @@ pub unsafe fn vcopy_laneq_s8<const LANE1: i32, const LANE2: i32>(a: int8x8_t, b:
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2377,6 +2801,8 @@ pub unsafe fn vcopy_laneq_s16<const LANE1: i32, const LANE2: i32>(a: int16x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2394,6 +2820,8 @@ pub unsafe fn vcopy_laneq_s32<const LANE1: i32, const LANE2: i32>(a: int32x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2417,6 +2845,8 @@ pub unsafe fn vcopy_laneq_u8<const LANE1: i32, const LANE2: i32>(a: uint8x8_t, b
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2436,6 +2866,8 @@ pub unsafe fn vcopy_laneq_u16<const LANE1: i32, const LANE2: i32>(a: uint16x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2453,6 +2885,8 @@ pub unsafe fn vcopy_laneq_u32<const LANE1: i32, const LANE2: i32>(a: uint32x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2476,6 +2910,8 @@ pub unsafe fn vcopy_laneq_p8<const LANE1: i32, const LANE2: i32>(a: poly8x8_t, b
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2495,6 +2931,8 @@ pub unsafe fn vcopy_laneq_p16<const LANE1: i32, const LANE2: i32>(a: poly16x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopy_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2512,6 +2950,8 @@ pub unsafe fn vcopy_laneq_f32<const LANE1: i32, const LANE2: i32>(a: float32x2_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2543,6 +2983,8 @@ pub unsafe fn vcopyq_lane_s8<const LANE1: i32, const LANE2: i32>(a: int8x16_t, b
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2566,6 +3008,8 @@ pub unsafe fn vcopyq_lane_s16<const LANE1: i32, const LANE2: i32>(a: int16x8_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2585,6 +3029,8 @@ pub unsafe fn vcopyq_lane_s32<const LANE1: i32, const LANE2: i32>(a: int32x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2616,6 +3062,8 @@ pub unsafe fn vcopyq_lane_u8<const LANE1: i32, const LANE2: i32>(a: uint8x16_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2639,6 +3087,8 @@ pub unsafe fn vcopyq_lane_u16<const LANE1: i32, const LANE2: i32>(a: uint16x8_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2658,6 +3108,8 @@ pub unsafe fn vcopyq_lane_u32<const LANE1: i32, const LANE2: i32>(a: uint32x4_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2689,6 +3141,8 @@ pub unsafe fn vcopyq_lane_p8<const LANE1: i32, const LANE2: i32>(a: poly8x16_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 0, LANE2 = 1))]
@@ -2712,6 +3166,8 @@ pub unsafe fn vcopyq_lane_p16<const LANE1: i32, const LANE2: i32>(a: poly16x8_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 1, LANE2 = 0))]
@@ -2729,6 +3185,8 @@ pub unsafe fn vcopyq_lane_s64<const LANE1: i32, const LANE2: i32>(a: int64x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 1, LANE2 = 0))]
@@ -2746,6 +3204,8 @@ pub unsafe fn vcopyq_lane_u64<const LANE1: i32, const LANE2: i32>(a: uint64x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 1, LANE2 = 0))]
@@ -2763,6 +3223,8 @@ pub unsafe fn vcopyq_lane_p64<const LANE1: i32, const LANE2: i32>(a: poly64x2_t,
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 1, LANE2 = 0))]
@@ -2782,6 +3244,8 @@ pub unsafe fn vcopyq_lane_f32<const LANE1: i32, const LANE2: i32>(a: float32x4_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcopyq_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(mov, LANE1 = 1, LANE2 = 0))]
@@ -2799,6 +3263,8 @@ pub unsafe fn vcopyq_lane_f64<const LANE1: i32, const LANE2: i32>(a: float64x2_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -2808,6 +3274,8 @@ pub unsafe fn vcreate_f64(a: u64) -> float64x1_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf))]
@@ -2817,6 +3285,8 @@ pub unsafe fn vcvt_f64_s64(a: int64x1_t) -> float64x1_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf))]
@@ -2826,6 +3296,8 @@ pub unsafe fn vcvtq_f64_s64(a: int64x2_t) -> float64x2_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf))]
@@ -2835,6 +3307,8 @@ pub unsafe fn vcvt_f64_u64(a: uint64x1_t) -> float64x1_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf))]
@@ -2844,6 +3318,8 @@ pub unsafe fn vcvtq_f64_u64(a: uint64x2_t) -> float64x2_t {
 }
 
 /// Floating-point convert to higher precision long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_f64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtl))]
@@ -2853,6 +3329,8 @@ pub unsafe fn vcvt_f64_f32(a: float32x2_t) -> float64x2_t {
 }
 
 /// Floating-point convert to higher precision long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_high_f64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtl))]
@@ -2863,6 +3341,8 @@ pub unsafe fn vcvt_high_f64_f32(a: float32x4_t) -> float64x2_t {
 }
 
 /// Floating-point convert to lower precision narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_f32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtn))]
@@ -2872,6 +3352,8 @@ pub unsafe fn vcvt_f32_f64(a: float64x2_t) -> float32x2_t {
 }
 
 /// Floating-point convert to lower precision narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_high_f32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtn))]
@@ -2881,6 +3363,8 @@ pub unsafe fn vcvt_high_f32_f64(a: float32x2_t, b: float64x2_t) -> float32x4_t {
 }
 
 /// Floating-point convert to lower precision narrow, rounding to odd
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtx_f32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtxn))]
@@ -2895,6 +3379,8 @@ pub unsafe fn vcvtx_f32_f64(a: float64x2_t) -> float32x2_t {
 }
 
 /// Floating-point convert to lower precision narrow, rounding to odd
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtxd_f32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtxn))]
@@ -2904,6 +3390,8 @@ pub unsafe fn vcvtxd_f32_f64(a: f64) -> f32 {
 }
 
 /// Floating-point convert to lower precision narrow, rounding to odd
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtx_high_f32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtxn))]
@@ -2913,6 +3401,8 @@ pub unsafe fn vcvtx_high_f32_f64(a: float32x2_t, b: float64x2_t) -> float32x4_t
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf, N = 2))]
@@ -2929,6 +3419,8 @@ pub unsafe fn vcvt_n_f64_s64<const N: i32>(a: int64x1_t) -> float64x1_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf, N = 2))]
@@ -2945,6 +3437,8 @@ pub unsafe fn vcvtq_n_f64_s64<const N: i32>(a: int64x2_t) -> float64x2_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_n_f32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf, N = 2))]
@@ -2961,6 +3455,8 @@ pub unsafe fn vcvts_n_f32_s32<const N: i32>(a: i32) -> f32 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_n_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf, N = 2))]
@@ -2977,6 +3473,8 @@ pub unsafe fn vcvtd_n_f64_s64<const N: i32>(a: i64) -> f64 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf, N = 2))]
@@ -2993,6 +3491,8 @@ pub unsafe fn vcvt_n_f64_u64<const N: i32>(a: uint64x1_t) -> float64x1_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf, N = 2))]
@@ -3009,6 +3509,8 @@ pub unsafe fn vcvtq_n_f64_u64<const N: i32>(a: uint64x2_t) -> float64x2_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_n_f32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf, N = 2))]
@@ -3025,6 +3527,8 @@ pub unsafe fn vcvts_n_f32_u32<const N: i32>(a: u32) -> f32 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_n_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf, N = 2))]
@@ -3041,6 +3545,8 @@ pub unsafe fn vcvtd_n_f64_u64<const N: i32>(a: u64) -> f64 {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs, N = 2))]
@@ -3057,6 +3563,8 @@ pub unsafe fn vcvt_n_s64_f64<const N: i32>(a: float64x1_t) -> int64x1_t {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs, N = 2))]
@@ -3073,6 +3581,8 @@ pub unsafe fn vcvtq_n_s64_f64<const N: i32>(a: float64x2_t) -> int64x2_t {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_n_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs, N = 2))]
@@ -3089,6 +3599,8 @@ pub unsafe fn vcvts_n_s32_f32<const N: i32>(a: f32) -> i32 {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_n_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs, N = 2))]
@@ -3105,6 +3617,8 @@ pub unsafe fn vcvtd_n_s64_f64<const N: i32>(a: f64) -> i64 {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu, N = 2))]
@@ -3121,6 +3635,8 @@ pub unsafe fn vcvt_n_u64_f64<const N: i32>(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu, N = 2))]
@@ -3137,6 +3653,8 @@ pub unsafe fn vcvtq_n_u64_f64<const N: i32>(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_n_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu, N = 2))]
@@ -3153,6 +3671,8 @@ pub unsafe fn vcvts_n_u32_f32<const N: i32>(a: f32) -> u32 {
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_n_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu, N = 2))]
@@ -3169,6 +3689,8 @@ pub unsafe fn vcvtd_n_u64_f64<const N: i32>(a: f64) -> u64 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_f32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf))]
@@ -3178,6 +3700,8 @@ pub unsafe fn vcvts_f32_s32(a: i32) -> f32 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(scvtf))]
@@ -3187,6 +3711,8 @@ pub unsafe fn vcvtd_f64_s64(a: i64) -> f64 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_f32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf))]
@@ -3196,6 +3722,8 @@ pub unsafe fn vcvts_f32_u32(a: u32) -> f32 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ucvtf))]
@@ -3205,6 +3733,8 @@ pub unsafe fn vcvtd_f64_u64(a: u64) -> f64 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs))]
@@ -3214,6 +3744,8 @@ pub unsafe fn vcvts_s32_f32(a: f32) -> i32 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs))]
@@ -3223,6 +3755,8 @@ pub unsafe fn vcvtd_s64_f64(a: f64) -> i64 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvts_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu))]
@@ -3232,6 +3766,8 @@ pub unsafe fn vcvts_u32_f32(a: f32) -> u32 {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtd_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu))]
@@ -3241,6 +3777,8 @@ pub unsafe fn vcvtd_u64_f64(a: f64) -> u64 {
 }
 
 /// Floating-point convert to signed fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs))]
@@ -3255,6 +3793,8 @@ pub unsafe fn vcvt_s64_f64(a: float64x1_t) -> int64x1_t {
 }
 
 /// Floating-point convert to signed fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzs))]
@@ -3269,6 +3809,8 @@ pub unsafe fn vcvtq_s64_f64(a: float64x2_t) -> int64x2_t {
 }
 
 /// Floating-point convert to unsigned fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu))]
@@ -3283,6 +3825,8 @@ pub unsafe fn vcvt_u64_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point convert to unsigned fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtzu))]
@@ -3297,6 +3841,8 @@ pub unsafe fn vcvtq_u64_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvta_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtas))]
@@ -3311,6 +3857,8 @@ pub unsafe fn vcvta_s32_f32(a: float32x2_t) -> int32x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtaq_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtas))]
@@ -3325,6 +3873,8 @@ pub unsafe fn vcvtaq_s32_f32(a: float32x4_t) -> int32x4_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvta_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtas))]
@@ -3339,6 +3889,8 @@ pub unsafe fn vcvta_s64_f64(a: float64x1_t) -> int64x1_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtaq_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtas))]
@@ -3353,6 +3905,8 @@ pub unsafe fn vcvtaq_s64_f64(a: float64x2_t) -> int64x2_t {
 }
 
 /// Floating-point convert to integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtas_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtas))]
@@ -3367,6 +3921,8 @@ pub unsafe fn vcvtas_s32_f32(a: f32) -> i32 {
 }
 
 /// Floating-point convert to integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtad_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtas))]
@@ -3381,6 +3937,8 @@ pub unsafe fn vcvtad_s64_f64(a: f64) -> i64 {
 }
 
 /// Floating-point convert to integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtas_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtau))]
@@ -3395,6 +3953,8 @@ pub unsafe fn vcvtas_u32_f32(a: f32) -> u32 {
 }
 
 /// Floating-point convert to integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtad_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtau))]
@@ -3409,6 +3969,8 @@ pub unsafe fn vcvtad_u64_f64(a: f64) -> u64 {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtn_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtns))]
@@ -3423,6 +3985,8 @@ pub unsafe fn vcvtn_s32_f32(a: float32x2_t) -> int32x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtnq_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtns))]
@@ -3437,6 +4001,8 @@ pub unsafe fn vcvtnq_s32_f32(a: float32x4_t) -> int32x4_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtn_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtns))]
@@ -3451,6 +4017,8 @@ pub unsafe fn vcvtn_s64_f64(a: float64x1_t) -> int64x1_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtnq_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtns))]
@@ -3465,6 +4033,8 @@ pub unsafe fn vcvtnq_s64_f64(a: float64x2_t) -> int64x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtns_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtns))]
@@ -3479,6 +4049,8 @@ pub unsafe fn vcvtns_s32_f32(a: f32) -> i32 {
 }
 
 /// Floating-point convert to signed integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtnd_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtns))]
@@ -3493,6 +4065,8 @@ pub unsafe fn vcvtnd_s64_f64(a: f64) -> i64 {
 }
 
 /// Floating-point convert to signed integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtm_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtms))]
@@ -3507,6 +4081,8 @@ pub unsafe fn vcvtm_s32_f32(a: float32x2_t) -> int32x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtmq_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtms))]
@@ -3521,6 +4097,8 @@ pub unsafe fn vcvtmq_s32_f32(a: float32x4_t) -> int32x4_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtm_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtms))]
@@ -3535,6 +4113,8 @@ pub unsafe fn vcvtm_s64_f64(a: float64x1_t) -> int64x1_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtmq_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtms))]
@@ -3549,6 +4129,8 @@ pub unsafe fn vcvtmq_s64_f64(a: float64x2_t) -> int64x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtms_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtms))]
@@ -3563,6 +4145,8 @@ pub unsafe fn vcvtms_s32_f32(a: f32) -> i32 {
 }
 
 /// Floating-point convert to signed integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtmd_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtms))]
@@ -3577,6 +4161,8 @@ pub unsafe fn vcvtmd_s64_f64(a: f64) -> i64 {
 }
 
 /// Floating-point convert to signed integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtp_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtps))]
@@ -3591,6 +4177,8 @@ pub unsafe fn vcvtp_s32_f32(a: float32x2_t) -> int32x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtpq_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtps))]
@@ -3605,6 +4193,8 @@ pub unsafe fn vcvtpq_s32_f32(a: float32x4_t) -> int32x4_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtp_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtps))]
@@ -3619,6 +4209,8 @@ pub unsafe fn vcvtp_s64_f64(a: float64x1_t) -> int64x1_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtpq_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtps))]
@@ -3633,6 +4225,8 @@ pub unsafe fn vcvtpq_s64_f64(a: float64x2_t) -> int64x2_t {
 }
 
 /// Floating-point convert to signed integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtps_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtps))]
@@ -3647,6 +4241,8 @@ pub unsafe fn vcvtps_s32_f32(a: f32) -> i32 {
 }
 
 /// Floating-point convert to signed integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtpd_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtps))]
@@ -3661,6 +4257,8 @@ pub unsafe fn vcvtpd_s64_f64(a: f64) -> i64 {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvta_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtau))]
@@ -3675,6 +4273,8 @@ pub unsafe fn vcvta_u32_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtaq_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtau))]
@@ -3689,6 +4289,8 @@ pub unsafe fn vcvtaq_u32_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvta_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtau))]
@@ -3703,6 +4305,8 @@ pub unsafe fn vcvta_u64_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtaq_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtau))]
@@ -3717,6 +4321,8 @@ pub unsafe fn vcvtaq_u64_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtn_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtnu))]
@@ -3731,6 +4337,8 @@ pub unsafe fn vcvtn_u32_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtnq_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtnu))]
@@ -3745,6 +4353,8 @@ pub unsafe fn vcvtnq_u32_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtn_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtnu))]
@@ -3759,6 +4369,8 @@ pub unsafe fn vcvtn_u64_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtnq_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtnu))]
@@ -3773,6 +4385,8 @@ pub unsafe fn vcvtnq_u64_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtns_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtnu))]
@@ -3787,6 +4401,8 @@ pub unsafe fn vcvtns_u32_f32(a: f32) -> u32 {
 }
 
 /// Floating-point convert to unsigned integer, rounding to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtnd_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtnu))]
@@ -3801,6 +4417,8 @@ pub unsafe fn vcvtnd_u64_f64(a: f64) -> u64 {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtm_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtmu))]
@@ -3815,6 +4433,8 @@ pub unsafe fn vcvtm_u32_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtmq_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtmu))]
@@ -3829,6 +4449,8 @@ pub unsafe fn vcvtmq_u32_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtm_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtmu))]
@@ -3843,6 +4465,8 @@ pub unsafe fn vcvtm_u64_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtmq_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtmu))]
@@ -3857,6 +4481,8 @@ pub unsafe fn vcvtmq_u64_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtms_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtmu))]
@@ -3871,6 +4497,8 @@ pub unsafe fn vcvtms_u32_f32(a: f32) -> u32 {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtmd_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtmu))]
@@ -3885,6 +4513,8 @@ pub unsafe fn vcvtmd_u64_f64(a: f64) -> u64 {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtp_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtpu))]
@@ -3899,6 +4529,8 @@ pub unsafe fn vcvtp_u32_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtpq_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtpu))]
@@ -3913,6 +4545,8 @@ pub unsafe fn vcvtpq_u32_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtp_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtpu))]
@@ -3927,6 +4561,8 @@ pub unsafe fn vcvtp_u64_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtpq_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtpu))]
@@ -3941,6 +4577,8 @@ pub unsafe fn vcvtpq_u64_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtps_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtpu))]
@@ -3955,6 +4593,8 @@ pub unsafe fn vcvtps_u32_f32(a: f32) -> u32 {
 }
 
 /// Floating-point convert to unsigned integer, rounding toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtpd_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fcvtpu))]
@@ -3969,6 +4609,8 @@ pub unsafe fn vcvtpd_u64_f64(a: f64) -> u64 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(dup, N = 1))]
@@ -3980,6 +4622,8 @@ pub unsafe fn vdupq_laneq_p64<const N: i32>(a: poly64x2_t) -> poly64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(dup, N = 0))]
@@ -3991,6 +4635,8 @@ pub unsafe fn vdupq_lane_p64<const N: i32>(a: poly64x1_t) -> poly64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(dup, N = 1))]
@@ -4002,6 +4648,8 @@ pub unsafe fn vdupq_laneq_f64<const N: i32>(a: float64x2_t) -> float64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(dup, N = 0))]
@@ -4013,6 +4661,8 @@ pub unsafe fn vdupq_lane_f64<const N: i32>(a: float64x1_t) -> float64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 0))]
@@ -4024,6 +4674,8 @@ pub unsafe fn vdup_lane_p64<const N: i32>(a: poly64x1_t) -> poly64x1_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 0))]
@@ -4035,6 +4687,8 @@ pub unsafe fn vdup_lane_f64<const N: i32>(a: float64x1_t) -> float64x1_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4046,6 +4700,8 @@ pub unsafe fn vdup_laneq_p64<const N: i32>(a: poly64x2_t) -> poly64x1_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4057,6 +4713,8 @@ pub unsafe fn vdup_laneq_f64<const N: i32>(a: float64x2_t) -> float64x1_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupb_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 4))]
@@ -4068,6 +4726,8 @@ pub unsafe fn vdupb_lane_s8<const N: i32>(a: int8x8_t) -> i8 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupb_laneq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 8))]
@@ -4079,6 +4739,8 @@ pub unsafe fn vdupb_laneq_s8<const N: i32>(a: int8x16_t) -> i8 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vduph_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 2))]
@@ -4090,6 +4752,8 @@ pub unsafe fn vduph_lane_s16<const N: i32>(a: int16x4_t) -> i16 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vduph_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 4))]
@@ -4101,6 +4765,8 @@ pub unsafe fn vduph_laneq_s16<const N: i32>(a: int16x8_t) -> i16 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdups_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4112,6 +4778,8 @@ pub unsafe fn vdups_lane_s32<const N: i32>(a: int32x2_t) -> i32 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdups_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 2))]
@@ -4123,6 +4791,8 @@ pub unsafe fn vdups_laneq_s32<const N: i32>(a: int32x4_t) -> i32 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupd_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 0))]
@@ -4134,6 +4804,8 @@ pub unsafe fn vdupd_lane_s64<const N: i32>(a: int64x1_t) -> i64 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupd_laneq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4145,6 +4817,8 @@ pub unsafe fn vdupd_laneq_s64<const N: i32>(a: int64x2_t) -> i64 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupb_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 4))]
@@ -4156,6 +4830,8 @@ pub unsafe fn vdupb_lane_u8<const N: i32>(a: uint8x8_t) -> u8 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupb_laneq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 8))]
@@ -4167,6 +4843,8 @@ pub unsafe fn vdupb_laneq_u8<const N: i32>(a: uint8x16_t) -> u8 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vduph_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 2))]
@@ -4178,6 +4856,8 @@ pub unsafe fn vduph_lane_u16<const N: i32>(a: uint16x4_t) -> u16 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vduph_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 4))]
@@ -4189,6 +4869,8 @@ pub unsafe fn vduph_laneq_u16<const N: i32>(a: uint16x8_t) -> u16 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdups_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4200,6 +4882,8 @@ pub unsafe fn vdups_lane_u32<const N: i32>(a: uint32x2_t) -> u32 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdups_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 2))]
@@ -4211,6 +4895,8 @@ pub unsafe fn vdups_laneq_u32<const N: i32>(a: uint32x4_t) -> u32 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupd_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 0))]
@@ -4222,6 +4908,8 @@ pub unsafe fn vdupd_lane_u64<const N: i32>(a: uint64x1_t) -> u64 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupd_laneq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4233,6 +4921,8 @@ pub unsafe fn vdupd_laneq_u64<const N: i32>(a: uint64x2_t) -> u64 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupb_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 4))]
@@ -4244,6 +4934,8 @@ pub unsafe fn vdupb_lane_p8<const N: i32>(a: poly8x8_t) -> p8 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupb_laneq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 8))]
@@ -4255,6 +4947,8 @@ pub unsafe fn vdupb_laneq_p8<const N: i32>(a: poly8x16_t) -> p8 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vduph_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 2))]
@@ -4266,6 +4960,8 @@ pub unsafe fn vduph_lane_p16<const N: i32>(a: poly16x4_t) -> p16 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vduph_laneq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 4))]
@@ -4277,6 +4973,8 @@ pub unsafe fn vduph_laneq_p16<const N: i32>(a: poly16x8_t) -> p16 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdups_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4288,6 +4986,8 @@ pub unsafe fn vdups_lane_f32<const N: i32>(a: float32x2_t) -> f32 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdups_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 2))]
@@ -4299,6 +4999,8 @@ pub unsafe fn vdups_laneq_f32<const N: i32>(a: float32x4_t) -> f32 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupd_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 0))]
@@ -4310,6 +5012,8 @@ pub unsafe fn vdupd_lane_f64<const N: i32>(a: float64x1_t) -> f64 {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupd_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, N = 1))]
@@ -4321,6 +5025,8 @@ pub unsafe fn vdupd_laneq_f64<const N: i32>(a: float64x2_t) -> f64 {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ext, N = 1))]
@@ -4336,6 +5042,8 @@ pub unsafe fn vextq_p64<const N: i32>(a: poly64x2_t, b: poly64x2_t) -> poly64x2_
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ext, N = 1))]
@@ -4351,6 +5059,8 @@ pub unsafe fn vextq_f64<const N: i32>(a: float64x2_t, b: float64x2_t) -> float64
 }
 
 /// Floating-point multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -4360,6 +5070,8 @@ pub unsafe fn vmla_f64(a: float64x1_t, b: float64x1_t, c: float64x1_t) -> float6
 }
 
 /// Floating-point multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -4369,6 +5081,8 @@ pub unsafe fn vmlaq_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t) -> float
 }
 
 /// Signed multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2))]
@@ -4380,6 +5094,8 @@ pub unsafe fn vmlal_high_s8(a: int16x8_t, b: int8x16_t, c: int8x16_t) -> int16x8
 }
 
 /// Signed multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2))]
@@ -4391,6 +5107,8 @@ pub unsafe fn vmlal_high_s16(a: int32x4_t, b: int16x8_t, c: int16x8_t) -> int32x
 }
 
 /// Signed multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2))]
@@ -4402,6 +5120,8 @@ pub unsafe fn vmlal_high_s32(a: int64x2_t, b: int32x4_t, c: int32x4_t) -> int64x
 }
 
 /// Unsigned multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2))]
@@ -4413,6 +5133,8 @@ pub unsafe fn vmlal_high_u8(a: uint16x8_t, b: uint8x16_t, c: uint8x16_t) -> uint
 }
 
 /// Unsigned multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2))]
@@ -4424,6 +5146,8 @@ pub unsafe fn vmlal_high_u16(a: uint32x4_t, b: uint16x8_t, c: uint16x8_t) -> uin
 }
 
 /// Unsigned multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2))]
@@ -4435,6 +5159,8 @@ pub unsafe fn vmlal_high_u32(a: uint64x2_t, b: uint32x4_t, c: uint32x4_t) -> uin
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2))]
@@ -4444,6 +5170,8 @@ pub unsafe fn vmlal_high_n_s16(a: int32x4_t, b: int16x8_t, c: i16) -> int32x4_t
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2))]
@@ -4453,6 +5181,8 @@ pub unsafe fn vmlal_high_n_s32(a: int64x2_t, b: int32x4_t, c: i32) -> int64x2_t
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2))]
@@ -4462,6 +5192,8 @@ pub unsafe fn vmlal_high_n_u16(a: uint32x4_t, b: uint16x8_t, c: u16) -> uint32x4
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2))]
@@ -4471,6 +5203,8 @@ pub unsafe fn vmlal_high_n_u32(a: uint64x2_t, b: uint32x4_t, c: u32) -> uint64x2
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2, LANE = 1))]
@@ -4482,6 +5216,8 @@ pub unsafe fn vmlal_high_lane_s16<const LANE: i32>(a: int32x4_t, b: int16x8_t, c
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2, LANE = 1))]
@@ -4493,6 +5229,8 @@ pub unsafe fn vmlal_high_laneq_s16<const LANE: i32>(a: int32x4_t, b: int16x8_t,
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2, LANE = 1))]
@@ -4504,6 +5242,8 @@ pub unsafe fn vmlal_high_lane_s32<const LANE: i32>(a: int64x2_t, b: int32x4_t, c
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlal2, LANE = 1))]
@@ -4515,6 +5255,8 @@ pub unsafe fn vmlal_high_laneq_s32<const LANE: i32>(a: int64x2_t, b: int32x4_t,
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2, LANE = 1))]
@@ -4526,6 +5268,8 @@ pub unsafe fn vmlal_high_lane_u16<const LANE: i32>(a: uint32x4_t, b: uint16x8_t,
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2, LANE = 1))]
@@ -4537,6 +5281,8 @@ pub unsafe fn vmlal_high_laneq_u16<const LANE: i32>(a: uint32x4_t, b: uint16x8_t
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2, LANE = 1))]
@@ -4548,6 +5294,8 @@ pub unsafe fn vmlal_high_lane_u32<const LANE: i32>(a: uint64x2_t, b: uint32x4_t,
 }
 
 /// Multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_high_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlal2, LANE = 1))]
@@ -4559,6 +5307,8 @@ pub unsafe fn vmlal_high_laneq_u32<const LANE: i32>(a: uint64x2_t, b: uint32x4_t
 }
 
 /// Floating-point multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -4568,6 +5318,8 @@ pub unsafe fn vmls_f64(a: float64x1_t, b: float64x1_t, c: float64x1_t) -> float6
 }
 
 /// Floating-point multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -4577,6 +5329,8 @@ pub unsafe fn vmlsq_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t) -> float
 }
 
 /// Signed multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2))]
@@ -4588,6 +5342,8 @@ pub unsafe fn vmlsl_high_s8(a: int16x8_t, b: int8x16_t, c: int8x16_t) -> int16x8
 }
 
 /// Signed multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2))]
@@ -4599,6 +5355,8 @@ pub unsafe fn vmlsl_high_s16(a: int32x4_t, b: int16x8_t, c: int16x8_t) -> int32x
 }
 
 /// Signed multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2))]
@@ -4610,6 +5368,8 @@ pub unsafe fn vmlsl_high_s32(a: int64x2_t, b: int32x4_t, c: int32x4_t) -> int64x
 }
 
 /// Unsigned multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2))]
@@ -4621,6 +5381,8 @@ pub unsafe fn vmlsl_high_u8(a: uint16x8_t, b: uint8x16_t, c: uint8x16_t) -> uint
 }
 
 /// Unsigned multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2))]
@@ -4632,6 +5394,8 @@ pub unsafe fn vmlsl_high_u16(a: uint32x4_t, b: uint16x8_t, c: uint16x8_t) -> uin
 }
 
 /// Unsigned multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2))]
@@ -4643,6 +5407,8 @@ pub unsafe fn vmlsl_high_u32(a: uint64x2_t, b: uint32x4_t, c: uint32x4_t) -> uin
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2))]
@@ -4652,6 +5418,8 @@ pub unsafe fn vmlsl_high_n_s16(a: int32x4_t, b: int16x8_t, c: i16) -> int32x4_t
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2))]
@@ -4661,6 +5429,8 @@ pub unsafe fn vmlsl_high_n_s32(a: int64x2_t, b: int32x4_t, c: i32) -> int64x2_t
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2))]
@@ -4670,6 +5440,8 @@ pub unsafe fn vmlsl_high_n_u16(a: uint32x4_t, b: uint16x8_t, c: u16) -> uint32x4
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2))]
@@ -4679,6 +5451,8 @@ pub unsafe fn vmlsl_high_n_u32(a: uint64x2_t, b: uint32x4_t, c: u32) -> uint64x2
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2, LANE = 1))]
@@ -4690,6 +5464,8 @@ pub unsafe fn vmlsl_high_lane_s16<const LANE: i32>(a: int32x4_t, b: int16x8_t, c
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2, LANE = 1))]
@@ -4701,6 +5477,8 @@ pub unsafe fn vmlsl_high_laneq_s16<const LANE: i32>(a: int32x4_t, b: int16x8_t,
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2, LANE = 1))]
@@ -4712,6 +5490,8 @@ pub unsafe fn vmlsl_high_lane_s32<const LANE: i32>(a: int64x2_t, b: int32x4_t, c
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smlsl2, LANE = 1))]
@@ -4723,6 +5503,8 @@ pub unsafe fn vmlsl_high_laneq_s32<const LANE: i32>(a: int64x2_t, b: int32x4_t,
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2, LANE = 1))]
@@ -4734,6 +5516,8 @@ pub unsafe fn vmlsl_high_lane_u16<const LANE: i32>(a: uint32x4_t, b: uint16x8_t,
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2, LANE = 1))]
@@ -4745,6 +5529,8 @@ pub unsafe fn vmlsl_high_laneq_u16<const LANE: i32>(a: uint32x4_t, b: uint16x8_t
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2, LANE = 1))]
@@ -4756,6 +5542,8 @@ pub unsafe fn vmlsl_high_lane_u32<const LANE: i32>(a: uint64x2_t, b: uint32x4_t,
 }
 
 /// Multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_high_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umlsl2, LANE = 1))]
@@ -4767,6 +5555,8 @@ pub unsafe fn vmlsl_high_laneq_u32<const LANE: i32>(a: uint64x2_t, b: uint32x4_t
 }
 
 /// Extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovn_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(xtn2))]
@@ -4777,6 +5567,8 @@ pub unsafe fn vmovn_high_s16(a: int8x8_t, b: int16x8_t) -> int8x16_t {
 }
 
 /// Extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovn_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(xtn2))]
@@ -4787,6 +5579,8 @@ pub unsafe fn vmovn_high_s32(a: int16x4_t, b: int32x4_t) -> int16x8_t {
 }
 
 /// Extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovn_high_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(xtn2))]
@@ -4797,6 +5591,8 @@ pub unsafe fn vmovn_high_s64(a: int32x2_t, b: int64x2_t) -> int32x4_t {
 }
 
 /// Extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovn_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(xtn2))]
@@ -4807,6 +5603,8 @@ pub unsafe fn vmovn_high_u16(a: uint8x8_t, b: uint16x8_t) -> uint8x16_t {
 }
 
 /// Extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovn_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(xtn2))]
@@ -4817,6 +5615,8 @@ pub unsafe fn vmovn_high_u32(a: uint16x4_t, b: uint32x4_t) -> uint16x8_t {
 }
 
 /// Extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovn_high_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(xtn2))]
@@ -4827,6 +5627,8 @@ pub unsafe fn vmovn_high_u64(a: uint32x2_t, b: uint64x2_t) -> uint32x4_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vneg_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(neg))]
@@ -4836,6 +5638,8 @@ pub unsafe fn vneg_s64(a: int64x1_t) -> int64x1_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vnegq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(neg))]
@@ -4845,6 +5649,8 @@ pub unsafe fn vnegq_s64(a: int64x2_t) -> int64x2_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vnegd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(neg))]
@@ -4854,6 +5660,8 @@ pub unsafe fn vnegd_s64(a: i64) -> i64 {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vneg_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fneg))]
@@ -4863,6 +5671,8 @@ pub unsafe fn vneg_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vnegq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fneg))]
@@ -4872,6 +5682,8 @@ pub unsafe fn vnegq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqneg_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqneg))]
@@ -4886,6 +5698,8 @@ pub unsafe fn vqneg_s64(a: int64x1_t) -> int64x1_t {
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqneg))]
@@ -4900,6 +5714,8 @@ pub unsafe fn vqnegq_s64(a: int64x2_t) -> int64x2_t {
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegb_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqneg))]
@@ -4909,6 +5725,8 @@ pub unsafe fn vqnegb_s8(a: i8) -> i8 {
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqneg))]
@@ -4918,6 +5736,8 @@ pub unsafe fn vqnegh_s16(a: i16) -> i16 {
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegs_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqneg))]
@@ -4927,6 +5747,8 @@ pub unsafe fn vqnegs_s32(a: i32) -> i32 {
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqneg))]
@@ -4936,6 +5758,8 @@ pub unsafe fn vqnegd_s64(a: i64) -> i64 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubb_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqsub))]
@@ -4947,6 +5771,8 @@ pub unsafe fn vqsubb_s8(a: i8, b: i8) -> i8 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqsub))]
@@ -4958,6 +5784,8 @@ pub unsafe fn vqsubh_s16(a: i16, b: i16) -> i16 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubb_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqsub))]
@@ -4969,6 +5797,8 @@ pub unsafe fn vqsubb_u8(a: u8, b: u8) -> u8 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubh_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqsub))]
@@ -4980,6 +5810,8 @@ pub unsafe fn vqsubh_u16(a: u16, b: u16) -> u16 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubs_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqsub))]
@@ -4994,6 +5826,8 @@ pub unsafe fn vqsubs_u32(a: u32, b: u32) -> u32 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqsub))]
@@ -5008,6 +5842,8 @@ pub unsafe fn vqsubd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubs_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqsub))]
@@ -5022,6 +5858,8 @@ pub unsafe fn vqsubs_s32(a: i32, b: i32) -> i32 {
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqsub))]
@@ -5036,6 +5874,8 @@ pub unsafe fn vqsubd_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Reverse bit order
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrbit_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rbit))]
@@ -5050,6 +5890,8 @@ pub unsafe fn vrbit_s8(a: int8x8_t) -> int8x8_t {
 }
 
 /// Reverse bit order
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrbitq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rbit))]
@@ -5064,6 +5906,8 @@ pub unsafe fn vrbitq_s8(a: int8x16_t) -> int8x16_t {
 }
 
 /// Reverse bit order
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrbit_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rbit))]
@@ -5073,6 +5917,8 @@ pub unsafe fn vrbit_u8(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Reverse bit order
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrbitq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rbit))]
@@ -5082,6 +5928,8 @@ pub unsafe fn vrbitq_u8(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Reverse bit order
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrbit_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rbit))]
@@ -5091,6 +5939,8 @@ pub unsafe fn vrbit_p8(a: poly8x8_t) -> poly8x8_t {
 }
 
 /// Reverse bit order
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrbitq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rbit))]
@@ -5100,6 +5950,8 @@ pub unsafe fn vrbitq_p8(a: poly8x16_t) -> poly8x16_t {
 }
 
 /// Floating-point round to integral exact, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndx_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintx))]
@@ -5114,6 +5966,8 @@ pub unsafe fn vrndx_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to integral exact, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndxq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintx))]
@@ -5128,6 +5982,8 @@ pub unsafe fn vrndxq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to integral exact, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndx_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintx))]
@@ -5142,6 +5998,8 @@ pub unsafe fn vrndx_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point round to integral exact, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndxq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintx))]
@@ -5156,6 +6014,8 @@ pub unsafe fn vrndxq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point round to integral, to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnda_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinta))]
@@ -5170,6 +6030,8 @@ pub unsafe fn vrnda_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to integral, to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndaq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinta))]
@@ -5184,6 +6046,8 @@ pub unsafe fn vrndaq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to integral, to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnda_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinta))]
@@ -5198,6 +6062,8 @@ pub unsafe fn vrnda_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point round to integral, to nearest with ties to away
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndaq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinta))]
@@ -5212,6 +6078,8 @@ pub unsafe fn vrndaq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point round to integral, to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndn_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintn))]
@@ -5226,6 +6094,8 @@ pub unsafe fn vrndn_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point round to integral, to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndnq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintn))]
@@ -5240,6 +6110,8 @@ pub unsafe fn vrndnq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point round to integral, to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndns_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintn))]
@@ -5254,6 +6126,8 @@ pub unsafe fn vrndns_f32(a: f32) -> f32 {
 }
 
 /// Floating-point round to integral, toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndm_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintm))]
@@ -5268,6 +6142,8 @@ pub unsafe fn vrndm_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to integral, toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndmq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintm))]
@@ -5282,6 +6158,8 @@ pub unsafe fn vrndmq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to integral, toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndm_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintm))]
@@ -5296,6 +6174,8 @@ pub unsafe fn vrndm_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point round to integral, toward minus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndmq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintm))]
@@ -5310,6 +6190,8 @@ pub unsafe fn vrndmq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point round to integral, toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndp_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintp))]
@@ -5324,6 +6206,8 @@ pub unsafe fn vrndp_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to integral, toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndpq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintp))]
@@ -5338,6 +6222,8 @@ pub unsafe fn vrndpq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to integral, toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndp_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintp))]
@@ -5352,6 +6238,8 @@ pub unsafe fn vrndp_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point round to integral, toward plus infinity
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndpq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintp))]
@@ -5366,6 +6254,8 @@ pub unsafe fn vrndpq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point round to integral, toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintz))]
@@ -5380,6 +6270,8 @@ pub unsafe fn vrnd_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to integral, toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintz))]
@@ -5394,6 +6286,8 @@ pub unsafe fn vrndq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to integral, toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintz))]
@@ -5408,6 +6302,8 @@ pub unsafe fn vrnd_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point round to integral, toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frintz))]
@@ -5422,6 +6318,8 @@ pub unsafe fn vrndq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point round to integral, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndi_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinti))]
@@ -5436,6 +6334,8 @@ pub unsafe fn vrndi_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to integral, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndiq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinti))]
@@ -5450,6 +6350,8 @@ pub unsafe fn vrndiq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to integral, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndi_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinti))]
@@ -5464,6 +6366,8 @@ pub unsafe fn vrndi_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point round to integral, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndiq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frinti))]
@@ -5478,6 +6382,8 @@ pub unsafe fn vrndiq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddb_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqadd))]
@@ -5489,6 +6395,8 @@ pub unsafe fn vqaddb_s8(a: i8, b: i8) -> i8 {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqadd))]
@@ -5500,6 +6408,8 @@ pub unsafe fn vqaddh_s16(a: i16, b: i16) -> i16 {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddb_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqadd))]
@@ -5511,6 +6421,8 @@ pub unsafe fn vqaddb_u8(a: u8, b: u8) -> u8 {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddh_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqadd))]
@@ -5522,6 +6434,8 @@ pub unsafe fn vqaddh_u16(a: u16, b: u16) -> u16 {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadds_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqadd))]
@@ -5536,6 +6450,8 @@ pub unsafe fn vqadds_u32(a: u32, b: u32) -> u32 {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqadd))]
@@ -5550,6 +6466,8 @@ pub unsafe fn vqaddd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadds_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqadd))]
@@ -5564,6 +6482,8 @@ pub unsafe fn vqadds_s32(a: i32, b: i32) -> i32 {
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqadd))]
@@ -5578,6 +6498,8 @@ pub unsafe fn vqaddd_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_f64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld1))]
@@ -5592,6 +6514,8 @@ pub unsafe fn vld1_f64_x2(a: *const f64) -> float64x1x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_f64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld1))]
@@ -5606,6 +6530,8 @@ pub unsafe fn vld1q_f64_x2(a: *const f64) -> float64x2x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_f64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld1))]
@@ -5620,6 +6546,8 @@ pub unsafe fn vld1_f64_x3(a: *const f64) -> float64x1x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_f64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld1))]
@@ -5634,6 +6562,8 @@ pub unsafe fn vld1q_f64_x3(a: *const f64) -> float64x2x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_f64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld1))]
@@ -5648,6 +6578,8 @@ pub unsafe fn vld1_f64_x4(a: *const f64) -> float64x1x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_f64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld1))]
@@ -5662,6 +6594,8 @@ pub unsafe fn vld1q_f64_x4(a: *const f64) -> float64x2x4_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2))]
@@ -5676,6 +6610,8 @@ pub unsafe fn vld2q_s64(a: *const i64) -> int64x2x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2))]
@@ -5685,6 +6621,8 @@ pub unsafe fn vld2q_u64(a: *const u64) -> uint64x2x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld2))]
@@ -5694,6 +6632,8 @@ pub unsafe fn vld2q_p64(a: *const p64) -> poly64x2x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -5708,6 +6648,8 @@ pub unsafe fn vld2_f64(a: *const f64) -> float64x1x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2))]
@@ -5722,6 +6664,8 @@ pub unsafe fn vld2q_f64(a: *const f64) -> float64x2x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2r))]
@@ -5736,6 +6680,8 @@ pub unsafe fn vld2q_dup_s64(a: *const i64) -> int64x2x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2r))]
@@ -5745,6 +6691,8 @@ pub unsafe fn vld2q_dup_u64(a: *const u64) -> uint64x2x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld2r))]
@@ -5754,6 +6702,8 @@ pub unsafe fn vld2q_dup_p64(a: *const p64) -> poly64x2x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2r))]
@@ -5768,6 +6718,8 @@ pub unsafe fn vld2_dup_f64(a: *const f64) -> float64x1x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2r))]
@@ -5782,6 +6734,8 @@ pub unsafe fn vld2q_dup_f64(a: *const f64) -> float64x2x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5798,6 +6752,8 @@ pub unsafe fn vld2q_lane_s8<const LANE: i32>(a: *const i8, b: int8x16x2_t) -> in
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5814,6 +6770,8 @@ pub unsafe fn vld2_lane_s64<const LANE: i32>(a: *const i64, b: int64x1x2_t) -> i
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5830,6 +6788,8 @@ pub unsafe fn vld2q_lane_s64<const LANE: i32>(a: *const i64, b: int64x2x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5841,6 +6801,8 @@ pub unsafe fn vld2_lane_p64<const LANE: i32>(a: *const p64, b: poly64x1x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5852,6 +6814,8 @@ pub unsafe fn vld2q_lane_p64<const LANE: i32>(a: *const p64, b: poly64x2x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5863,6 +6827,8 @@ pub unsafe fn vld2q_lane_u8<const LANE: i32>(a: *const u8, b: uint8x16x2_t) -> u
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5874,6 +6840,8 @@ pub unsafe fn vld2_lane_u64<const LANE: i32>(a: *const u64, b: uint64x1x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5885,6 +6853,8 @@ pub unsafe fn vld2q_lane_u64<const LANE: i32>(a: *const u64, b: uint64x2x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5896,6 +6866,8 @@ pub unsafe fn vld2q_lane_p8<const LANE: i32>(a: *const p8, b: poly8x16x2_t) -> p
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5912,6 +6884,8 @@ pub unsafe fn vld2_lane_f64<const LANE: i32>(a: *const f64, b: float64x1x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld2, LANE = 0))]
@@ -5928,6 +6902,8 @@ pub unsafe fn vld2q_lane_f64<const LANE: i32>(a: *const f64, b: float64x2x2_t) -
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3))]
@@ -5942,6 +6918,8 @@ pub unsafe fn vld3q_s64(a: *const i64) -> int64x2x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3))]
@@ -5951,6 +6929,8 @@ pub unsafe fn vld3q_u64(a: *const u64) -> uint64x2x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld3))]
@@ -5960,6 +6940,8 @@ pub unsafe fn vld3q_p64(a: *const p64) -> poly64x2x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -5974,6 +6956,8 @@ pub unsafe fn vld3_f64(a: *const f64) -> float64x1x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3))]
@@ -5988,6 +6972,8 @@ pub unsafe fn vld3q_f64(a: *const f64) -> float64x2x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3r))]
@@ -6002,6 +6988,8 @@ pub unsafe fn vld3q_dup_s64(a: *const i64) -> int64x2x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3r))]
@@ -6011,6 +6999,8 @@ pub unsafe fn vld3q_dup_u64(a: *const u64) -> uint64x2x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld3r))]
@@ -6020,6 +7010,8 @@ pub unsafe fn vld3q_dup_p64(a: *const p64) -> poly64x2x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3r))]
@@ -6034,6 +7026,8 @@ pub unsafe fn vld3_dup_f64(a: *const f64) -> float64x1x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3r))]
@@ -6048,6 +7042,8 @@ pub unsafe fn vld3q_dup_f64(a: *const f64) -> float64x2x3_t {
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6064,6 +7060,8 @@ pub unsafe fn vld3q_lane_s8<const LANE: i32>(a: *const i8, b: int8x16x3_t) -> in
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6080,6 +7078,8 @@ pub unsafe fn vld3_lane_s64<const LANE: i32>(a: *const i64, b: int64x1x3_t) -> i
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6096,6 +7096,8 @@ pub unsafe fn vld3q_lane_s64<const LANE: i32>(a: *const i64, b: int64x2x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6107,6 +7109,8 @@ pub unsafe fn vld3_lane_p64<const LANE: i32>(a: *const p64, b: poly64x1x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6118,6 +7122,8 @@ pub unsafe fn vld3q_lane_p64<const LANE: i32>(a: *const p64, b: poly64x2x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6129,6 +7135,8 @@ pub unsafe fn vld3q_lane_p8<const LANE: i32>(a: *const p8, b: poly8x16x3_t) -> p
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6140,6 +7148,8 @@ pub unsafe fn vld3q_lane_u8<const LANE: i32>(a: *const u8, b: uint8x16x3_t) -> u
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6151,6 +7161,8 @@ pub unsafe fn vld3_lane_u64<const LANE: i32>(a: *const u64, b: uint64x1x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6162,6 +7174,8 @@ pub unsafe fn vld3q_lane_u64<const LANE: i32>(a: *const u64, b: uint64x2x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6178,6 +7192,8 @@ pub unsafe fn vld3_lane_f64<const LANE: i32>(a: *const f64, b: float64x1x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld3, LANE = 0))]
@@ -6194,6 +7210,8 @@ pub unsafe fn vld3q_lane_f64<const LANE: i32>(a: *const f64, b: float64x2x3_t) -
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4))]
@@ -6208,6 +7226,8 @@ pub unsafe fn vld4q_s64(a: *const i64) -> int64x2x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4))]
@@ -6217,6 +7237,8 @@ pub unsafe fn vld4q_u64(a: *const u64) -> uint64x2x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld4))]
@@ -6226,6 +7248,8 @@ pub unsafe fn vld4q_p64(a: *const p64) -> poly64x2x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -6240,6 +7264,8 @@ pub unsafe fn vld4_f64(a: *const f64) -> float64x1x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4))]
@@ -6254,6 +7280,8 @@ pub unsafe fn vld4q_f64(a: *const f64) -> float64x2x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4r))]
@@ -6268,6 +7296,8 @@ pub unsafe fn vld4q_dup_s64(a: *const i64) -> int64x2x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4r))]
@@ -6277,6 +7307,8 @@ pub unsafe fn vld4q_dup_u64(a: *const u64) -> uint64x2x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld4r))]
@@ -6286,6 +7318,8 @@ pub unsafe fn vld4q_dup_p64(a: *const p64) -> poly64x2x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4r))]
@@ -6300,6 +7334,8 @@ pub unsafe fn vld4_dup_f64(a: *const f64) -> float64x1x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4r))]
@@ -6314,6 +7350,8 @@ pub unsafe fn vld4q_dup_f64(a: *const f64) -> float64x2x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6330,6 +7368,8 @@ pub unsafe fn vld4q_lane_s8<const LANE: i32>(a: *const i8, b: int8x16x4_t) -> in
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6346,6 +7386,8 @@ pub unsafe fn vld4_lane_s64<const LANE: i32>(a: *const i64, b: int64x1x4_t) -> i
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6362,6 +7404,8 @@ pub unsafe fn vld4q_lane_s64<const LANE: i32>(a: *const i64, b: int64x2x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6373,6 +7417,8 @@ pub unsafe fn vld4_lane_p64<const LANE: i32>(a: *const p64, b: poly64x1x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6384,6 +7430,8 @@ pub unsafe fn vld4q_lane_p64<const LANE: i32>(a: *const p64, b: poly64x2x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6395,6 +7443,8 @@ pub unsafe fn vld4q_lane_p8<const LANE: i32>(a: *const p8, b: poly8x16x4_t) -> p
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6406,6 +7456,8 @@ pub unsafe fn vld4q_lane_u8<const LANE: i32>(a: *const u8, b: uint8x16x4_t) -> u
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6417,6 +7469,8 @@ pub unsafe fn vld4_lane_u64<const LANE: i32>(a: *const u64, b: uint64x1x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6428,6 +7482,8 @@ pub unsafe fn vld4q_lane_u64<const LANE: i32>(a: *const u64, b: uint64x2x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6444,6 +7500,8 @@ pub unsafe fn vld4_lane_f64<const LANE: i32>(a: *const f64, b: float64x1x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ld4, LANE = 0))]
@@ -6460,6 +7518,8 @@ pub unsafe fn vld4q_lane_f64<const LANE: i32>(a: *const f64, b: float64x2x4_t) -
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, LANE = 0))]
@@ -6471,6 +7531,8 @@ pub unsafe fn vst1_lane_f64<const LANE: i32>(a: *mut f64, b: float64x1_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, LANE = 0))]
@@ -6482,6 +7544,8 @@ pub unsafe fn vst1q_lane_f64<const LANE: i32>(a: *mut f64, b: float64x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st1))]
@@ -6496,6 +7560,8 @@ pub unsafe fn vst1_f64_x2(a: *mut f64, b: float64x1x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st1))]
@@ -6510,6 +7576,8 @@ pub unsafe fn vst1q_f64_x2(a: *mut f64, b: float64x2x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st1))]
@@ -6524,6 +7592,8 @@ pub unsafe fn vst1_f64_x3(a: *mut f64, b: float64x1x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st1))]
@@ -6538,6 +7608,8 @@ pub unsafe fn vst1q_f64_x3(a: *mut f64, b: float64x2x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st1))]
@@ -6552,6 +7624,8 @@ pub unsafe fn vst1_f64_x4(a: *mut f64, b: float64x1x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st1))]
@@ -6566,6 +7640,8 @@ pub unsafe fn vst1q_f64_x4(a: *mut f64, b: float64x2x4_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2))]
@@ -6580,6 +7656,8 @@ pub unsafe fn vst2q_s64(a: *mut i64, b: int64x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2))]
@@ -6589,6 +7667,8 @@ pub unsafe fn vst2q_u64(a: *mut u64, b: uint64x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st2))]
@@ -6598,6 +7678,8 @@ pub unsafe fn vst2q_p64(a: *mut p64, b: poly64x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st1))]
@@ -6612,6 +7694,8 @@ pub unsafe fn vst2_f64(a: *mut f64, b: float64x1x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2))]
@@ -6626,6 +7710,8 @@ pub unsafe fn vst2q_f64(a: *mut f64, b: float64x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6642,6 +7728,8 @@ pub unsafe fn vst2q_lane_s8<const LANE: i32>(a: *mut i8, b: int8x16x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6658,6 +7746,8 @@ pub unsafe fn vst2_lane_s64<const LANE: i32>(a: *mut i64, b: int64x1x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6674,6 +7764,8 @@ pub unsafe fn vst2q_lane_s64<const LANE: i32>(a: *mut i64, b: int64x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6685,6 +7777,8 @@ pub unsafe fn vst2q_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x16x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6696,6 +7790,8 @@ pub unsafe fn vst2_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x1x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6707,6 +7803,8 @@ pub unsafe fn vst2q_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6718,6 +7816,8 @@ pub unsafe fn vst2q_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x16x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6729,6 +7829,8 @@ pub unsafe fn vst2_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x1x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6740,6 +7842,8 @@ pub unsafe fn vst2q_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6756,6 +7860,8 @@ pub unsafe fn vst2_lane_f64<const LANE: i32>(a: *mut f64, b: float64x1x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st2, LANE = 0))]
@@ -6772,6 +7878,8 @@ pub unsafe fn vst2q_lane_f64<const LANE: i32>(a: *mut f64, b: float64x2x2_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3))]
@@ -6786,6 +7894,8 @@ pub unsafe fn vst3q_s64(a: *mut i64, b: int64x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3))]
@@ -6795,6 +7905,8 @@ pub unsafe fn vst3q_u64(a: *mut u64, b: uint64x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st3))]
@@ -6804,6 +7916,8 @@ pub unsafe fn vst3q_p64(a: *mut p64, b: poly64x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -6818,6 +7932,8 @@ pub unsafe fn vst3_f64(a: *mut f64, b: float64x1x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3))]
@@ -6832,6 +7948,8 @@ pub unsafe fn vst3q_f64(a: *mut f64, b: float64x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6848,6 +7966,8 @@ pub unsafe fn vst3q_lane_s8<const LANE: i32>(a: *mut i8, b: int8x16x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6864,6 +7984,8 @@ pub unsafe fn vst3_lane_s64<const LANE: i32>(a: *mut i64, b: int64x1x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6880,6 +8002,8 @@ pub unsafe fn vst3q_lane_s64<const LANE: i32>(a: *mut i64, b: int64x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6891,6 +8015,8 @@ pub unsafe fn vst3q_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x16x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6902,6 +8028,8 @@ pub unsafe fn vst3_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x1x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6913,6 +8041,8 @@ pub unsafe fn vst3q_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6924,6 +8054,8 @@ pub unsafe fn vst3q_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x16x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6935,6 +8067,8 @@ pub unsafe fn vst3_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x1x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6946,6 +8080,8 @@ pub unsafe fn vst3q_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6962,6 +8098,8 @@ pub unsafe fn vst3_lane_f64<const LANE: i32>(a: *mut f64, b: float64x1x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st3, LANE = 0))]
@@ -6978,6 +8116,8 @@ pub unsafe fn vst3q_lane_f64<const LANE: i32>(a: *mut f64, b: float64x2x3_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4))]
@@ -6992,6 +8132,8 @@ pub unsafe fn vst4q_s64(a: *mut i64, b: int64x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4))]
@@ -7001,6 +8143,8 @@ pub unsafe fn vst4q_u64(a: *mut u64, b: uint64x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st4))]
@@ -7010,6 +8154,8 @@ pub unsafe fn vst4q_p64(a: *mut p64, b: poly64x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -7024,6 +8170,8 @@ pub unsafe fn vst4_f64(a: *mut f64, b: float64x1x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4))]
@@ -7038,6 +8186,8 @@ pub unsafe fn vst4q_f64(a: *mut f64, b: float64x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7054,6 +8204,8 @@ pub unsafe fn vst4q_lane_s8<const LANE: i32>(a: *mut i8, b: int8x16x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7070,6 +8222,8 @@ pub unsafe fn vst4_lane_s64<const LANE: i32>(a: *mut i64, b: int64x1x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7086,6 +8240,8 @@ pub unsafe fn vst4q_lane_s64<const LANE: i32>(a: *mut i64, b: int64x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7097,6 +8253,8 @@ pub unsafe fn vst4q_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x16x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7108,6 +8266,8 @@ pub unsafe fn vst4_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x1x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7119,6 +8279,8 @@ pub unsafe fn vst4q_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7130,6 +8292,8 @@ pub unsafe fn vst4q_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x16x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7141,6 +8305,8 @@ pub unsafe fn vst4_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x1x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7152,6 +8318,8 @@ pub unsafe fn vst4q_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7168,6 +8336,8 @@ pub unsafe fn vst4_lane_f64<const LANE: i32>(a: *mut f64, b: float64x1x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(st4, LANE = 0))]
@@ -7184,6 +8354,8 @@ pub unsafe fn vst4q_lane_f64<const LANE: i32>(a: *mut f64, b: float64x2x4_t) {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -7193,6 +8365,8 @@ pub unsafe fn vmul_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -7202,6 +8376,8 @@ pub unsafe fn vmulq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_n_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -7211,6 +8387,8 @@ pub unsafe fn vmul_n_f64(a: float64x1_t, b: f64) -> float64x1_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_n_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul))]
@@ -7220,6 +8398,8 @@ pub unsafe fn vmulq_n_f64(a: float64x2_t, b: f64) -> float64x2_t {
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7231,6 +8411,8 @@ pub unsafe fn vmul_lane_f64<const LANE: i32>(a: float64x1_t, b: float64x1_t) ->
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7242,6 +8424,8 @@ pub unsafe fn vmul_laneq_f64<const LANE: i32>(a: float64x1_t, b: float64x2_t) ->
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7253,6 +8437,8 @@ pub unsafe fn vmulq_lane_f64<const LANE: i32>(a: float64x2_t, b: float64x1_t) ->
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7264,6 +8450,8 @@ pub unsafe fn vmulq_laneq_f64<const LANE: i32>(a: float64x2_t, b: float64x2_t) -
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmuls_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7276,6 +8464,8 @@ pub unsafe fn vmuls_lane_f32<const LANE: i32>(a: f32, b: float32x2_t) -> f32 {
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmuls_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7288,6 +8478,8 @@ pub unsafe fn vmuls_laneq_f32<const LANE: i32>(a: f32, b: float32x4_t) -> f32 {
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmuld_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7300,6 +8492,8 @@ pub unsafe fn vmuld_lane_f64<const LANE: i32>(a: f64, b: float64x1_t) -> f64 {
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmuld_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmul, LANE = 0))]
@@ -7312,6 +8506,8 @@ pub unsafe fn vmuld_laneq_f64<const LANE: i32>(a: f64, b: float64x2_t) -> f64 {
 }
 
 /// Signed multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2))]
@@ -7323,6 +8519,8 @@ pub unsafe fn vmull_high_s8(a: int8x16_t, b: int8x16_t) -> int16x8_t {
 }
 
 /// Signed multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2))]
@@ -7334,6 +8532,8 @@ pub unsafe fn vmull_high_s16(a: int16x8_t, b: int16x8_t) -> int32x4_t {
 }
 
 /// Signed multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2))]
@@ -7345,6 +8545,8 @@ pub unsafe fn vmull_high_s32(a: int32x4_t, b: int32x4_t) -> int64x2_t {
 }
 
 /// Unsigned multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2))]
@@ -7356,6 +8558,8 @@ pub unsafe fn vmull_high_u8(a: uint8x16_t, b: uint8x16_t) -> uint16x8_t {
 }
 
 /// Unsigned multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2))]
@@ -7367,6 +8571,8 @@ pub unsafe fn vmull_high_u16(a: uint16x8_t, b: uint16x8_t) -> uint32x4_t {
 }
 
 /// Unsigned multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2))]
@@ -7378,6 +8584,8 @@ pub unsafe fn vmull_high_u32(a: uint32x4_t, b: uint32x4_t) -> uint64x2_t {
 }
 
 /// Polynomial multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(pmull))]
@@ -7392,6 +8600,8 @@ pub unsafe fn vmull_p64(a: p64, b: p64) -> p128 {
 }
 
 /// Polynomial multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(pmull))]
@@ -7403,6 +8613,8 @@ pub unsafe fn vmull_high_p8(a: poly8x16_t, b: poly8x16_t) -> poly16x8_t {
 }
 
 /// Polynomial multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(pmull))]
@@ -7412,6 +8624,8 @@ pub unsafe fn vmull_high_p64(a: poly64x2_t, b: poly64x2_t) -> p128 {
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2))]
@@ -7421,6 +8635,8 @@ pub unsafe fn vmull_high_n_s16(a: int16x8_t, b: i16) -> int32x4_t {
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2))]
@@ -7430,6 +8646,8 @@ pub unsafe fn vmull_high_n_s32(a: int32x4_t, b: i32) -> int64x2_t {
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2))]
@@ -7439,6 +8657,8 @@ pub unsafe fn vmull_high_n_u16(a: uint16x8_t, b: u16) -> uint32x4_t {
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2))]
@@ -7448,6 +8668,8 @@ pub unsafe fn vmull_high_n_u32(a: uint32x4_t, b: u32) -> uint64x2_t {
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2, LANE = 1))]
@@ -7459,6 +8681,8 @@ pub unsafe fn vmull_high_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x4_t) -
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2, LANE = 1))]
@@ -7470,6 +8694,8 @@ pub unsafe fn vmull_high_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t)
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2, LANE = 1))]
@@ -7481,6 +8707,8 @@ pub unsafe fn vmull_high_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x2_t) -
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(smull2, LANE = 1))]
@@ -7492,6 +8720,8 @@ pub unsafe fn vmull_high_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t)
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2, LANE = 1))]
@@ -7503,6 +8733,8 @@ pub unsafe fn vmull_high_lane_u16<const LANE: i32>(a: uint16x8_t, b: uint16x4_t)
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2, LANE = 1))]
@@ -7514,6 +8746,8 @@ pub unsafe fn vmull_high_laneq_u16<const LANE: i32>(a: uint16x8_t, b: uint16x8_t
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2, LANE = 1))]
@@ -7525,6 +8759,8 @@ pub unsafe fn vmull_high_lane_u32<const LANE: i32>(a: uint32x4_t, b: uint32x2_t)
 }
 
 /// Multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_high_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(umull2, LANE = 1))]
@@ -7536,6 +8772,8 @@ pub unsafe fn vmull_high_laneq_u32<const LANE: i32>(a: uint32x4_t, b: uint32x4_t
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulx_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx))]
@@ -7550,6 +8788,8 @@ pub unsafe fn vmulx_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx))]
@@ -7564,6 +8804,8 @@ pub unsafe fn vmulxq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulx_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx))]
@@ -7578,6 +8820,8 @@ pub unsafe fn vmulx_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx))]
@@ -7592,6 +8836,8 @@ pub unsafe fn vmulxq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulx_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7603,6 +8849,8 @@ pub unsafe fn vmulx_lane_f64<const LANE: i32>(a: float64x1_t, b: float64x1_t) ->
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulx_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7614,6 +8862,8 @@ pub unsafe fn vmulx_laneq_f64<const LANE: i32>(a: float64x1_t, b: float64x2_t) -
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulx_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7625,6 +8875,8 @@ pub unsafe fn vmulx_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t) ->
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulx_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7636,6 +8888,8 @@ pub unsafe fn vmulx_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x4_t) -
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7647,6 +8901,8 @@ pub unsafe fn vmulxq_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x2_t) -
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7658,6 +8914,8 @@ pub unsafe fn vmulxq_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t)
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxq_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7669,6 +8927,8 @@ pub unsafe fn vmulxq_lane_f64<const LANE: i32>(a: float64x2_t, b: float64x1_t) -
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxq_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7680,6 +8940,8 @@ pub unsafe fn vmulxq_laneq_f64<const LANE: i32>(a: float64x2_t, b: float64x2_t)
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx))]
@@ -7694,6 +8956,8 @@ pub unsafe fn vmulxs_f32(a: f32, b: f32) -> f32 {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx))]
@@ -7708,6 +8972,8 @@ pub unsafe fn vmulxd_f64(a: f64, b: f64) -> f64 {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxs_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7719,6 +8985,8 @@ pub unsafe fn vmulxs_lane_f32<const LANE: i32>(a: f32, b: float32x2_t) -> f32 {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxs_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7730,6 +8998,8 @@ pub unsafe fn vmulxs_laneq_f32<const LANE: i32>(a: f32, b: float32x4_t) -> f32 {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxd_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7741,6 +9011,8 @@ pub unsafe fn vmulxd_lane_f64<const LANE: i32>(a: f64, b: float64x1_t) -> f64 {
 }
 
 /// Floating-point multiply extended
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulxd_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmulx, LANE = 0))]
@@ -7752,6 +9024,8 @@ pub unsafe fn vmulxd_laneq_f64<const LANE: i32>(a: f64, b: float64x2_t) -> f64 {
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmadd))]
@@ -7766,6 +9040,8 @@ pub unsafe fn vfma_f64(a: float64x1_t, b: float64x1_t, c: float64x1_t) -> float6
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla))]
@@ -7780,6 +9056,8 @@ pub unsafe fn vfmaq_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t) -> float
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_n_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmadd))]
@@ -7789,6 +9067,8 @@ pub unsafe fn vfma_n_f64(a: float64x1_t, b: float64x1_t, c: f64) -> float64x1_t
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_n_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla))]
@@ -7798,6 +9078,8 @@ pub unsafe fn vfmaq_n_f64(a: float64x2_t, b: float64x2_t, c: f64) -> float64x2_t
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7809,6 +9091,8 @@ pub unsafe fn vfma_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7820,6 +9104,8 @@ pub unsafe fn vfma_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7831,6 +9117,8 @@ pub unsafe fn vfmaq_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c:
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7842,6 +9130,8 @@ pub unsafe fn vfmaq_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmadd, LANE = 0))]
@@ -7853,6 +9143,8 @@ pub unsafe fn vfma_lane_f64<const LANE: i32>(a: float64x1_t, b: float64x1_t, c:
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7864,6 +9156,8 @@ pub unsafe fn vfma_laneq_f64<const LANE: i32>(a: float64x1_t, b: float64x1_t, c:
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7875,6 +9169,8 @@ pub unsafe fn vfmaq_lane_f64<const LANE: i32>(a: float64x2_t, b: float64x2_t, c:
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7886,6 +9182,8 @@ pub unsafe fn vfmaq_laneq_f64<const LANE: i32>(a: float64x2_t, b: float64x2_t, c
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmas_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7903,6 +9201,8 @@ pub unsafe fn vfmas_lane_f32<const LANE: i32>(a: f32, b: f32, c: float32x2_t) ->
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmas_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7920,6 +9220,8 @@ pub unsafe fn vfmas_laneq_f32<const LANE: i32>(a: f32, b: f32, c: float32x4_t) -
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmad_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmadd, LANE = 0))]
@@ -7937,6 +9239,8 @@ pub unsafe fn vfmad_lane_f64<const LANE: i32>(a: f64, b: f64, c: float64x1_t) ->
 }
 
 /// Floating-point fused multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmad_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmla, LANE = 0))]
@@ -7954,6 +9258,8 @@ pub unsafe fn vfmad_laneq_f64<const LANE: i32>(a: f64, b: f64, c: float64x2_t) -
 }
 
 /// Floating-point fused multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmsub))]
@@ -7964,6 +9270,8 @@ pub unsafe fn vfms_f64(a: float64x1_t, b: float64x1_t, c: float64x1_t) -> float6
 }
 
 /// Floating-point fused multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls))]
@@ -7974,6 +9282,8 @@ pub unsafe fn vfmsq_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t) -> float
 }
 
 /// Floating-point fused Multiply-subtract to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_n_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmsub))]
@@ -7983,6 +9293,8 @@ pub unsafe fn vfms_n_f64(a: float64x1_t, b: float64x1_t, c: f64) -> float64x1_t
 }
 
 /// Floating-point fused Multiply-subtract to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_n_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls))]
@@ -7992,6 +9304,8 @@ pub unsafe fn vfmsq_n_f64(a: float64x2_t, b: float64x2_t, c: f64) -> float64x2_t
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8003,6 +9317,8 @@ pub unsafe fn vfms_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8014,6 +9330,8 @@ pub unsafe fn vfms_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8025,6 +9343,8 @@ pub unsafe fn vfmsq_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c:
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8036,6 +9356,8 @@ pub unsafe fn vfmsq_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmsub, LANE = 0))]
@@ -8047,6 +9369,8 @@ pub unsafe fn vfms_lane_f64<const LANE: i32>(a: float64x1_t, b: float64x1_t, c:
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8058,6 +9382,8 @@ pub unsafe fn vfms_laneq_f64<const LANE: i32>(a: float64x1_t, b: float64x1_t, c:
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8069,6 +9395,8 @@ pub unsafe fn vfmsq_lane_f64<const LANE: i32>(a: float64x2_t, b: float64x2_t, c:
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8080,6 +9408,8 @@ pub unsafe fn vfmsq_laneq_f64<const LANE: i32>(a: float64x2_t, b: float64x2_t, c
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmss_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8090,6 +9420,8 @@ pub unsafe fn vfmss_lane_f32<const LANE: i32>(a: f32, b: f32, c: float32x2_t) ->
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmss_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8100,6 +9432,8 @@ pub unsafe fn vfmss_laneq_f32<const LANE: i32>(a: f32, b: f32, c: float32x4_t) -
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsd_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmsub, LANE = 0))]
@@ -8110,6 +9444,8 @@ pub unsafe fn vfmsd_lane_f64<const LANE: i32>(a: f64, b: f64, c: float64x1_t) ->
 }
 
 /// Floating-point fused multiply-subtract to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsd_laneq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmls, LANE = 0))]
@@ -8120,6 +9456,8 @@ pub unsafe fn vfmsd_laneq_f64<const LANE: i32>(a: f64, b: f64, c: float64x2_t) -
 }
 
 /// Divide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdiv_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fdiv))]
@@ -8129,6 +9467,8 @@ pub unsafe fn vdiv_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Divide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdivq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fdiv))]
@@ -8138,6 +9478,8 @@ pub unsafe fn vdivq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Divide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdiv_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fdiv))]
@@ -8147,6 +9489,8 @@ pub unsafe fn vdiv_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Divide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdivq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fdiv))]
@@ -8156,6 +9500,8 @@ pub unsafe fn vdivq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fsub))]
@@ -8165,6 +9511,8 @@ pub unsafe fn vsub_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fsub))]
@@ -8174,6 +9522,8 @@ pub unsafe fn vsubq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -8183,6 +9533,8 @@ pub unsafe fn vsubd_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -8192,6 +9544,8 @@ pub unsafe fn vsubd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -8201,6 +9555,8 @@ pub unsafe fn vaddd_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -8210,6 +9566,8 @@ pub unsafe fn vaddd_u64(a: u64, b: u64) -> u64 {
 }
 
 /// Floating-point add across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddv_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(faddp))]
@@ -8224,6 +9582,8 @@ pub unsafe fn vaddv_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point add across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddvq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(faddp))]
@@ -8238,6 +9598,8 @@ pub unsafe fn vaddvq_f32(a: float32x4_t) -> f32 {
 }
 
 /// Floating-point add across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddvq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(faddp))]
@@ -8252,6 +9614,8 @@ pub unsafe fn vaddvq_f64(a: float64x2_t) -> f64 {
 }
 
 /// Signed Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlv_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(saddlv))]
@@ -8266,6 +9630,8 @@ pub unsafe fn vaddlv_s16(a: int16x4_t) -> i32 {
 }
 
 /// Signed Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlvq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(saddlv))]
@@ -8280,6 +9646,8 @@ pub unsafe fn vaddlvq_s16(a: int16x8_t) -> i32 {
 }
 
 /// Signed Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlv_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(saddlp))]
@@ -8294,6 +9662,8 @@ pub unsafe fn vaddlv_s32(a: int32x2_t) -> i64 {
 }
 
 /// Signed Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlvq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(saddlv))]
@@ -8308,6 +9678,8 @@ pub unsafe fn vaddlvq_s32(a: int32x4_t) -> i64 {
 }
 
 /// Unsigned Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlv_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uaddlv))]
@@ -8322,6 +9694,8 @@ pub unsafe fn vaddlv_u16(a: uint16x4_t) -> u32 {
 }
 
 /// Unsigned Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlvq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uaddlv))]
@@ -8336,6 +9710,8 @@ pub unsafe fn vaddlvq_u16(a: uint16x8_t) -> u32 {
 }
 
 /// Unsigned Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlv_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uaddlp))]
@@ -8350,6 +9726,8 @@ pub unsafe fn vaddlv_u32(a: uint32x2_t) -> u64 {
 }
 
 /// Unsigned Add Long across Vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddlvq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uaddlv))]
@@ -8364,6 +9742,8 @@ pub unsafe fn vaddlvq_u32(a: uint32x4_t) -> u64 {
 }
 
 /// Signed Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ssubw))]
@@ -8374,6 +9754,8 @@ pub unsafe fn vsubw_high_s8(a: int16x8_t, b: int8x16_t) -> int16x8_t {
 }
 
 /// Signed Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ssubw))]
@@ -8384,6 +9766,8 @@ pub unsafe fn vsubw_high_s16(a: int32x4_t, b: int16x8_t) -> int32x4_t {
 }
 
 /// Signed Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ssubw))]
@@ -8394,6 +9778,8 @@ pub unsafe fn vsubw_high_s32(a: int64x2_t, b: int32x4_t) -> int64x2_t {
 }
 
 /// Unsigned Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usubw))]
@@ -8404,6 +9790,8 @@ pub unsafe fn vsubw_high_u8(a: uint16x8_t, b: uint8x16_t) -> uint16x8_t {
 }
 
 /// Unsigned Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usubw))]
@@ -8414,6 +9802,8 @@ pub unsafe fn vsubw_high_u16(a: uint32x4_t, b: uint16x8_t) -> uint32x4_t {
 }
 
 /// Unsigned Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usubw))]
@@ -8424,6 +9814,8 @@ pub unsafe fn vsubw_high_u32(a: uint64x2_t, b: uint32x4_t) -> uint64x2_t {
 }
 
 /// Signed Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ssubl))]
@@ -8437,6 +9829,8 @@ pub unsafe fn vsubl_high_s8(a: int8x16_t, b: int8x16_t) -> int16x8_t {
 }
 
 /// Signed Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ssubl))]
@@ -8450,6 +9844,8 @@ pub unsafe fn vsubl_high_s16(a: int16x8_t, b: int16x8_t) -> int32x4_t {
 }
 
 /// Signed Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ssubl))]
@@ -8463,6 +9859,8 @@ pub unsafe fn vsubl_high_s32(a: int32x4_t, b: int32x4_t) -> int64x2_t {
 }
 
 /// Unsigned Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usubl))]
@@ -8476,6 +9874,8 @@ pub unsafe fn vsubl_high_u8(a: uint8x16_t, b: uint8x16_t) -> uint16x8_t {
 }
 
 /// Unsigned Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usubl))]
@@ -8489,6 +9889,8 @@ pub unsafe fn vsubl_high_u16(a: uint16x8_t, b: uint16x8_t) -> uint32x4_t {
 }
 
 /// Unsigned Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usubl))]
@@ -8502,6 +9904,8 @@ pub unsafe fn vsubl_high_u32(a: uint32x4_t, b: uint32x4_t) -> uint64x2_t {
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_s8)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8515,6 +9919,8 @@ pub unsafe fn vbcaxq_s8(a: int8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_s16)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8528,6 +9934,8 @@ pub unsafe fn vbcaxq_s16(a: int16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_s32)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8541,6 +9949,8 @@ pub unsafe fn vbcaxq_s32(a: int32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_s64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8554,6 +9964,8 @@ pub unsafe fn vbcaxq_s64(a: int64x2_t, b: int64x2_t, c: int64x2_t) -> int64x2_t
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_u8)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8567,6 +9979,8 @@ pub unsafe fn vbcaxq_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_u16)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8580,6 +9994,8 @@ pub unsafe fn vbcaxq_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_u32)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8593,6 +10009,8 @@ pub unsafe fn vbcaxq_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x
 }
 
 /// Bit clear and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vbcaxq_u64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(bcax))]
@@ -8606,6 +10024,8 @@ pub unsafe fn vbcaxq_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> uint64x
 }
 
 /// Floating-point complex add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcadd_rot270_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcadd))]
@@ -8619,6 +10039,8 @@ pub unsafe fn vcadd_rot270_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point complex add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaddq_rot270_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcadd))]
@@ -8632,6 +10054,8 @@ pub unsafe fn vcaddq_rot270_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point complex add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaddq_rot270_f64)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcadd))]
@@ -8645,6 +10069,8 @@ pub unsafe fn vcaddq_rot270_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point complex add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcadd_rot90_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcadd))]
@@ -8658,6 +10084,8 @@ pub unsafe fn vcadd_rot90_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point complex add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaddq_rot90_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcadd))]
@@ -8671,6 +10099,8 @@ pub unsafe fn vcaddq_rot90_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point complex add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaddq_rot90_f64)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcadd))]
@@ -8684,6 +10114,8 @@ pub unsafe fn vcaddq_rot90_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8697,6 +10129,8 @@ pub unsafe fn vcmla_f32(a: float32x2_t, b: float32x2_t, c: float32x2_t) -> float
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8710,6 +10144,8 @@ pub unsafe fn vcmlaq_f32(a: float32x4_t, b: float32x4_t, c: float32x4_t) -> floa
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_f64)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8723,6 +10159,8 @@ pub unsafe fn vcmlaq_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t) -> floa
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot90_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8736,6 +10174,8 @@ pub unsafe fn vcmla_rot90_f32(a: float32x2_t, b: float32x2_t, c: float32x2_t) ->
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot90_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8749,6 +10189,8 @@ pub unsafe fn vcmlaq_rot90_f32(a: float32x4_t, b: float32x4_t, c: float32x4_t) -
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot90_f64)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8762,6 +10204,8 @@ pub unsafe fn vcmlaq_rot90_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t) -
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot180_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8775,6 +10219,8 @@ pub unsafe fn vcmla_rot180_f32(a: float32x2_t, b: float32x2_t, c: float32x2_t) -
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot180_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8788,6 +10234,8 @@ pub unsafe fn vcmlaq_rot180_f32(a: float32x4_t, b: float32x4_t, c: float32x4_t)
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot180_f64)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8801,6 +10249,8 @@ pub unsafe fn vcmlaq_rot180_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t)
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot270_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8814,6 +10264,8 @@ pub unsafe fn vcmla_rot270_f32(a: float32x2_t, b: float32x2_t, c: float32x2_t) -
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot270_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8827,6 +10279,8 @@ pub unsafe fn vcmlaq_rot270_f32(a: float32x4_t, b: float32x4_t, c: float32x4_t)
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot270_f64)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla))]
@@ -8840,6 +10294,8 @@ pub unsafe fn vcmlaq_rot270_f64(a: float64x2_t, b: float64x2_t, c: float64x2_t)
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8851,6 +10307,8 @@ pub unsafe fn vcmla_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8862,6 +10320,8 @@ pub unsafe fn vcmla_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8873,6 +10333,8 @@ pub unsafe fn vcmlaq_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8884,6 +10346,8 @@ pub unsafe fn vcmlaq_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t,
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot90_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8895,6 +10359,8 @@ pub unsafe fn vcmla_rot90_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot90_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8906,6 +10372,8 @@ pub unsafe fn vcmla_rot90_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot90_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8917,6 +10385,8 @@ pub unsafe fn vcmlaq_rot90_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot90_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8928,6 +10398,8 @@ pub unsafe fn vcmlaq_rot90_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot180_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8939,6 +10411,8 @@ pub unsafe fn vcmla_rot180_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot180_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8950,6 +10424,8 @@ pub unsafe fn vcmla_rot180_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot180_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8961,6 +10437,8 @@ pub unsafe fn vcmlaq_rot180_lane_f32<const LANE: i32>(a: float32x4_t, b: float32
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot180_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8972,6 +10450,8 @@ pub unsafe fn vcmlaq_rot180_laneq_f32<const LANE: i32>(a: float32x4_t, b: float3
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot270_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8983,6 +10463,8 @@ pub unsafe fn vcmla_rot270_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmla_rot270_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -8994,6 +10476,8 @@ pub unsafe fn vcmla_rot270_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot270_lane_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -9005,6 +10489,8 @@ pub unsafe fn vcmlaq_rot270_lane_f32<const LANE: i32>(a: float32x4_t, b: float32
 }
 
 /// Floating-point complex multiply accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcmlaq_rot270_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon,fcma")]
 #[cfg_attr(test, assert_instr(fcmla, LANE = 0))]
@@ -9016,6 +10502,8 @@ pub unsafe fn vcmlaq_rot270_laneq_f32<const LANE: i32>(a: float32x4_t, b: float3
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdot_s32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(sdot))]
@@ -9029,6 +10517,8 @@ pub unsafe fn vdot_s32(a: int32x2_t, b: int8x8_t, c: int8x8_t) -> int32x2_t {
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdotq_s32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(sdot))]
@@ -9042,6 +10532,8 @@ pub unsafe fn vdotq_s32(a: int32x4_t, b: int8x16_t, c: int8x16_t) -> int32x4_t {
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdot_u32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(udot))]
@@ -9055,6 +10547,8 @@ pub unsafe fn vdot_u32(a: uint32x2_t, b: uint8x8_t, c: uint8x8_t) -> uint32x2_t
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdotq_u32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(udot))]
@@ -9068,6 +10562,8 @@ pub unsafe fn vdotq_u32(a: uint32x4_t, b: uint8x16_t, c: uint8x16_t) -> uint32x4
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdot_lane_s32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(sdot, LANE = 0))]
@@ -9079,6 +10575,8 @@ pub unsafe fn vdot_lane_s32<const LANE: i32>(a: int32x2_t, b: int8x8_t, c: int8x
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdot_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(sdot, LANE = 0))]
@@ -9090,6 +10588,8 @@ pub unsafe fn vdot_laneq_s32<const LANE: i32>(a: int32x2_t, b: int8x8_t, c: int8
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdotq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(sdot, LANE = 0))]
@@ -9101,6 +10601,8 @@ pub unsafe fn vdotq_lane_s32<const LANE: i32>(a: int32x4_t, b: int8x16_t, c: int
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdotq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(sdot, LANE = 0))]
@@ -9112,6 +10614,8 @@ pub unsafe fn vdotq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int8x16_t, c: in
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdot_lane_u32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(udot, LANE = 0))]
@@ -9123,6 +10627,8 @@ pub unsafe fn vdot_lane_u32<const LANE: i32>(a: uint32x2_t, b: uint8x8_t, c: uin
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdot_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(udot, LANE = 0))]
@@ -9134,6 +10640,8 @@ pub unsafe fn vdot_laneq_u32<const LANE: i32>(a: uint32x2_t, b: uint8x8_t, c: ui
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdotq_lane_u32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(udot, LANE = 0))]
@@ -9145,6 +10653,8 @@ pub unsafe fn vdotq_lane_u32<const LANE: i32>(a: uint32x4_t, b: uint8x16_t, c: u
 }
 
 /// Dot product arithmetic
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdotq_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon,dotprod")]
 #[cfg_attr(test, assert_instr(udot, LANE = 0))]
@@ -9156,6 +10666,8 @@ pub unsafe fn vdotq_laneq_u32<const LANE: i32>(a: uint32x4_t, b: uint8x16_t, c:
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmax))]
@@ -9170,6 +10682,8 @@ pub unsafe fn vmax_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmax))]
@@ -9184,6 +10698,8 @@ pub unsafe fn vmaxq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point Maximum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxnm_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnm))]
@@ -9198,6 +10714,8 @@ pub unsafe fn vmaxnm_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point Maximum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxnmq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnm))]
@@ -9212,6 +10730,8 @@ pub unsafe fn vmaxnmq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point maximum number across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxnmv_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmp))]
@@ -9226,6 +10746,8 @@ pub unsafe fn vmaxnmv_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point maximum number across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxnmvq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmp))]
@@ -9240,6 +10762,8 @@ pub unsafe fn vmaxnmvq_f64(a: float64x2_t) -> f64 {
 }
 
 /// Floating-point maximum number across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxnmvq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmv))]
@@ -9254,6 +10778,8 @@ pub unsafe fn vmaxnmvq_f32(a: float32x4_t) -> f32 {
 }
 
 /// Floating-point Maximum Number Pairwise (vector).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmaxnm_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmp))]
@@ -9268,6 +10794,8 @@ pub unsafe fn vpmaxnm_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point Maximum Number Pairwise (vector).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmaxnmq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmp))]
@@ -9282,6 +10810,8 @@ pub unsafe fn vpmaxnmq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point Maximum Number Pairwise (vector).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmaxnmq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmp))]
@@ -9296,6 +10826,8 @@ pub unsafe fn vpmaxnmq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point maximum number pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmaxnms_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmp))]
@@ -9310,6 +10842,8 @@ pub unsafe fn vpmaxnms_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point maximum number pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmaxnmqd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxnmp))]
@@ -9324,6 +10858,8 @@ pub unsafe fn vpmaxnmqd_f64(a: float64x2_t) -> f64 {
 }
 
 /// Floating-point maximum pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmaxs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxp))]
@@ -9338,6 +10874,8 @@ pub unsafe fn vpmaxs_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point maximum pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmaxqd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmaxp))]
@@ -9352,6 +10890,8 @@ pub unsafe fn vpmaxqd_f64(a: float64x2_t) -> f64 {
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmin))]
@@ -9366,6 +10906,8 @@ pub unsafe fn vmin_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fmin))]
@@ -9380,6 +10922,8 @@ pub unsafe fn vminq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point Minimum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminnm_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnm))]
@@ -9394,6 +10938,8 @@ pub unsafe fn vminnm_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point Minimum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminnmq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnm))]
@@ -9408,6 +10954,8 @@ pub unsafe fn vminnmq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point minimum number across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminnmv_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmp))]
@@ -9422,6 +10970,8 @@ pub unsafe fn vminnmv_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point minimum number across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminnmvq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmp))]
@@ -9436,6 +10986,8 @@ pub unsafe fn vminnmvq_f64(a: float64x2_t) -> f64 {
 }
 
 /// Floating-point minimum number across vector
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminnmvq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmv))]
@@ -9450,6 +11002,8 @@ pub unsafe fn vminnmvq_f32(a: float32x4_t) -> f32 {
 }
 
 /// Vector move
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovl_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sxtl2))]
@@ -9460,6 +11014,8 @@ pub unsafe fn vmovl_high_s8(a: int8x16_t) -> int16x8_t {
 }
 
 /// Vector move
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovl_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sxtl2))]
@@ -9470,6 +11026,8 @@ pub unsafe fn vmovl_high_s16(a: int16x8_t) -> int32x4_t {
 }
 
 /// Vector move
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovl_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sxtl2))]
@@ -9480,6 +11038,8 @@ pub unsafe fn vmovl_high_s32(a: int32x4_t) -> int64x2_t {
 }
 
 /// Vector move
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovl_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uxtl2))]
@@ -9490,6 +11050,8 @@ pub unsafe fn vmovl_high_u8(a: uint8x16_t) -> uint16x8_t {
 }
 
 /// Vector move
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovl_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uxtl2))]
@@ -9500,6 +11062,8 @@ pub unsafe fn vmovl_high_u16(a: uint16x8_t) -> uint32x4_t {
 }
 
 /// Vector move
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmovl_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uxtl2))]
@@ -9510,6 +11074,8 @@ pub unsafe fn vmovl_high_u32(a: uint32x4_t) -> uint64x2_t {
 }
 
 /// Floating-point add pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpaddq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(faddp))]
@@ -9524,6 +11090,8 @@ pub unsafe fn vpaddq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point add pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpaddq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(faddp))]
@@ -9538,6 +11106,8 @@ pub unsafe fn vpaddq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point add pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpadds_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -9549,6 +11119,8 @@ pub unsafe fn vpadds_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point add pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpaddd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -9560,6 +11132,8 @@ pub unsafe fn vpaddd_f64(a: float64x2_t) -> f64 {
 }
 
 /// Floating-point Minimum Number Pairwise (vector).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpminnm_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmp))]
@@ -9574,6 +11148,8 @@ pub unsafe fn vpminnm_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point Minimum Number Pairwise (vector).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpminnmq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmp))]
@@ -9588,6 +11164,8 @@ pub unsafe fn vpminnmq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point Minimum Number Pairwise (vector).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpminnmq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmp))]
@@ -9602,6 +11180,8 @@ pub unsafe fn vpminnmq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point minimum number pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpminnms_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmp))]
@@ -9616,6 +11196,8 @@ pub unsafe fn vpminnms_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point minimum number pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpminnmqd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminnmp))]
@@ -9630,6 +11212,8 @@ pub unsafe fn vpminnmqd_f64(a: float64x2_t) -> f64 {
 }
 
 /// Floating-point minimum pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpmins_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminp))]
@@ -9644,6 +11228,8 @@ pub unsafe fn vpmins_f32(a: float32x2_t) -> f32 {
 }
 
 /// Floating-point minimum pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpminqd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fminp))]
@@ -9658,6 +11244,8 @@ pub unsafe fn vpminqd_f64(a: float64x2_t) -> f64 {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmullh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull))]
@@ -9669,6 +11257,8 @@ pub unsafe fn vqdmullh_s16(a: i16, b: i16) -> i32 {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulls_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull))]
@@ -9683,6 +11273,8 @@ pub unsafe fn vqdmulls_s32(a: i32, b: i32) -> i64 {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2))]
@@ -9694,6 +11286,8 @@ pub unsafe fn vqdmull_high_s16(a: int16x8_t, b: int16x8_t) -> int32x4_t {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2))]
@@ -9705,6 +11299,8 @@ pub unsafe fn vqdmull_high_s32(a: int32x4_t, b: int32x4_t) -> int64x2_t {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2))]
@@ -9716,6 +11312,8 @@ pub unsafe fn vqdmull_high_n_s16(a: int16x8_t, b: i16) -> int32x4_t {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2))]
@@ -9727,6 +11325,8 @@ pub unsafe fn vqdmull_high_n_s32(a: int32x4_t, b: i32) -> int64x2_t {
 }
 
 /// Vector saturating doubling long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, N = 4))]
@@ -9739,6 +11339,8 @@ pub unsafe fn vqdmull_laneq_s16<const N: i32>(a: int16x4_t, b: int16x8_t) -> int
 }
 
 /// Vector saturating doubling long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, N = 2))]
@@ -9751,6 +11353,8 @@ pub unsafe fn vqdmull_laneq_s32<const N: i32>(a: int32x2_t, b: int32x4_t) -> int
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmullh_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, N = 2))]
@@ -9763,6 +11367,8 @@ pub unsafe fn vqdmullh_lane_s16<const N: i32>(a: i16, b: int16x4_t) -> i32 {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmullh_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, N = 4))]
@@ -9775,6 +11381,8 @@ pub unsafe fn vqdmullh_laneq_s16<const N: i32>(a: i16, b: int16x8_t) -> i32 {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulls_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, N = 1))]
@@ -9787,6 +11395,8 @@ pub unsafe fn vqdmulls_lane_s32<const N: i32>(a: i32, b: int32x2_t) -> i64 {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulls_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, N = 2))]
@@ -9799,6 +11409,8 @@ pub unsafe fn vqdmulls_laneq_s32<const N: i32>(a: i32, b: int32x4_t) -> i64 {
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2, N = 2))]
@@ -9812,6 +11424,8 @@ pub unsafe fn vqdmull_high_lane_s16<const N: i32>(a: int16x8_t, b: int16x4_t) ->
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2, N = 1))]
@@ -9825,6 +11439,8 @@ pub unsafe fn vqdmull_high_lane_s32<const N: i32>(a: int32x4_t, b: int32x2_t) ->
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2, N = 4))]
@@ -9838,6 +11454,8 @@ pub unsafe fn vqdmull_high_laneq_s16<const N: i32>(a: int16x8_t, b: int16x8_t) -
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_high_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull2, N = 2))]
@@ -9851,6 +11469,8 @@ pub unsafe fn vqdmull_high_laneq_s32<const N: i32>(a: int32x4_t, b: int32x4_t) -
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2))]
@@ -9860,6 +11480,8 @@ pub unsafe fn vqdmlal_high_s16(a: int32x4_t, b: int16x8_t, c: int16x8_t) -> int3
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2))]
@@ -9869,6 +11491,8 @@ pub unsafe fn vqdmlal_high_s32(a: int64x2_t, b: int32x4_t, c: int32x4_t) -> int6
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2))]
@@ -9878,6 +11502,8 @@ pub unsafe fn vqdmlal_high_n_s16(a: int32x4_t, b: int16x8_t, c: i16) -> int32x4_
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2))]
@@ -9887,6 +11513,8 @@ pub unsafe fn vqdmlal_high_n_s32(a: int64x2_t, b: int32x4_t, c: i32) -> int64x2_
 }
 
 /// Vector widening saturating doubling multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal, N = 2))]
@@ -9898,6 +11526,8 @@ pub unsafe fn vqdmlal_laneq_s16<const N: i32>(a: int32x4_t, b: int16x4_t, c: int
 }
 
 /// Vector widening saturating doubling multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal, N = 1))]
@@ -9909,6 +11539,8 @@ pub unsafe fn vqdmlal_laneq_s32<const N: i32>(a: int64x2_t, b: int32x2_t, c: int
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2, N = 1))]
@@ -9920,6 +11552,8 @@ pub unsafe fn vqdmlal_high_lane_s16<const N: i32>(a: int32x4_t, b: int16x8_t, c:
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2, N = 1))]
@@ -9931,6 +11565,8 @@ pub unsafe fn vqdmlal_high_laneq_s16<const N: i32>(a: int32x4_t, b: int16x8_t, c
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2, N = 1))]
@@ -9942,6 +11578,8 @@ pub unsafe fn vqdmlal_high_lane_s32<const N: i32>(a: int64x2_t, b: int32x4_t, c:
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_high_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal2, N = 1))]
@@ -9953,6 +11591,8 @@ pub unsafe fn vqdmlal_high_laneq_s32<const N: i32>(a: int64x2_t, b: int32x4_t, c
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlalh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull))]
@@ -9963,6 +11603,8 @@ pub unsafe fn vqdmlalh_s16(a: i32, b: i16, c: i16) -> i32 {
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlals_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull))]
@@ -9973,6 +11615,8 @@ pub unsafe fn vqdmlals_s32(a: i64, b: i32, c: i32) -> i64 {
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlalh_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal, LANE = 0))]
@@ -9984,6 +11628,8 @@ pub unsafe fn vqdmlalh_lane_s16<const LANE: i32>(a: i32, b: i16, c: int16x4_t) -
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlalh_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlal, LANE = 0))]
@@ -9995,6 +11641,8 @@ pub unsafe fn vqdmlalh_laneq_s16<const LANE: i32>(a: i32, b: i16, c: int16x8_t)
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlals_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, LANE = 0))]
@@ -10006,6 +11654,8 @@ pub unsafe fn vqdmlals_lane_s32<const LANE: i32>(a: i64, b: i32, c: int32x2_t) -
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlals_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, LANE = 0))]
@@ -10017,6 +11667,8 @@ pub unsafe fn vqdmlals_laneq_s32<const LANE: i32>(a: i64, b: i32, c: int32x4_t)
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2))]
@@ -10026,6 +11678,8 @@ pub unsafe fn vqdmlsl_high_s16(a: int32x4_t, b: int16x8_t, c: int16x8_t) -> int3
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2))]
@@ -10035,6 +11689,8 @@ pub unsafe fn vqdmlsl_high_s32(a: int64x2_t, b: int32x4_t, c: int32x4_t) -> int6
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2))]
@@ -10044,6 +11700,8 @@ pub unsafe fn vqdmlsl_high_n_s16(a: int32x4_t, b: int16x8_t, c: i16) -> int32x4_
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2))]
@@ -10053,6 +11711,8 @@ pub unsafe fn vqdmlsl_high_n_s32(a: int64x2_t, b: int32x4_t, c: i32) -> int64x2_
 }
 
 /// Vector widening saturating doubling multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl, N = 2))]
@@ -10064,6 +11724,8 @@ pub unsafe fn vqdmlsl_laneq_s16<const N: i32>(a: int32x4_t, b: int16x4_t, c: int
 }
 
 /// Vector widening saturating doubling multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl, N = 1))]
@@ -10075,6 +11737,8 @@ pub unsafe fn vqdmlsl_laneq_s32<const N: i32>(a: int64x2_t, b: int32x2_t, c: int
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2, N = 1))]
@@ -10086,6 +11750,8 @@ pub unsafe fn vqdmlsl_high_lane_s16<const N: i32>(a: int32x4_t, b: int16x8_t, c:
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2, N = 1))]
@@ -10097,6 +11763,8 @@ pub unsafe fn vqdmlsl_high_laneq_s16<const N: i32>(a: int32x4_t, b: int16x8_t, c
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2, N = 1))]
@@ -10108,6 +11776,8 @@ pub unsafe fn vqdmlsl_high_lane_s32<const N: i32>(a: int64x2_t, b: int32x4_t, c:
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_high_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl2, N = 1))]
@@ -10119,6 +11789,8 @@ pub unsafe fn vqdmlsl_high_laneq_s32<const N: i32>(a: int64x2_t, b: int32x4_t, c
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlslh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull))]
@@ -10129,6 +11801,8 @@ pub unsafe fn vqdmlslh_s16(a: i32, b: i16, c: i16) -> i32 {
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsls_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull))]
@@ -10139,6 +11813,8 @@ pub unsafe fn vqdmlsls_s32(a: i64, b: i32, c: i32) -> i64 {
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlslh_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl, LANE = 0))]
@@ -10150,6 +11826,8 @@ pub unsafe fn vqdmlslh_lane_s16<const LANE: i32>(a: i32, b: i16, c: int16x4_t) -
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlslh_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmlsl, LANE = 0))]
@@ -10161,6 +11839,8 @@ pub unsafe fn vqdmlslh_laneq_s16<const LANE: i32>(a: i32, b: i16, c: int16x8_t)
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsls_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, LANE = 0))]
@@ -10172,6 +11852,8 @@ pub unsafe fn vqdmlsls_lane_s32<const LANE: i32>(a: i64, b: i32, c: int32x2_t) -
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsls_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmull, LANE = 0))]
@@ -10183,6 +11865,8 @@ pub unsafe fn vqdmlsls_laneq_s32<const LANE: i32>(a: i64, b: i32, c: int32x4_t)
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh))]
@@ -10194,6 +11878,8 @@ pub unsafe fn vqdmulhh_s16(a: i16, b: i16) -> i16 {
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhs_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh))]
@@ -10205,6 +11891,8 @@ pub unsafe fn vqdmulhs_s32(a: i32, b: i32) -> i32 {
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhh_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, N = 2))]
@@ -10217,6 +11905,8 @@ pub unsafe fn vqdmulhh_lane_s16<const N: i32>(a: i16, b: int16x4_t) -> i16 {
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhh_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, N = 2))]
@@ -10229,6 +11919,8 @@ pub unsafe fn vqdmulhh_laneq_s16<const N: i32>(a: i16, b: int16x8_t) -> i16 {
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhs_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, N = 1))]
@@ -10241,6 +11933,8 @@ pub unsafe fn vqdmulhs_lane_s32<const N: i32>(a: i32, b: int32x2_t) -> i32 {
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhs_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, N = 1))]
@@ -10253,6 +11947,8 @@ pub unsafe fn vqdmulhs_laneq_s32<const N: i32>(a: i32, b: int32x4_t) -> i32 {
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, LANE = 0))]
@@ -10264,6 +11960,8 @@ pub unsafe fn vqdmulh_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t) -> i
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, LANE = 0))]
@@ -10275,6 +11973,8 @@ pub unsafe fn vqdmulhq_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x4_t) ->
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, LANE = 0))]
@@ -10286,6 +11986,8 @@ pub unsafe fn vqdmulh_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t) -> i
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqdmulh, LANE = 0))]
@@ -10297,6 +11999,8 @@ pub unsafe fn vqdmulhq_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x2_t) ->
 }
 
 /// Saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovnh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtn))]
@@ -10306,6 +12010,8 @@ pub unsafe fn vqmovnh_s16(a: i16) -> i8 {
 }
 
 /// Saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovns_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtn))]
@@ -10315,6 +12021,8 @@ pub unsafe fn vqmovns_s32(a: i32) -> i16 {
 }
 
 /// Saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovnh_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqxtn))]
@@ -10324,6 +12032,8 @@ pub unsafe fn vqmovnh_u16(a: u16) -> u8 {
 }
 
 /// Saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovns_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqxtn))]
@@ -10333,6 +12043,8 @@ pub unsafe fn vqmovns_u32(a: u32) -> u16 {
 }
 
 /// Saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovnd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtn))]
@@ -10347,6 +12059,8 @@ pub unsafe fn vqmovnd_s64(a: i64) -> i32 {
 }
 
 /// Saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovnd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqxtn))]
@@ -10361,6 +12075,8 @@ pub unsafe fn vqmovnd_u64(a: u64) -> u32 {
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtn2))]
@@ -10370,6 +12086,8 @@ pub unsafe fn vqmovn_high_s16(a: int8x8_t, b: int16x8_t) -> int8x16_t {
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtn2))]
@@ -10379,6 +12097,8 @@ pub unsafe fn vqmovn_high_s32(a: int16x4_t, b: int32x4_t) -> int16x8_t {
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_high_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtn2))]
@@ -10388,6 +12108,8 @@ pub unsafe fn vqmovn_high_s64(a: int32x2_t, b: int64x2_t) -> int32x4_t {
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqxtn2))]
@@ -10397,6 +12119,8 @@ pub unsafe fn vqmovn_high_u16(a: uint8x8_t, b: uint16x8_t) -> uint8x16_t {
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqxtn2))]
@@ -10406,6 +12130,8 @@ pub unsafe fn vqmovn_high_u32(a: uint16x4_t, b: uint32x4_t) -> uint16x8_t {
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_high_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqxtn2))]
@@ -10415,6 +12141,8 @@ pub unsafe fn vqmovn_high_u64(a: uint32x2_t, b: uint64x2_t) -> uint32x4_t {
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovunh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtun))]
@@ -10424,6 +12152,8 @@ pub unsafe fn vqmovunh_s16(a: i16) -> u8 {
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovuns_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtun))]
@@ -10433,6 +12163,8 @@ pub unsafe fn vqmovuns_s32(a: i32) -> u16 {
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovund_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtun))]
@@ -10442,6 +12174,8 @@ pub unsafe fn vqmovund_s64(a: i64) -> u32 {
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovun_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtun2))]
@@ -10451,6 +12185,8 @@ pub unsafe fn vqmovun_high_s16(a: uint8x8_t, b: int16x8_t) -> uint8x16_t {
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovun_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtun2))]
@@ -10460,6 +12196,8 @@ pub unsafe fn vqmovun_high_s32(a: uint16x4_t, b: int32x4_t) -> uint16x8_t {
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovun_high_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqxtun2))]
@@ -10469,6 +12207,8 @@ pub unsafe fn vqmovun_high_s64(a: uint32x2_t, b: int64x2_t) -> uint32x4_t {
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrdmulh))]
@@ -10478,6 +12218,8 @@ pub unsafe fn vqrdmulhh_s16(a: i16, b: i16) -> i16 {
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhs_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrdmulh))]
@@ -10487,6 +12229,8 @@ pub unsafe fn vqrdmulhs_s32(a: i32, b: i32) -> i32 {
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhh_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrdmulh, LANE = 1))]
@@ -10498,6 +12242,8 @@ pub unsafe fn vqrdmulhh_lane_s16<const LANE: i32>(a: i16, b: int16x4_t) -> i16 {
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhh_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrdmulh, LANE = 1))]
@@ -10509,6 +12255,8 @@ pub unsafe fn vqrdmulhh_laneq_s16<const LANE: i32>(a: i16, b: int16x8_t) -> i16
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhs_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrdmulh, LANE = 1))]
@@ -10520,6 +12268,8 @@ pub unsafe fn vqrdmulhs_lane_s32<const LANE: i32>(a: i32, b: int32x2_t) -> i32 {
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhs_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrdmulh, LANE = 1))]
@@ -10531,6 +12281,8 @@ pub unsafe fn vqrdmulhs_laneq_s32<const LANE: i32>(a: i32, b: int32x4_t) -> i32
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlah_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah))]
@@ -10545,6 +12297,8 @@ pub unsafe fn vqrdmlah_s16(a: int16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah))]
@@ -10559,6 +12313,8 @@ pub unsafe fn vqrdmlahq_s16(a: int16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlah_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah))]
@@ -10573,6 +12329,8 @@ pub unsafe fn vqrdmlah_s32(a: int32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah))]
@@ -10587,6 +12345,8 @@ pub unsafe fn vqrdmlahq_s32(a: int32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahh_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah))]
@@ -10599,6 +12359,8 @@ pub unsafe fn vqrdmlahh_s16(a: i16, b: i16, c: i16) -> i16 {
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahs_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah))]
@@ -10611,6 +12373,8 @@ pub unsafe fn vqrdmlahs_s32(a: i32, b: i32, c: i32) -> i32 {
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlah_lane_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10623,6 +12387,8 @@ pub unsafe fn vqrdmlah_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c:
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlah_laneq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10635,6 +12401,8 @@ pub unsafe fn vqrdmlah_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c:
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahq_lane_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10647,6 +12415,8 @@ pub unsafe fn vqrdmlahq_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c:
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahq_laneq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10659,6 +12429,8 @@ pub unsafe fn vqrdmlahq_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlah_lane_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10671,6 +12443,8 @@ pub unsafe fn vqrdmlah_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c:
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlah_laneq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10683,6 +12457,8 @@ pub unsafe fn vqrdmlah_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c:
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahq_lane_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10695,6 +12471,8 @@ pub unsafe fn vqrdmlahq_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c:
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahq_laneq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10707,6 +12485,8 @@ pub unsafe fn vqrdmlahq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahh_lane_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10718,6 +12498,8 @@ pub unsafe fn vqrdmlahh_lane_s16<const LANE: i32>(a: i16, b: i16, c: int16x4_t)
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahh_laneq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10729,6 +12511,8 @@ pub unsafe fn vqrdmlahh_laneq_s16<const LANE: i32>(a: i16, b: i16, c: int16x8_t)
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahs_lane_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10740,6 +12524,8 @@ pub unsafe fn vqrdmlahs_lane_s32<const LANE: i32>(a: i32, b: i32, c: int32x2_t)
 }
 
 /// Signed saturating rounding doubling multiply accumulate returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlahs_laneq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlah, LANE = 1))]
@@ -10751,6 +12537,8 @@ pub unsafe fn vqrdmlahs_laneq_s32<const LANE: i32>(a: i32, b: i32, c: int32x4_t)
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlsh_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh))]
@@ -10765,6 +12553,8 @@ pub unsafe fn vqrdmlsh_s16(a: int16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh))]
@@ -10779,6 +12569,8 @@ pub unsafe fn vqrdmlshq_s16(a: int16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlsh_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh))]
@@ -10793,6 +12585,8 @@ pub unsafe fn vqrdmlsh_s32(a: int32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh))]
@@ -10807,6 +12601,8 @@ pub unsafe fn vqrdmlshq_s32(a: int32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshh_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh))]
@@ -10819,6 +12615,8 @@ pub unsafe fn vqrdmlshh_s16(a: i16, b: i16, c: i16) -> i16 {
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshs_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh))]
@@ -10831,6 +12629,8 @@ pub unsafe fn vqrdmlshs_s32(a: i32, b: i32, c: i32) -> i32 {
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlsh_lane_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10843,6 +12643,8 @@ pub unsafe fn vqrdmlsh_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c:
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlsh_laneq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10855,6 +12657,8 @@ pub unsafe fn vqrdmlsh_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c:
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshq_lane_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10867,6 +12671,8 @@ pub unsafe fn vqrdmlshq_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c:
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshq_laneq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10879,6 +12685,8 @@ pub unsafe fn vqrdmlshq_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlsh_lane_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10891,6 +12699,8 @@ pub unsafe fn vqrdmlsh_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c:
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlsh_laneq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10903,6 +12713,8 @@ pub unsafe fn vqrdmlsh_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c:
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshq_lane_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10915,6 +12727,8 @@ pub unsafe fn vqrdmlshq_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c:
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshq_laneq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10927,6 +12741,8 @@ pub unsafe fn vqrdmlshq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshh_lane_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10938,6 +12754,8 @@ pub unsafe fn vqrdmlshh_lane_s16<const LANE: i32>(a: i16, b: i16, c: int16x4_t)
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshh_laneq_s16)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10949,6 +12767,8 @@ pub unsafe fn vqrdmlshh_laneq_s16<const LANE: i32>(a: i16, b: i16, c: int16x8_t)
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshs_lane_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10960,6 +12780,8 @@ pub unsafe fn vqrdmlshs_lane_s32<const LANE: i32>(a: i32, b: i32, c: int32x2_t)
 }
 
 /// Signed saturating rounding doubling multiply subtract returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmlshs_laneq_s32)
 #[inline]
 #[target_feature(enable = "rdm")]
 #[cfg_attr(test, assert_instr(sqrdmlsh, LANE = 1))]
@@ -10971,6 +12793,8 @@ pub unsafe fn vqrdmlshs_laneq_s32<const LANE: i32>(a: i32, b: i32, c: int32x4_t)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshls_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshl))]
@@ -10985,6 +12809,8 @@ pub unsafe fn vqrshls_s32(a: i32, b: i32) -> i32 {
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshld_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshl))]
@@ -10999,6 +12825,8 @@ pub unsafe fn vqrshld_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlb_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshl))]
@@ -11010,6 +12838,8 @@ pub unsafe fn vqrshlb_s8(a: i8, b: i8) -> i8 {
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshl))]
@@ -11021,6 +12851,8 @@ pub unsafe fn vqrshlh_s16(a: i16, b: i16) -> i16 {
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshls_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshl))]
@@ -11035,6 +12867,8 @@ pub unsafe fn vqrshls_u32(a: u32, b: i32) -> u32 {
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshld_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshl))]
@@ -11049,6 +12883,8 @@ pub unsafe fn vqrshld_u64(a: u64, b: i64) -> u64 {
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlb_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshl))]
@@ -11060,6 +12896,8 @@ pub unsafe fn vqrshlb_u8(a: u8, b: i8) -> u8 {
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlh_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshl))]
@@ -11071,6 +12909,8 @@ pub unsafe fn vqrshlh_u16(a: u16, b: i16) -> u16 {
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrnh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrn, N = 2))]
@@ -11083,6 +12923,8 @@ pub unsafe fn vqrshrnh_n_s16<const N: i32>(a: i16) -> i8 {
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrns_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrn, N = 2))]
@@ -11095,6 +12937,8 @@ pub unsafe fn vqrshrns_n_s32<const N: i32>(a: i32) -> i16 {
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrnd_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrn, N = 2))]
@@ -11107,6 +12951,8 @@ pub unsafe fn vqrshrnd_n_s64<const N: i32>(a: i64) -> i32 {
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrn2, N = 2))]
@@ -11118,6 +12964,8 @@ pub unsafe fn vqrshrn_high_n_s16<const N: i32>(a: int8x8_t, b: int16x8_t) -> int
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrn2, N = 2))]
@@ -11129,6 +12977,8 @@ pub unsafe fn vqrshrn_high_n_s32<const N: i32>(a: int16x4_t, b: int32x4_t) -> in
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_high_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrn2, N = 2))]
@@ -11140,6 +12990,8 @@ pub unsafe fn vqrshrn_high_n_s64<const N: i32>(a: int32x2_t, b: int64x2_t) -> in
 }
 
 /// Unsigned saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrnh_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshrn, N = 2))]
@@ -11152,6 +13004,8 @@ pub unsafe fn vqrshrnh_n_u16<const N: i32>(a: u16) -> u8 {
 }
 
 /// Unsigned saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrns_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshrn, N = 2))]
@@ -11164,6 +13018,8 @@ pub unsafe fn vqrshrns_n_u32<const N: i32>(a: u32) -> u16 {
 }
 
 /// Unsigned saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrnd_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshrn, N = 2))]
@@ -11176,6 +13032,8 @@ pub unsafe fn vqrshrnd_n_u64<const N: i32>(a: u64) -> u32 {
 }
 
 /// Unsigned saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshrn2, N = 2))]
@@ -11187,6 +13045,8 @@ pub unsafe fn vqrshrn_high_n_u16<const N: i32>(a: uint8x8_t, b: uint16x8_t) -> u
 }
 
 /// Unsigned saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshrn2, N = 2))]
@@ -11198,6 +13058,8 @@ pub unsafe fn vqrshrn_high_n_u32<const N: i32>(a: uint16x4_t, b: uint32x4_t) ->
 }
 
 /// Unsigned saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_high_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqrshrn2, N = 2))]
@@ -11209,6 +13071,8 @@ pub unsafe fn vqrshrn_high_n_u64<const N: i32>(a: uint32x2_t, b: uint64x2_t) ->
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrunh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrun, N = 2))]
@@ -11221,6 +13085,8 @@ pub unsafe fn vqrshrunh_n_s16<const N: i32>(a: i16) -> u8 {
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshruns_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrun, N = 2))]
@@ -11233,6 +13099,8 @@ pub unsafe fn vqrshruns_n_s32<const N: i32>(a: i32) -> u16 {
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrund_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrun, N = 2))]
@@ -11245,6 +13113,8 @@ pub unsafe fn vqrshrund_n_s64<const N: i32>(a: i64) -> u32 {
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrun2, N = 2))]
@@ -11256,6 +13126,8 @@ pub unsafe fn vqrshrun_high_n_s16<const N: i32>(a: uint8x8_t, b: int16x8_t) -> u
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrun2, N = 2))]
@@ -11267,6 +13139,8 @@ pub unsafe fn vqrshrun_high_n_s32<const N: i32>(a: uint16x4_t, b: int32x4_t) ->
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_high_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqrshrun2, N = 2))]
@@ -11278,6 +13152,8 @@ pub unsafe fn vqrshrun_high_n_s64<const N: i32>(a: uint32x2_t, b: int64x2_t) ->
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshld_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl))]
@@ -11292,6 +13168,8 @@ pub unsafe fn vqshld_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlb_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl))]
@@ -11302,6 +13180,8 @@ pub unsafe fn vqshlb_s8(a: i8, b: i8) -> i8 {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl))]
@@ -11312,6 +13192,8 @@ pub unsafe fn vqshlh_s16(a: i16, b: i16) -> i16 {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshls_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl))]
@@ -11322,6 +13204,8 @@ pub unsafe fn vqshls_s32(a: i32, b: i32) -> i32 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshld_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl))]
@@ -11336,6 +13220,8 @@ pub unsafe fn vqshld_u64(a: u64, b: i64) -> u64 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlb_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl))]
@@ -11346,6 +13232,8 @@ pub unsafe fn vqshlb_u8(a: u8, b: i8) -> u8 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlh_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl))]
@@ -11356,6 +13244,8 @@ pub unsafe fn vqshlh_u16(a: u16, b: i16) -> u16 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshls_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl))]
@@ -11366,6 +13256,8 @@ pub unsafe fn vqshls_u32(a: u32, b: i32) -> u32 {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlb_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl, N = 2))]
@@ -11377,6 +13269,8 @@ pub unsafe fn vqshlb_n_s8<const N: i32>(a: i8) -> i8 {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl, N = 2))]
@@ -11388,6 +13282,8 @@ pub unsafe fn vqshlh_n_s16<const N: i32>(a: i16) -> i16 {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshls_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl, N = 2))]
@@ -11399,6 +13295,8 @@ pub unsafe fn vqshls_n_s32<const N: i32>(a: i32) -> i32 {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshld_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshl, N = 2))]
@@ -11410,6 +13308,8 @@ pub unsafe fn vqshld_n_s64<const N: i32>(a: i64) -> i64 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlb_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl, N = 2))]
@@ -11421,6 +13321,8 @@ pub unsafe fn vqshlb_n_u8<const N: i32>(a: u8) -> u8 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlh_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl, N = 2))]
@@ -11432,6 +13334,8 @@ pub unsafe fn vqshlh_n_u16<const N: i32>(a: u16) -> u16 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshls_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl, N = 2))]
@@ -11443,6 +13347,8 @@ pub unsafe fn vqshls_n_u32<const N: i32>(a: u32) -> u32 {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshld_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshl, N = 2))]
@@ -11454,6 +13360,8 @@ pub unsafe fn vqshld_n_u64<const N: i32>(a: u64) -> u64 {
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlub_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshlu, N = 2))]
@@ -11465,6 +13373,8 @@ pub unsafe fn vqshlub_n_s8<const N: i32>(a: i8) -> u8 {
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshlu, N = 2))]
@@ -11476,6 +13386,8 @@ pub unsafe fn vqshluh_n_s16<const N: i32>(a: i16) -> u16 {
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlus_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshlu, N = 2))]
@@ -11487,6 +13399,8 @@ pub unsafe fn vqshlus_n_s32<const N: i32>(a: i32) -> u32 {
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlud_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshlu, N = 2))]
@@ -11498,6 +13412,8 @@ pub unsafe fn vqshlud_n_s64<const N: i32>(a: i64) -> u64 {
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrnd_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrn, N = 2))]
@@ -11514,6 +13430,8 @@ pub unsafe fn vqshrnd_n_s64<const N: i32>(a: i64) -> i32 {
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrnh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrn, N = 2))]
@@ -11525,6 +13443,8 @@ pub unsafe fn vqshrnh_n_s16<const N: i32>(a: i16) -> i8 {
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrns_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrn, N = 2))]
@@ -11536,6 +13456,8 @@ pub unsafe fn vqshrns_n_s32<const N: i32>(a: i32) -> i16 {
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrn2, N = 2))]
@@ -11547,6 +13469,8 @@ pub unsafe fn vqshrn_high_n_s16<const N: i32>(a: int8x8_t, b: int16x8_t) -> int8
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrn2, N = 2))]
@@ -11558,6 +13482,8 @@ pub unsafe fn vqshrn_high_n_s32<const N: i32>(a: int16x4_t, b: int32x4_t) -> int
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_high_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrn2, N = 2))]
@@ -11569,6 +13495,8 @@ pub unsafe fn vqshrn_high_n_s64<const N: i32>(a: int32x2_t, b: int64x2_t) -> int
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrnd_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshrn, N = 2))]
@@ -11585,6 +13513,8 @@ pub unsafe fn vqshrnd_n_u64<const N: i32>(a: u64) -> u32 {
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrnh_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshrn, N = 2))]
@@ -11596,6 +13526,8 @@ pub unsafe fn vqshrnh_n_u16<const N: i32>(a: u16) -> u8 {
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrns_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshrn, N = 2))]
@@ -11607,6 +13539,8 @@ pub unsafe fn vqshrns_n_u32<const N: i32>(a: u32) -> u16 {
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshrn2, N = 2))]
@@ -11618,6 +13552,8 @@ pub unsafe fn vqshrn_high_n_u16<const N: i32>(a: uint8x8_t, b: uint16x8_t) -> ui
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshrn2, N = 2))]
@@ -11629,6 +13565,8 @@ pub unsafe fn vqshrn_high_n_u32<const N: i32>(a: uint16x4_t, b: uint32x4_t) -> u
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_high_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uqshrn2, N = 2))]
@@ -11640,6 +13578,8 @@ pub unsafe fn vqshrn_high_n_u64<const N: i32>(a: uint32x2_t, b: uint64x2_t) -> u
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrunh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrun, N = 2))]
@@ -11651,6 +13591,8 @@ pub unsafe fn vqshrunh_n_s16<const N: i32>(a: i16) -> u8 {
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshruns_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrun, N = 2))]
@@ -11662,6 +13604,8 @@ pub unsafe fn vqshruns_n_s32<const N: i32>(a: i32) -> u16 {
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrund_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrun, N = 2))]
@@ -11673,6 +13617,8 @@ pub unsafe fn vqshrund_n_s64<const N: i32>(a: i64) -> u32 {
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrun2, N = 2))]
@@ -11684,6 +13630,8 @@ pub unsafe fn vqshrun_high_n_s16<const N: i32>(a: uint8x8_t, b: int16x8_t) -> ui
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrun2, N = 2))]
@@ -11695,6 +13643,8 @@ pub unsafe fn vqshrun_high_n_s32<const N: i32>(a: uint16x4_t, b: int32x4_t) -> u
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_high_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqshrun2, N = 2))]
@@ -11706,6 +13656,8 @@ pub unsafe fn vqshrun_high_n_s64<const N: i32>(a: uint32x2_t, b: int64x2_t) -> u
 }
 
 /// Unsigned saturating accumulate of signed value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqaddb_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usqadd))]
@@ -11715,6 +13667,8 @@ pub unsafe fn vsqaddb_u8(a: u8, b: i8) -> u8 {
 }
 
 /// Unsigned saturating accumulate of signed value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqaddh_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usqadd))]
@@ -11724,6 +13678,8 @@ pub unsafe fn vsqaddh_u16(a: u16, b: i16) -> u16 {
 }
 
 /// Unsigned saturating accumulate of signed value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqadds_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usqadd))]
@@ -11738,6 +13694,8 @@ pub unsafe fn vsqadds_u32(a: u32, b: i32) -> u32 {
 }
 
 /// Unsigned saturating accumulate of signed value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqaddd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(usqadd))]
@@ -11752,6 +13710,8 @@ pub unsafe fn vsqaddd_u64(a: u64, b: i64) -> u64 {
 }
 
 /// Calculates the square root of each lane.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqrt_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fsqrt))]
@@ -11761,6 +13721,8 @@ pub unsafe fn vsqrt_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Calculates the square root of each lane.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqrtq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fsqrt))]
@@ -11770,6 +13732,8 @@ pub unsafe fn vsqrtq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Calculates the square root of each lane.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqrt_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fsqrt))]
@@ -11779,6 +13743,8 @@ pub unsafe fn vsqrt_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Calculates the square root of each lane.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsqrtq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(fsqrt))]
@@ -11788,6 +13754,8 @@ pub unsafe fn vsqrtq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Reciprocal square-root estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrte_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrte))]
@@ -11802,6 +13770,8 @@ pub unsafe fn vrsqrte_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Reciprocal square-root estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrteq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrte))]
@@ -11816,6 +13786,8 @@ pub unsafe fn vrsqrteq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Reciprocal square-root estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrtes_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrte))]
@@ -11830,6 +13802,8 @@ pub unsafe fn vrsqrtes_f32(a: f32) -> f32 {
 }
 
 /// Reciprocal square-root estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrted_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrte))]
@@ -11844,6 +13818,8 @@ pub unsafe fn vrsqrted_f64(a: f64) -> f64 {
 }
 
 /// Floating-point reciprocal square root step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrts_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrts))]
@@ -11858,6 +13834,8 @@ pub unsafe fn vrsqrts_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point reciprocal square root step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrtsq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrts))]
@@ -11872,6 +13850,8 @@ pub unsafe fn vrsqrtsq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point reciprocal square root step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrtss_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrts))]
@@ -11886,6 +13866,8 @@ pub unsafe fn vrsqrtss_f32(a: f32, b: f32) -> f32 {
 }
 
 /// Floating-point reciprocal square root step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrtsd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frsqrts))]
@@ -11900,6 +13882,8 @@ pub unsafe fn vrsqrtsd_f64(a: f64, b: f64) -> f64 {
 }
 
 /// Reciprocal estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpe_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecpe))]
@@ -11914,6 +13898,8 @@ pub unsafe fn vrecpe_f64(a: float64x1_t) -> float64x1_t {
 }
 
 /// Reciprocal estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpeq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecpe))]
@@ -11928,6 +13914,8 @@ pub unsafe fn vrecpeq_f64(a: float64x2_t) -> float64x2_t {
 }
 
 /// Reciprocal estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpes_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecpe))]
@@ -11942,6 +13930,8 @@ pub unsafe fn vrecpes_f32(a: f32) -> f32 {
 }
 
 /// Reciprocal estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecped_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecpe))]
@@ -11956,6 +13946,8 @@ pub unsafe fn vrecped_f64(a: f64) -> f64 {
 }
 
 /// Floating-point reciprocal step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecps_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecps))]
@@ -11970,6 +13962,8 @@ pub unsafe fn vrecps_f64(a: float64x1_t, b: float64x1_t) -> float64x1_t {
 }
 
 /// Floating-point reciprocal step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpsq_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecps))]
@@ -11984,6 +13978,8 @@ pub unsafe fn vrecpsq_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Floating-point reciprocal step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpss_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecps))]
@@ -11998,6 +13994,8 @@ pub unsafe fn vrecpss_f32(a: f32, b: f32) -> f32 {
 }
 
 /// Floating-point reciprocal step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpsd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecps))]
@@ -12012,6 +14010,8 @@ pub unsafe fn vrecpsd_f64(a: f64, b: f64) -> f64 {
 }
 
 /// Floating-point reciprocal exponent
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpxs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecpx))]
@@ -12026,6 +14026,8 @@ pub unsafe fn vrecpxs_f32(a: f32) -> f32 {
 }
 
 /// Floating-point reciprocal exponent
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpxd_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(frecpx))]
@@ -12040,6 +14042,8 @@ pub unsafe fn vrecpxd_f64(a: f64) -> f64 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12049,6 +14053,8 @@ pub unsafe fn vreinterpret_s64_p64(a: poly64x1_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12058,6 +14064,8 @@ pub unsafe fn vreinterpret_u64_p64(a: poly64x1_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12067,6 +14075,8 @@ pub unsafe fn vreinterpret_p64_s64(a: int64x1_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12076,6 +14086,8 @@ pub unsafe fn vreinterpret_p64_u64(a: uint64x1_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12085,6 +14097,8 @@ pub unsafe fn vreinterpretq_s64_p64(a: poly64x2_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12094,6 +14108,8 @@ pub unsafe fn vreinterpretq_u64_p64(a: poly64x2_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12103,6 +14119,8 @@ pub unsafe fn vreinterpretq_p64_s64(a: int64x2_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12112,6 +14130,8 @@ pub unsafe fn vreinterpretq_p64_u64(a: uint64x2_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12121,6 +14141,8 @@ pub unsafe fn vreinterpret_s8_f64(a: float64x1_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12130,6 +14152,8 @@ pub unsafe fn vreinterpret_s16_f64(a: float64x1_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12139,6 +14163,8 @@ pub unsafe fn vreinterpret_s32_f64(a: float64x1_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12148,6 +14174,8 @@ pub unsafe fn vreinterpret_s64_f64(a: float64x1_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12157,6 +14185,8 @@ pub unsafe fn vreinterpretq_s8_f64(a: float64x2_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12166,6 +14196,8 @@ pub unsafe fn vreinterpretq_s16_f64(a: float64x2_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12175,6 +14207,8 @@ pub unsafe fn vreinterpretq_s32_f64(a: float64x2_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12184,6 +14218,8 @@ pub unsafe fn vreinterpretq_s64_f64(a: float64x2_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12193,6 +14229,8 @@ pub unsafe fn vreinterpret_u8_f64(a: float64x1_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12202,6 +14240,8 @@ pub unsafe fn vreinterpret_u16_f64(a: float64x1_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12211,6 +14251,8 @@ pub unsafe fn vreinterpret_u32_f64(a: float64x1_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12220,6 +14262,8 @@ pub unsafe fn vreinterpret_u64_f64(a: float64x1_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12229,6 +14273,8 @@ pub unsafe fn vreinterpretq_u8_f64(a: float64x2_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12238,6 +14284,8 @@ pub unsafe fn vreinterpretq_u16_f64(a: float64x2_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12247,6 +14295,8 @@ pub unsafe fn vreinterpretq_u32_f64(a: float64x2_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12256,6 +14306,8 @@ pub unsafe fn vreinterpretq_u64_f64(a: float64x2_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12265,6 +14317,8 @@ pub unsafe fn vreinterpret_p8_f64(a: float64x1_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12274,6 +14328,8 @@ pub unsafe fn vreinterpret_p16_f64(a: float64x1_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12283,6 +14339,8 @@ pub unsafe fn vreinterpret_p64_f32(a: float32x2_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12292,6 +14350,8 @@ pub unsafe fn vreinterpret_p64_f64(a: float64x1_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12301,6 +14361,8 @@ pub unsafe fn vreinterpretq_p8_f64(a: float64x2_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12310,6 +14372,8 @@ pub unsafe fn vreinterpretq_p16_f64(a: float64x2_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12319,6 +14383,8 @@ pub unsafe fn vreinterpretq_p64_f32(a: float32x4_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12328,6 +14394,8 @@ pub unsafe fn vreinterpretq_p64_f64(a: float64x2_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12337,6 +14405,8 @@ pub unsafe fn vreinterpretq_p128_f64(a: float64x2_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12346,6 +14416,8 @@ pub unsafe fn vreinterpret_f64_s8(a: int8x8_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12355,6 +14427,8 @@ pub unsafe fn vreinterpret_f64_s16(a: int16x4_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12364,6 +14438,8 @@ pub unsafe fn vreinterpret_f64_s32(a: int32x2_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12373,6 +14449,8 @@ pub unsafe fn vreinterpret_f64_s64(a: int64x1_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12382,6 +14460,8 @@ pub unsafe fn vreinterpretq_f64_s8(a: int8x16_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12391,6 +14471,8 @@ pub unsafe fn vreinterpretq_f64_s16(a: int16x8_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12400,6 +14482,8 @@ pub unsafe fn vreinterpretq_f64_s32(a: int32x4_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12409,6 +14493,8 @@ pub unsafe fn vreinterpretq_f64_s64(a: int64x2_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12418,6 +14504,8 @@ pub unsafe fn vreinterpret_f64_p8(a: poly8x8_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12427,6 +14515,8 @@ pub unsafe fn vreinterpret_f64_u16(a: uint16x4_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12436,6 +14526,8 @@ pub unsafe fn vreinterpret_f64_u32(a: uint32x2_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12445,6 +14537,8 @@ pub unsafe fn vreinterpret_f64_u64(a: uint64x1_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12454,6 +14548,8 @@ pub unsafe fn vreinterpretq_f64_p8(a: poly8x16_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12463,6 +14559,8 @@ pub unsafe fn vreinterpretq_f64_u16(a: uint16x8_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12472,6 +14570,8 @@ pub unsafe fn vreinterpretq_f64_u32(a: uint32x4_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12481,6 +14581,8 @@ pub unsafe fn vreinterpretq_f64_u64(a: uint64x2_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12490,6 +14592,8 @@ pub unsafe fn vreinterpret_f64_u8(a: uint8x8_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12499,6 +14603,8 @@ pub unsafe fn vreinterpret_f64_p16(a: poly16x4_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12508,6 +14614,8 @@ pub unsafe fn vreinterpret_f64_p64(a: poly64x1_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12517,6 +14625,8 @@ pub unsafe fn vreinterpret_f32_p64(a: poly64x1_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12526,6 +14636,8 @@ pub unsafe fn vreinterpretq_f64_u8(a: uint8x16_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12535,6 +14647,8 @@ pub unsafe fn vreinterpretq_f64_p16(a: poly16x8_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12544,6 +14658,8 @@ pub unsafe fn vreinterpretq_f64_p64(a: poly64x2_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12553,6 +14669,8 @@ pub unsafe fn vreinterpretq_f32_p64(a: poly64x2_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_p128)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12562,6 +14680,8 @@ pub unsafe fn vreinterpretq_f64_p128(a: p128) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12571,6 +14691,8 @@ pub unsafe fn vreinterpret_f64_f32(a: float32x2_t) -> float64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12580,6 +14702,8 @@ pub unsafe fn vreinterpret_f32_f64(a: float64x1_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12589,6 +14713,8 @@ pub unsafe fn vreinterpretq_f64_f32(a: float32x4_t) -> float64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop))]
@@ -12598,6 +14724,8 @@ pub unsafe fn vreinterpretq_f32_f64(a: float64x2_t) -> float32x4_t {
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshld_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(srshl))]
@@ -12612,6 +14740,8 @@ pub unsafe fn vrshld_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshld_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(urshl))]
@@ -12626,6 +14756,8 @@ pub unsafe fn vrshld_u64(a: u64, b: i64) -> u64 {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrd_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(srshr, N = 2))]
@@ -12637,6 +14769,8 @@ pub unsafe fn vrshrd_n_s64<const N: i32>(a: i64) -> i64 {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrd_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(urshr, N = 2))]
@@ -12648,6 +14782,8 @@ pub unsafe fn vrshrd_n_u64<const N: i32>(a: u64) -> u64 {
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rshrn2, N = 2))]
@@ -12659,6 +14795,8 @@ pub unsafe fn vrshrn_high_n_s16<const N: i32>(a: int8x8_t, b: int16x8_t) -> int8
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rshrn2, N = 2))]
@@ -12670,6 +14808,8 @@ pub unsafe fn vrshrn_high_n_s32<const N: i32>(a: int16x4_t, b: int32x4_t) -> int
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_high_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rshrn2, N = 2))]
@@ -12681,6 +14821,8 @@ pub unsafe fn vrshrn_high_n_s64<const N: i32>(a: int32x2_t, b: int64x2_t) -> int
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rshrn2, N = 2))]
@@ -12692,6 +14834,8 @@ pub unsafe fn vrshrn_high_n_u16<const N: i32>(a: uint8x8_t, b: uint16x8_t) -> ui
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rshrn2, N = 2))]
@@ -12703,6 +14847,8 @@ pub unsafe fn vrshrn_high_n_u32<const N: i32>(a: uint16x4_t, b: uint32x4_t) -> u
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_high_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rshrn2, N = 2))]
@@ -12714,6 +14860,8 @@ pub unsafe fn vrshrn_high_n_u64<const N: i32>(a: uint32x2_t, b: uint64x2_t) -> u
 }
 
 /// Signed rounding shift right and accumulate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsrad_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(srsra, N = 2))]
@@ -12726,6 +14874,8 @@ pub unsafe fn vrsrad_n_s64<const N: i32>(a: i64, b: i64) -> i64 {
 }
 
 /// Ungisned rounding shift right and accumulate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsrad_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ursra, N = 2))]
@@ -12738,6 +14888,8 @@ pub unsafe fn vrsrad_n_u64<const N: i32>(a: u64, b: u64) -> u64 {
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rsubhn2))]
@@ -12748,6 +14900,8 @@ pub unsafe fn vrsubhn_high_s16(a: int8x8_t, b: int16x8_t, c: int16x8_t) -> int8x
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rsubhn2))]
@@ -12758,6 +14912,8 @@ pub unsafe fn vrsubhn_high_s32(a: int16x4_t, b: int32x4_t, c: int32x4_t) -> int1
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_high_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rsubhn2))]
@@ -12768,6 +14924,8 @@ pub unsafe fn vrsubhn_high_s64(a: int32x2_t, b: int64x2_t, c: int64x2_t) -> int3
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rsubhn2))]
@@ -12778,6 +14936,8 @@ pub unsafe fn vrsubhn_high_u16(a: uint8x8_t, b: uint16x8_t, c: uint16x8_t) -> ui
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rsubhn2))]
@@ -12788,6 +14948,8 @@ pub unsafe fn vrsubhn_high_u32(a: uint16x4_t, b: uint32x4_t, c: uint32x4_t) -> u
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_high_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(rsubhn2))]
@@ -12798,6 +14960,8 @@ pub unsafe fn vrsubhn_high_u64(a: uint32x2_t, b: uint64x2_t, c: uint64x2_t) -> u
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, LANE = 0))]
@@ -12809,6 +14973,8 @@ pub unsafe fn vset_lane_f64<const LANE: i32>(a: f64, b: float64x1_t) -> float64x
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(nop, LANE = 0))]
@@ -12820,6 +14986,8 @@ pub unsafe fn vsetq_lane_f64<const LANE: i32>(a: f64, b: float64x2_t) -> float64
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshld_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sshl))]
@@ -12829,6 +14997,8 @@ pub unsafe fn vshld_s64(a: i64, b: i64) -> i64 {
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshld_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ushl))]
@@ -12838,6 +15008,8 @@ pub unsafe fn vshld_u64(a: u64, b: i64) -> u64 {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_high_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sshll2, N = 2))]
@@ -12850,6 +15022,8 @@ pub unsafe fn vshll_high_n_s8<const N: i32>(a: int8x16_t) -> int16x8_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sshll2, N = 2))]
@@ -12862,6 +15036,8 @@ pub unsafe fn vshll_high_n_s16<const N: i32>(a: int16x8_t) -> int32x4_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sshll2, N = 2))]
@@ -12874,6 +15050,8 @@ pub unsafe fn vshll_high_n_s32<const N: i32>(a: int32x4_t) -> int64x2_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_high_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ushll2, N = 2))]
@@ -12886,6 +15064,8 @@ pub unsafe fn vshll_high_n_u8<const N: i32>(a: uint8x16_t) -> uint16x8_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ushll2, N = 2))]
@@ -12898,6 +15078,8 @@ pub unsafe fn vshll_high_n_u16<const N: i32>(a: uint16x8_t) -> uint32x4_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(ushll2, N = 2))]
@@ -12910,6 +15092,8 @@ pub unsafe fn vshll_high_n_u32<const N: i32>(a: uint32x4_t) -> uint64x2_t {
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_high_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(shrn2, N = 2))]
@@ -12921,6 +15105,8 @@ pub unsafe fn vshrn_high_n_s16<const N: i32>(a: int8x8_t, b: int16x8_t) -> int8x
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_high_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(shrn2, N = 2))]
@@ -12932,6 +15118,8 @@ pub unsafe fn vshrn_high_n_s32<const N: i32>(a: int16x4_t, b: int32x4_t) -> int1
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_high_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(shrn2, N = 2))]
@@ -12943,6 +15131,8 @@ pub unsafe fn vshrn_high_n_s64<const N: i32>(a: int32x2_t, b: int64x2_t) -> int3
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_high_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(shrn2, N = 2))]
@@ -12954,6 +15144,8 @@ pub unsafe fn vshrn_high_n_u16<const N: i32>(a: uint8x8_t, b: uint16x8_t) -> uin
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_high_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(shrn2, N = 2))]
@@ -12965,6 +15157,8 @@ pub unsafe fn vshrn_high_n_u32<const N: i32>(a: uint16x4_t, b: uint32x4_t) -> ui
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_high_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(shrn2, N = 2))]
@@ -12976,6 +15170,8 @@ pub unsafe fn vshrn_high_n_u64<const N: i32>(a: uint32x2_t, b: uint64x2_t) -> ui
 }
 
 /// SM3PARTW1
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsm3partw1q_u32)
 #[inline]
 #[target_feature(enable = "neon,sm4")]
 #[cfg_attr(test, assert_instr(sm3partw1))]
@@ -12989,6 +15185,8 @@ pub unsafe fn vsm3partw1q_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> ui
 }
 
 /// SM3PARTW2
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsm3partw2q_u32)
 #[inline]
 #[target_feature(enable = "neon,sm4")]
 #[cfg_attr(test, assert_instr(sm3partw2))]
@@ -13002,6 +15200,8 @@ pub unsafe fn vsm3partw2q_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> ui
 }
 
 /// SM3SS1
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsm3ss1q_u32)
 #[inline]
 #[target_feature(enable = "neon,sm4")]
 #[cfg_attr(test, assert_instr(sm3ss1))]
@@ -13015,6 +15215,8 @@ pub unsafe fn vsm3ss1q_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint3
 }
 
 /// SM4 key
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsm4ekeyq_u32)
 #[inline]
 #[target_feature(enable = "neon,sm4")]
 #[cfg_attr(test, assert_instr(sm4ekey))]
@@ -13028,6 +15230,8 @@ pub unsafe fn vsm4ekeyq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// SM4 encode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsm4eq_u32)
 #[inline]
 #[target_feature(enable = "neon,sm4")]
 #[cfg_attr(test, assert_instr(sm4e))]
@@ -13041,6 +15245,8 @@ pub unsafe fn vsm4eq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Rotate and exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrax1q_u64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(rax1))]
@@ -13054,6 +15260,8 @@ pub unsafe fn vrax1q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// SHA512 hash update part 1
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha512hq_u64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(sha512h))]
@@ -13067,6 +15275,8 @@ pub unsafe fn vsha512hq_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> uint
 }
 
 /// SHA512 hash update part 2
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha512h2q_u64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(sha512h2))]
@@ -13080,6 +15290,8 @@ pub unsafe fn vsha512h2q_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> uin
 }
 
 /// SHA512 schedule update 0
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha512su0q_u64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(sha512su0))]
@@ -13093,6 +15305,8 @@ pub unsafe fn vsha512su0q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// SHA512 schedule update 1
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha512su1q_u64)
 #[inline]
 #[target_feature(enable = "neon,sha3")]
 #[cfg_attr(test, assert_instr(sha512su1))]
@@ -13106,6 +15320,8 @@ pub unsafe fn vsha512su1q_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> ui
 }
 
 /// Floating-point round to 32-bit integer, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd32x_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint32x))]
@@ -13119,6 +15335,8 @@ pub unsafe fn vrnd32x_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to 32-bit integer, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd32xq_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint32x))]
@@ -13132,6 +15350,8 @@ pub unsafe fn vrnd32xq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to 32-bit integer toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd32z_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint32z))]
@@ -13145,6 +15365,8 @@ pub unsafe fn vrnd32z_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to 32-bit integer toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd32zq_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint32z))]
@@ -13158,6 +15380,8 @@ pub unsafe fn vrnd32zq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to 64-bit integer, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd64x_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint64x))]
@@ -13171,6 +15395,8 @@ pub unsafe fn vrnd64x_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to 64-bit integer, using current rounding mode
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd64xq_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint64x))]
@@ -13184,6 +15410,8 @@ pub unsafe fn vrnd64xq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Floating-point round to 64-bit integer toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd64z_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint64z))]
@@ -13197,6 +15425,8 @@ pub unsafe fn vrnd64z_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point round to 64-bit integer toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrnd64zq_f32)
 #[inline]
 #[target_feature(enable = "neon,frintts")]
 #[cfg_attr(test, assert_instr(frint64z))]
@@ -13210,6 +15440,8 @@ pub unsafe fn vrnd64zq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13219,6 +15451,8 @@ pub unsafe fn vtrn1_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13228,6 +15462,8 @@ pub unsafe fn vtrn1q_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13237,6 +15473,8 @@ pub unsafe fn vtrn1_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13246,6 +15484,8 @@ pub unsafe fn vtrn1q_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13255,6 +15495,8 @@ pub unsafe fn vtrn1q_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13264,6 +15506,8 @@ pub unsafe fn vtrn1_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13273,6 +15517,8 @@ pub unsafe fn vtrn1q_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13282,6 +15528,8 @@ pub unsafe fn vtrn1_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13291,6 +15539,8 @@ pub unsafe fn vtrn1q_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13300,6 +15550,8 @@ pub unsafe fn vtrn1q_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13309,6 +15561,8 @@ pub unsafe fn vtrn1_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13318,6 +15572,8 @@ pub unsafe fn vtrn1q_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13327,6 +15583,8 @@ pub unsafe fn vtrn1_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13336,6 +15594,8 @@ pub unsafe fn vtrn1q_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13345,6 +15605,8 @@ pub unsafe fn vtrn1_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13354,6 +15616,8 @@ pub unsafe fn vtrn1q_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13363,6 +15627,8 @@ pub unsafe fn vtrn1_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13372,6 +15638,8 @@ pub unsafe fn vtrn1q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13381,6 +15649,8 @@ pub unsafe fn vtrn1q_p64(a: poly64x2_t, b: poly64x2_t) -> poly64x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn1))]
@@ -13390,6 +15660,8 @@ pub unsafe fn vtrn1q_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13399,6 +15671,8 @@ pub unsafe fn vtrn1_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn1q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13408,6 +15682,8 @@ pub unsafe fn vtrn1q_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13417,6 +15693,8 @@ pub unsafe fn vtrn2_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13426,6 +15704,8 @@ pub unsafe fn vtrn2q_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13435,6 +15715,8 @@ pub unsafe fn vtrn2_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13444,6 +15726,8 @@ pub unsafe fn vtrn2q_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13453,6 +15737,8 @@ pub unsafe fn vtrn2q_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13462,6 +15748,8 @@ pub unsafe fn vtrn2_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13471,6 +15759,8 @@ pub unsafe fn vtrn2q_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13480,6 +15770,8 @@ pub unsafe fn vtrn2_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13489,6 +15781,8 @@ pub unsafe fn vtrn2q_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13498,6 +15792,8 @@ pub unsafe fn vtrn2q_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13507,6 +15803,8 @@ pub unsafe fn vtrn2_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13516,6 +15814,8 @@ pub unsafe fn vtrn2q_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13525,6 +15825,8 @@ pub unsafe fn vtrn2_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13534,6 +15836,8 @@ pub unsafe fn vtrn2q_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13543,6 +15847,8 @@ pub unsafe fn vtrn2_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13552,6 +15858,8 @@ pub unsafe fn vtrn2q_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13561,6 +15869,8 @@ pub unsafe fn vtrn2_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13570,6 +15880,8 @@ pub unsafe fn vtrn2q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13579,6 +15891,8 @@ pub unsafe fn vtrn2q_p64(a: poly64x2_t, b: poly64x2_t) -> poly64x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(trn2))]
@@ -13588,6 +15902,8 @@ pub unsafe fn vtrn2q_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13597,6 +15913,8 @@ pub unsafe fn vtrn2_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Transpose vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn2q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13606,6 +15924,8 @@ pub unsafe fn vtrn2q_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13615,6 +15935,8 @@ pub unsafe fn vzip1_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13624,6 +15946,8 @@ pub unsafe fn vzip1q_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13633,6 +15957,8 @@ pub unsafe fn vzip1_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13642,6 +15968,8 @@ pub unsafe fn vzip1q_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13651,6 +15979,8 @@ pub unsafe fn vzip1_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13660,6 +15990,8 @@ pub unsafe fn vzip1q_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13669,6 +16001,8 @@ pub unsafe fn vzip1q_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13678,6 +16012,8 @@ pub unsafe fn vzip1_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13687,6 +16023,8 @@ pub unsafe fn vzip1q_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13696,6 +16034,8 @@ pub unsafe fn vzip1_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13705,6 +16045,8 @@ pub unsafe fn vzip1q_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13714,6 +16056,8 @@ pub unsafe fn vzip1_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13723,6 +16067,8 @@ pub unsafe fn vzip1q_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13732,6 +16078,8 @@ pub unsafe fn vzip1q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13741,6 +16089,8 @@ pub unsafe fn vzip1_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13750,6 +16100,8 @@ pub unsafe fn vzip1q_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13759,6 +16111,8 @@ pub unsafe fn vzip1_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13768,6 +16122,8 @@ pub unsafe fn vzip1q_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13777,6 +16133,8 @@ pub unsafe fn vzip1q_p64(a: poly64x2_t, b: poly64x2_t) -> poly64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13786,6 +16144,8 @@ pub unsafe fn vzip1_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13795,6 +16155,8 @@ pub unsafe fn vzip1q_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip1q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -13804,6 +16166,8 @@ pub unsafe fn vzip1q_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13813,6 +16177,8 @@ pub unsafe fn vzip2_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13822,6 +16188,8 @@ pub unsafe fn vzip2q_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13831,6 +16199,8 @@ pub unsafe fn vzip2_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13840,6 +16210,8 @@ pub unsafe fn vzip2q_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13849,6 +16221,8 @@ pub unsafe fn vzip2_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13858,6 +16232,8 @@ pub unsafe fn vzip2q_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13867,6 +16243,8 @@ pub unsafe fn vzip2q_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13876,6 +16254,8 @@ pub unsafe fn vzip2_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13885,6 +16265,8 @@ pub unsafe fn vzip2q_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13894,6 +16276,8 @@ pub unsafe fn vzip2_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13903,6 +16287,8 @@ pub unsafe fn vzip2q_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13912,6 +16298,8 @@ pub unsafe fn vzip2_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13921,6 +16309,8 @@ pub unsafe fn vzip2q_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13930,6 +16320,8 @@ pub unsafe fn vzip2q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13939,6 +16331,8 @@ pub unsafe fn vzip2_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13948,6 +16342,8 @@ pub unsafe fn vzip2q_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13957,6 +16353,8 @@ pub unsafe fn vzip2_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13966,6 +16364,8 @@ pub unsafe fn vzip2q_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13975,6 +16375,8 @@ pub unsafe fn vzip2q_p64(a: poly64x2_t, b: poly64x2_t) -> poly64x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13984,6 +16386,8 @@ pub unsafe fn vzip2_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -13993,6 +16397,8 @@ pub unsafe fn vzip2q_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip2q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14002,6 +16408,8 @@ pub unsafe fn vzip2q_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14011,6 +16419,8 @@ pub unsafe fn vuzp1_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14020,6 +16430,8 @@ pub unsafe fn vuzp1q_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14029,6 +16441,8 @@ pub unsafe fn vuzp1_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14038,6 +16452,8 @@ pub unsafe fn vuzp1q_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14047,6 +16463,8 @@ pub unsafe fn vuzp1q_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14056,6 +16474,8 @@ pub unsafe fn vuzp1_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14065,6 +16485,8 @@ pub unsafe fn vuzp1q_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14074,6 +16496,8 @@ pub unsafe fn vuzp1_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14083,6 +16507,8 @@ pub unsafe fn vuzp1q_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14092,6 +16518,8 @@ pub unsafe fn vuzp1q_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14101,6 +16529,8 @@ pub unsafe fn vuzp1_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14110,6 +16540,8 @@ pub unsafe fn vuzp1q_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14119,6 +16551,8 @@ pub unsafe fn vuzp1_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14128,6 +16562,8 @@ pub unsafe fn vuzp1q_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -14137,6 +16573,8 @@ pub unsafe fn vuzp1_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -14146,6 +16584,8 @@ pub unsafe fn vuzp1q_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -14155,6 +16595,8 @@ pub unsafe fn vuzp1_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -14164,6 +16606,8 @@ pub unsafe fn vuzp1q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -14173,6 +16617,8 @@ pub unsafe fn vuzp1q_p64(a: poly64x2_t, b: poly64x2_t) -> poly64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp1))]
@@ -14182,6 +16628,8 @@ pub unsafe fn vuzp1q_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -14191,6 +16639,8 @@ pub unsafe fn vuzp1_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp1q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip1))]
@@ -14200,6 +16650,8 @@ pub unsafe fn vuzp1q_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14209,6 +16661,8 @@ pub unsafe fn vuzp2_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14218,6 +16672,8 @@ pub unsafe fn vuzp2q_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14227,6 +16683,8 @@ pub unsafe fn vuzp2_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14236,6 +16694,8 @@ pub unsafe fn vuzp2q_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14245,6 +16705,8 @@ pub unsafe fn vuzp2q_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14254,6 +16716,8 @@ pub unsafe fn vuzp2_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14263,6 +16727,8 @@ pub unsafe fn vuzp2q_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14272,6 +16738,8 @@ pub unsafe fn vuzp2_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14281,6 +16749,8 @@ pub unsafe fn vuzp2q_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14290,6 +16760,8 @@ pub unsafe fn vuzp2q_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14299,6 +16771,8 @@ pub unsafe fn vuzp2_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14308,6 +16782,8 @@ pub unsafe fn vuzp2q_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14317,6 +16793,8 @@ pub unsafe fn vuzp2_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14326,6 +16804,8 @@ pub unsafe fn vuzp2q_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14335,6 +16815,8 @@ pub unsafe fn vuzp2_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14344,6 +16826,8 @@ pub unsafe fn vuzp2q_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14353,6 +16837,8 @@ pub unsafe fn vuzp2_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14362,6 +16848,8 @@ pub unsafe fn vuzp2q_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14371,6 +16859,8 @@ pub unsafe fn vuzp2q_p64(a: poly64x2_t, b: poly64x2_t) -> poly64x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uzp2))]
@@ -14380,6 +16870,8 @@ pub unsafe fn vuzp2q_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14389,6 +16881,8 @@ pub unsafe fn vuzp2_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp2q_f64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(zip2))]
@@ -14398,6 +16892,8 @@ pub unsafe fn vuzp2q_f64(a: float64x2_t, b: float64x2_t) -> float64x2_t {
 }
 
 /// Unsigned Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_high_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uabal))]
@@ -14410,6 +16906,8 @@ pub unsafe fn vabal_high_u8(a: uint16x8_t, b: uint8x16_t, c: uint8x16_t) -> uint
 }
 
 /// Unsigned Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uabal))]
@@ -14422,6 +16920,8 @@ pub unsafe fn vabal_high_u16(a: uint32x4_t, b: uint16x8_t, c: uint16x8_t) -> uin
 }
 
 /// Unsigned Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(uabal))]
@@ -14434,6 +16934,8 @@ pub unsafe fn vabal_high_u32(a: uint64x2_t, b: uint32x4_t, c: uint32x4_t) -> uin
 }
 
 /// Signed Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_high_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sabal))]
@@ -14447,6 +16949,8 @@ pub unsafe fn vabal_high_s8(a: int16x8_t, b: int8x16_t, c: int8x16_t) -> int16x8
 }
 
 /// Signed Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sabal))]
@@ -14460,6 +16964,8 @@ pub unsafe fn vabal_high_s16(a: int32x4_t, b: int16x8_t, c: int16x8_t) -> int32x
 }
 
 /// Signed Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sabal))]
@@ -14473,6 +16979,8 @@ pub unsafe fn vabal_high_s32(a: int64x2_t, b: int32x4_t, c: int32x4_t) -> int64x
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabs_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqabs))]
@@ -14487,6 +16995,8 @@ pub unsafe fn vqabs_s64(a: int64x1_t) -> int64x1_t {
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabsq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqabs))]
@@ -14501,6 +17011,8 @@ pub unsafe fn vqabsq_s64(a: int64x2_t) -> int64x2_t {
 }
 
 /// Signed saturating absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabsb_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqabs))]
@@ -14510,6 +17022,8 @@ pub unsafe fn vqabsb_s8(a: i8) -> i8 {
 }
 
 /// Signed saturating absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabsh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqabs))]
@@ -14519,6 +17033,8 @@ pub unsafe fn vqabsh_s16(a: i16) -> i16 {
 }
 
 /// Signed saturating absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabss_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqabs))]
@@ -14533,6 +17049,8 @@ pub unsafe fn vqabss_s32(a: i32) -> i32 {
 }
 
 /// Signed saturating absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabsd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sqabs))]
@@ -14547,6 +17065,8 @@ pub unsafe fn vqabsd_s64(a: i64) -> i64 {
 }
 
 /// Shift left and insert
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vslid_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sli, N = 2))]
@@ -14558,6 +17078,8 @@ pub unsafe fn vslid_n_s64<const N: i32>(a: i64, b: i64) -> i64 {
 }
 
 /// Shift left and insert
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vslid_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sli, N = 2))]
@@ -14569,6 +17091,8 @@ pub unsafe fn vslid_n_u64<const N: i32>(a: u64, b: u64) -> u64 {
 }
 
 /// Shift right and insert
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsrid_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sri, N = 2))]
@@ -14580,6 +17104,8 @@ pub unsafe fn vsrid_n_s64<const N: i32>(a: i64, b: i64) -> i64 {
 }
 
 /// Shift right and insert
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsrid_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(test, assert_instr(sri, N = 2))]
@@ -17603,18 +20129,18 @@ mod test {
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_p64() {
-        let a: i64x2 = i64x2::new(0, 8);
-        let b: i64x2 = i64x2::new(9, 11);
-        let e: i64x2 = i64x2::new(8, 9);
+        let a: i64x2 = i64x2::new(1, 1);
+        let b: i64x2 = i64x2::new(2, 2);
+        let e: i64x2 = i64x2::new(1, 2);
         let r: i64x2 = transmute(vextq_p64::<1>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_f64() {
-        let a: f64x2 = f64x2::new(0., 2.);
-        let b: f64x2 = f64x2::new(3., 4.);
-        let e: f64x2 = f64x2::new(2., 3.);
+        let a: f64x2 = f64x2::new(1., 1.);
+        let b: f64x2 = f64x2::new(2., 2.);
+        let e: f64x2 = f64x2::new(1., 2.);
         let r: f64x2 = transmute(vextq_f64::<1>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
diff --git a/library/stdarch/crates/core_arch/src/aarch64/neon/mod.rs b/library/stdarch/crates/core_arch/src/aarch64/neon/mod.rs
index 65ba527ee..9d9946b4f 100644
--- a/library/stdarch/crates/core_arch/src/aarch64/neon/mod.rs
+++ b/library/stdarch/crates/core_arch/src/aarch64/neon/mod.rs
@@ -28,14 +28,17 @@ types! {
 }
 
 /// ARM-specific type containing two `float64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub struct float64x1x2_t(pub float64x1_t, pub float64x1_t);
 /// ARM-specific type containing three `float64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub struct float64x1x3_t(pub float64x1_t, pub float64x1_t, pub float64x1_t);
 /// ARM-specific type containing four `float64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub struct float64x1x4_t(
@@ -46,14 +49,17 @@ pub struct float64x1x4_t(
 );
 
 /// ARM-specific type containing two `float64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub struct float64x2x2_t(pub float64x2_t, pub float64x2_t);
 /// ARM-specific type containing three `float64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub struct float64x2x3_t(pub float64x2_t, pub float64x2_t, pub float64x2_t);
 /// ARM-specific type containing four `float64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub struct float64x2x4_t(
@@ -658,6 +664,8 @@ pub unsafe fn vld1q_p16(ptr: *const p16) -> poly16x8_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ldr))]
@@ -667,6 +675,8 @@ pub unsafe fn vld1_p64(ptr: *const p64) -> poly64x1_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(ldr))]
@@ -953,6 +963,8 @@ pub unsafe fn vst1q_p16(ptr: *mut p16, a: poly16x8_t) {
 }
 
 // Store multiple single-element structures from one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(str))]
@@ -963,6 +975,8 @@ pub unsafe fn vst1_p64(ptr: *mut p64, a: poly64x1_t) {
 }
 
 // Store multiple single-element structures from one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(str))]
@@ -1045,7 +1059,11 @@ pub unsafe fn vabsq_s64(a: int64x2_t) -> int64x2_t {
 #[cfg_attr(test, assert_instr(bsl))]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub unsafe fn vbsl_f64(a: uint64x1_t, b: float64x1_t, c: float64x1_t) -> float64x1_t {
-    simd_select(transmute::<_, int64x1_t>(a), b, c)
+    let not = int64x1_t(-1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 /// Bitwise Select.
 #[inline]
@@ -1053,7 +1071,11 @@ pub unsafe fn vbsl_f64(a: uint64x1_t, b: float64x1_t, c: float64x1_t) -> float64
 #[cfg_attr(test, assert_instr(bsl))]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub unsafe fn vbsl_p64(a: poly64x1_t, b: poly64x1_t, c: poly64x1_t) -> poly64x1_t {
-    simd_select(transmute::<_, int64x1_t>(a), b, c)
+    let not = int64x1_t(-1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 /// Bitwise Select. (128-bit)
 #[inline]
@@ -1061,7 +1083,11 @@ pub unsafe fn vbsl_p64(a: poly64x1_t, b: poly64x1_t, c: poly64x1_t) -> poly64x1_
 #[cfg_attr(test, assert_instr(bsl))]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub unsafe fn vbslq_f64(a: uint64x2_t, b: float64x2_t, c: float64x2_t) -> float64x2_t {
-    simd_select(transmute::<_, int64x2_t>(a), b, c)
+    let not = int64x2_t(-1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 /// Bitwise Select. (128-bit)
 #[inline]
@@ -1069,7 +1095,11 @@ pub unsafe fn vbslq_f64(a: uint64x2_t, b: float64x2_t, c: float64x2_t) -> float6
 #[cfg_attr(test, assert_instr(bsl))]
 #[stable(feature = "neon_intrinsics", since = "1.59.0")]
 pub unsafe fn vbslq_p64(a: poly64x2_t, b: poly64x2_t, c: poly64x2_t) -> poly64x2_t {
-    simd_select(transmute::<_, int64x2_t>(a), b, c)
+    let not = int64x2_t(-1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Signed saturating Accumulate of Unsigned value.
@@ -3365,7 +3395,10 @@ pub unsafe fn vsliq_n_p16<const N: i32>(a: poly16x8_t, b: poly16x8_t) -> poly16x
     static_assert_imm4!(N);
     transmute(vsliq_n_s16_(transmute(a), transmute(b), N))
 }
+
 /// Shift Left and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsli_n_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(sli, N = 1))]
@@ -3375,7 +3408,10 @@ pub unsafe fn vsli_n_p64<const N: i32>(a: poly64x1_t, b: poly64x1_t) -> poly64x1
     static_assert!(N: i32 where N >= 0 && N <= 63);
     transmute(vsli_n_s64_(transmute(a), transmute(b), N))
 }
+
 /// Shift Left and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsliq_n_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(sli, N = 1))]
@@ -3585,7 +3621,10 @@ pub unsafe fn vsriq_n_p16<const N: i32>(a: poly16x8_t, b: poly16x8_t) -> poly16x
     static_assert!(N: i32 where N >= 1 && N <= 16);
     transmute(vsriq_n_s16_(transmute(a), transmute(b), N))
 }
+
 /// Shift Right and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsri_n_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(sri, N = 1))]
@@ -3595,7 +3634,10 @@ pub unsafe fn vsri_n_p64<const N: i32>(a: poly64x1_t, b: poly64x1_t) -> poly64x1
     static_assert!(N: i32 where N >= 1 && N <= 64);
     transmute(vsri_n_s64_(transmute(a), transmute(b), N))
 }
+
 /// Shift Right and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsriq_n_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(sri, N = 1))]
@@ -5136,37 +5178,37 @@ mod tests {
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_f64() {
-        let a = u64x1::new(u64::MAX);
-        let b = f64x1::new(f64::MAX);
-        let c = f64x1::new(f64::MIN);
-        let e = f64x1::new(f64::MAX);
+        let a = u64x1::new(0x8000000000000000);
+        let b = f64x1::new(-1.23f64);
+        let c = f64x1::new(2.34f64);
+        let e = f64x1::new(-2.34f64);
         let r: f64x1 = transmute(vbsl_f64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_p64() {
-        let a = u64x1::new(u64::MAX);
+        let a = u64x1::new(1);
         let b = u64x1::new(u64::MAX);
         let c = u64x1::new(u64::MIN);
-        let e = u64x1::new(u64::MAX);
+        let e = u64x1::new(1);
         let r: u64x1 = transmute(vbsl_p64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_f64() {
-        let a = u64x2::new(u64::MAX, 0);
-        let b = f64x2::new(f64::MAX, f64::MAX);
-        let c = f64x2::new(f64::MIN, f64::MIN);
-        let e = f64x2::new(f64::MAX, f64::MIN);
+        let a = u64x2::new(1, 0x8000000000000000);
+        let b = f64x2::new(f64::MAX, -1.23f64);
+        let c = f64x2::new(f64::MIN, 2.34f64);
+        let e = f64x2::new(f64::MIN, -2.34f64);
         let r: f64x2 = transmute(vbslq_f64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_p64() {
-        let a = u64x2::new(u64::MAX, 0);
+        let a = u64x2::new(u64::MAX, 1);
         let b = u64x2::new(u64::MAX, u64::MAX);
         let c = u64x2::new(u64::MIN, u64::MIN);
-        let e = u64x2::new(u64::MAX, u64::MIN);
+        let e = u64x2::new(u64::MAX, 1);
         let r: u64x2 = transmute(vbslq_p64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
diff --git a/library/stdarch/crates/core_arch/src/arm/neon.rs b/library/stdarch/crates/core_arch/src/arm/neon.rs
index a0ad92c33..a6291c95c 100644
--- a/library/stdarch/crates/core_arch/src/arm/neon.rs
+++ b/library/stdarch/crates/core_arch/src/arm/neon.rs
@@ -289,6 +289,8 @@ pub unsafe fn vld1q_p16(ptr: *const p16) -> poly16x8_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr(vldr))]
@@ -297,6 +299,8 @@ pub unsafe fn vld1_p64(ptr: *const p64) -> poly64x1_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(test, assert_instr("vld1.64"))]
@@ -481,6 +485,8 @@ pub unsafe fn vst1q_p16(ptr: *mut p16, a: poly16x8_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p64)
 #[inline]
 #[target_feature(enable = "neon,aes,v8")]
 #[cfg_attr(test, assert_instr("vst1.64"))]
@@ -489,6 +495,8 @@ pub unsafe fn vst1_p64(ptr: *mut p64, a: poly64x1_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p64)
 #[inline]
 #[target_feature(enable = "neon,aes,v8")]
 #[cfg_attr(test, assert_instr("vst1.64"))]
@@ -1033,6 +1041,7 @@ pub unsafe fn vsli_n_p16<const N: i32>(a: poly16x4_t, b: poly16x4_t) -> poly16x4
         int16x4_t(n, n, n, n),
     ))
 }
+
 /// Shift Left and Insert (immediate)
 #[inline]
 #[target_feature(enable = "neon,v7")]
@@ -1047,7 +1056,10 @@ pub unsafe fn vsliq_n_p16<const N: i32>(a: poly16x8_t, b: poly16x8_t) -> poly16x
         int16x8_t(n, n, n, n, n, n, n, n),
     ))
 }
+
 /// Shift Left and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsli_n_p64)
 #[inline]
 #[target_feature(enable = "neon,v7,aes")]
 #[cfg_attr(test, assert_instr("vsli.64", N = 1))]
@@ -1060,7 +1072,10 @@ pub unsafe fn vsli_n_p64<const N: i32>(a: poly64x1_t, b: poly64x1_t) -> poly64x1
         int64x1_t(N as i64),
     ))
 }
+
 /// Shift Left and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsliq_n_p64)
 #[inline]
 #[target_feature(enable = "neon,v7,aes")]
 #[cfg_attr(test, assert_instr("vsli.64", N = 1))]
@@ -1317,7 +1332,10 @@ pub unsafe fn vsriq_n_p16<const N: i32>(a: poly16x8_t, b: poly16x8_t) -> poly16x
         int16x8_t(n, n, n, n, n, n, n, n),
     ))
 }
+
 /// Shift Right and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsri_n_p64)
 #[inline]
 #[target_feature(enable = "neon,v7,aes")]
 #[cfg_attr(test, assert_instr("vsri.64", N = 1))]
@@ -1330,7 +1348,10 @@ pub unsafe fn vsri_n_p64<const N: i32>(a: poly64x1_t, b: poly64x1_t) -> poly64x1
         int64x1_t(-N as i64),
     ))
 }
+
 /// Shift Right and Insert (immediate)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsriq_n_p64)
 #[inline]
 #[target_feature(enable = "neon,v7,aes")]
 #[cfg_attr(test, assert_instr("vsri.64", N = 1))]
diff --git a/library/stdarch/crates/core_arch/src/arm/v7.rs b/library/stdarch/crates/core_arch/src/arm/v7.rs
index e7507f9b9..59beaf722 100644
--- a/library/stdarch/crates/core_arch/src/arm/v7.rs
+++ b/library/stdarch/crates/core_arch/src/arm/v7.rs
@@ -76,7 +76,6 @@ mod tests {
     }
 
     #[test]
-    #[cfg(dont_compile_me)] // FIXME need to add `v7` upstream in rustc
     fn _rbit_u32() {
         unsafe {
             assert_eq!(
diff --git a/library/stdarch/crates/core_arch/src/arm_shared/crc.rs b/library/stdarch/crates/core_arch/src/arm_shared/crc.rs
index e0d0fbe35..779d1ed42 100644
--- a/library/stdarch/crates/core_arch/src/arm_shared/crc.rs
+++ b/library/stdarch/crates/core_arch/src/arm_shared/crc.rs
@@ -24,6 +24,8 @@ extern "unadjusted" {
 use stdarch_test::assert_instr;
 
 /// CRC32 single round checksum for bytes (8 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32b)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v8"))]
@@ -33,6 +35,8 @@ pub unsafe fn __crc32b(crc: u32, data: u8) -> u32 {
 }
 
 /// CRC32 single round checksum for half words (16 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32h)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v8"))]
@@ -42,6 +46,8 @@ pub unsafe fn __crc32h(crc: u32, data: u16) -> u32 {
 }
 
 /// CRC32 single round checksum for words (32 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32w)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v8"))]
@@ -51,6 +57,8 @@ pub unsafe fn __crc32w(crc: u32, data: u32) -> u32 {
 }
 
 /// CRC32-C single round checksum for bytes (8 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32cb)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v8"))]
@@ -60,6 +68,8 @@ pub unsafe fn __crc32cb(crc: u32, data: u8) -> u32 {
 }
 
 /// CRC32-C single round checksum for half words (16 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32ch)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v8"))]
@@ -69,6 +79,8 @@ pub unsafe fn __crc32ch(crc: u32, data: u16) -> u32 {
 }
 
 /// CRC32-C single round checksum for words (32 bits).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/__crc32cw)
 #[inline]
 #[target_feature(enable = "crc")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v8"))]
diff --git a/library/stdarch/crates/core_arch/src/arm_shared/crypto.rs b/library/stdarch/crates/core_arch/src/arm_shared/crypto.rs
index 3e9515e59..060091136 100644
--- a/library/stdarch/crates/core_arch/src/arm_shared/crypto.rs
+++ b/library/stdarch/crates/core_arch/src/arm_shared/crypto.rs
@@ -52,6 +52,8 @@ extern "unadjusted" {
 use stdarch_test::assert_instr;
 
 /// AES single round encryption.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaeseq_u8)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "aes"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -61,6 +63,8 @@ pub unsafe fn vaeseq_u8(data: uint8x16_t, key: uint8x16_t) -> uint8x16_t {
 }
 
 /// AES single round decryption.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaesdq_u8)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "aes"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -70,6 +74,8 @@ pub unsafe fn vaesdq_u8(data: uint8x16_t, key: uint8x16_t) -> uint8x16_t {
 }
 
 /// AES mix columns.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaesmcq_u8)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "aes"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -79,6 +85,8 @@ pub unsafe fn vaesmcq_u8(data: uint8x16_t) -> uint8x16_t {
 }
 
 /// AES inverse mix columns.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaesimcq_u8)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "aes"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -88,6 +96,8 @@ pub unsafe fn vaesimcq_u8(data: uint8x16_t) -> uint8x16_t {
 }
 
 /// SHA1 fixed rotate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha1h_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -97,6 +107,8 @@ pub unsafe fn vsha1h_u32(hash_e: u32) -> u32 {
 }
 
 /// SHA1 hash update accelerator, choose.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha1cq_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -106,6 +118,8 @@ pub unsafe fn vsha1cq_u32(hash_abcd: uint32x4_t, hash_e: u32, wk: uint32x4_t) ->
 }
 
 /// SHA1 hash update accelerator, majority.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha1mq_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -115,6 +129,8 @@ pub unsafe fn vsha1mq_u32(hash_abcd: uint32x4_t, hash_e: u32, wk: uint32x4_t) ->
 }
 
 /// SHA1 hash update accelerator, parity.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha1pq_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -124,6 +140,8 @@ pub unsafe fn vsha1pq_u32(hash_abcd: uint32x4_t, hash_e: u32, wk: uint32x4_t) ->
 }
 
 /// SHA1 schedule update accelerator, first part.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha1su0q_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -133,6 +151,8 @@ pub unsafe fn vsha1su0q_u32(w0_3: uint32x4_t, w4_7: uint32x4_t, w8_11: uint32x4_
 }
 
 /// SHA1 schedule update accelerator, second part.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha1su1q_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -142,6 +162,8 @@ pub unsafe fn vsha1su1q_u32(tw0_3: uint32x4_t, w12_15: uint32x4_t) -> uint32x4_t
 }
 
 /// SHA256 hash update accelerator.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha256hq_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -155,6 +177,8 @@ pub unsafe fn vsha256hq_u32(
 }
 
 /// SHA256 hash update accelerator, upper part.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha256h2q_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -168,6 +192,8 @@ pub unsafe fn vsha256h2q_u32(
 }
 
 /// SHA256 schedule update accelerator, first part.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha256su0q_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
@@ -177,6 +203,8 @@ pub unsafe fn vsha256su0q_u32(w0_3: uint32x4_t, w4_7: uint32x4_t) -> uint32x4_t
 }
 
 /// SHA256 schedule update accelerator, second part.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsha256su1q_u32)
 #[inline]
 #[cfg_attr(not(target_arch = "arm"), target_feature(enable = "sha2"))]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "crypto,v8"))]
diff --git a/library/stdarch/crates/core_arch/src/arm_shared/neon/generated.rs b/library/stdarch/crates/core_arch/src/arm_shared/neon/generated.rs
index d69fbd8e8..ac2709744 100644
--- a/library/stdarch/crates/core_arch/src/arm_shared/neon/generated.rs
+++ b/library/stdarch/crates/core_arch/src/arm_shared/neon/generated.rs
@@ -10,6 +10,8 @@ use super::*;
 use stdarch_test::assert_instr;
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21,6 +23,8 @@ pub unsafe fn vand_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -32,6 +36,8 @@ pub unsafe fn vandq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -43,6 +49,8 @@ pub unsafe fn vand_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -54,6 +62,8 @@ pub unsafe fn vandq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -65,6 +75,8 @@ pub unsafe fn vand_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -76,6 +88,8 @@ pub unsafe fn vandq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -87,6 +101,8 @@ pub unsafe fn vand_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -98,6 +114,8 @@ pub unsafe fn vandq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -109,6 +127,8 @@ pub unsafe fn vand_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -120,6 +140,8 @@ pub unsafe fn vandq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -131,6 +153,8 @@ pub unsafe fn vand_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -142,6 +166,8 @@ pub unsafe fn vandq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -153,6 +179,8 @@ pub unsafe fn vand_s64(a: int64x1_t, b: int64x1_t) -> int64x1_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -164,6 +192,8 @@ pub unsafe fn vandq_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vand_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -175,6 +205,8 @@ pub unsafe fn vand_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Vector bitwise and
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vandq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -186,6 +218,8 @@ pub unsafe fn vandq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -197,6 +231,8 @@ pub unsafe fn vorr_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -208,6 +244,8 @@ pub unsafe fn vorrq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -219,6 +257,8 @@ pub unsafe fn vorr_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -230,6 +270,8 @@ pub unsafe fn vorrq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -241,6 +283,8 @@ pub unsafe fn vorr_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -252,6 +296,8 @@ pub unsafe fn vorrq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -263,6 +309,8 @@ pub unsafe fn vorr_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -274,6 +322,8 @@ pub unsafe fn vorrq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -285,6 +335,8 @@ pub unsafe fn vorr_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -296,6 +348,8 @@ pub unsafe fn vorrq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -307,6 +361,8 @@ pub unsafe fn vorr_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -318,6 +374,8 @@ pub unsafe fn vorrq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -329,6 +387,8 @@ pub unsafe fn vorr_s64(a: int64x1_t, b: int64x1_t) -> int64x1_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -340,6 +400,8 @@ pub unsafe fn vorrq_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorr_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -351,6 +413,8 @@ pub unsafe fn vorr_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Vector bitwise or (immediate, inclusive)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vorrq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -362,6 +426,8 @@ pub unsafe fn vorrq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -373,6 +439,8 @@ pub unsafe fn veor_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -384,6 +452,8 @@ pub unsafe fn veorq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -395,6 +465,8 @@ pub unsafe fn veor_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -406,6 +478,8 @@ pub unsafe fn veorq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -417,6 +491,8 @@ pub unsafe fn veor_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -428,6 +504,8 @@ pub unsafe fn veorq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -439,6 +517,8 @@ pub unsafe fn veor_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -450,6 +530,8 @@ pub unsafe fn veorq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -461,6 +543,8 @@ pub unsafe fn veor_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -472,6 +556,8 @@ pub unsafe fn veorq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -483,6 +569,8 @@ pub unsafe fn veor_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -494,6 +582,8 @@ pub unsafe fn veorq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -505,6 +595,8 @@ pub unsafe fn veor_s64(a: int64x1_t, b: int64x1_t) -> int64x1_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -516,6 +608,8 @@ pub unsafe fn veorq_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veor_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -527,6 +621,8 @@ pub unsafe fn veor_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Vector bitwise exclusive or (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/veorq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -538,6 +634,8 @@ pub unsafe fn veorq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -555,6 +653,8 @@ vabd_s8_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -572,6 +672,8 @@ vabdq_s8_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -589,6 +691,8 @@ vabd_s16_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -606,6 +710,8 @@ vabdq_s16_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -623,6 +729,8 @@ vabd_s32_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -640,6 +748,8 @@ vabdq_s32_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -657,6 +767,8 @@ vabd_u8_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -674,6 +786,8 @@ vabdq_u8_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -691,6 +805,8 @@ vabd_u16_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -708,6 +824,8 @@ vabdq_u16_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -725,6 +843,8 @@ vabd_u32_(a, b)
 }
 
 /// Absolute difference between the arguments
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -742,6 +862,8 @@ vabdq_u32_(a, b)
 }
 
 /// Absolute difference between the arguments of Floating
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabd_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -759,6 +881,8 @@ vabd_f32_(a, b)
 }
 
 /// Absolute difference between the arguments of Floating
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -776,6 +900,8 @@ vabdq_f32_(a, b)
 }
 
 /// Unsigned Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -787,6 +913,8 @@ pub unsafe fn vabdl_u8(a: uint8x8_t, b: uint8x8_t) -> uint16x8_t {
 }
 
 /// Unsigned Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -798,6 +926,8 @@ pub unsafe fn vabdl_u16(a: uint16x4_t, b: uint16x4_t) -> uint32x4_t {
 }
 
 /// Unsigned Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -809,6 +939,8 @@ pub unsafe fn vabdl_u32(a: uint32x2_t, b: uint32x2_t) -> uint64x2_t {
 }
 
 /// Signed Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -821,6 +953,8 @@ pub unsafe fn vabdl_s8(a: int8x8_t, b: int8x8_t) -> int16x8_t {
 }
 
 /// Signed Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -833,6 +967,8 @@ pub unsafe fn vabdl_s16(a: int16x4_t, b: int16x4_t) -> int32x4_t {
 }
 
 /// Signed Absolute difference Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabdl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -845,6 +981,8 @@ pub unsafe fn vabdl_s32(a: int32x2_t, b: int32x2_t) -> int64x2_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -856,6 +994,8 @@ pub unsafe fn vceq_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -867,6 +1007,8 @@ pub unsafe fn vceqq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -878,6 +1020,8 @@ pub unsafe fn vceq_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -889,6 +1033,8 @@ pub unsafe fn vceqq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -900,6 +1046,8 @@ pub unsafe fn vceq_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -911,6 +1059,8 @@ pub unsafe fn vceqq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -922,6 +1072,8 @@ pub unsafe fn vceq_s8(a: int8x8_t, b: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -933,6 +1085,8 @@ pub unsafe fn vceqq_s8(a: int8x16_t, b: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -944,6 +1098,8 @@ pub unsafe fn vceq_s16(a: int16x4_t, b: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -955,6 +1111,8 @@ pub unsafe fn vceqq_s16(a: int16x8_t, b: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -966,6 +1124,8 @@ pub unsafe fn vceq_s32(a: int32x2_t, b: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -977,6 +1137,8 @@ pub unsafe fn vceqq_s32(a: int32x4_t, b: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -988,6 +1150,8 @@ pub unsafe fn vceq_p8(a: poly8x8_t, b: poly8x8_t) -> uint8x8_t {
 }
 
 /// Compare bitwise Equal (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -999,6 +1163,8 @@ pub unsafe fn vceqq_p8(a: poly8x16_t, b: poly8x16_t) -> uint8x16_t {
 }
 
 /// Floating-point compare equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1010,6 +1176,8 @@ pub unsafe fn vceq_f32(a: float32x2_t, b: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vceqq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1021,6 +1189,8 @@ pub unsafe fn vceqq_f32(a: float32x4_t, b: float32x4_t) -> uint32x4_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1034,6 +1204,8 @@ pub unsafe fn vtst_s8(a: int8x8_t, b: int8x8_t) -> uint8x8_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1047,6 +1219,8 @@ pub unsafe fn vtstq_s8(a: int8x16_t, b: int8x16_t) -> uint8x16_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1060,6 +1234,8 @@ pub unsafe fn vtst_s16(a: int16x4_t, b: int16x4_t) -> uint16x4_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1073,6 +1249,8 @@ pub unsafe fn vtstq_s16(a: int16x8_t, b: int16x8_t) -> uint16x8_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1086,6 +1264,8 @@ pub unsafe fn vtst_s32(a: int32x2_t, b: int32x2_t) -> uint32x2_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1099,6 +1279,8 @@ pub unsafe fn vtstq_s32(a: int32x4_t, b: int32x4_t) -> uint32x4_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1112,6 +1294,8 @@ pub unsafe fn vtst_p8(a: poly8x8_t, b: poly8x8_t) -> uint8x8_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1125,6 +1309,8 @@ pub unsafe fn vtstq_p8(a: poly8x16_t, b: poly8x16_t) -> uint8x16_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1138,6 +1324,8 @@ pub unsafe fn vtst_p16(a: poly16x4_t, b: poly16x4_t) -> uint16x4_t {
 }
 
 /// Signed compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1151,6 +1339,8 @@ pub unsafe fn vtstq_p16(a: poly16x8_t, b: poly16x8_t) -> uint16x8_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1164,6 +1354,8 @@ pub unsafe fn vtst_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1177,6 +1369,8 @@ pub unsafe fn vtstq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1190,6 +1384,8 @@ pub unsafe fn vtst_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1203,6 +1399,8 @@ pub unsafe fn vtstq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtst_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1216,6 +1414,8 @@ pub unsafe fn vtst_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Unsigned compare bitwise Test bits nonzero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtstq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1229,6 +1429,8 @@ pub unsafe fn vtstq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabs_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1240,6 +1442,8 @@ pub unsafe fn vabs_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Floating-point absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabsq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1251,6 +1455,8 @@ pub unsafe fn vabsq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1262,6 +1468,8 @@ pub unsafe fn vcgt_s8(a: int8x8_t, b: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1273,6 +1481,8 @@ pub unsafe fn vcgtq_s8(a: int8x16_t, b: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1284,6 +1494,8 @@ pub unsafe fn vcgt_s16(a: int16x4_t, b: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1295,6 +1507,8 @@ pub unsafe fn vcgtq_s16(a: int16x8_t, b: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1306,6 +1520,8 @@ pub unsafe fn vcgt_s32(a: int32x2_t, b: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1317,6 +1533,8 @@ pub unsafe fn vcgtq_s32(a: int32x4_t, b: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1328,6 +1546,8 @@ pub unsafe fn vcgt_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1339,6 +1559,8 @@ pub unsafe fn vcgtq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1350,6 +1572,8 @@ pub unsafe fn vcgt_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1361,6 +1585,8 @@ pub unsafe fn vcgtq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1372,6 +1598,8 @@ pub unsafe fn vcgt_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Compare unsigned highe
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1383,6 +1611,8 @@ pub unsafe fn vcgtq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgt_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1394,6 +1624,8 @@ pub unsafe fn vcgt_f32(a: float32x2_t, b: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgtq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1405,6 +1637,8 @@ pub unsafe fn vcgtq_f32(a: float32x4_t, b: float32x4_t) -> uint32x4_t {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1416,6 +1650,8 @@ pub unsafe fn vclt_s8(a: int8x8_t, b: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1427,6 +1663,8 @@ pub unsafe fn vcltq_s8(a: int8x16_t, b: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1438,6 +1676,8 @@ pub unsafe fn vclt_s16(a: int16x4_t, b: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1449,6 +1689,8 @@ pub unsafe fn vcltq_s16(a: int16x8_t, b: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1460,6 +1702,8 @@ pub unsafe fn vclt_s32(a: int32x2_t, b: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1471,6 +1715,8 @@ pub unsafe fn vcltq_s32(a: int32x4_t, b: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1482,6 +1728,8 @@ pub unsafe fn vclt_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1493,6 +1741,8 @@ pub unsafe fn vcltq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1504,6 +1754,8 @@ pub unsafe fn vclt_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1515,6 +1767,8 @@ pub unsafe fn vcltq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1526,6 +1780,8 @@ pub unsafe fn vclt_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Compare unsigned less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1537,6 +1793,8 @@ pub unsafe fn vcltq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclt_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1548,6 +1806,8 @@ pub unsafe fn vclt_f32(a: float32x2_t, b: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcltq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1559,6 +1819,8 @@ pub unsafe fn vcltq_f32(a: float32x4_t, b: float32x4_t) -> uint32x4_t {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1570,6 +1832,8 @@ pub unsafe fn vcle_s8(a: int8x8_t, b: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1581,6 +1845,8 @@ pub unsafe fn vcleq_s8(a: int8x16_t, b: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1592,6 +1858,8 @@ pub unsafe fn vcle_s16(a: int16x4_t, b: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1603,6 +1871,8 @@ pub unsafe fn vcleq_s16(a: int16x8_t, b: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1614,6 +1884,8 @@ pub unsafe fn vcle_s32(a: int32x2_t, b: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1625,6 +1897,8 @@ pub unsafe fn vcleq_s32(a: int32x4_t, b: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1636,6 +1910,8 @@ pub unsafe fn vcle_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1647,6 +1923,8 @@ pub unsafe fn vcleq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1658,6 +1936,8 @@ pub unsafe fn vcle_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1669,6 +1949,8 @@ pub unsafe fn vcleq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1680,6 +1962,8 @@ pub unsafe fn vcle_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Compare unsigned less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1691,6 +1975,8 @@ pub unsafe fn vcleq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcle_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1702,6 +1988,8 @@ pub unsafe fn vcle_f32(a: float32x2_t, b: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcleq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1713,6 +2001,8 @@ pub unsafe fn vcleq_f32(a: float32x4_t, b: float32x4_t) -> uint32x4_t {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1724,6 +2014,8 @@ pub unsafe fn vcge_s8(a: int8x8_t, b: int8x8_t) -> uint8x8_t {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1735,6 +2027,8 @@ pub unsafe fn vcgeq_s8(a: int8x16_t, b: int8x16_t) -> uint8x16_t {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1746,6 +2040,8 @@ pub unsafe fn vcge_s16(a: int16x4_t, b: int16x4_t) -> uint16x4_t {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1757,6 +2053,8 @@ pub unsafe fn vcgeq_s16(a: int16x8_t, b: int16x8_t) -> uint16x8_t {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1768,6 +2066,8 @@ pub unsafe fn vcge_s32(a: int32x2_t, b: int32x2_t) -> uint32x2_t {
 }
 
 /// Compare signed greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1779,6 +2079,8 @@ pub unsafe fn vcgeq_s32(a: int32x4_t, b: int32x4_t) -> uint32x4_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1790,6 +2092,8 @@ pub unsafe fn vcge_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1801,6 +2105,8 @@ pub unsafe fn vcgeq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1812,6 +2118,8 @@ pub unsafe fn vcge_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1823,6 +2131,8 @@ pub unsafe fn vcgeq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1834,6 +2144,8 @@ pub unsafe fn vcge_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Compare unsigned greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1845,6 +2157,8 @@ pub unsafe fn vcgeq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcge_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1856,6 +2170,8 @@ pub unsafe fn vcge_f32(a: float32x2_t, b: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcgeq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1867,6 +2183,8 @@ pub unsafe fn vcgeq_f32(a: float32x4_t, b: float32x4_t) -> uint32x4_t {
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcls_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1884,6 +2202,8 @@ vcls_s8_(a)
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclsq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1901,6 +2221,8 @@ vclsq_s8_(a)
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcls_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1918,6 +2240,8 @@ vcls_s16_(a)
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclsq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1935,6 +2259,8 @@ vclsq_s16_(a)
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcls_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1952,6 +2278,8 @@ vcls_s32_(a)
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclsq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1969,6 +2297,8 @@ vclsq_s32_(a)
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcls_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1980,6 +2310,8 @@ pub unsafe fn vcls_u8(a: uint8x8_t) -> int8x8_t {
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclsq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1991,6 +2323,8 @@ pub unsafe fn vclsq_u8(a: uint8x16_t) -> int8x16_t {
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcls_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2002,6 +2336,8 @@ pub unsafe fn vcls_u16(a: uint16x4_t) -> int16x4_t {
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclsq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2013,6 +2349,8 @@ pub unsafe fn vclsq_u16(a: uint16x8_t) -> int16x8_t {
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcls_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2024,6 +2362,8 @@ pub unsafe fn vcls_u32(a: uint32x2_t) -> int32x2_t {
 }
 
 /// Count leading sign bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclsq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2035,6 +2375,8 @@ pub unsafe fn vclsq_u32(a: uint32x4_t) -> int32x4_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclz_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2046,6 +2388,8 @@ pub unsafe fn vclz_s8(a: int8x8_t) -> int8x8_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclzq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2057,6 +2401,8 @@ pub unsafe fn vclzq_s8(a: int8x16_t) -> int8x16_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclz_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2068,6 +2414,8 @@ pub unsafe fn vclz_s16(a: int16x4_t) -> int16x4_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclzq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2079,6 +2427,8 @@ pub unsafe fn vclzq_s16(a: int16x8_t) -> int16x8_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclz_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2090,6 +2440,8 @@ pub unsafe fn vclz_s32(a: int32x2_t) -> int32x2_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclzq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2101,6 +2453,8 @@ pub unsafe fn vclzq_s32(a: int32x4_t) -> int32x4_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclz_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2112,6 +2466,8 @@ pub unsafe fn vclz_u8(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclzq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2123,6 +2479,8 @@ pub unsafe fn vclzq_u8(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclz_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2134,6 +2492,8 @@ pub unsafe fn vclz_u16(a: uint16x4_t) -> uint16x4_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclzq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2145,6 +2505,8 @@ pub unsafe fn vclzq_u16(a: uint16x8_t) -> uint16x8_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclz_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2156,6 +2518,8 @@ pub unsafe fn vclz_u32(a: uint32x2_t) -> uint32x2_t {
 }
 
 /// Count leading zero bits
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vclzq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2167,6 +2531,8 @@ pub unsafe fn vclzq_u32(a: uint32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point absolute compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcagt_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2184,6 +2550,8 @@ vcagt_f32_(a, b)
 }
 
 /// Floating-point absolute compare greater than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcagtq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2201,6 +2569,8 @@ vcagtq_f32_(a, b)
 }
 
 /// Floating-point absolute compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcage_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2218,6 +2588,8 @@ vcage_f32_(a, b)
 }
 
 /// Floating-point absolute compare greater than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcageq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2235,6 +2607,8 @@ vcageq_f32_(a, b)
 }
 
 /// Floating-point absolute compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcalt_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2246,6 +2620,8 @@ pub unsafe fn vcalt_f32(a: float32x2_t, b: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point absolute compare less than
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaltq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2257,6 +2633,8 @@ pub unsafe fn vcaltq_f32(a: float32x4_t, b: float32x4_t) -> uint32x4_t {
 }
 
 /// Floating-point absolute compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcale_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2268,6 +2646,8 @@ pub unsafe fn vcale_f32(a: float32x2_t, b: float32x2_t) -> uint32x2_t {
 }
 
 /// Floating-point absolute compare less than or equal
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcaleq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2279,6 +2659,8 @@ pub unsafe fn vcaleq_f32(a: float32x4_t, b: float32x4_t) -> uint32x4_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2290,6 +2672,8 @@ pub unsafe fn vcreate_s8(a: u64) -> int8x8_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2301,6 +2685,8 @@ pub unsafe fn vcreate_s16(a: u64) -> int16x4_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2312,6 +2698,8 @@ pub unsafe fn vcreate_s32(a: u64) -> int32x2_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2323,6 +2711,8 @@ pub unsafe fn vcreate_s64(a: u64) -> int64x1_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2334,6 +2724,8 @@ pub unsafe fn vcreate_u8(a: u64) -> uint8x8_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2345,6 +2737,8 @@ pub unsafe fn vcreate_u16(a: u64) -> uint16x4_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2356,6 +2750,8 @@ pub unsafe fn vcreate_u32(a: u64) -> uint32x2_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2367,6 +2763,8 @@ pub unsafe fn vcreate_u64(a: u64) -> uint64x1_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2378,6 +2776,8 @@ pub unsafe fn vcreate_p8(a: u64) -> poly8x8_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2389,6 +2789,8 @@ pub unsafe fn vcreate_p16(a: u64) -> poly16x4_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -2400,6 +2802,8 @@ pub unsafe fn vcreate_p64(a: u64) -> poly64x1_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcreate_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2411,6 +2815,8 @@ pub unsafe fn vcreate_f32(a: u64) -> float32x2_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_f32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2422,6 +2828,8 @@ pub unsafe fn vcvt_f32_s32(a: int32x2_t) -> float32x2_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_f32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2433,6 +2841,8 @@ pub unsafe fn vcvtq_f32_s32(a: int32x4_t) -> float32x4_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_f32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2444,6 +2854,8 @@ pub unsafe fn vcvt_f32_u32(a: uint32x2_t) -> float32x2_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_f32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2455,6 +2867,8 @@ pub unsafe fn vcvtq_f32_u32(a: uint32x4_t) -> float32x4_t {
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_f32_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2471,6 +2885,8 @@ vcvt_n_f32_s32_(a, N)
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_f32_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2488,6 +2904,8 @@ vcvt_n_f32_s32_(a, N)
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_f32_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2504,6 +2922,8 @@ vcvtq_n_f32_s32_(a, N)
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_f32_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2521,6 +2941,8 @@ vcvtq_n_f32_s32_(a, N)
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_f32_u32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2537,6 +2959,8 @@ vcvt_n_f32_u32_(a, N)
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_f32_u32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2554,6 +2978,8 @@ vcvt_n_f32_u32_(a, N)
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_f32_u32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2570,6 +2996,8 @@ vcvtq_n_f32_u32_(a, N)
 }
 
 /// Fixed-point convert to floating-point
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_f32_u32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2587,6 +3015,8 @@ vcvtq_n_f32_u32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_s32_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2603,6 +3033,8 @@ vcvt_n_s32_f32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_s32_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2620,6 +3052,8 @@ vcvt_n_s32_f32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_s32_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2636,6 +3070,8 @@ vcvtq_n_s32_f32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_s32_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2653,6 +3089,8 @@ vcvtq_n_s32_f32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_u32_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2669,6 +3107,8 @@ vcvt_n_u32_f32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_n_u32_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2686,6 +3126,8 @@ vcvt_n_u32_f32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_u32_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -2702,6 +3144,8 @@ vcvtq_n_u32_f32_(a, N)
 }
 
 /// Floating-point convert to fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_n_u32_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -2719,6 +3163,8 @@ vcvtq_n_u32_f32_(a, N)
 }
 
 /// Floating-point convert to signed fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2736,6 +3182,8 @@ vcvt_s32_f32_(a)
 }
 
 /// Floating-point convert to signed fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2753,6 +3201,8 @@ vcvtq_s32_f32_(a)
 }
 
 /// Floating-point convert to unsigned fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvt_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2770,6 +3220,8 @@ vcvt_u32_f32_(a)
 }
 
 /// Floating-point convert to unsigned fixed-point, rounding toward zero
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vcvtq_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2787,6 +3239,8 @@ vcvtq_u32_f32_(a)
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2800,6 +3254,8 @@ pub unsafe fn vdup_lane_s8<const N: i32>(a: int8x8_t) -> int8x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2813,6 +3269,8 @@ pub unsafe fn vdupq_laneq_s8<const N: i32>(a: int8x16_t) -> int8x16_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2826,6 +3284,8 @@ pub unsafe fn vdup_lane_s16<const N: i32>(a: int16x4_t) -> int16x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2839,6 +3299,8 @@ pub unsafe fn vdupq_laneq_s16<const N: i32>(a: int16x8_t) -> int16x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2852,6 +3314,8 @@ pub unsafe fn vdup_lane_s32<const N: i32>(a: int32x2_t) -> int32x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2865,6 +3329,8 @@ pub unsafe fn vdupq_laneq_s32<const N: i32>(a: int32x4_t) -> int32x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2878,6 +3344,8 @@ pub unsafe fn vdup_laneq_s8<const N: i32>(a: int8x16_t) -> int8x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2891,6 +3359,8 @@ pub unsafe fn vdup_laneq_s16<const N: i32>(a: int16x8_t) -> int16x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2904,6 +3374,8 @@ pub unsafe fn vdup_laneq_s32<const N: i32>(a: int32x4_t) -> int32x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2917,6 +3389,8 @@ pub unsafe fn vdupq_lane_s8<const N: i32>(a: int8x8_t) -> int8x16_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2930,6 +3404,8 @@ pub unsafe fn vdupq_lane_s16<const N: i32>(a: int16x4_t) -> int16x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2943,6 +3419,8 @@ pub unsafe fn vdupq_lane_s32<const N: i32>(a: int32x2_t) -> int32x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2956,6 +3434,8 @@ pub unsafe fn vdup_lane_u8<const N: i32>(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2969,6 +3449,8 @@ pub unsafe fn vdupq_laneq_u8<const N: i32>(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2982,6 +3464,8 @@ pub unsafe fn vdup_lane_u16<const N: i32>(a: uint16x4_t) -> uint16x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -2995,6 +3479,8 @@ pub unsafe fn vdupq_laneq_u16<const N: i32>(a: uint16x8_t) -> uint16x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3008,6 +3494,8 @@ pub unsafe fn vdup_lane_u32<const N: i32>(a: uint32x2_t) -> uint32x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3021,6 +3509,8 @@ pub unsafe fn vdupq_laneq_u32<const N: i32>(a: uint32x4_t) -> uint32x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3034,6 +3524,8 @@ pub unsafe fn vdup_laneq_u8<const N: i32>(a: uint8x16_t) -> uint8x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3047,6 +3539,8 @@ pub unsafe fn vdup_laneq_u16<const N: i32>(a: uint16x8_t) -> uint16x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3060,6 +3554,8 @@ pub unsafe fn vdup_laneq_u32<const N: i32>(a: uint32x4_t) -> uint32x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3073,6 +3569,8 @@ pub unsafe fn vdupq_lane_u8<const N: i32>(a: uint8x8_t) -> uint8x16_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3086,6 +3584,8 @@ pub unsafe fn vdupq_lane_u16<const N: i32>(a: uint16x4_t) -> uint16x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3099,6 +3599,8 @@ pub unsafe fn vdupq_lane_u32<const N: i32>(a: uint32x2_t) -> uint32x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3112,6 +3614,8 @@ pub unsafe fn vdup_lane_p8<const N: i32>(a: poly8x8_t) -> poly8x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3125,6 +3629,8 @@ pub unsafe fn vdupq_laneq_p8<const N: i32>(a: poly8x16_t) -> poly8x16_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3138,6 +3644,8 @@ pub unsafe fn vdup_lane_p16<const N: i32>(a: poly16x4_t) -> poly16x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3151,6 +3659,8 @@ pub unsafe fn vdupq_laneq_p16<const N: i32>(a: poly16x8_t) -> poly16x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3164,6 +3674,8 @@ pub unsafe fn vdup_laneq_p8<const N: i32>(a: poly8x16_t) -> poly8x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3177,6 +3689,8 @@ pub unsafe fn vdup_laneq_p16<const N: i32>(a: poly16x8_t) -> poly16x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3190,6 +3704,8 @@ pub unsafe fn vdupq_lane_p8<const N: i32>(a: poly8x8_t) -> poly8x16_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3203,6 +3719,8 @@ pub unsafe fn vdupq_lane_p16<const N: i32>(a: poly16x4_t) -> poly16x8_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3216,6 +3734,8 @@ pub unsafe fn vdupq_laneq_s64<const N: i32>(a: int64x2_t) -> int64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3229,6 +3749,8 @@ pub unsafe fn vdupq_lane_s64<const N: i32>(a: int64x1_t) -> int64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3242,6 +3764,8 @@ pub unsafe fn vdupq_laneq_u64<const N: i32>(a: uint64x2_t) -> uint64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3255,6 +3779,8 @@ pub unsafe fn vdupq_lane_u64<const N: i32>(a: uint64x1_t) -> uint64x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3268,6 +3794,8 @@ pub unsafe fn vdup_lane_f32<const N: i32>(a: float32x2_t) -> float32x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3281,6 +3809,8 @@ pub unsafe fn vdupq_laneq_f32<const N: i32>(a: float32x4_t) -> float32x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3294,6 +3824,8 @@ pub unsafe fn vdup_laneq_f32<const N: i32>(a: float32x4_t) -> float32x2_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdupq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3307,6 +3839,8 @@ pub unsafe fn vdupq_lane_f32<const N: i32>(a: float32x2_t) -> float32x4_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3320,6 +3854,8 @@ pub unsafe fn vdup_lane_s64<const N: i32>(a: int64x1_t) -> int64x1_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3333,6 +3869,8 @@ pub unsafe fn vdup_lane_u64<const N: i32>(a: uint64x1_t) -> uint64x1_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3346,6 +3884,8 @@ pub unsafe fn vdup_laneq_s64<const N: i32>(a: int64x2_t) -> int64x1_t {
 }
 
 /// Set all vector lanes to the same value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vdup_laneq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3359,11 +3899,13 @@ pub unsafe fn vdup_laneq_u64<const N: i32>(a: uint64x2_t) -> uint64x1_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 4))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 4))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 7))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 7))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vext_s8<const N: i32>(a: int8x8_t, b: int8x8_t) -> int8x8_t {
@@ -3382,11 +3924,13 @@ pub unsafe fn vext_s8<const N: i32>(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 8))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 8))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 15))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 15))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_s8<const N: i32>(a: int8x16_t, b: int8x16_t) -> int8x16_t {
@@ -3413,11 +3957,13 @@ pub unsafe fn vextq_s8<const N: i32>(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 2))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 2))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 3))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 3))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vext_s16<const N: i32>(a: int16x4_t, b: int16x4_t) -> int16x4_t {
@@ -3432,11 +3978,13 @@ pub unsafe fn vext_s16<const N: i32>(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 4))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 4))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 7))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 7))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_s16<const N: i32>(a: int16x8_t, b: int16x8_t) -> int16x8_t {
@@ -3455,6 +4003,8 @@ pub unsafe fn vextq_s16<const N: i32>(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3472,11 +4022,13 @@ pub unsafe fn vext_s32<const N: i32>(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 2))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 2))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 3))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 3))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_s32<const N: i32>(a: int32x4_t, b: int32x4_t) -> int32x4_t {
@@ -3491,11 +4043,13 @@ pub unsafe fn vextq_s32<const N: i32>(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 4))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 4))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 7))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 7))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vext_u8<const N: i32>(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
@@ -3514,11 +4068,13 @@ pub unsafe fn vext_u8<const N: i32>(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 8))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 8))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 15))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 15))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_u8<const N: i32>(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
@@ -3545,11 +4101,13 @@ pub unsafe fn vextq_u8<const N: i32>(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 2))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 2))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 3))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 3))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vext_u16<const N: i32>(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
@@ -3564,11 +4122,13 @@ pub unsafe fn vext_u16<const N: i32>(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 4))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 4))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 7))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 7))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_u16<const N: i32>(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
@@ -3587,6 +4147,8 @@ pub unsafe fn vextq_u16<const N: i32>(a: uint16x8_t, b: uint16x8_t) -> uint16x8_
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3604,11 +4166,13 @@ pub unsafe fn vext_u32<const N: i32>(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 2))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 2))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 3))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 3))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_u32<const N: i32>(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
@@ -3623,11 +4187,13 @@ pub unsafe fn vextq_u32<const N: i32>(a: uint32x4_t, b: uint32x4_t) -> uint32x4_
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 4))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 4))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 7))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 7))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vext_p8<const N: i32>(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
@@ -3646,11 +4212,13 @@ pub unsafe fn vext_p8<const N: i32>(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 8))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 8))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 15))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 15))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_p8<const N: i32>(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
@@ -3677,11 +4245,13 @@ pub unsafe fn vextq_p8<const N: i32>(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 2))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 2))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 3))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 3))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vext_p16<const N: i32>(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
@@ -3696,11 +4266,13 @@ pub unsafe fn vext_p16<const N: i32>(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 4))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 4))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 7))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 7))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_p16<const N: i32>(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
@@ -3719,6 +4291,8 @@ pub unsafe fn vextq_p16<const N: i32>(a: poly16x8_t, b: poly16x8_t) -> poly16x8_
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3736,6 +4310,8 @@ pub unsafe fn vextq_s64<const N: i32>(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3753,6 +4329,8 @@ pub unsafe fn vextq_u64<const N: i32>(a: uint64x2_t, b: uint64x2_t) -> uint64x2_
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vext_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3770,11 +4348,13 @@ pub unsafe fn vext_f32<const N: i32>(a: float32x2_t, b: float32x2_t) -> float32x
 }
 
 /// Extract vector from pair of vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vextq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
-#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 2))]
-#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 2))]
+#[cfg_attr(all(test, target_arch = "arm"), assert_instr("vext.8", N = 3))]
+#[cfg_attr(all(test, target_arch = "aarch64"), assert_instr(ext, N = 3))]
 #[rustc_legacy_const_generics(2)]
 #[cfg_attr(target_arch = "aarch64", stable(feature = "neon_intrinsics", since = "1.59.0"))]
 pub unsafe fn vextq_f32<const N: i32>(a: float32x4_t, b: float32x4_t) -> float32x4_t {
@@ -3789,6 +4369,8 @@ pub unsafe fn vextq_f32<const N: i32>(a: float32x4_t, b: float32x4_t) -> float32
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3800,6 +4382,8 @@ pub unsafe fn vmla_s8(a: int8x8_t, b: int8x8_t, c: int8x8_t) -> int8x8_t {
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3811,6 +4395,8 @@ pub unsafe fn vmlaq_s8(a: int8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3822,6 +4408,8 @@ pub unsafe fn vmla_s16(a: int16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_t {
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3833,6 +4421,8 @@ pub unsafe fn vmlaq_s16(a: int16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t {
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3844,6 +4434,8 @@ pub unsafe fn vmla_s32(a: int32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_t {
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3855,6 +4447,8 @@ pub unsafe fn vmlaq_s32(a: int32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t {
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3866,6 +4460,8 @@ pub unsafe fn vmla_u8(a: uint8x8_t, b: uint8x8_t, c: uint8x8_t) -> uint8x8_t {
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3877,6 +4473,8 @@ pub unsafe fn vmlaq_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16_
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3888,6 +4486,8 @@ pub unsafe fn vmla_u16(a: uint16x4_t, b: uint16x4_t, c: uint16x4_t) -> uint16x4_
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3899,6 +4499,8 @@ pub unsafe fn vmlaq_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x8
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3910,6 +4512,8 @@ pub unsafe fn vmla_u32(a: uint32x2_t, b: uint32x2_t, c: uint32x2_t) -> uint32x2_
 }
 
 /// Multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3921,6 +4525,8 @@ pub unsafe fn vmlaq_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x4
 }
 
 /// Floating-point multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3932,6 +4538,8 @@ pub unsafe fn vmla_f32(a: float32x2_t, b: float32x2_t, c: float32x2_t) -> float3
 }
 
 /// Floating-point multiply-add to accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3943,6 +4551,8 @@ pub unsafe fn vmlaq_f32(a: float32x4_t, b: float32x4_t, c: float32x4_t) -> float
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3954,6 +4564,8 @@ pub unsafe fn vmla_n_s16(a: int16x4_t, b: int16x4_t, c: i16) -> int16x4_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3965,6 +4577,8 @@ pub unsafe fn vmlaq_n_s16(a: int16x8_t, b: int16x8_t, c: i16) -> int16x8_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3976,6 +4590,8 @@ pub unsafe fn vmla_n_s32(a: int32x2_t, b: int32x2_t, c: i32) -> int32x2_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3987,6 +4603,8 @@ pub unsafe fn vmlaq_n_s32(a: int32x4_t, b: int32x4_t, c: i32) -> int32x4_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3998,6 +4616,8 @@ pub unsafe fn vmla_n_u16(a: uint16x4_t, b: uint16x4_t, c: u16) -> uint16x4_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4009,6 +4629,8 @@ pub unsafe fn vmlaq_n_u16(a: uint16x8_t, b: uint16x8_t, c: u16) -> uint16x8_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4020,6 +4642,8 @@ pub unsafe fn vmla_n_u32(a: uint32x2_t, b: uint32x2_t, c: u32) -> uint32x2_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4031,6 +4655,8 @@ pub unsafe fn vmlaq_n_u32(a: uint32x4_t, b: uint32x4_t, c: u32) -> uint32x4_t {
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4042,6 +4668,8 @@ pub unsafe fn vmla_n_f32(a: float32x2_t, b: float32x2_t, c: f32) -> float32x2_t
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4053,6 +4681,8 @@ pub unsafe fn vmlaq_n_f32(a: float32x4_t, b: float32x4_t, c: f32) -> float32x4_t
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4066,6 +4696,8 @@ pub unsafe fn vmla_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c: int1
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4079,6 +4711,8 @@ pub unsafe fn vmla_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c: int
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4092,6 +4726,8 @@ pub unsafe fn vmlaq_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c: int
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4105,6 +4741,8 @@ pub unsafe fn vmlaq_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c: in
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4118,6 +4756,8 @@ pub unsafe fn vmla_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c: int3
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4131,6 +4771,8 @@ pub unsafe fn vmla_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c: int
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4144,6 +4786,8 @@ pub unsafe fn vmlaq_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c: int
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4157,6 +4801,8 @@ pub unsafe fn vmlaq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c: in
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4170,6 +4816,8 @@ pub unsafe fn vmla_lane_u16<const LANE: i32>(a: uint16x4_t, b: uint16x4_t, c: ui
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4183,6 +4831,8 @@ pub unsafe fn vmla_laneq_u16<const LANE: i32>(a: uint16x4_t, b: uint16x4_t, c: u
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4196,6 +4846,8 @@ pub unsafe fn vmlaq_lane_u16<const LANE: i32>(a: uint16x8_t, b: uint16x8_t, c: u
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4209,6 +4861,8 @@ pub unsafe fn vmlaq_laneq_u16<const LANE: i32>(a: uint16x8_t, b: uint16x8_t, c:
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4222,6 +4876,8 @@ pub unsafe fn vmla_lane_u32<const LANE: i32>(a: uint32x2_t, b: uint32x2_t, c: ui
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4235,6 +4891,8 @@ pub unsafe fn vmla_laneq_u32<const LANE: i32>(a: uint32x2_t, b: uint32x2_t, c: u
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4248,6 +4906,8 @@ pub unsafe fn vmlaq_lane_u32<const LANE: i32>(a: uint32x4_t, b: uint32x4_t, c: u
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4261,6 +4921,8 @@ pub unsafe fn vmlaq_laneq_u32<const LANE: i32>(a: uint32x4_t, b: uint32x4_t, c:
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4274,6 +4936,8 @@ pub unsafe fn vmla_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmla_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4287,6 +4951,8 @@ pub unsafe fn vmla_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4300,6 +4966,8 @@ pub unsafe fn vmlaq_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c:
 }
 
 /// Vector multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlaq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4313,6 +4981,8 @@ pub unsafe fn vmlaq_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c
 }
 
 /// Signed multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4324,6 +4994,8 @@ pub unsafe fn vmlal_s8(a: int16x8_t, b: int8x8_t, c: int8x8_t) -> int16x8_t {
 }
 
 /// Signed multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4335,6 +5007,8 @@ pub unsafe fn vmlal_s16(a: int32x4_t, b: int16x4_t, c: int16x4_t) -> int32x4_t {
 }
 
 /// Signed multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4346,6 +5020,8 @@ pub unsafe fn vmlal_s32(a: int64x2_t, b: int32x2_t, c: int32x2_t) -> int64x2_t {
 }
 
 /// Unsigned multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4357,6 +5033,8 @@ pub unsafe fn vmlal_u8(a: uint16x8_t, b: uint8x8_t, c: uint8x8_t) -> uint16x8_t
 }
 
 /// Unsigned multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4368,6 +5046,8 @@ pub unsafe fn vmlal_u16(a: uint32x4_t, b: uint16x4_t, c: uint16x4_t) -> uint32x4
 }
 
 /// Unsigned multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4379,6 +5059,8 @@ pub unsafe fn vmlal_u32(a: uint64x2_t, b: uint32x2_t, c: uint32x2_t) -> uint64x2
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4390,6 +5072,8 @@ pub unsafe fn vmlal_n_s16(a: int32x4_t, b: int16x4_t, c: i16) -> int32x4_t {
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4401,6 +5085,8 @@ pub unsafe fn vmlal_n_s32(a: int64x2_t, b: int32x2_t, c: i32) -> int64x2_t {
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4412,6 +5098,8 @@ pub unsafe fn vmlal_n_u16(a: uint32x4_t, b: uint16x4_t, c: u16) -> uint32x4_t {
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4423,6 +5111,8 @@ pub unsafe fn vmlal_n_u32(a: uint64x2_t, b: uint32x2_t, c: u32) -> uint64x2_t {
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4436,6 +5126,8 @@ pub unsafe fn vmlal_lane_s16<const LANE: i32>(a: int32x4_t, b: int16x4_t, c: int
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4449,6 +5141,8 @@ pub unsafe fn vmlal_laneq_s16<const LANE: i32>(a: int32x4_t, b: int16x4_t, c: in
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4462,6 +5156,8 @@ pub unsafe fn vmlal_lane_s32<const LANE: i32>(a: int64x2_t, b: int32x2_t, c: int
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4475,6 +5171,8 @@ pub unsafe fn vmlal_laneq_s32<const LANE: i32>(a: int64x2_t, b: int32x2_t, c: in
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4488,6 +5186,8 @@ pub unsafe fn vmlal_lane_u16<const LANE: i32>(a: uint32x4_t, b: uint16x4_t, c: u
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4501,6 +5201,8 @@ pub unsafe fn vmlal_laneq_u16<const LANE: i32>(a: uint32x4_t, b: uint16x4_t, c:
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4514,6 +5216,8 @@ pub unsafe fn vmlal_lane_u32<const LANE: i32>(a: uint64x2_t, b: uint32x2_t, c: u
 }
 
 /// Vector widening multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlal_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4527,6 +5231,8 @@ pub unsafe fn vmlal_laneq_u32<const LANE: i32>(a: uint64x2_t, b: uint32x2_t, c:
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4538,6 +5244,8 @@ pub unsafe fn vmls_s8(a: int8x8_t, b: int8x8_t, c: int8x8_t) -> int8x8_t {
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4549,6 +5257,8 @@ pub unsafe fn vmlsq_s8(a: int8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4560,6 +5270,8 @@ pub unsafe fn vmls_s16(a: int16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_t {
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4571,6 +5283,8 @@ pub unsafe fn vmlsq_s16(a: int16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t {
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4582,6 +5296,8 @@ pub unsafe fn vmls_s32(a: int32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_t {
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4593,6 +5309,8 @@ pub unsafe fn vmlsq_s32(a: int32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t {
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4604,6 +5322,8 @@ pub unsafe fn vmls_u8(a: uint8x8_t, b: uint8x8_t, c: uint8x8_t) -> uint8x8_t {
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4615,6 +5335,8 @@ pub unsafe fn vmlsq_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16_
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4626,6 +5348,8 @@ pub unsafe fn vmls_u16(a: uint16x4_t, b: uint16x4_t, c: uint16x4_t) -> uint16x4_
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4637,6 +5361,8 @@ pub unsafe fn vmlsq_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x8
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4648,6 +5374,8 @@ pub unsafe fn vmls_u32(a: uint32x2_t, b: uint32x2_t, c: uint32x2_t) -> uint32x2_
 }
 
 /// Multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4659,6 +5387,8 @@ pub unsafe fn vmlsq_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x4
 }
 
 /// Floating-point multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4670,6 +5400,8 @@ pub unsafe fn vmls_f32(a: float32x2_t, b: float32x2_t, c: float32x2_t) -> float3
 }
 
 /// Floating-point multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4681,6 +5413,8 @@ pub unsafe fn vmlsq_f32(a: float32x4_t, b: float32x4_t, c: float32x4_t) -> float
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4692,6 +5426,8 @@ pub unsafe fn vmls_n_s16(a: int16x4_t, b: int16x4_t, c: i16) -> int16x4_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4703,6 +5439,8 @@ pub unsafe fn vmlsq_n_s16(a: int16x8_t, b: int16x8_t, c: i16) -> int16x8_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4714,6 +5452,8 @@ pub unsafe fn vmls_n_s32(a: int32x2_t, b: int32x2_t, c: i32) -> int32x2_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4725,6 +5465,8 @@ pub unsafe fn vmlsq_n_s32(a: int32x4_t, b: int32x4_t, c: i32) -> int32x4_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4736,6 +5478,8 @@ pub unsafe fn vmls_n_u16(a: uint16x4_t, b: uint16x4_t, c: u16) -> uint16x4_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4747,6 +5491,8 @@ pub unsafe fn vmlsq_n_u16(a: uint16x8_t, b: uint16x8_t, c: u16) -> uint16x8_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4758,6 +5504,8 @@ pub unsafe fn vmls_n_u32(a: uint32x2_t, b: uint32x2_t, c: u32) -> uint32x2_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4769,6 +5517,8 @@ pub unsafe fn vmlsq_n_u32(a: uint32x4_t, b: uint32x4_t, c: u32) -> uint32x4_t {
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4780,6 +5530,8 @@ pub unsafe fn vmls_n_f32(a: float32x2_t, b: float32x2_t, c: f32) -> float32x2_t
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4791,6 +5543,8 @@ pub unsafe fn vmlsq_n_f32(a: float32x4_t, b: float32x4_t, c: f32) -> float32x4_t
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4804,6 +5558,8 @@ pub unsafe fn vmls_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c: int1
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4817,6 +5573,8 @@ pub unsafe fn vmls_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t, c: int
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4830,6 +5588,8 @@ pub unsafe fn vmlsq_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c: int
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4843,6 +5603,8 @@ pub unsafe fn vmlsq_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t, c: in
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4856,6 +5618,8 @@ pub unsafe fn vmls_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c: int3
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4869,6 +5633,8 @@ pub unsafe fn vmls_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t, c: int
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4882,6 +5648,8 @@ pub unsafe fn vmlsq_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c: int
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4895,6 +5663,8 @@ pub unsafe fn vmlsq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t, c: in
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4908,6 +5678,8 @@ pub unsafe fn vmls_lane_u16<const LANE: i32>(a: uint16x4_t, b: uint16x4_t, c: ui
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4921,6 +5693,8 @@ pub unsafe fn vmls_laneq_u16<const LANE: i32>(a: uint16x4_t, b: uint16x4_t, c: u
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4934,6 +5708,8 @@ pub unsafe fn vmlsq_lane_u16<const LANE: i32>(a: uint16x8_t, b: uint16x8_t, c: u
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4947,6 +5723,8 @@ pub unsafe fn vmlsq_laneq_u16<const LANE: i32>(a: uint16x8_t, b: uint16x8_t, c:
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4960,6 +5738,8 @@ pub unsafe fn vmls_lane_u32<const LANE: i32>(a: uint32x2_t, b: uint32x2_t, c: ui
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4973,6 +5753,8 @@ pub unsafe fn vmls_laneq_u32<const LANE: i32>(a: uint32x2_t, b: uint32x2_t, c: u
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4986,6 +5768,8 @@ pub unsafe fn vmlsq_lane_u32<const LANE: i32>(a: uint32x4_t, b: uint32x4_t, c: u
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -4999,6 +5783,8 @@ pub unsafe fn vmlsq_laneq_u32<const LANE: i32>(a: uint32x4_t, b: uint32x4_t, c:
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5012,6 +5798,8 @@ pub unsafe fn vmls_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmls_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5025,6 +5813,8 @@ pub unsafe fn vmls_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t, c:
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5038,6 +5828,8 @@ pub unsafe fn vmlsq_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c:
 }
 
 /// Vector multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5051,6 +5843,8 @@ pub unsafe fn vmlsq_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t, c
 }
 
 /// Signed multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5062,6 +5856,8 @@ pub unsafe fn vmlsl_s8(a: int16x8_t, b: int8x8_t, c: int8x8_t) -> int16x8_t {
 }
 
 /// Signed multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5073,6 +5869,8 @@ pub unsafe fn vmlsl_s16(a: int32x4_t, b: int16x4_t, c: int16x4_t) -> int32x4_t {
 }
 
 /// Signed multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5084,6 +5882,8 @@ pub unsafe fn vmlsl_s32(a: int64x2_t, b: int32x2_t, c: int32x2_t) -> int64x2_t {
 }
 
 /// Unsigned multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5095,6 +5895,8 @@ pub unsafe fn vmlsl_u8(a: uint16x8_t, b: uint8x8_t, c: uint8x8_t) -> uint16x8_t
 }
 
 /// Unsigned multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5106,6 +5908,8 @@ pub unsafe fn vmlsl_u16(a: uint32x4_t, b: uint16x4_t, c: uint16x4_t) -> uint32x4
 }
 
 /// Unsigned multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5117,6 +5921,8 @@ pub unsafe fn vmlsl_u32(a: uint64x2_t, b: uint32x2_t, c: uint32x2_t) -> uint64x2
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5128,6 +5934,8 @@ pub unsafe fn vmlsl_n_s16(a: int32x4_t, b: int16x4_t, c: i16) -> int32x4_t {
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5139,6 +5947,8 @@ pub unsafe fn vmlsl_n_s32(a: int64x2_t, b: int32x2_t, c: i32) -> int64x2_t {
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5150,6 +5960,8 @@ pub unsafe fn vmlsl_n_u16(a: uint32x4_t, b: uint16x4_t, c: u16) -> uint32x4_t {
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5161,6 +5973,8 @@ pub unsafe fn vmlsl_n_u32(a: uint64x2_t, b: uint32x2_t, c: u32) -> uint64x2_t {
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5174,6 +5988,8 @@ pub unsafe fn vmlsl_lane_s16<const LANE: i32>(a: int32x4_t, b: int16x4_t, c: int
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5187,6 +6003,8 @@ pub unsafe fn vmlsl_laneq_s16<const LANE: i32>(a: int32x4_t, b: int16x4_t, c: in
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5200,6 +6018,8 @@ pub unsafe fn vmlsl_lane_s32<const LANE: i32>(a: int64x2_t, b: int32x2_t, c: int
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5213,6 +6033,8 @@ pub unsafe fn vmlsl_laneq_s32<const LANE: i32>(a: int64x2_t, b: int32x2_t, c: in
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5226,6 +6048,8 @@ pub unsafe fn vmlsl_lane_u16<const LANE: i32>(a: uint32x4_t, b: uint16x4_t, c: u
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5239,6 +6063,8 @@ pub unsafe fn vmlsl_laneq_u16<const LANE: i32>(a: uint32x4_t, b: uint16x4_t, c:
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5252,6 +6078,8 @@ pub unsafe fn vmlsl_lane_u32<const LANE: i32>(a: uint64x2_t, b: uint32x2_t, c: u
 }
 
 /// Vector widening multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmlsl_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5265,6 +6093,8 @@ pub unsafe fn vmlsl_laneq_u32<const LANE: i32>(a: uint64x2_t, b: uint32x2_t, c:
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vneg_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5276,6 +6106,8 @@ pub unsafe fn vneg_s8(a: int8x8_t) -> int8x8_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vnegq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5287,6 +6119,8 @@ pub unsafe fn vnegq_s8(a: int8x16_t) -> int8x16_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vneg_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5298,6 +6132,8 @@ pub unsafe fn vneg_s16(a: int16x4_t) -> int16x4_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vnegq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5309,6 +6145,8 @@ pub unsafe fn vnegq_s16(a: int16x8_t) -> int16x8_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vneg_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5320,6 +6158,8 @@ pub unsafe fn vneg_s32(a: int32x2_t) -> int32x2_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vnegq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5331,6 +6171,8 @@ pub unsafe fn vnegq_s32(a: int32x4_t) -> int32x4_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vneg_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5342,6 +6184,8 @@ pub unsafe fn vneg_f32(a: float32x2_t) -> float32x2_t {
 }
 
 /// Negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vnegq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5353,6 +6197,8 @@ pub unsafe fn vnegq_f32(a: float32x4_t) -> float32x4_t {
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqneg_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5370,6 +6216,8 @@ vqneg_s8_(a)
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5387,6 +6235,8 @@ vqnegq_s8_(a)
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqneg_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5404,6 +6254,8 @@ vqneg_s16_(a)
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5421,6 +6273,8 @@ vqnegq_s16_(a)
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqneg_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5438,6 +6292,8 @@ vqneg_s32_(a)
 }
 
 /// Signed saturating negate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqnegq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5455,6 +6311,8 @@ vqnegq_s32_(a)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5472,6 +6330,8 @@ vqsub_u8_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5489,6 +6349,8 @@ vqsubq_u8_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5506,6 +6368,8 @@ vqsub_u16_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5523,6 +6387,8 @@ vqsubq_u16_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5540,6 +6406,8 @@ vqsub_u32_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5557,6 +6425,8 @@ vqsubq_u32_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5574,6 +6444,8 @@ vqsub_u64_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5591,6 +6463,8 @@ vqsubq_u64_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5608,6 +6482,8 @@ vqsub_s8_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5625,6 +6501,8 @@ vqsubq_s8_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5642,6 +6520,8 @@ vqsub_s16_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5659,6 +6539,8 @@ vqsubq_s16_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5676,6 +6558,8 @@ vqsub_s32_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5693,6 +6577,8 @@ vqsubq_s32_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsub_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5710,6 +6596,8 @@ vqsub_s64_(a, b)
 }
 
 /// Saturating subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqsubq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5727,6 +6615,8 @@ vqsubq_s64_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhadd_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5744,6 +6634,8 @@ vhadd_u8_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhaddq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5761,6 +6653,8 @@ vhaddq_u8_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhadd_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5778,6 +6672,8 @@ vhadd_u16_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhaddq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5795,6 +6691,8 @@ vhaddq_u16_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhadd_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5812,6 +6710,8 @@ vhadd_u32_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhaddq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5829,6 +6729,8 @@ vhaddq_u32_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhadd_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5846,6 +6748,8 @@ vhadd_s8_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhaddq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5863,6 +6767,8 @@ vhaddq_s8_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhadd_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5880,6 +6786,8 @@ vhadd_s16_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhaddq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5897,6 +6805,8 @@ vhaddq_s16_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhadd_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5914,6 +6824,8 @@ vhadd_s32_(a, b)
 }
 
 /// Halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhaddq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5931,6 +6843,8 @@ vhaddq_s32_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhadd_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5948,6 +6862,8 @@ vrhadd_u8_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhaddq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5965,6 +6881,8 @@ vrhaddq_u8_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhadd_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5982,6 +6900,8 @@ vrhadd_u16_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhaddq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -5999,6 +6919,8 @@ vrhaddq_u16_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhadd_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6016,6 +6938,8 @@ vrhadd_u32_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhaddq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6033,6 +6957,8 @@ vrhaddq_u32_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhadd_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6050,6 +6976,8 @@ vrhadd_s8_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhaddq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6067,6 +6995,8 @@ vrhaddq_s8_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhadd_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6084,6 +7014,8 @@ vrhadd_s16_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhaddq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6101,6 +7033,8 @@ vrhaddq_s16_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhadd_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6118,6 +7052,8 @@ vrhadd_s32_(a, b)
 }
 
 /// Rounding halving add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrhaddq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6135,6 +7071,8 @@ vrhaddq_s32_(a, b)
 }
 
 /// Floating-point round to integral, to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndn_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "fp-armv8,v8"))]
@@ -6152,6 +7090,8 @@ vrndn_f32_(a)
 }
 
 /// Floating-point round to integral, to nearest with ties to even
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrndnq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "fp-armv8,v8"))]
@@ -6169,6 +7109,8 @@ vrndnq_f32_(a)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6186,6 +7128,8 @@ vqadd_u8_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6203,6 +7147,8 @@ vqaddq_u8_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6220,6 +7166,8 @@ vqadd_u16_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6237,6 +7185,8 @@ vqaddq_u16_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6254,6 +7204,8 @@ vqadd_u32_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6271,6 +7223,8 @@ vqaddq_u32_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6288,6 +7242,8 @@ vqadd_u64_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6305,6 +7261,8 @@ vqaddq_u64_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6322,6 +7280,8 @@ vqadd_s8_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6339,6 +7299,8 @@ vqaddq_s8_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6356,6 +7318,8 @@ vqadd_s16_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6373,6 +7337,8 @@ vqaddq_s16_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6390,6 +7356,8 @@ vqadd_s32_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6407,6 +7375,8 @@ vqaddq_s32_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqadd_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6424,6 +7394,8 @@ vqadd_s64_(a, b)
 }
 
 /// Saturating add
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqaddq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6441,6 +7413,8 @@ vqaddq_s64_(a, b)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6458,6 +7432,8 @@ vld1_s8_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6475,6 +7451,8 @@ vld1_s16_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6492,6 +7470,8 @@ vld1_s32_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6509,6 +7489,8 @@ vld1_s64_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6526,6 +7508,8 @@ vld1q_s8_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6543,6 +7527,8 @@ vld1q_s16_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6560,6 +7546,8 @@ vld1q_s32_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6577,6 +7565,8 @@ vld1q_s64_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6594,6 +7584,8 @@ vld1_s8_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6611,6 +7603,8 @@ vld1_s16_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6628,6 +7622,8 @@ vld1_s32_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6645,6 +7641,8 @@ vld1_s64_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6662,6 +7660,8 @@ vld1q_s8_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6679,6 +7679,8 @@ vld1q_s16_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6696,6 +7698,8 @@ vld1q_s32_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6713,6 +7717,8 @@ vld1q_s64_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6730,6 +7736,8 @@ vld1_s8_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6747,6 +7755,8 @@ vld1_s16_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6764,6 +7774,8 @@ vld1_s32_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_s64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6781,6 +7793,8 @@ vld1_s64_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6798,6 +7812,8 @@ vld1q_s8_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6815,6 +7831,8 @@ vld1q_s16_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6832,6 +7850,8 @@ vld1q_s32_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_s64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6849,6 +7869,8 @@ vld1q_s64_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6860,6 +7882,8 @@ pub unsafe fn vld1_u8_x2(a: *const u8) -> uint8x8x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6871,6 +7895,8 @@ pub unsafe fn vld1_u16_x2(a: *const u16) -> uint16x4x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6882,6 +7908,8 @@ pub unsafe fn vld1_u32_x2(a: *const u32) -> uint32x2x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6893,6 +7921,8 @@ pub unsafe fn vld1_u64_x2(a: *const u64) -> uint64x1x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6904,6 +7934,8 @@ pub unsafe fn vld1q_u8_x2(a: *const u8) -> uint8x16x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6915,6 +7947,8 @@ pub unsafe fn vld1q_u16_x2(a: *const u16) -> uint16x8x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6926,6 +7960,8 @@ pub unsafe fn vld1q_u32_x2(a: *const u32) -> uint32x4x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6937,6 +7973,8 @@ pub unsafe fn vld1q_u64_x2(a: *const u64) -> uint64x2x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6948,6 +7986,8 @@ pub unsafe fn vld1_u8_x3(a: *const u8) -> uint8x8x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6959,6 +7999,8 @@ pub unsafe fn vld1_u16_x3(a: *const u16) -> uint16x4x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6970,6 +8012,8 @@ pub unsafe fn vld1_u32_x3(a: *const u32) -> uint32x2x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6981,6 +8025,8 @@ pub unsafe fn vld1_u64_x3(a: *const u64) -> uint64x1x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -6992,6 +8038,8 @@ pub unsafe fn vld1q_u8_x3(a: *const u8) -> uint8x16x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7003,6 +8051,8 @@ pub unsafe fn vld1q_u16_x3(a: *const u16) -> uint16x8x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7014,6 +8064,8 @@ pub unsafe fn vld1q_u32_x3(a: *const u32) -> uint32x4x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7025,6 +8077,8 @@ pub unsafe fn vld1q_u64_x3(a: *const u64) -> uint64x2x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7036,6 +8090,8 @@ pub unsafe fn vld1_u8_x4(a: *const u8) -> uint8x8x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7047,6 +8103,8 @@ pub unsafe fn vld1_u16_x4(a: *const u16) -> uint16x4x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7058,6 +8116,8 @@ pub unsafe fn vld1_u32_x4(a: *const u32) -> uint32x2x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_u64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7069,6 +8129,8 @@ pub unsafe fn vld1_u64_x4(a: *const u64) -> uint64x1x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7080,6 +8142,8 @@ pub unsafe fn vld1q_u8_x4(a: *const u8) -> uint8x16x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7091,6 +8155,8 @@ pub unsafe fn vld1q_u16_x4(a: *const u16) -> uint16x8x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7102,6 +8168,8 @@ pub unsafe fn vld1q_u32_x4(a: *const u32) -> uint32x4x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_u64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7113,6 +8181,8 @@ pub unsafe fn vld1q_u64_x4(a: *const u64) -> uint64x2x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7124,6 +8194,8 @@ pub unsafe fn vld1_p8_x2(a: *const p8) -> poly8x8x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7135,6 +8207,8 @@ pub unsafe fn vld1_p8_x3(a: *const p8) -> poly8x8x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7146,6 +8220,8 @@ pub unsafe fn vld1_p8_x4(a: *const p8) -> poly8x8x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7157,6 +8233,8 @@ pub unsafe fn vld1q_p8_x2(a: *const p8) -> poly8x16x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7168,6 +8246,8 @@ pub unsafe fn vld1q_p8_x3(a: *const p8) -> poly8x16x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7179,6 +8259,8 @@ pub unsafe fn vld1q_p8_x4(a: *const p8) -> poly8x16x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7190,6 +8272,8 @@ pub unsafe fn vld1_p16_x2(a: *const p16) -> poly16x4x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7201,6 +8285,8 @@ pub unsafe fn vld1_p16_x3(a: *const p16) -> poly16x4x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7212,6 +8298,8 @@ pub unsafe fn vld1_p16_x4(a: *const p16) -> poly16x4x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7223,6 +8311,8 @@ pub unsafe fn vld1q_p16_x2(a: *const p16) -> poly16x8x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7234,6 +8324,8 @@ pub unsafe fn vld1q_p16_x3(a: *const p16) -> poly16x8x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7245,6 +8337,8 @@ pub unsafe fn vld1q_p16_x4(a: *const p16) -> poly16x8x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p64_x2)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -7256,6 +8350,8 @@ pub unsafe fn vld1_p64_x2(a: *const p64) -> poly64x1x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p64_x3)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -7267,6 +8363,8 @@ pub unsafe fn vld1_p64_x3(a: *const p64) -> poly64x1x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_p64_x4)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -7278,6 +8376,8 @@ pub unsafe fn vld1_p64_x4(a: *const p64) -> poly64x1x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p64_x2)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -7289,6 +8389,8 @@ pub unsafe fn vld1q_p64_x2(a: *const p64) -> poly64x2x2_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p64_x3)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -7300,6 +8402,8 @@ pub unsafe fn vld1q_p64_x3(a: *const p64) -> poly64x2x3_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_p64_x4)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -7311,6 +8415,8 @@ pub unsafe fn vld1q_p64_x4(a: *const p64) -> poly64x2x4_t {
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_f32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7328,6 +8434,8 @@ vld1_f32_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_f32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7345,6 +8453,8 @@ vld1q_f32_x2_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_f32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7362,6 +8472,8 @@ vld1_f32_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_f32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7379,6 +8491,8 @@ vld1q_f32_x3_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_f32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7396,6 +8510,8 @@ vld1_f32_x4_(a)
 }
 
 /// Load multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_f32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7413,6 +8529,8 @@ vld1q_f32_x4_(a)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7427,6 +8545,8 @@ vld2_s8_(a as *const i8, 1)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7442,6 +8562,8 @@ vld2_s8_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7456,6 +8578,8 @@ vld2_s16_(a as *const i8, 2)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7471,6 +8595,8 @@ vld2_s16_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7485,6 +8611,8 @@ vld2_s32_(a as *const i8, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7500,6 +8628,8 @@ vld2_s32_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7514,6 +8644,8 @@ vld2q_s8_(a as *const i8, 1)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7529,6 +8661,8 @@ vld2q_s8_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7543,6 +8677,8 @@ vld2q_s16_(a as *const i8, 2)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7558,6 +8694,8 @@ vld2q_s16_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7572,6 +8710,8 @@ vld2q_s32_(a as *const i8, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7587,6 +8727,8 @@ vld2q_s32_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7601,6 +8743,8 @@ vld2_s64_(a as *const i8, 8)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7616,6 +8760,8 @@ vld2_s64_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7627,6 +8773,8 @@ pub unsafe fn vld2_u8(a: *const u8) -> uint8x8x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7638,6 +8786,8 @@ pub unsafe fn vld2_u16(a: *const u16) -> uint16x4x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7649,6 +8799,8 @@ pub unsafe fn vld2_u32(a: *const u32) -> uint32x2x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7660,6 +8812,8 @@ pub unsafe fn vld2q_u8(a: *const u8) -> uint8x16x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7671,6 +8825,8 @@ pub unsafe fn vld2q_u16(a: *const u16) -> uint16x8x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7682,6 +8838,8 @@ pub unsafe fn vld2q_u32(a: *const u32) -> uint32x4x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7693,6 +8851,8 @@ pub unsafe fn vld2_p8(a: *const p8) -> poly8x8x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7704,6 +8864,8 @@ pub unsafe fn vld2_p16(a: *const p16) -> poly16x4x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7715,6 +8877,8 @@ pub unsafe fn vld2q_p8(a: *const p8) -> poly8x16x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7726,6 +8890,8 @@ pub unsafe fn vld2q_p16(a: *const p16) -> poly16x8x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -7737,6 +8903,8 @@ pub unsafe fn vld2_u64(a: *const u64) -> uint64x1x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -7748,6 +8916,8 @@ pub unsafe fn vld2_p64(a: *const p64) -> poly64x1x2_t {
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7762,6 +8932,8 @@ vld2_f32_(a as *const i8, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7777,6 +8949,8 @@ vld2_f32_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7791,6 +8965,8 @@ vld2q_f32_(a as *const i8, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7806,6 +8982,8 @@ vld2q_f32_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7820,6 +8998,8 @@ vld2_dup_s8_(a as *const i8, 1)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7835,6 +9015,8 @@ vld2_dup_s8_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7849,6 +9031,8 @@ vld2_dup_s16_(a as *const i8, 2)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7864,6 +9048,8 @@ vld2_dup_s16_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7878,6 +9064,8 @@ vld2_dup_s32_(a as *const i8, 4)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7893,6 +9081,8 @@ vld2_dup_s32_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7907,6 +9097,8 @@ vld2q_dup_s8_(a as *const i8, 1)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7922,6 +9114,8 @@ vld2q_dup_s8_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7936,6 +9130,8 @@ vld2q_dup_s16_(a as *const i8, 2)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7951,6 +9147,8 @@ vld2q_dup_s16_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7965,6 +9163,8 @@ vld2q_dup_s32_(a as *const i8, 4)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -7980,6 +9180,8 @@ vld2q_dup_s32_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -7994,6 +9196,8 @@ vld2_dup_s64_(a as *const i8, 8)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8009,6 +9213,8 @@ vld2_dup_s64_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8020,6 +9226,8 @@ pub unsafe fn vld2_dup_u8(a: *const u8) -> uint8x8x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8031,6 +9239,8 @@ pub unsafe fn vld2_dup_u16(a: *const u16) -> uint16x4x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8042,6 +9252,8 @@ pub unsafe fn vld2_dup_u32(a: *const u32) -> uint32x2x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8053,6 +9265,8 @@ pub unsafe fn vld2q_dup_u8(a: *const u8) -> uint8x16x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8064,6 +9278,8 @@ pub unsafe fn vld2q_dup_u16(a: *const u16) -> uint16x8x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8075,6 +9291,8 @@ pub unsafe fn vld2q_dup_u32(a: *const u32) -> uint32x4x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8086,6 +9304,8 @@ pub unsafe fn vld2_dup_p8(a: *const p8) -> poly8x8x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8097,6 +9317,8 @@ pub unsafe fn vld2_dup_p16(a: *const p16) -> poly16x4x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8108,6 +9330,8 @@ pub unsafe fn vld2q_dup_p8(a: *const p8) -> poly8x16x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8119,6 +9343,8 @@ pub unsafe fn vld2q_dup_p16(a: *const p16) -> poly16x8x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8130,6 +9356,8 @@ pub unsafe fn vld2_dup_u64(a: *const u64) -> uint64x1x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -8141,6 +9369,8 @@ pub unsafe fn vld2_dup_p64(a: *const p64) -> poly64x1x2_t {
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8155,6 +9385,8 @@ vld2_dup_f32_(a as *const i8, 4)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_dup_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8170,6 +9402,8 @@ vld2_dup_f32_(a as _)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8184,6 +9418,8 @@ vld2q_dup_f32_(a as *const i8, 4)
 }
 
 /// Load single 2-element structure and replicate to all lanes of two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_dup_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8199,6 +9435,8 @@ vld2q_dup_f32_(a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8215,6 +9453,8 @@ vld2_lane_s8_(a as _, b.0, b.1, LANE, 1)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8232,6 +9472,8 @@ vld2_lane_s8_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8248,6 +9490,8 @@ vld2_lane_s16_(a as _, b.0, b.1, LANE, 2)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8265,6 +9509,8 @@ vld2_lane_s16_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8281,6 +9527,8 @@ vld2_lane_s32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8298,6 +9546,8 @@ vld2_lane_s32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8314,6 +9564,8 @@ vld2q_lane_s16_(a as _, b.0, b.1, LANE, 2)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8331,6 +9583,8 @@ vld2q_lane_s16_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8347,6 +9601,8 @@ vld2q_lane_s32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8364,6 +9620,8 @@ vld2q_lane_s32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8377,6 +9635,8 @@ pub unsafe fn vld2_lane_u8<const LANE: i32>(a: *const u8, b: uint8x8x2_t) -> uin
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8390,6 +9650,8 @@ pub unsafe fn vld2_lane_u16<const LANE: i32>(a: *const u16, b: uint16x4x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8403,6 +9665,8 @@ pub unsafe fn vld2_lane_u32<const LANE: i32>(a: *const u32, b: uint32x2x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8416,6 +9680,8 @@ pub unsafe fn vld2q_lane_u16<const LANE: i32>(a: *const u16, b: uint16x8x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8429,6 +9695,8 @@ pub unsafe fn vld2q_lane_u32<const LANE: i32>(a: *const u32, b: uint32x4x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8442,6 +9710,8 @@ pub unsafe fn vld2_lane_p8<const LANE: i32>(a: *const p8, b: poly8x8x2_t) -> pol
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8455,6 +9725,8 @@ pub unsafe fn vld2_lane_p16<const LANE: i32>(a: *const p16, b: poly16x4x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8468,6 +9740,8 @@ pub unsafe fn vld2q_lane_p16<const LANE: i32>(a: *const p16, b: poly16x8x2_t) ->
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8484,6 +9758,8 @@ vld2_lane_f32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8501,6 +9777,8 @@ vld2_lane_f32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8517,6 +9795,8 @@ vld2q_lane_f32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Load multiple 2-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld2q_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8534,6 +9814,8 @@ vld2q_lane_f32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8548,6 +9830,8 @@ vld3_s8_(a as *const i8, 1)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8563,6 +9847,8 @@ vld3_s8_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8577,6 +9863,8 @@ vld3_s16_(a as *const i8, 2)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8592,6 +9880,8 @@ vld3_s16_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8606,6 +9896,8 @@ vld3_s32_(a as *const i8, 4)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8621,6 +9913,8 @@ vld3_s32_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8635,6 +9929,8 @@ vld3q_s8_(a as *const i8, 1)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8650,6 +9946,8 @@ vld3q_s8_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8664,6 +9962,8 @@ vld3q_s16_(a as *const i8, 2)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8679,6 +9979,8 @@ vld3q_s16_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8693,6 +9995,8 @@ vld3q_s32_(a as *const i8, 4)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8708,6 +10012,8 @@ vld3q_s32_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8722,6 +10028,8 @@ vld3_s64_(a as *const i8, 8)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8737,6 +10045,8 @@ vld3_s64_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8748,6 +10058,8 @@ pub unsafe fn vld3_u8(a: *const u8) -> uint8x8x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8759,6 +10071,8 @@ pub unsafe fn vld3_u16(a: *const u16) -> uint16x4x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8770,6 +10084,8 @@ pub unsafe fn vld3_u32(a: *const u32) -> uint32x2x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8781,6 +10097,8 @@ pub unsafe fn vld3q_u8(a: *const u8) -> uint8x16x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8792,6 +10110,8 @@ pub unsafe fn vld3q_u16(a: *const u16) -> uint16x8x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8803,6 +10123,8 @@ pub unsafe fn vld3q_u32(a: *const u32) -> uint32x4x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8814,6 +10136,8 @@ pub unsafe fn vld3_p8(a: *const p8) -> poly8x8x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8825,6 +10149,8 @@ pub unsafe fn vld3_p16(a: *const p16) -> poly16x4x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8836,6 +10162,8 @@ pub unsafe fn vld3q_p8(a: *const p8) -> poly8x16x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8847,6 +10175,8 @@ pub unsafe fn vld3q_p16(a: *const p16) -> poly16x8x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -8858,6 +10188,8 @@ pub unsafe fn vld3_u64(a: *const u64) -> uint64x1x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -8869,6 +10201,8 @@ pub unsafe fn vld3_p64(a: *const p64) -> poly64x1x3_t {
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8883,6 +10217,8 @@ vld3_f32_(a as *const i8, 4)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8898,6 +10234,8 @@ vld3_f32_(a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8912,6 +10250,8 @@ vld3q_f32_(a as *const i8, 4)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8927,6 +10267,8 @@ vld3q_f32_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8941,6 +10283,8 @@ vld3_dup_s8_(a as *const i8, 1)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8956,6 +10300,8 @@ vld3_dup_s8_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8970,6 +10316,8 @@ vld3_dup_s16_(a as *const i8, 2)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -8985,6 +10333,8 @@ vld3_dup_s16_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -8999,6 +10349,8 @@ vld3_dup_s32_(a as *const i8, 4)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9014,6 +10366,8 @@ vld3_dup_s32_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9028,6 +10382,8 @@ vld3q_dup_s8_(a as *const i8, 1)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9043,6 +10399,8 @@ vld3q_dup_s8_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9057,6 +10415,8 @@ vld3q_dup_s16_(a as *const i8, 2)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9072,6 +10432,8 @@ vld3q_dup_s16_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9086,6 +10448,8 @@ vld3q_dup_s32_(a as *const i8, 4)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9101,6 +10465,8 @@ vld3q_dup_s32_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9115,6 +10481,8 @@ vld3_dup_s64_(a as *const i8, 8)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9130,6 +10498,8 @@ vld3_dup_s64_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9141,6 +10511,8 @@ pub unsafe fn vld3_dup_u8(a: *const u8) -> uint8x8x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9152,6 +10524,8 @@ pub unsafe fn vld3_dup_u16(a: *const u16) -> uint16x4x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9163,6 +10537,8 @@ pub unsafe fn vld3_dup_u32(a: *const u32) -> uint32x2x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9174,6 +10550,8 @@ pub unsafe fn vld3q_dup_u8(a: *const u8) -> uint8x16x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9185,6 +10563,8 @@ pub unsafe fn vld3q_dup_u16(a: *const u16) -> uint16x8x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9196,6 +10576,8 @@ pub unsafe fn vld3q_dup_u32(a: *const u32) -> uint32x4x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9207,6 +10589,8 @@ pub unsafe fn vld3_dup_p8(a: *const p8) -> poly8x8x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9218,6 +10602,8 @@ pub unsafe fn vld3_dup_p16(a: *const p16) -> poly16x4x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9229,6 +10615,8 @@ pub unsafe fn vld3q_dup_p8(a: *const p8) -> poly8x16x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9240,6 +10628,8 @@ pub unsafe fn vld3q_dup_p16(a: *const p16) -> poly16x8x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9251,6 +10641,8 @@ pub unsafe fn vld3_dup_u64(a: *const u64) -> uint64x1x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -9262,6 +10654,8 @@ pub unsafe fn vld3_dup_p64(a: *const p64) -> poly64x1x3_t {
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9276,6 +10670,8 @@ vld3_dup_f32_(a as *const i8, 4)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_dup_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9291,6 +10687,8 @@ vld3_dup_f32_(a as _)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9305,6 +10703,8 @@ vld3q_dup_f32_(a as *const i8, 4)
 }
 
 /// Load single 3-element structure and replicate to all lanes of three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_dup_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9320,6 +10720,8 @@ vld3q_dup_f32_(a as _)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9336,6 +10738,8 @@ vld3_lane_s8_(a as _, b.0, b.1, b.2, LANE, 1)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9353,6 +10757,8 @@ vld3_lane_s8_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9369,6 +10775,8 @@ vld3_lane_s16_(a as _, b.0, b.1, b.2, LANE, 2)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9386,6 +10794,8 @@ vld3_lane_s16_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9402,6 +10812,8 @@ vld3_lane_s32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9419,6 +10831,8 @@ vld3_lane_s32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9435,6 +10849,8 @@ vld3q_lane_s16_(a as _, b.0, b.1, b.2, LANE, 2)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9452,6 +10868,8 @@ vld3q_lane_s16_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9468,6 +10886,8 @@ vld3q_lane_s32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Load multiple 3-element structures to two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9485,6 +10905,8 @@ vld3q_lane_s32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9498,6 +10920,8 @@ pub unsafe fn vld3_lane_u8<const LANE: i32>(a: *const u8, b: uint8x8x3_t) -> uin
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9511,6 +10935,8 @@ pub unsafe fn vld3_lane_u16<const LANE: i32>(a: *const u16, b: uint16x4x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9524,6 +10950,8 @@ pub unsafe fn vld3_lane_u32<const LANE: i32>(a: *const u32, b: uint32x2x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9537,6 +10965,8 @@ pub unsafe fn vld3q_lane_u16<const LANE: i32>(a: *const u16, b: uint16x8x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9550,6 +10980,8 @@ pub unsafe fn vld3q_lane_u32<const LANE: i32>(a: *const u32, b: uint32x4x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9563,6 +10995,8 @@ pub unsafe fn vld3_lane_p8<const LANE: i32>(a: *const p8, b: poly8x8x3_t) -> pol
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9576,6 +11010,8 @@ pub unsafe fn vld3_lane_p16<const LANE: i32>(a: *const p16, b: poly16x4x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9589,6 +11025,8 @@ pub unsafe fn vld3q_lane_p16<const LANE: i32>(a: *const p16, b: poly16x8x3_t) ->
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9605,6 +11043,8 @@ vld3_lane_f32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9622,6 +11062,8 @@ vld3_lane_f32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9638,6 +11080,8 @@ vld3q_lane_f32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Load multiple 3-element structures to three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld3q_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9655,6 +11099,8 @@ vld3q_lane_f32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9669,6 +11115,8 @@ vld4_s8_(a as *const i8, 1)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9684,6 +11132,8 @@ vld4_s8_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9698,6 +11148,8 @@ vld4_s16_(a as *const i8, 2)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9713,6 +11165,8 @@ vld4_s16_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9727,6 +11181,8 @@ vld4_s32_(a as *const i8, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9742,6 +11198,8 @@ vld4_s32_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9756,6 +11214,8 @@ vld4q_s8_(a as *const i8, 1)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9771,6 +11231,8 @@ vld4q_s8_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9785,6 +11247,8 @@ vld4q_s16_(a as *const i8, 2)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9800,6 +11264,8 @@ vld4q_s16_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9814,6 +11280,8 @@ vld4q_s32_(a as *const i8, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9829,6 +11297,8 @@ vld4q_s32_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -9843,6 +11313,8 @@ vld4_s64_(a as *const i8, 8)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -9858,6 +11330,8 @@ vld4_s64_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9869,6 +11343,8 @@ pub unsafe fn vld4_u8(a: *const u8) -> uint8x8x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9880,6 +11356,8 @@ pub unsafe fn vld4_u16(a: *const u16) -> uint16x4x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9891,6 +11369,8 @@ pub unsafe fn vld4_u32(a: *const u32) -> uint32x2x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9902,6 +11382,8 @@ pub unsafe fn vld4q_u8(a: *const u8) -> uint8x16x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9913,6 +11395,8 @@ pub unsafe fn vld4q_u16(a: *const u16) -> uint16x8x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9924,6 +11408,8 @@ pub unsafe fn vld4q_u32(a: *const u32) -> uint32x4x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9935,6 +11421,8 @@ pub unsafe fn vld4_p8(a: *const p8) -> poly8x8x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9946,6 +11434,8 @@ pub unsafe fn vld4_p16(a: *const p16) -> poly16x4x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9957,6 +11447,8 @@ pub unsafe fn vld4q_p8(a: *const p8) -> poly8x16x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9968,6 +11460,8 @@ pub unsafe fn vld4q_p16(a: *const p16) -> poly16x8x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -9979,6 +11473,8 @@ pub unsafe fn vld4_u64(a: *const u64) -> uint64x1x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -9990,6 +11486,8 @@ pub unsafe fn vld4_p64(a: *const p64) -> poly64x1x4_t {
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10004,6 +11502,8 @@ vld4_f32_(a as *const i8, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10019,6 +11519,8 @@ vld4_f32_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10033,6 +11535,8 @@ vld4q_f32_(a as *const i8, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10048,6 +11552,8 @@ vld4q_f32_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10062,6 +11568,8 @@ vld4_dup_s8_(a as *const i8, 1)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10077,6 +11585,8 @@ vld4_dup_s8_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10091,6 +11601,8 @@ vld4_dup_s16_(a as *const i8, 2)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10106,6 +11618,8 @@ vld4_dup_s16_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10120,6 +11634,8 @@ vld4_dup_s32_(a as *const i8, 4)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10135,6 +11651,8 @@ vld4_dup_s32_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10149,6 +11667,8 @@ vld4q_dup_s8_(a as *const i8, 1)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10164,6 +11684,8 @@ vld4q_dup_s8_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10178,6 +11700,8 @@ vld4q_dup_s16_(a as *const i8, 2)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10193,6 +11717,8 @@ vld4q_dup_s16_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10207,6 +11733,8 @@ vld4q_dup_s32_(a as *const i8, 4)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10222,6 +11750,8 @@ vld4q_dup_s32_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10236,6 +11766,8 @@ vld4_dup_s64_(a as *const i8, 8)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10251,6 +11783,8 @@ vld4_dup_s64_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10262,6 +11796,8 @@ pub unsafe fn vld4_dup_u8(a: *const u8) -> uint8x8x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10273,6 +11809,8 @@ pub unsafe fn vld4_dup_u16(a: *const u16) -> uint16x4x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10284,6 +11822,8 @@ pub unsafe fn vld4_dup_u32(a: *const u32) -> uint32x2x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10295,6 +11835,8 @@ pub unsafe fn vld4q_dup_u8(a: *const u8) -> uint8x16x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10306,6 +11848,8 @@ pub unsafe fn vld4q_dup_u16(a: *const u16) -> uint16x8x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10317,6 +11861,8 @@ pub unsafe fn vld4q_dup_u32(a: *const u32) -> uint32x4x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10328,6 +11874,8 @@ pub unsafe fn vld4_dup_p8(a: *const p8) -> poly8x8x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10339,6 +11887,8 @@ pub unsafe fn vld4_dup_p16(a: *const p16) -> poly16x4x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10350,6 +11900,8 @@ pub unsafe fn vld4q_dup_p8(a: *const p8) -> poly8x16x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10361,6 +11913,8 @@ pub unsafe fn vld4q_dup_p16(a: *const p16) -> poly16x8x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10372,6 +11926,8 @@ pub unsafe fn vld4_dup_u64(a: *const u64) -> uint64x1x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -10383,6 +11939,8 @@ pub unsafe fn vld4_dup_p64(a: *const p64) -> poly64x1x4_t {
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10397,6 +11955,8 @@ vld4_dup_f32_(a as *const i8, 4)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_dup_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10412,6 +11972,8 @@ vld4_dup_f32_(a as _)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10426,6 +11988,8 @@ vld4q_dup_f32_(a as *const i8, 4)
 }
 
 /// Load single 4-element structure and replicate to all lanes of four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_dup_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10441,6 +12005,8 @@ vld4q_dup_f32_(a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10457,6 +12023,8 @@ vld4_lane_s8_(a as _, b.0, b.1, b.2, b.3, LANE, 1)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10474,6 +12042,8 @@ vld4_lane_s8_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10490,6 +12060,8 @@ vld4_lane_s16_(a as _, b.0, b.1, b.2, b.3, LANE, 2)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10507,6 +12079,8 @@ vld4_lane_s16_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10523,6 +12097,8 @@ vld4_lane_s32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10540,6 +12116,8 @@ vld4_lane_s32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10556,6 +12134,8 @@ vld4q_lane_s16_(a as _, b.0, b.1, b.2, b.3, LANE, 2)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10573,6 +12153,8 @@ vld4q_lane_s16_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10589,6 +12171,8 @@ vld4q_lane_s32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10606,6 +12190,8 @@ vld4q_lane_s32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10619,6 +12205,8 @@ pub unsafe fn vld4_lane_u8<const LANE: i32>(a: *const u8, b: uint8x8x4_t) -> uin
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10632,6 +12220,8 @@ pub unsafe fn vld4_lane_u16<const LANE: i32>(a: *const u16, b: uint16x4x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10645,6 +12235,8 @@ pub unsafe fn vld4_lane_u32<const LANE: i32>(a: *const u32, b: uint32x2x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10658,6 +12250,8 @@ pub unsafe fn vld4q_lane_u16<const LANE: i32>(a: *const u16, b: uint16x8x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10671,6 +12265,8 @@ pub unsafe fn vld4q_lane_u32<const LANE: i32>(a: *const u32, b: uint32x4x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10684,6 +12280,8 @@ pub unsafe fn vld4_lane_p8<const LANE: i32>(a: *const p8, b: poly8x8x4_t) -> pol
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10697,6 +12295,8 @@ pub unsafe fn vld4_lane_p16<const LANE: i32>(a: *const p16, b: poly16x4x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10710,6 +12310,8 @@ pub unsafe fn vld4q_lane_p16<const LANE: i32>(a: *const p16, b: poly16x8x4_t) ->
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10726,6 +12328,8 @@ vld4_lane_f32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10743,6 +12347,8 @@ vld4_lane_f32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -10759,6 +12365,8 @@ vld4q_lane_f32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Load multiple 4-element structures to four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld4q_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -10776,6 +12384,8 @@ vld4q_lane_f32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10789,6 +12399,8 @@ pub unsafe fn vst1_lane_s8<const LANE: i32>(a: *mut i8, b: int8x8_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10802,6 +12414,8 @@ pub unsafe fn vst1_lane_s16<const LANE: i32>(a: *mut i16, b: int16x4_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10815,6 +12429,8 @@ pub unsafe fn vst1_lane_s32<const LANE: i32>(a: *mut i32, b: int32x2_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10828,6 +12444,8 @@ pub unsafe fn vst1_lane_s64<const LANE: i32>(a: *mut i64, b: int64x1_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10841,6 +12459,8 @@ pub unsafe fn vst1q_lane_s8<const LANE: i32>(a: *mut i8, b: int8x16_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10854,6 +12474,8 @@ pub unsafe fn vst1q_lane_s16<const LANE: i32>(a: *mut i16, b: int16x8_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10867,6 +12489,8 @@ pub unsafe fn vst1q_lane_s32<const LANE: i32>(a: *mut i32, b: int32x4_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10880,6 +12504,8 @@ pub unsafe fn vst1q_lane_s64<const LANE: i32>(a: *mut i64, b: int64x2_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10893,6 +12519,8 @@ pub unsafe fn vst1_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x8_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10906,6 +12534,8 @@ pub unsafe fn vst1_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x4_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10919,6 +12549,8 @@ pub unsafe fn vst1_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x2_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10932,6 +12564,8 @@ pub unsafe fn vst1_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x1_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10945,6 +12579,8 @@ pub unsafe fn vst1q_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x16_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10958,6 +12594,8 @@ pub unsafe fn vst1q_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x8_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10971,6 +12609,8 @@ pub unsafe fn vst1q_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x4_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10984,6 +12624,8 @@ pub unsafe fn vst1q_lane_u64<const LANE: i32>(a: *mut u64, b: uint64x2_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -10997,6 +12639,8 @@ pub unsafe fn vst1_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x8_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11010,6 +12654,8 @@ pub unsafe fn vst1_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x4_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11023,6 +12669,8 @@ pub unsafe fn vst1q_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x16_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11036,6 +12684,8 @@ pub unsafe fn vst1q_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x8_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -11049,6 +12699,8 @@ pub unsafe fn vst1_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x1_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -11062,6 +12714,8 @@ pub unsafe fn vst1q_lane_p64<const LANE: i32>(a: *mut p64, b: poly64x2_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11075,6 +12729,8 @@ pub unsafe fn vst1_lane_f32<const LANE: i32>(a: *mut f32, b: float32x2_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11088,6 +12744,8 @@ pub unsafe fn vst1q_lane_f32<const LANE: i32>(a: *mut f32, b: float32x4_t) {
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s8_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11102,6 +12760,8 @@ vst1_s8_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s8_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11117,6 +12777,8 @@ vst1_s8_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s16_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11131,6 +12793,8 @@ vst1_s16_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s16_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11146,6 +12810,8 @@ vst1_s16_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s32_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11160,6 +12826,8 @@ vst1_s32_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s32_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11175,6 +12843,8 @@ vst1_s32_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s64_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11189,6 +12859,8 @@ vst1_s64_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s64_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11204,6 +12876,8 @@ vst1_s64_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s8_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11218,6 +12892,8 @@ vst1q_s8_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s8_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11233,6 +12909,8 @@ vst1q_s8_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s16_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11247,6 +12925,8 @@ vst1q_s16_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s16_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11262,6 +12942,8 @@ vst1q_s16_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s32_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11276,6 +12958,8 @@ vst1q_s32_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s32_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11291,6 +12975,8 @@ vst1q_s32_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s64_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11305,6 +12991,8 @@ vst1q_s64_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s64_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11320,6 +13008,8 @@ vst1q_s64_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s8_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11334,6 +13024,8 @@ vst1_s8_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s8_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11349,6 +13041,8 @@ vst1_s8_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s16_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11363,6 +13057,8 @@ vst1_s16_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s16_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11378,6 +13074,8 @@ vst1_s16_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s32_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11392,6 +13090,8 @@ vst1_s32_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s32_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11407,6 +13107,8 @@ vst1_s32_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s64_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11421,6 +13123,8 @@ vst1_s64_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s64_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11436,6 +13140,8 @@ vst1_s64_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s8_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11450,6 +13156,8 @@ vst1q_s8_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s8_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11465,6 +13173,8 @@ vst1q_s8_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s16_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11479,6 +13189,8 @@ vst1q_s16_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s16_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11494,6 +13206,8 @@ vst1q_s16_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s32_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11508,6 +13222,8 @@ vst1q_s32_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s32_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11523,6 +13239,8 @@ vst1q_s32_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s64_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11537,6 +13255,8 @@ vst1q_s64_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s64_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11552,6 +13272,8 @@ vst1q_s64_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s8_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11566,6 +13288,8 @@ vst1_s8_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s8_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11581,6 +13305,8 @@ vst1_s8_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s16_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11595,6 +13321,8 @@ vst1_s16_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s16_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11610,6 +13338,8 @@ vst1_s16_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s32_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11624,6 +13354,8 @@ vst1_s32_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s32_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11639,6 +13371,8 @@ vst1_s32_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s64_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11653,6 +13387,8 @@ vst1_s64_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_s64_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11668,6 +13404,8 @@ vst1_s64_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s8_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11682,6 +13420,8 @@ vst1q_s8_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s8_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11697,6 +13437,8 @@ vst1q_s8_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s16_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11711,6 +13453,8 @@ vst1q_s16_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s16_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11726,6 +13470,8 @@ vst1q_s16_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s32_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11740,6 +13486,8 @@ vst1q_s32_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s32_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11755,6 +13503,8 @@ vst1q_s32_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s64_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -11769,6 +13519,8 @@ vst1q_s64_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures from one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_s64_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -11784,6 +13536,8 @@ vst1q_s64_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11795,6 +13549,8 @@ pub unsafe fn vst1_u8_x2(a: *mut u8, b: uint8x8x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11806,6 +13562,8 @@ pub unsafe fn vst1_u16_x2(a: *mut u16, b: uint16x4x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11817,6 +13575,8 @@ pub unsafe fn vst1_u32_x2(a: *mut u32, b: uint32x2x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11828,6 +13588,8 @@ pub unsafe fn vst1_u64_x2(a: *mut u64, b: uint64x1x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11839,6 +13601,8 @@ pub unsafe fn vst1q_u8_x2(a: *mut u8, b: uint8x16x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11850,6 +13614,8 @@ pub unsafe fn vst1q_u16_x2(a: *mut u16, b: uint16x8x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u32_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11861,6 +13627,8 @@ pub unsafe fn vst1q_u32_x2(a: *mut u32, b: uint32x4x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u64_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11872,6 +13640,8 @@ pub unsafe fn vst1q_u64_x2(a: *mut u64, b: uint64x2x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11883,6 +13653,8 @@ pub unsafe fn vst1_u8_x3(a: *mut u8, b: uint8x8x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11894,6 +13666,8 @@ pub unsafe fn vst1_u16_x3(a: *mut u16, b: uint16x4x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11905,6 +13679,8 @@ pub unsafe fn vst1_u32_x3(a: *mut u32, b: uint32x2x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11916,6 +13692,8 @@ pub unsafe fn vst1_u64_x3(a: *mut u64, b: uint64x1x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11927,6 +13705,8 @@ pub unsafe fn vst1q_u8_x3(a: *mut u8, b: uint8x16x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11938,6 +13718,8 @@ pub unsafe fn vst1q_u16_x3(a: *mut u16, b: uint16x8x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u32_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11949,6 +13731,8 @@ pub unsafe fn vst1q_u32_x3(a: *mut u32, b: uint32x4x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u64_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11960,6 +13744,8 @@ pub unsafe fn vst1q_u64_x3(a: *mut u64, b: uint64x2x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11971,6 +13757,8 @@ pub unsafe fn vst1_u8_x4(a: *mut u8, b: uint8x8x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11982,6 +13770,8 @@ pub unsafe fn vst1_u16_x4(a: *mut u16, b: uint16x4x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -11993,6 +13783,8 @@ pub unsafe fn vst1_u32_x4(a: *mut u32, b: uint32x2x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_u64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12004,6 +13796,8 @@ pub unsafe fn vst1_u64_x4(a: *mut u64, b: uint64x1x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12015,6 +13809,8 @@ pub unsafe fn vst1q_u8_x4(a: *mut u8, b: uint8x16x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12026,6 +13822,8 @@ pub unsafe fn vst1q_u16_x4(a: *mut u16, b: uint16x8x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u32_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12037,6 +13835,8 @@ pub unsafe fn vst1q_u32_x4(a: *mut u32, b: uint32x4x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_u64_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12048,6 +13848,8 @@ pub unsafe fn vst1q_u64_x4(a: *mut u64, b: uint64x2x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12059,6 +13861,8 @@ pub unsafe fn vst1_p8_x2(a: *mut p8, b: poly8x8x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12070,6 +13874,8 @@ pub unsafe fn vst1_p8_x3(a: *mut p8, b: poly8x8x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12081,6 +13887,8 @@ pub unsafe fn vst1_p8_x4(a: *mut p8, b: poly8x8x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p8_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12092,6 +13900,8 @@ pub unsafe fn vst1q_p8_x2(a: *mut p8, b: poly8x16x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p8_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12103,6 +13913,8 @@ pub unsafe fn vst1q_p8_x3(a: *mut p8, b: poly8x16x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p8_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12114,6 +13926,8 @@ pub unsafe fn vst1q_p8_x4(a: *mut p8, b: poly8x16x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12125,6 +13939,8 @@ pub unsafe fn vst1_p16_x2(a: *mut p16, b: poly16x4x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12136,6 +13952,8 @@ pub unsafe fn vst1_p16_x3(a: *mut p16, b: poly16x4x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12147,6 +13965,8 @@ pub unsafe fn vst1_p16_x4(a: *mut p16, b: poly16x4x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p16_x2)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12158,6 +13978,8 @@ pub unsafe fn vst1q_p16_x2(a: *mut p16, b: poly16x8x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p16_x3)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12169,6 +13991,8 @@ pub unsafe fn vst1q_p16_x3(a: *mut p16, b: poly16x8x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p16_x4)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12180,6 +14004,8 @@ pub unsafe fn vst1q_p16_x4(a: *mut p16, b: poly16x8x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p64_x2)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -12191,6 +14017,8 @@ pub unsafe fn vst1_p64_x2(a: *mut p64, b: poly64x1x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p64_x3)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -12202,6 +14030,8 @@ pub unsafe fn vst1_p64_x3(a: *mut p64, b: poly64x1x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_p64_x4)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -12213,6 +14043,8 @@ pub unsafe fn vst1_p64_x4(a: *mut p64, b: poly64x1x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p64_x2)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -12224,6 +14056,8 @@ pub unsafe fn vst1q_p64_x2(a: *mut p64, b: poly64x2x2_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p64_x3)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -12235,6 +14069,8 @@ pub unsafe fn vst1q_p64_x3(a: *mut p64, b: poly64x2x3_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_p64_x4)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -12246,6 +14082,8 @@ pub unsafe fn vst1q_p64_x4(a: *mut p64, b: poly64x2x4_t) {
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f32_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12260,6 +14098,8 @@ vst1_f32_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f32_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12275,6 +14115,8 @@ vst1_f32_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f32_x2)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12289,6 +14131,8 @@ vst1q_f32_x2_(a, b.0, b.1)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f32_x2)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12304,6 +14148,8 @@ vst1q_f32_x2_(b.0, b.1, a)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f32_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12318,6 +14164,8 @@ vst1_f32_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f32_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12333,6 +14181,8 @@ vst1_f32_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f32_x3)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12347,6 +14197,8 @@ vst1q_f32_x3_(a, b.0, b.1, b.2)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f32_x3)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12362,6 +14214,8 @@ vst1q_f32_x3_(b.0, b.1, b.2, a)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f32_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12376,6 +14230,8 @@ vst1_f32_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1_f32_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12391,6 +14247,8 @@ vst1_f32_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f32_x4)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12405,6 +14263,8 @@ vst1q_f32_x4_(a, b.0, b.1, b.2, b.3)
 }
 
 /// Store multiple single-element structures to one, two, three, or four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst1q_f32_x4)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12420,6 +14280,8 @@ vst1q_f32_x4_(b.0, b.1, b.2, b.3, a)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12434,6 +14296,8 @@ vst2_s8_(a as _, b.0, b.1, 1)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12449,6 +14313,8 @@ vst2_s8_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12463,6 +14329,8 @@ vst2_s16_(a as _, b.0, b.1, 2)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12478,6 +14346,8 @@ vst2_s16_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12492,6 +14362,8 @@ vst2_s32_(a as _, b.0, b.1, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12507,6 +14379,8 @@ vst2_s32_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12521,6 +14395,8 @@ vst2q_s8_(a as _, b.0, b.1, 1)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12536,6 +14412,8 @@ vst2q_s8_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12550,6 +14428,8 @@ vst2q_s16_(a as _, b.0, b.1, 2)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12565,6 +14445,8 @@ vst2q_s16_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12579,6 +14461,8 @@ vst2q_s32_(a as _, b.0, b.1, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12594,6 +14478,8 @@ vst2q_s32_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12608,6 +14494,8 @@ vst2_s64_(a as _, b.0, b.1, 8)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12623,6 +14511,8 @@ vst2_s64_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12634,6 +14524,8 @@ pub unsafe fn vst2_u8(a: *mut u8, b: uint8x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12645,6 +14537,8 @@ pub unsafe fn vst2_u16(a: *mut u16, b: uint16x4x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12656,6 +14550,8 @@ pub unsafe fn vst2_u32(a: *mut u32, b: uint32x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12667,6 +14563,8 @@ pub unsafe fn vst2q_u8(a: *mut u8, b: uint8x16x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12678,6 +14576,8 @@ pub unsafe fn vst2q_u16(a: *mut u16, b: uint16x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12689,6 +14589,8 @@ pub unsafe fn vst2q_u32(a: *mut u32, b: uint32x4x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12700,6 +14602,8 @@ pub unsafe fn vst2_p8(a: *mut p8, b: poly8x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12711,6 +14615,8 @@ pub unsafe fn vst2_p16(a: *mut p16, b: poly16x4x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12722,6 +14628,8 @@ pub unsafe fn vst2q_p8(a: *mut p8, b: poly8x16x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12733,6 +14641,8 @@ pub unsafe fn vst2q_p16(a: *mut p16, b: poly16x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12744,6 +14654,8 @@ pub unsafe fn vst2_u64(a: *mut u64, b: uint64x1x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -12755,6 +14667,8 @@ pub unsafe fn vst2_p64(a: *mut p64, b: poly64x1x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12769,6 +14683,8 @@ vst2_f32_(a as _, b.0, b.1, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12784,6 +14700,8 @@ vst2_f32_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12798,6 +14716,8 @@ vst2q_f32_(a as _, b.0, b.1, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12813,6 +14733,8 @@ vst2q_f32_(b.0, b.1, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12829,6 +14751,8 @@ vst2_lane_s8_(a as _, b.0, b.1, LANE, 1)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12846,6 +14770,8 @@ vst2_lane_s8_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12862,6 +14788,8 @@ vst2_lane_s16_(a as _, b.0, b.1, LANE, 2)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12879,6 +14807,8 @@ vst2_lane_s16_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12895,6 +14825,8 @@ vst2_lane_s32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12912,6 +14844,8 @@ vst2_lane_s32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12928,6 +14862,8 @@ vst2q_lane_s16_(a as _, b.0, b.1, LANE, 2)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12945,6 +14881,8 @@ vst2q_lane_s16_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -12961,6 +14899,8 @@ vst2q_lane_s32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -12978,6 +14918,8 @@ vst2q_lane_s32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -12991,6 +14933,8 @@ pub unsafe fn vst2_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13004,6 +14948,8 @@ pub unsafe fn vst2_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x4x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13017,6 +14963,8 @@ pub unsafe fn vst2_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x2x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13030,6 +14978,8 @@ pub unsafe fn vst2q_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13043,6 +14993,8 @@ pub unsafe fn vst2q_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x4x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13056,6 +15008,8 @@ pub unsafe fn vst2_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13069,6 +15023,8 @@ pub unsafe fn vst2_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x4x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13082,6 +15038,8 @@ pub unsafe fn vst2q_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x8x2_t) {
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13098,6 +15056,8 @@ vst2_lane_f32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13115,6 +15075,8 @@ vst2_lane_f32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13131,6 +15093,8 @@ vst2q_lane_f32_(a as _, b.0, b.1, LANE, 4)
 }
 
 /// Store multiple 2-element structures from two registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13148,6 +15112,8 @@ vst2q_lane_f32_(b.0, b.1, LANE as i64, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13162,6 +15128,8 @@ vst3_s8_(a as _, b.0, b.1, b.2, 1)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13177,6 +15145,8 @@ vst3_s8_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13191,6 +15161,8 @@ vst3_s16_(a as _, b.0, b.1, b.2, 2)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13206,6 +15178,8 @@ vst3_s16_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13220,6 +15194,8 @@ vst3_s32_(a as _, b.0, b.1, b.2, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13235,6 +15211,8 @@ vst3_s32_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13249,6 +15227,8 @@ vst3q_s8_(a as _, b.0, b.1, b.2, 1)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13264,6 +15244,8 @@ vst3q_s8_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13278,6 +15260,8 @@ vst3q_s16_(a as _, b.0, b.1, b.2, 2)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13293,6 +15277,8 @@ vst3q_s16_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13307,6 +15293,8 @@ vst3q_s32_(a as _, b.0, b.1, b.2, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13322,6 +15310,8 @@ vst3q_s32_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13336,6 +15326,8 @@ vst3_s64_(a as _, b.0, b.1, b.2, 8)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13351,6 +15343,8 @@ vst3_s64_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13362,6 +15356,8 @@ pub unsafe fn vst3_u8(a: *mut u8, b: uint8x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13373,6 +15369,8 @@ pub unsafe fn vst3_u16(a: *mut u16, b: uint16x4x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13384,6 +15382,8 @@ pub unsafe fn vst3_u32(a: *mut u32, b: uint32x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13395,6 +15395,8 @@ pub unsafe fn vst3q_u8(a: *mut u8, b: uint8x16x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13406,6 +15408,8 @@ pub unsafe fn vst3q_u16(a: *mut u16, b: uint16x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13417,6 +15421,8 @@ pub unsafe fn vst3q_u32(a: *mut u32, b: uint32x4x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13428,6 +15434,8 @@ pub unsafe fn vst3_p8(a: *mut p8, b: poly8x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13439,6 +15447,8 @@ pub unsafe fn vst3_p16(a: *mut p16, b: poly16x4x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13450,6 +15460,8 @@ pub unsafe fn vst3q_p8(a: *mut p8, b: poly8x16x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13461,6 +15473,8 @@ pub unsafe fn vst3q_p16(a: *mut p16, b: poly16x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13472,6 +15486,8 @@ pub unsafe fn vst3_u64(a: *mut u64, b: uint64x1x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -13483,6 +15499,8 @@ pub unsafe fn vst3_p64(a: *mut p64, b: poly64x1x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13497,6 +15515,8 @@ vst3_f32_(a as _, b.0, b.1, b.2, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13512,6 +15532,8 @@ vst3_f32_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13526,6 +15548,8 @@ vst3q_f32_(a as _, b.0, b.1, b.2, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13541,6 +15565,8 @@ vst3q_f32_(b.0, b.1, b.2, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13557,6 +15583,8 @@ vst3_lane_s8_(a as _, b.0, b.1, b.2, LANE, 1)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13574,6 +15602,8 @@ vst3_lane_s8_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13590,6 +15620,8 @@ vst3_lane_s16_(a as _, b.0, b.1, b.2, LANE, 2)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13607,6 +15639,8 @@ vst3_lane_s16_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13623,6 +15657,8 @@ vst3_lane_s32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13640,6 +15676,8 @@ vst3_lane_s32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13656,6 +15694,8 @@ vst3q_lane_s16_(a as _, b.0, b.1, b.2, LANE, 2)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13673,6 +15713,8 @@ vst3q_lane_s16_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13689,6 +15731,8 @@ vst3q_lane_s32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13706,6 +15750,8 @@ vst3q_lane_s32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13719,6 +15765,8 @@ pub unsafe fn vst3_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13732,6 +15780,8 @@ pub unsafe fn vst3_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x4x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13745,6 +15795,8 @@ pub unsafe fn vst3_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x2x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13758,6 +15810,8 @@ pub unsafe fn vst3q_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13771,6 +15825,8 @@ pub unsafe fn vst3q_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x4x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13784,6 +15840,8 @@ pub unsafe fn vst3_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13797,6 +15855,8 @@ pub unsafe fn vst3_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x4x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -13810,6 +15870,8 @@ pub unsafe fn vst3q_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x8x3_t) {
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13826,6 +15888,8 @@ vst3_lane_f32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13843,6 +15907,8 @@ vst3_lane_f32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13859,6 +15925,8 @@ vst3q_lane_f32_(a as _, b.0, b.1, b.2, LANE, 4)
 }
 
 /// Store multiple 3-element structures from three registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13876,6 +15944,8 @@ vst3q_lane_f32_(b.0, b.1, b.2, LANE as i64, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13890,6 +15960,8 @@ vst4_s8_(a as _, b.0, b.1, b.2, b.3, 1)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13905,6 +15977,8 @@ vst4_s8_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13919,6 +15993,8 @@ vst4_s16_(a as _, b.0, b.1, b.2, b.3, 2)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13934,6 +16010,8 @@ vst4_s16_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13948,6 +16026,8 @@ vst4_s32_(a as _, b.0, b.1, b.2, b.3, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13963,6 +16043,8 @@ vst4_s32_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -13977,6 +16059,8 @@ vst4q_s8_(a as _, b.0, b.1, b.2, b.3, 1)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -13992,6 +16076,8 @@ vst4q_s8_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14006,6 +16092,8 @@ vst4q_s16_(a as _, b.0, b.1, b.2, b.3, 2)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14021,6 +16109,8 @@ vst4q_s16_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14035,6 +16125,8 @@ vst4q_s32_(a as _, b.0, b.1, b.2, b.3, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14050,6 +16142,8 @@ vst4q_s32_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14064,6 +16158,8 @@ vst4_s64_(a as _, b.0, b.1, b.2, b.3, 8)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14079,6 +16175,8 @@ vst4_s64_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14090,6 +16188,8 @@ pub unsafe fn vst4_u8(a: *mut u8, b: uint8x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14101,6 +16201,8 @@ pub unsafe fn vst4_u16(a: *mut u16, b: uint16x4x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14112,6 +16214,8 @@ pub unsafe fn vst4_u32(a: *mut u32, b: uint32x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14123,6 +16227,8 @@ pub unsafe fn vst4q_u8(a: *mut u8, b: uint8x16x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14134,6 +16240,8 @@ pub unsafe fn vst4q_u16(a: *mut u16, b: uint16x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14145,6 +16253,8 @@ pub unsafe fn vst4q_u32(a: *mut u32, b: uint32x4x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14156,6 +16266,8 @@ pub unsafe fn vst4_p8(a: *mut p8, b: poly8x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14167,6 +16279,8 @@ pub unsafe fn vst4_p16(a: *mut p16, b: poly16x4x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14178,6 +16292,8 @@ pub unsafe fn vst4q_p8(a: *mut p8, b: poly8x16x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14189,6 +16305,8 @@ pub unsafe fn vst4q_p16(a: *mut p16, b: poly16x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14200,6 +16318,8 @@ pub unsafe fn vst4_u64(a: *mut u64, b: uint64x1x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -14211,6 +16331,8 @@ pub unsafe fn vst4_p64(a: *mut p64, b: poly64x1x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14225,6 +16347,8 @@ vst4_f32_(a as _, b.0, b.1, b.2, b.3, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14240,6 +16364,8 @@ vst4_f32_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14254,6 +16380,8 @@ vst4q_f32_(a as _, b.0, b.1, b.2, b.3, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14269,6 +16397,8 @@ vst4q_f32_(b.0, b.1, b.2, b.3, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14285,6 +16415,8 @@ vst4_lane_s8_(a as _, b.0, b.1, b.2, b.3, LANE, 1)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14302,6 +16434,8 @@ vst4_lane_s8_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14318,6 +16452,8 @@ vst4_lane_s16_(a as _, b.0, b.1, b.2, b.3, LANE, 2)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14335,6 +16471,8 @@ vst4_lane_s16_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14351,6 +16489,8 @@ vst4_lane_s32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14368,6 +16508,8 @@ vst4_lane_s32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14384,6 +16526,8 @@ vst4q_lane_s16_(a as _, b.0, b.1, b.2, b.3, LANE, 2)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14401,6 +16545,8 @@ vst4q_lane_s16_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14417,6 +16563,8 @@ vst4q_lane_s32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14434,6 +16582,8 @@ vst4q_lane_s32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14447,6 +16597,8 @@ pub unsafe fn vst4_lane_u8<const LANE: i32>(a: *mut u8, b: uint8x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14460,6 +16612,8 @@ pub unsafe fn vst4_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x4x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14473,6 +16627,8 @@ pub unsafe fn vst4_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x2x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14486,6 +16642,8 @@ pub unsafe fn vst4q_lane_u16<const LANE: i32>(a: *mut u16, b: uint16x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14499,6 +16657,8 @@ pub unsafe fn vst4q_lane_u32<const LANE: i32>(a: *mut u32, b: uint32x4x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14512,6 +16672,8 @@ pub unsafe fn vst4_lane_p8<const LANE: i32>(a: *mut p8, b: poly8x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14525,6 +16687,8 @@ pub unsafe fn vst4_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x4x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14538,6 +16702,8 @@ pub unsafe fn vst4q_lane_p16<const LANE: i32>(a: *mut p16, b: poly16x8x4_t) {
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14554,6 +16720,8 @@ vst4_lane_f32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14571,6 +16739,8 @@ vst4_lane_f32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_f32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -14587,6 +16757,8 @@ vst4q_lane_f32_(a as _, b.0, b.1, b.2, b.3, LANE, 4)
 }
 
 /// Store multiple 4-element structures from four registers
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vst4q_lane_f32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -14604,6 +16776,8 @@ vst4q_lane_f32_(b.0, b.1, b.2, b.3, LANE as i64, a as _)
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14615,6 +16789,8 @@ pub unsafe fn vmul_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14626,6 +16802,8 @@ pub unsafe fn vmulq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14637,6 +16815,8 @@ pub unsafe fn vmul_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14648,6 +16828,8 @@ pub unsafe fn vmulq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14659,6 +16841,8 @@ pub unsafe fn vmul_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14670,6 +16854,8 @@ pub unsafe fn vmulq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14681,6 +16867,8 @@ pub unsafe fn vmul_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14692,6 +16880,8 @@ pub unsafe fn vmulq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14703,6 +16893,8 @@ pub unsafe fn vmul_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14714,6 +16906,8 @@ pub unsafe fn vmulq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14725,6 +16919,8 @@ pub unsafe fn vmul_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14736,6 +16932,8 @@ pub unsafe fn vmulq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Polynomial multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14753,6 +16951,8 @@ vmul_p8_(a, b)
 }
 
 /// Polynomial multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14770,6 +16970,8 @@ vmulq_p8_(a, b)
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14781,6 +16983,8 @@ pub unsafe fn vmul_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14792,6 +16996,8 @@ pub unsafe fn vmulq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14803,6 +17009,8 @@ pub unsafe fn vmul_n_s16(a: int16x4_t, b: i16) -> int16x4_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14814,6 +17022,8 @@ pub unsafe fn vmulq_n_s16(a: int16x8_t, b: i16) -> int16x8_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14825,6 +17035,8 @@ pub unsafe fn vmul_n_s32(a: int32x2_t, b: i32) -> int32x2_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14836,6 +17048,8 @@ pub unsafe fn vmulq_n_s32(a: int32x4_t, b: i32) -> int32x4_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14847,6 +17061,8 @@ pub unsafe fn vmul_n_u16(a: uint16x4_t, b: u16) -> uint16x4_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14858,6 +17074,8 @@ pub unsafe fn vmulq_n_u16(a: uint16x8_t, b: u16) -> uint16x8_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14869,6 +17087,8 @@ pub unsafe fn vmul_n_u32(a: uint32x2_t, b: u32) -> uint32x2_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14880,6 +17100,8 @@ pub unsafe fn vmulq_n_u32(a: uint32x4_t, b: u32) -> uint32x4_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14891,6 +17113,8 @@ pub unsafe fn vmul_n_f32(a: float32x2_t, b: f32) -> float32x2_t {
 }
 
 /// Vector multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14902,6 +17126,8 @@ pub unsafe fn vmulq_n_f32(a: float32x4_t, b: f32) -> float32x4_t {
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14915,6 +17141,8 @@ pub unsafe fn vmul_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t) -> int1
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14928,6 +17156,8 @@ pub unsafe fn vmul_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x8_t) -> int
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14941,6 +17171,8 @@ pub unsafe fn vmulq_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x4_t) -> int
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14954,6 +17186,8 @@ pub unsafe fn vmulq_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t) -> in
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14967,6 +17201,8 @@ pub unsafe fn vmul_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t) -> int3
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14980,6 +17216,8 @@ pub unsafe fn vmul_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x4_t) -> int
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -14993,6 +17231,8 @@ pub unsafe fn vmulq_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x2_t) -> int
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15006,6 +17246,8 @@ pub unsafe fn vmulq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t) -> in
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15019,6 +17261,8 @@ pub unsafe fn vmul_lane_u16<const LANE: i32>(a: uint16x4_t, b: uint16x4_t) -> ui
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15032,6 +17276,8 @@ pub unsafe fn vmul_laneq_u16<const LANE: i32>(a: uint16x4_t, b: uint16x8_t) -> u
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15045,6 +17291,8 @@ pub unsafe fn vmulq_lane_u16<const LANE: i32>(a: uint16x8_t, b: uint16x4_t) -> u
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15058,6 +17306,8 @@ pub unsafe fn vmulq_laneq_u16<const LANE: i32>(a: uint16x8_t, b: uint16x8_t) ->
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15071,6 +17321,8 @@ pub unsafe fn vmul_lane_u32<const LANE: i32>(a: uint32x2_t, b: uint32x2_t) -> ui
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15084,6 +17336,8 @@ pub unsafe fn vmul_laneq_u32<const LANE: i32>(a: uint32x2_t, b: uint32x4_t) -> u
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15097,6 +17351,8 @@ pub unsafe fn vmulq_lane_u32<const LANE: i32>(a: uint32x4_t, b: uint32x2_t) -> u
 }
 
 /// Multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15110,6 +17366,8 @@ pub unsafe fn vmulq_laneq_u32<const LANE: i32>(a: uint32x4_t, b: uint32x4_t) ->
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15123,6 +17381,8 @@ pub unsafe fn vmul_lane_f32<const LANE: i32>(a: float32x2_t, b: float32x2_t) ->
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmul_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15136,6 +17396,8 @@ pub unsafe fn vmul_laneq_f32<const LANE: i32>(a: float32x2_t, b: float32x4_t) ->
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15149,6 +17411,8 @@ pub unsafe fn vmulq_lane_f32<const LANE: i32>(a: float32x4_t, b: float32x2_t) ->
 }
 
 /// Floating-point multiply
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmulq_laneq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15162,6 +17426,8 @@ pub unsafe fn vmulq_laneq_f32<const LANE: i32>(a: float32x4_t, b: float32x4_t) -
 }
 
 /// Signed multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15179,6 +17445,8 @@ vmull_s8_(a, b)
 }
 
 /// Signed multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15196,6 +17464,8 @@ vmull_s16_(a, b)
 }
 
 /// Signed multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15213,6 +17483,8 @@ vmull_s32_(a, b)
 }
 
 /// Unsigned multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15230,6 +17502,8 @@ vmull_u8_(a, b)
 }
 
 /// Unsigned multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15247,6 +17521,8 @@ vmull_u16_(a, b)
 }
 
 /// Unsigned multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15264,6 +17540,8 @@ vmull_u32_(a, b)
 }
 
 /// Polynomial multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15281,6 +17559,8 @@ vmull_p8_(a, b)
 }
 
 /// Vector long multiply with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15292,6 +17572,8 @@ pub unsafe fn vmull_n_s16(a: int16x4_t, b: i16) -> int32x4_t {
 }
 
 /// Vector long multiply with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15303,6 +17585,8 @@ pub unsafe fn vmull_n_s32(a: int32x2_t, b: i32) -> int64x2_t {
 }
 
 /// Vector long multiply with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15314,6 +17598,8 @@ pub unsafe fn vmull_n_u16(a: uint16x4_t, b: u16) -> uint32x4_t {
 }
 
 /// Vector long multiply with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15325,6 +17611,8 @@ pub unsafe fn vmull_n_u32(a: uint32x2_t, b: u32) -> uint64x2_t {
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15338,6 +17626,8 @@ pub unsafe fn vmull_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t) -> int
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15351,6 +17641,8 @@ pub unsafe fn vmull_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x8_t) -> in
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15364,6 +17656,8 @@ pub unsafe fn vmull_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t) -> int
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15377,6 +17671,8 @@ pub unsafe fn vmull_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x4_t) -> in
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15390,6 +17686,8 @@ pub unsafe fn vmull_lane_u16<const LANE: i32>(a: uint16x4_t, b: uint16x4_t) -> u
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_laneq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15403,6 +17701,8 @@ pub unsafe fn vmull_laneq_u16<const LANE: i32>(a: uint16x4_t, b: uint16x8_t) ->
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15416,6 +17716,8 @@ pub unsafe fn vmull_lane_u32<const LANE: i32>(a: uint32x2_t, b: uint32x2_t) -> u
 }
 
 /// Vector long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmull_laneq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15429,6 +17731,8 @@ pub unsafe fn vmull_laneq_u32<const LANE: i32>(a: uint32x2_t, b: uint32x4_t) ->
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15446,6 +17750,8 @@ vfma_f32_(b, c, a)
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15463,6 +17769,8 @@ vfmaq_f32_(b, c, a)
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfma_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15474,6 +17782,8 @@ pub unsafe fn vfma_n_f32(a: float32x2_t, b: float32x2_t, c: f32) -> float32x2_t
 }
 
 /// Floating-point fused Multiply-Add to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmaq_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15485,6 +17795,8 @@ pub unsafe fn vfmaq_n_f32(a: float32x4_t, b: float32x4_t, c: f32) -> float32x4_t
 }
 
 /// Floating-point fused multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15497,6 +17809,8 @@ pub unsafe fn vfms_f32(a: float32x2_t, b: float32x2_t, c: float32x2_t) -> float3
 }
 
 /// Floating-point fused multiply-subtract from accumulator
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15509,6 +17823,8 @@ pub unsafe fn vfmsq_f32(a: float32x4_t, b: float32x4_t, c: float32x4_t) -> float
 }
 
 /// Floating-point fused Multiply-subtract to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfms_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15520,6 +17836,8 @@ pub unsafe fn vfms_n_f32(a: float32x2_t, b: float32x2_t, c: f32) -> float32x2_t
 }
 
 /// Floating-point fused Multiply-subtract to accumulator(vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vfmsq_n_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "vfp4"))]
@@ -15531,6 +17849,8 @@ pub unsafe fn vfmsq_n_f32(a: float32x4_t, b: float32x4_t, c: f32) -> float32x4_t
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15542,6 +17862,8 @@ pub unsafe fn vsub_s8(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15553,6 +17875,8 @@ pub unsafe fn vsubq_s8(a: int8x16_t, b: int8x16_t) -> int8x16_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15564,6 +17888,8 @@ pub unsafe fn vsub_s16(a: int16x4_t, b: int16x4_t) -> int16x4_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15575,6 +17901,8 @@ pub unsafe fn vsubq_s16(a: int16x8_t, b: int16x8_t) -> int16x8_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15586,6 +17914,8 @@ pub unsafe fn vsub_s32(a: int32x2_t, b: int32x2_t) -> int32x2_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15597,6 +17927,8 @@ pub unsafe fn vsubq_s32(a: int32x4_t, b: int32x4_t) -> int32x4_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15608,6 +17940,8 @@ pub unsafe fn vsub_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15619,6 +17953,8 @@ pub unsafe fn vsubq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15630,6 +17966,8 @@ pub unsafe fn vsub_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15641,6 +17979,8 @@ pub unsafe fn vsubq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15652,6 +17992,8 @@ pub unsafe fn vsub_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15663,6 +18005,8 @@ pub unsafe fn vsubq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15674,6 +18018,8 @@ pub unsafe fn vsub_s64(a: int64x1_t, b: int64x1_t) -> int64x1_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15685,6 +18031,8 @@ pub unsafe fn vsubq_s64(a: int64x2_t, b: int64x2_t) -> int64x2_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15696,6 +18044,8 @@ pub unsafe fn vsub_u64(a: uint64x1_t, b: uint64x1_t) -> uint64x1_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15707,6 +18057,8 @@ pub unsafe fn vsubq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsub_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15718,6 +18070,8 @@ pub unsafe fn vsub_f32(a: float32x2_t, b: float32x2_t) -> float32x2_t {
 }
 
 /// Subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15729,6 +18083,8 @@ pub unsafe fn vsubq_f32(a: float32x4_t, b: float32x4_t) -> float32x4_t {
 }
 
 /// Bitwise exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vadd_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15740,6 +18096,8 @@ pub unsafe fn vadd_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Bitwise exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vadd_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15751,6 +18109,8 @@ pub unsafe fn vadd_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4_t {
 }
 
 /// Bitwise exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15762,6 +18122,8 @@ pub unsafe fn vaddq_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16_t {
 }
 
 /// Bitwise exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15773,6 +18135,8 @@ pub unsafe fn vaddq_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8_t {
 }
 
 /// Bitwise exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vadd_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15784,6 +18148,8 @@ pub unsafe fn vadd_p64(a: poly64x1_t, b: poly64x1_t) -> poly64x1_t {
 }
 
 /// Bitwise exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddq_p64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15795,6 +18161,8 @@ pub unsafe fn vaddq_p64(a: poly64x2_t, b: poly64x2_t) -> poly64x2_t {
 }
 
 /// Bitwise exclusive OR
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vaddq_p128)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15806,6 +18174,8 @@ pub unsafe fn vaddq_p128(a: p128, b: p128) -> p128 {
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15818,6 +18188,8 @@ pub unsafe fn vsubhn_s16(a: int16x8_t, b: int16x8_t) -> int8x8_t {
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15830,6 +18202,8 @@ pub unsafe fn vsubhn_s32(a: int32x4_t, b: int32x4_t) -> int16x4_t {
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15842,6 +18216,8 @@ pub unsafe fn vsubhn_s64(a: int64x2_t, b: int64x2_t) -> int32x2_t {
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15854,6 +18230,8 @@ pub unsafe fn vsubhn_u16(a: uint16x8_t, b: uint16x8_t) -> uint8x8_t {
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15866,6 +18244,8 @@ pub unsafe fn vsubhn_u32(a: uint32x4_t, b: uint32x4_t) -> uint16x4_t {
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15878,6 +18258,8 @@ pub unsafe fn vsubhn_u64(a: uint64x2_t, b: uint64x2_t) -> uint32x2_t {
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_high_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15890,6 +18272,8 @@ pub unsafe fn vsubhn_high_s16(a: int8x8_t, b: int16x8_t, c: int16x8_t) -> int8x1
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_high_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15902,6 +18286,8 @@ pub unsafe fn vsubhn_high_s32(a: int16x4_t, b: int32x4_t, c: int32x4_t) -> int16
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_high_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15914,6 +18300,8 @@ pub unsafe fn vsubhn_high_s64(a: int32x2_t, b: int64x2_t, c: int64x2_t) -> int32
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_high_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15926,6 +18314,8 @@ pub unsafe fn vsubhn_high_u16(a: uint8x8_t, b: uint16x8_t, c: uint16x8_t) -> uin
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_high_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15938,6 +18328,8 @@ pub unsafe fn vsubhn_high_u32(a: uint16x4_t, b: uint32x4_t, c: uint32x4_t) -> ui
 }
 
 /// Subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubhn_high_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15950,6 +18342,8 @@ pub unsafe fn vsubhn_high_u64(a: uint32x2_t, b: uint64x2_t, c: uint64x2_t) -> ui
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsub_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15967,6 +18361,8 @@ vhsub_u8_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsubq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -15984,6 +18380,8 @@ vhsubq_u8_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsub_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16001,6 +18399,8 @@ vhsub_u16_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsubq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16018,6 +18418,8 @@ vhsubq_u16_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsub_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16035,6 +18437,8 @@ vhsub_u32_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsubq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16052,6 +18456,8 @@ vhsubq_u32_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsub_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16069,6 +18475,8 @@ vhsub_s8_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsubq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16086,6 +18494,8 @@ vhsubq_s8_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsub_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16103,6 +18513,8 @@ vhsub_s16_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsubq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16120,6 +18532,8 @@ vhsubq_s16_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsub_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16137,6 +18551,8 @@ vhsub_s32_(a, b)
 }
 
 /// Signed halving subtract
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vhsubq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16154,6 +18570,8 @@ vhsubq_s32_(a, b)
 }
 
 /// Signed Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16165,6 +18583,8 @@ pub unsafe fn vsubw_s8(a: int16x8_t, b: int8x8_t) -> int16x8_t {
 }
 
 /// Signed Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16176,6 +18596,8 @@ pub unsafe fn vsubw_s16(a: int32x4_t, b: int16x4_t) -> int32x4_t {
 }
 
 /// Signed Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16187,6 +18609,8 @@ pub unsafe fn vsubw_s32(a: int64x2_t, b: int32x2_t) -> int64x2_t {
 }
 
 /// Unsigned Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16198,6 +18622,8 @@ pub unsafe fn vsubw_u8(a: uint16x8_t, b: uint8x8_t) -> uint16x8_t {
 }
 
 /// Unsigned Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16209,6 +18635,8 @@ pub unsafe fn vsubw_u16(a: uint32x4_t, b: uint16x4_t) -> uint32x4_t {
 }
 
 /// Unsigned Subtract Wide
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubw_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16220,6 +18648,8 @@ pub unsafe fn vsubw_u32(a: uint64x2_t, b: uint32x2_t) -> uint64x2_t {
 }
 
 /// Signed Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16233,6 +18663,8 @@ pub unsafe fn vsubl_s8(a: int8x8_t, b: int8x8_t) -> int16x8_t {
 }
 
 /// Signed Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16246,6 +18678,8 @@ pub unsafe fn vsubl_s16(a: int16x4_t, b: int16x4_t) -> int32x4_t {
 }
 
 /// Signed Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16259,6 +18693,8 @@ pub unsafe fn vsubl_s32(a: int32x2_t, b: int32x2_t) -> int64x2_t {
 }
 
 /// Unsigned Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16272,6 +18708,8 @@ pub unsafe fn vsubl_u8(a: uint8x8_t, b: uint8x8_t) -> uint16x8_t {
 }
 
 /// Unsigned Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16285,6 +18723,8 @@ pub unsafe fn vsubl_u16(a: uint16x4_t, b: uint16x4_t) -> uint32x4_t {
 }
 
 /// Unsigned Subtract Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsubl_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16298,6 +18738,8 @@ pub unsafe fn vsubl_u32(a: uint32x2_t, b: uint32x2_t) -> uint64x2_t {
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16315,6 +18757,8 @@ vmax_s8_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16332,6 +18776,8 @@ vmaxq_s8_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16349,6 +18795,8 @@ vmax_s16_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16366,6 +18814,8 @@ vmaxq_s16_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16383,6 +18833,8 @@ vmax_s32_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16400,6 +18852,8 @@ vmaxq_s32_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16417,6 +18871,8 @@ vmax_u8_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16434,6 +18890,8 @@ vmaxq_u8_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16451,6 +18909,8 @@ vmax_u16_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16468,6 +18928,8 @@ vmaxq_u16_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16485,6 +18947,8 @@ vmax_u32_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16502,6 +18966,8 @@ vmaxq_u32_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmax_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16519,6 +18985,8 @@ vmax_f32_(a, b)
 }
 
 /// Maximum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16536,6 +19004,8 @@ vmaxq_f32_(a, b)
 }
 
 /// Floating-point Maximum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxnm_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "fp-armv8,v8"))]
@@ -16553,6 +19023,8 @@ vmaxnm_f32_(a, b)
 }
 
 /// Floating-point Maximum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmaxnmq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "fp-armv8,v8"))]
@@ -16570,6 +19042,8 @@ vmaxnmq_f32_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16587,6 +19061,8 @@ vmin_s8_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16604,6 +19080,8 @@ vminq_s8_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16621,6 +19099,8 @@ vmin_s16_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16638,6 +19118,8 @@ vminq_s16_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16655,6 +19137,8 @@ vmin_s32_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16672,6 +19156,8 @@ vminq_s32_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16689,6 +19175,8 @@ vmin_u8_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16706,6 +19194,8 @@ vminq_u8_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16723,6 +19213,8 @@ vmin_u16_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16740,6 +19232,8 @@ vminq_u16_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16757,6 +19251,8 @@ vmin_u32_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16774,6 +19270,8 @@ vminq_u32_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vmin_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16791,6 +19289,8 @@ vmin_f32_(a, b)
 }
 
 /// Minimum (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16808,6 +19308,8 @@ vminq_f32_(a, b)
 }
 
 /// Floating-point Minimum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminnm_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "fp-armv8,v8"))]
@@ -16825,6 +19327,8 @@ vminnm_f32_(a, b)
 }
 
 /// Floating-point Minimum Number (vector)
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vminnmq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "fp-armv8,v8"))]
@@ -16842,6 +19346,8 @@ vminnmq_f32_(a, b)
 }
 
 /// Floating-point add pairwise
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vpadd_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16859,6 +19365,8 @@ vpadd_f32_(a, b)
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16876,6 +19384,8 @@ vqdmull_s16_(a, b)
 }
 
 /// Signed saturating doubling multiply long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16893,6 +19403,8 @@ vqdmull_s32_(a, b)
 }
 
 /// Vector saturating doubling long multiply with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16904,6 +19416,8 @@ pub unsafe fn vqdmull_n_s16(a: int16x4_t, b: i16) -> int32x4_t {
 }
 
 /// Vector saturating doubling long multiply with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16915,6 +19429,8 @@ pub unsafe fn vqdmull_n_s32(a: int32x2_t, b: i32) -> int64x2_t {
 }
 
 /// Vector saturating doubling long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16929,6 +19445,8 @@ pub unsafe fn vqdmull_lane_s16<const N: i32>(a: int16x4_t, b: int16x4_t) -> int3
 }
 
 /// Vector saturating doubling long multiply by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmull_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16943,6 +19461,8 @@ pub unsafe fn vqdmull_lane_s32<const N: i32>(a: int32x2_t, b: int32x2_t) -> int6
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16954,6 +19474,8 @@ pub unsafe fn vqdmlal_s16(a: int32x4_t, b: int16x4_t, c: int16x4_t) -> int32x4_t
 }
 
 /// Signed saturating doubling multiply-add long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16965,6 +19487,8 @@ pub unsafe fn vqdmlal_s32(a: int64x2_t, b: int32x2_t, c: int32x2_t) -> int64x2_t
 }
 
 /// Vector widening saturating doubling multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16976,6 +19500,8 @@ pub unsafe fn vqdmlal_n_s16(a: int32x4_t, b: int16x4_t, c: i16) -> int32x4_t {
 }
 
 /// Vector widening saturating doubling multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -16987,6 +19513,8 @@ pub unsafe fn vqdmlal_n_s32(a: int64x2_t, b: int32x2_t, c: i32) -> int64x2_t {
 }
 
 /// Vector widening saturating doubling multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17000,6 +19528,8 @@ pub unsafe fn vqdmlal_lane_s16<const N: i32>(a: int32x4_t, b: int16x4_t, c: int1
 }
 
 /// Vector widening saturating doubling multiply accumulate with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlal_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17013,6 +19543,8 @@ pub unsafe fn vqdmlal_lane_s32<const N: i32>(a: int64x2_t, b: int32x2_t, c: int3
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17024,6 +19556,8 @@ pub unsafe fn vqdmlsl_s16(a: int32x4_t, b: int16x4_t, c: int16x4_t) -> int32x4_t
 }
 
 /// Signed saturating doubling multiply-subtract long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17035,6 +19569,8 @@ pub unsafe fn vqdmlsl_s32(a: int64x2_t, b: int32x2_t, c: int32x2_t) -> int64x2_t
 }
 
 /// Vector widening saturating doubling multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17046,6 +19582,8 @@ pub unsafe fn vqdmlsl_n_s16(a: int32x4_t, b: int16x4_t, c: i16) -> int32x4_t {
 }
 
 /// Vector widening saturating doubling multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17057,6 +19595,8 @@ pub unsafe fn vqdmlsl_n_s32(a: int64x2_t, b: int32x2_t, c: i32) -> int64x2_t {
 }
 
 /// Vector widening saturating doubling multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17070,6 +19610,8 @@ pub unsafe fn vqdmlsl_lane_s16<const N: i32>(a: int32x4_t, b: int16x4_t, c: int1
 }
 
 /// Vector widening saturating doubling multiply subtract with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmlsl_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17083,6 +19625,8 @@ pub unsafe fn vqdmlsl_lane_s32<const N: i32>(a: int64x2_t, b: int32x2_t, c: int3
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17100,6 +19644,8 @@ vqdmulh_s16_(a, b)
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17117,6 +19663,8 @@ vqdmulhq_s16_(a, b)
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17134,6 +19682,8 @@ vqdmulh_s32_(a, b)
 }
 
 /// Signed saturating doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17151,6 +19701,8 @@ vqdmulhq_s32_(a, b)
 }
 
 /// Vector saturating doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17163,6 +19715,8 @@ pub unsafe fn vqdmulh_n_s16(a: int16x4_t, b: i16) -> int16x4_t {
 }
 
 /// Vector saturating doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17175,6 +19729,8 @@ pub unsafe fn vqdmulh_n_s32(a: int32x2_t, b: i32) -> int32x2_t {
 }
 
 /// Vector saturating doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17187,6 +19743,8 @@ pub unsafe fn vqdmulhq_n_s16(a: int16x8_t, b: i16) -> int16x8_t {
 }
 
 /// Vector saturating doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17199,6 +19757,8 @@ pub unsafe fn vqdmulhq_n_s32(a: int32x4_t, b: i32) -> int32x4_t {
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17212,6 +19772,8 @@ pub unsafe fn vqdmulhq_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t) ->
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17225,6 +19787,8 @@ pub unsafe fn vqdmulh_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x8_t) ->
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulhq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17238,6 +19802,8 @@ pub unsafe fn vqdmulhq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t) ->
 }
 
 /// Vector saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqdmulh_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17251,6 +19817,8 @@ pub unsafe fn vqdmulh_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x4_t) ->
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17268,6 +19836,8 @@ vqmovn_s16_(a)
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17285,6 +19855,8 @@ vqmovn_s32_(a)
 }
 
 /// Signed saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17302,6 +19874,8 @@ vqmovn_s64_(a)
 }
 
 /// Unsigned saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17319,6 +19893,8 @@ vqmovn_u16_(a)
 }
 
 /// Unsigned saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17336,6 +19912,8 @@ vqmovn_u32_(a)
 }
 
 /// Unsigned saturating extract narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovn_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17353,6 +19931,8 @@ vqmovn_u64_(a)
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovun_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17370,6 +19950,8 @@ vqmovun_s16_(a)
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovun_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17387,6 +19969,8 @@ vqmovun_s32_(a)
 }
 
 /// Signed saturating extract unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqmovun_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17404,6 +19988,8 @@ vqmovun_s64_(a)
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17421,6 +20007,8 @@ vqrdmulh_s16_(a, b)
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17438,6 +20026,8 @@ vqrdmulhq_s16_(a, b)
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17455,6 +20045,8 @@ vqrdmulh_s32_(a, b)
 }
 
 /// Signed saturating rounding doubling multiply returning high half
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17472,6 +20064,8 @@ vqrdmulhq_s32_(a, b)
 }
 
 /// Vector saturating rounding doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17483,6 +20077,8 @@ pub unsafe fn vqrdmulh_n_s16(a: int16x4_t, b: i16) -> int16x4_t {
 }
 
 /// Vector saturating rounding doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17494,6 +20090,8 @@ pub unsafe fn vqrdmulhq_n_s16(a: int16x8_t, b: i16) -> int16x8_t {
 }
 
 /// Vector saturating rounding doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17505,6 +20103,8 @@ pub unsafe fn vqrdmulh_n_s32(a: int32x2_t, b: i32) -> int32x2_t {
 }
 
 /// Vector saturating rounding doubling multiply high with scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17516,6 +20116,8 @@ pub unsafe fn vqrdmulhq_n_s32(a: int32x4_t, b: i32) -> int32x4_t {
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17530,6 +20132,8 @@ pub unsafe fn vqrdmulh_lane_s16<const LANE: i32>(a: int16x4_t, b: int16x4_t) ->
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17544,6 +20148,8 @@ pub unsafe fn vqrdmulh_laneq_s16<const LANE: i32>(a: int16x4_t, b: int16x8_t) ->
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17558,6 +20164,8 @@ pub unsafe fn vqrdmulhq_lane_s16<const LANE: i32>(a: int16x8_t, b: int16x4_t) ->
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_laneq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17572,6 +20180,8 @@ pub unsafe fn vqrdmulhq_laneq_s16<const LANE: i32>(a: int16x8_t, b: int16x8_t) -
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17586,6 +20196,8 @@ pub unsafe fn vqrdmulh_lane_s32<const LANE: i32>(a: int32x2_t, b: int32x2_t) ->
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulh_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17600,6 +20212,8 @@ pub unsafe fn vqrdmulh_laneq_s32<const LANE: i32>(a: int32x2_t, b: int32x4_t) ->
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17614,6 +20228,8 @@ pub unsafe fn vqrdmulhq_lane_s32<const LANE: i32>(a: int32x4_t, b: int32x2_t) ->
 }
 
 /// Vector rounding saturating doubling multiply high by scalar
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrdmulhq_laneq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17628,6 +20244,8 @@ pub unsafe fn vqrdmulhq_laneq_s32<const LANE: i32>(a: int32x4_t, b: int32x4_t) -
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17645,6 +20263,8 @@ vqrshl_s8_(a, b)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17662,6 +20282,8 @@ vqrshlq_s8_(a, b)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17679,6 +20301,8 @@ vqrshl_s16_(a, b)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17696,6 +20320,8 @@ vqrshlq_s16_(a, b)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17713,6 +20339,8 @@ vqrshl_s32_(a, b)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17730,6 +20358,8 @@ vqrshlq_s32_(a, b)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17747,6 +20377,8 @@ vqrshl_s64_(a, b)
 }
 
 /// Signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17764,6 +20396,8 @@ vqrshlq_s64_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17781,6 +20415,8 @@ vqrshl_u8_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17798,6 +20434,8 @@ vqrshlq_u8_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17815,6 +20453,8 @@ vqrshl_u16_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17832,6 +20472,8 @@ vqrshlq_u16_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17849,6 +20491,8 @@ vqrshl_u32_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17866,6 +20510,8 @@ vqrshlq_u32_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshl_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17883,6 +20529,8 @@ vqrshl_u64_(a, b)
 }
 
 /// Unsigned signed saturating rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshlq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -17900,6 +20548,8 @@ vqrshlq_u64_(a, b)
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -17916,6 +20566,8 @@ vqrshrn_n_s16_(a, int16x8_t(-N as i16, -N as i16, -N as i16, -N as i16, -N as i1
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -17933,6 +20585,8 @@ vqrshrn_n_s16_(a, N)
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -17949,6 +20603,8 @@ vqrshrn_n_s32_(a, int32x4_t(-N as i32, -N as i32, -N as i32, -N as i32))
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -17966,6 +20622,8 @@ vqrshrn_n_s32_(a, N)
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -17982,6 +20640,8 @@ vqrshrn_n_s64_(a, int64x2_t(-N as i64, -N as i64))
 }
 
 /// Signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -17999,6 +20659,8 @@ vqrshrn_n_s64_(a, N)
 }
 
 /// Unsigned signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_u16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18015,6 +20677,8 @@ vqrshrn_n_u16_(a, uint16x8_t(-N as u16, -N as u16, -N as u16, -N as u16, -N as u
 }
 
 /// Unsigned signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_u16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18032,6 +20696,8 @@ vqrshrn_n_u16_(a, N)
 }
 
 /// Unsigned signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_u32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18048,6 +20714,8 @@ vqrshrn_n_u32_(a, uint32x4_t(-N as u32, -N as u32, -N as u32, -N as u32))
 }
 
 /// Unsigned signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_u32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18065,6 +20733,8 @@ vqrshrn_n_u32_(a, N)
 }
 
 /// Unsigned signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_u64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18081,6 +20751,8 @@ vqrshrn_n_u64_(a, uint64x2_t(-N as u64, -N as u64))
 }
 
 /// Unsigned signed saturating rounded shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrn_n_u64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18098,6 +20770,8 @@ vqrshrn_n_u64_(a, N)
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_n_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18114,6 +20788,8 @@ vqrshrun_n_s16_(a, int16x8_t(-N as i16, -N as i16, -N as i16, -N as i16, -N as i
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_n_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18131,6 +20807,8 @@ vqrshrun_n_s16_(a, N)
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_n_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18147,6 +20825,8 @@ vqrshrun_n_s32_(a, int32x4_t(-N as i32, -N as i32, -N as i32, -N as i32))
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_n_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18164,6 +20844,8 @@ vqrshrun_n_s32_(a, N)
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_n_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18180,6 +20862,8 @@ vqrshrun_n_s64_(a, int64x2_t(-N as i64, -N as i64))
 }
 
 /// Signed saturating rounded shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqrshrun_n_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18197,6 +20881,8 @@ vqrshrun_n_s64_(a, N)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18214,6 +20900,8 @@ vqshl_s8_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18231,6 +20919,8 @@ vqshlq_s8_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18248,6 +20938,8 @@ vqshl_s16_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18265,6 +20957,8 @@ vqshlq_s16_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18282,6 +20976,8 @@ vqshl_s32_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18299,6 +20995,8 @@ vqshlq_s32_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18316,6 +21014,8 @@ vqshl_s64_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18333,6 +21033,8 @@ vqshlq_s64_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18350,6 +21052,8 @@ vqshl_u8_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18367,6 +21071,8 @@ vqshlq_u8_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18384,6 +21090,8 @@ vqshl_u16_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18401,6 +21109,8 @@ vqshlq_u16_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18418,6 +21128,8 @@ vqshl_u32_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18435,6 +21147,8 @@ vqshlq_u32_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18452,6 +21166,8 @@ vqshl_u64_(a, b)
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18469,6 +21185,8 @@ vqshlq_u64_(a, b)
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18482,6 +21200,8 @@ pub unsafe fn vqshl_n_s8<const N: i32>(a: int8x8_t) -> int8x8_t {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18495,6 +21215,8 @@ pub unsafe fn vqshlq_n_s8<const N: i32>(a: int8x16_t) -> int8x16_t {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18508,6 +21230,8 @@ pub unsafe fn vqshl_n_s16<const N: i32>(a: int16x4_t) -> int16x4_t {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18521,6 +21245,8 @@ pub unsafe fn vqshlq_n_s16<const N: i32>(a: int16x8_t) -> int16x8_t {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18534,6 +21260,8 @@ pub unsafe fn vqshl_n_s32<const N: i32>(a: int32x2_t) -> int32x2_t {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18547,6 +21275,8 @@ pub unsafe fn vqshlq_n_s32<const N: i32>(a: int32x4_t) -> int32x4_t {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18560,6 +21290,8 @@ pub unsafe fn vqshl_n_s64<const N: i32>(a: int64x1_t) -> int64x1_t {
 }
 
 /// Signed saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18573,6 +21305,8 @@ pub unsafe fn vqshlq_n_s64<const N: i32>(a: int64x2_t) -> int64x2_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18586,6 +21320,8 @@ pub unsafe fn vqshl_n_u8<const N: i32>(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18599,6 +21335,8 @@ pub unsafe fn vqshlq_n_u8<const N: i32>(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18612,6 +21350,8 @@ pub unsafe fn vqshl_n_u16<const N: i32>(a: uint16x4_t) -> uint16x4_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18625,6 +21365,8 @@ pub unsafe fn vqshlq_n_u16<const N: i32>(a: uint16x8_t) -> uint16x8_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18638,6 +21380,8 @@ pub unsafe fn vqshl_n_u32<const N: i32>(a: uint32x2_t) -> uint32x2_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18651,6 +21395,8 @@ pub unsafe fn vqshlq_n_u32<const N: i32>(a: uint32x4_t) -> uint32x4_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshl_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18664,6 +21410,8 @@ pub unsafe fn vqshl_n_u64<const N: i32>(a: uint64x1_t) -> uint64x1_t {
 }
 
 /// Unsigned saturating shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlq_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -18677,6 +21425,8 @@ pub unsafe fn vqshlq_n_u64<const N: i32>(a: uint64x2_t) -> uint64x2_t {
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18693,6 +21443,8 @@ vqshlu_n_s8_(a, int8x8_t(N as i8, N as i8, N as i8, N as i8, N as i8, N as i8, N
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18710,6 +21462,8 @@ vqshlu_n_s8_(a, int8x8_t(N as i8, N as i8, N as i8, N as i8, N as i8, N as i8, N
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18726,6 +21480,8 @@ vqshlu_n_s16_(a, int16x4_t(N as i16, N as i16, N as i16, N as i16))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18743,6 +21499,8 @@ vqshlu_n_s16_(a, int16x4_t(N as i16, N as i16, N as i16, N as i16))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18759,6 +21517,8 @@ vqshlu_n_s32_(a, int32x2_t(N as i32, N as i32))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18776,6 +21536,8 @@ vqshlu_n_s32_(a, int32x2_t(N as i32, N as i32))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18792,6 +21554,8 @@ vqshlu_n_s64_(a, int64x1_t(N as i64))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshlu_n_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18809,6 +21573,8 @@ vqshlu_n_s64_(a, int64x1_t(N as i64))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s8)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18825,6 +21591,8 @@ vqshluq_n_s8_(a, int8x16_t(N as i8, N as i8, N as i8, N as i8, N as i8, N as i8,
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s8)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18842,6 +21610,8 @@ vqshluq_n_s8_(a, int8x16_t(N as i8, N as i8, N as i8, N as i8, N as i8, N as i8,
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18858,6 +21628,8 @@ vqshluq_n_s16_(a, int16x8_t(N as i16, N as i16, N as i16, N as i16, N as i16, N
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18875,6 +21647,8 @@ vqshluq_n_s16_(a, int16x8_t(N as i16, N as i16, N as i16, N as i16, N as i16, N
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18891,6 +21665,8 @@ vqshluq_n_s32_(a, int32x4_t(N as i32, N as i32, N as i32, N as i32))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18908,6 +21684,8 @@ vqshluq_n_s32_(a, int32x4_t(N as i32, N as i32, N as i32, N as i32))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18924,6 +21702,8 @@ vqshluq_n_s64_(a, int64x2_t(N as i64, N as i64))
 }
 
 /// Signed saturating shift left unsigned
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshluq_n_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18941,6 +21721,8 @@ vqshluq_n_s64_(a, int64x2_t(N as i64, N as i64))
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18957,6 +21739,8 @@ vqshrn_n_s16_(a, int16x8_t(-N as i16, -N as i16, -N as i16, -N as i16, -N as i16
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -18974,6 +21758,8 @@ vqshrn_n_s16_(a, N)
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -18990,6 +21776,8 @@ vqshrn_n_s32_(a, int32x4_t(-N as i32, -N as i32, -N as i32, -N as i32))
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19007,6 +21795,8 @@ vqshrn_n_s32_(a, N)
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -19023,6 +21813,8 @@ vqshrn_n_s64_(a, int64x2_t(-N as i64, -N as i64))
 }
 
 /// Signed saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19040,6 +21832,8 @@ vqshrn_n_s64_(a, N)
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_u16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -19056,6 +21850,8 @@ vqshrn_n_u16_(a, uint16x8_t(-N as u16, -N as u16, -N as u16, -N as u16, -N as u1
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_u16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19073,6 +21869,8 @@ vqshrn_n_u16_(a, N)
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_u32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -19089,6 +21887,8 @@ vqshrn_n_u32_(a, uint32x4_t(-N as u32, -N as u32, -N as u32, -N as u32))
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_u32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19106,6 +21906,8 @@ vqshrn_n_u32_(a, N)
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_u64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -19122,6 +21924,8 @@ vqshrn_n_u64_(a, uint64x2_t(-N as u64, -N as u64))
 }
 
 /// Unsigned saturating shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrn_n_u64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19139,6 +21943,8 @@ vqshrn_n_u64_(a, N)
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_n_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -19155,6 +21961,8 @@ vqshrun_n_s16_(a, int16x8_t(-N as i16, -N as i16, -N as i16, -N as i16, -N as i1
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_n_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19172,6 +21980,8 @@ vqshrun_n_s16_(a, N)
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_n_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -19188,6 +21998,8 @@ vqshrun_n_s32_(a, int32x4_t(-N as i32, -N as i32, -N as i32, -N as i32))
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_n_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19205,6 +22017,8 @@ vqshrun_n_s32_(a, N)
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_n_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -19221,6 +22035,8 @@ vqshrun_n_s64_(a, int64x2_t(-N as i64, -N as i64))
 }
 
 /// Signed saturating shift right unsigned narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqshrun_n_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -19238,6 +22054,8 @@ vqshrun_n_s64_(a, N)
 }
 
 /// Reciprocal square-root estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrte_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19255,6 +22073,8 @@ vrsqrte_f32_(a)
 }
 
 /// Reciprocal square-root estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrteq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19272,6 +22092,8 @@ vrsqrteq_f32_(a)
 }
 
 /// Unsigned reciprocal square root estimate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrte_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19289,6 +22111,8 @@ vrsqrte_u32_(a)
 }
 
 /// Unsigned reciprocal square root estimate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrteq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19306,6 +22130,8 @@ vrsqrteq_u32_(a)
 }
 
 /// Floating-point reciprocal square root step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrts_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19323,6 +22149,8 @@ vrsqrts_f32_(a, b)
 }
 
 /// Floating-point reciprocal square root step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsqrtsq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19340,6 +22168,8 @@ vrsqrtsq_f32_(a, b)
 }
 
 /// Reciprocal estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpe_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19357,6 +22187,8 @@ vrecpe_f32_(a)
 }
 
 /// Reciprocal estimate.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpeq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19374,6 +22206,8 @@ vrecpeq_f32_(a)
 }
 
 /// Unsigned reciprocal estimate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpe_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19391,6 +22225,8 @@ vrecpe_u32_(a)
 }
 
 /// Unsigned reciprocal estimate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpeq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19408,6 +22244,8 @@ vrecpeq_u32_(a)
 }
 
 /// Floating-point reciprocal step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecps_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19425,6 +22263,8 @@ vrecps_f32_(a, b)
 }
 
 /// Floating-point reciprocal step
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrecpsq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19442,6 +22282,8 @@ vrecpsq_f32_(a, b)
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19453,6 +22295,8 @@ pub unsafe fn vreinterpret_s8_u8(a: uint8x8_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19464,6 +22308,8 @@ pub unsafe fn vreinterpret_s8_p8(a: poly8x8_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19475,6 +22321,8 @@ pub unsafe fn vreinterpret_s16_p16(a: poly16x4_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19486,6 +22334,8 @@ pub unsafe fn vreinterpret_s16_u16(a: uint16x4_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19497,6 +22347,8 @@ pub unsafe fn vreinterpret_s32_u32(a: uint32x2_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19508,6 +22360,8 @@ pub unsafe fn vreinterpret_s64_u64(a: uint64x1_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19519,6 +22373,8 @@ pub unsafe fn vreinterpretq_s8_u8(a: uint8x16_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19530,6 +22386,8 @@ pub unsafe fn vreinterpretq_s8_p8(a: poly8x16_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19541,6 +22399,8 @@ pub unsafe fn vreinterpretq_s16_p16(a: poly16x8_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19552,6 +22412,8 @@ pub unsafe fn vreinterpretq_s16_u16(a: uint16x8_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19563,6 +22425,8 @@ pub unsafe fn vreinterpretq_s32_u32(a: uint32x4_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19574,6 +22438,8 @@ pub unsafe fn vreinterpretq_s64_u64(a: uint64x2_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19585,6 +22451,8 @@ pub unsafe fn vreinterpret_u8_p8(a: poly8x8_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19596,6 +22464,8 @@ pub unsafe fn vreinterpret_u8_s8(a: int8x8_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19607,6 +22477,8 @@ pub unsafe fn vreinterpret_u16_p16(a: poly16x4_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19618,6 +22490,8 @@ pub unsafe fn vreinterpret_u16_s16(a: int16x4_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19629,6 +22503,8 @@ pub unsafe fn vreinterpret_u32_s32(a: int32x2_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19640,6 +22516,8 @@ pub unsafe fn vreinterpret_u64_s64(a: int64x1_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19651,6 +22529,8 @@ pub unsafe fn vreinterpretq_u8_p8(a: poly8x16_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19662,6 +22542,8 @@ pub unsafe fn vreinterpretq_u8_s8(a: int8x16_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19673,6 +22555,8 @@ pub unsafe fn vreinterpretq_u16_p16(a: poly16x8_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19684,6 +22568,8 @@ pub unsafe fn vreinterpretq_u16_s16(a: int16x8_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19695,6 +22581,8 @@ pub unsafe fn vreinterpretq_u32_s32(a: int32x4_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19706,6 +22594,8 @@ pub unsafe fn vreinterpretq_u64_s64(a: int64x2_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19717,6 +22607,8 @@ pub unsafe fn vreinterpret_p8_s8(a: int8x8_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19728,6 +22620,8 @@ pub unsafe fn vreinterpret_p8_u8(a: uint8x8_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19739,6 +22633,8 @@ pub unsafe fn vreinterpret_p16_s16(a: int16x4_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19750,6 +22646,8 @@ pub unsafe fn vreinterpret_p16_u16(a: uint16x4_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19761,6 +22659,8 @@ pub unsafe fn vreinterpretq_p8_s8(a: int8x16_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19772,6 +22672,8 @@ pub unsafe fn vreinterpretq_p8_u8(a: uint8x16_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19783,6 +22685,8 @@ pub unsafe fn vreinterpretq_p16_s16(a: int16x8_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19794,6 +22698,8 @@ pub unsafe fn vreinterpretq_p16_u16(a: uint16x8_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19805,6 +22711,8 @@ pub unsafe fn vreinterpret_s8_s16(a: int16x4_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19816,6 +22724,8 @@ pub unsafe fn vreinterpret_s8_u16(a: uint16x4_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19827,6 +22737,8 @@ pub unsafe fn vreinterpret_s8_p16(a: poly16x4_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19838,6 +22750,8 @@ pub unsafe fn vreinterpret_s16_s32(a: int32x2_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19849,6 +22763,8 @@ pub unsafe fn vreinterpret_s16_u32(a: uint32x2_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19860,6 +22776,8 @@ pub unsafe fn vreinterpret_s32_s64(a: int64x1_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19871,6 +22789,8 @@ pub unsafe fn vreinterpret_s32_u64(a: uint64x1_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19882,6 +22802,8 @@ pub unsafe fn vreinterpretq_s8_s16(a: int16x8_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19893,6 +22815,8 @@ pub unsafe fn vreinterpretq_s8_u16(a: uint16x8_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19904,6 +22828,8 @@ pub unsafe fn vreinterpretq_s8_p16(a: poly16x8_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19915,6 +22841,8 @@ pub unsafe fn vreinterpretq_s16_s32(a: int32x4_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19926,6 +22854,8 @@ pub unsafe fn vreinterpretq_s16_u32(a: uint32x4_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19937,6 +22867,8 @@ pub unsafe fn vreinterpretq_s32_s64(a: int64x2_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19948,6 +22880,8 @@ pub unsafe fn vreinterpretq_s32_u64(a: uint64x2_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19959,6 +22893,8 @@ pub unsafe fn vreinterpret_u8_p16(a: poly16x4_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19970,6 +22906,8 @@ pub unsafe fn vreinterpret_u8_s16(a: int16x4_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19981,6 +22919,8 @@ pub unsafe fn vreinterpret_u8_u16(a: uint16x4_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -19992,6 +22932,8 @@ pub unsafe fn vreinterpret_u16_s32(a: int32x2_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20003,6 +22945,8 @@ pub unsafe fn vreinterpret_u16_u32(a: uint32x2_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20014,6 +22958,8 @@ pub unsafe fn vreinterpret_u32_s64(a: int64x1_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20025,6 +22971,8 @@ pub unsafe fn vreinterpret_u32_u64(a: uint64x1_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20036,6 +22984,8 @@ pub unsafe fn vreinterpretq_u8_p16(a: poly16x8_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20047,6 +22997,8 @@ pub unsafe fn vreinterpretq_u8_s16(a: int16x8_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20058,6 +23010,8 @@ pub unsafe fn vreinterpretq_u8_u16(a: uint16x8_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20069,6 +23023,8 @@ pub unsafe fn vreinterpretq_u16_s32(a: int32x4_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20080,6 +23036,8 @@ pub unsafe fn vreinterpretq_u16_u32(a: uint32x4_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20091,6 +23049,8 @@ pub unsafe fn vreinterpretq_u32_s64(a: int64x2_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20102,6 +23062,8 @@ pub unsafe fn vreinterpretq_u32_u64(a: uint64x2_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20113,6 +23075,8 @@ pub unsafe fn vreinterpret_p8_p16(a: poly16x4_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20124,6 +23088,8 @@ pub unsafe fn vreinterpret_p8_s16(a: int16x4_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20135,6 +23101,8 @@ pub unsafe fn vreinterpret_p8_u16(a: uint16x4_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20146,6 +23114,8 @@ pub unsafe fn vreinterpret_p16_s32(a: int32x2_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20157,6 +23127,8 @@ pub unsafe fn vreinterpret_p16_u32(a: uint32x2_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20168,6 +23140,8 @@ pub unsafe fn vreinterpretq_p8_p16(a: poly16x8_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20179,6 +23153,8 @@ pub unsafe fn vreinterpretq_p8_s16(a: int16x8_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20190,6 +23166,8 @@ pub unsafe fn vreinterpretq_p8_u16(a: uint16x8_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20201,6 +23179,8 @@ pub unsafe fn vreinterpretq_p16_s32(a: int32x4_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20212,6 +23192,8 @@ pub unsafe fn vreinterpretq_p16_u32(a: uint32x4_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20223,6 +23205,8 @@ pub unsafe fn vreinterpret_s32_p64(a: poly64x1_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20234,6 +23218,8 @@ pub unsafe fn vreinterpret_u32_p64(a: poly64x1_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20245,6 +23231,8 @@ pub unsafe fn vreinterpretq_s32_p64(a: poly64x2_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20256,6 +23244,8 @@ pub unsafe fn vreinterpretq_u32_p64(a: poly64x2_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20267,6 +23257,8 @@ pub unsafe fn vreinterpretq_s64_p128(a: p128) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20278,6 +23270,8 @@ pub unsafe fn vreinterpretq_u64_p128(a: p128) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20289,6 +23283,8 @@ pub unsafe fn vreinterpretq_p64_p128(a: p128) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20300,6 +23296,8 @@ pub unsafe fn vreinterpret_s16_p8(a: poly8x8_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20311,6 +23309,8 @@ pub unsafe fn vreinterpret_s16_s8(a: int8x8_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20322,6 +23322,8 @@ pub unsafe fn vreinterpret_s16_u8(a: uint8x8_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20333,6 +23335,8 @@ pub unsafe fn vreinterpret_s32_p16(a: poly16x4_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20344,6 +23348,8 @@ pub unsafe fn vreinterpret_s32_s16(a: int16x4_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20355,6 +23361,8 @@ pub unsafe fn vreinterpret_s32_u16(a: uint16x4_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20366,6 +23374,8 @@ pub unsafe fn vreinterpret_s64_s32(a: int32x2_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20377,6 +23387,8 @@ pub unsafe fn vreinterpret_s64_u32(a: uint32x2_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20388,6 +23400,8 @@ pub unsafe fn vreinterpretq_s16_p8(a: poly8x16_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20399,6 +23413,8 @@ pub unsafe fn vreinterpretq_s16_s8(a: int8x16_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20410,6 +23426,8 @@ pub unsafe fn vreinterpretq_s16_u8(a: uint8x16_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20421,6 +23439,8 @@ pub unsafe fn vreinterpretq_s32_p16(a: poly16x8_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20432,6 +23452,8 @@ pub unsafe fn vreinterpretq_s32_s16(a: int16x8_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20443,6 +23465,8 @@ pub unsafe fn vreinterpretq_s32_u16(a: uint16x8_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20454,6 +23478,8 @@ pub unsafe fn vreinterpretq_s64_s32(a: int32x4_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20465,6 +23491,8 @@ pub unsafe fn vreinterpretq_s64_u32(a: uint32x4_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20476,6 +23504,8 @@ pub unsafe fn vreinterpret_u16_p8(a: poly8x8_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20487,6 +23517,8 @@ pub unsafe fn vreinterpret_u16_s8(a: int8x8_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20498,6 +23530,8 @@ pub unsafe fn vreinterpret_u16_u8(a: uint8x8_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20509,6 +23543,8 @@ pub unsafe fn vreinterpret_u32_p16(a: poly16x4_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20520,6 +23556,8 @@ pub unsafe fn vreinterpret_u32_s16(a: int16x4_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20531,6 +23569,8 @@ pub unsafe fn vreinterpret_u32_u16(a: uint16x4_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20542,6 +23582,8 @@ pub unsafe fn vreinterpret_u64_s32(a: int32x2_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20553,6 +23595,8 @@ pub unsafe fn vreinterpret_u64_u32(a: uint32x2_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20564,6 +23608,8 @@ pub unsafe fn vreinterpretq_u16_p8(a: poly8x16_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20575,6 +23621,8 @@ pub unsafe fn vreinterpretq_u16_s8(a: int8x16_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20586,6 +23634,8 @@ pub unsafe fn vreinterpretq_u16_u8(a: uint8x16_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20597,6 +23647,8 @@ pub unsafe fn vreinterpretq_u32_p16(a: poly16x8_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20608,6 +23660,8 @@ pub unsafe fn vreinterpretq_u32_s16(a: int16x8_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20619,6 +23673,8 @@ pub unsafe fn vreinterpretq_u32_u16(a: uint16x8_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20630,6 +23686,8 @@ pub unsafe fn vreinterpretq_u64_s32(a: int32x4_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20641,6 +23699,8 @@ pub unsafe fn vreinterpretq_u64_u32(a: uint32x4_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20652,6 +23712,8 @@ pub unsafe fn vreinterpret_p16_p8(a: poly8x8_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20663,6 +23725,8 @@ pub unsafe fn vreinterpret_p16_s8(a: int8x8_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20674,6 +23738,8 @@ pub unsafe fn vreinterpret_p16_u8(a: uint8x8_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20685,6 +23751,8 @@ pub unsafe fn vreinterpretq_p16_p8(a: poly8x16_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20696,6 +23764,8 @@ pub unsafe fn vreinterpretq_p16_s8(a: int8x16_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20707,6 +23777,8 @@ pub unsafe fn vreinterpretq_p16_u8(a: uint8x16_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_s32)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20718,6 +23790,8 @@ pub unsafe fn vreinterpret_p64_s32(a: int32x2_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_u32)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20729,6 +23803,8 @@ pub unsafe fn vreinterpret_p64_u32(a: uint32x2_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_s32)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20740,6 +23816,8 @@ pub unsafe fn vreinterpretq_p64_s32(a: int32x4_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_u32)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20751,6 +23829,8 @@ pub unsafe fn vreinterpretq_p64_u32(a: uint32x4_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_s64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20762,6 +23842,8 @@ pub unsafe fn vreinterpretq_p128_s64(a: int64x2_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_u64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20773,6 +23855,8 @@ pub unsafe fn vreinterpretq_p128_u64(a: uint64x2_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -20784,6 +23868,8 @@ pub unsafe fn vreinterpretq_p128_p64(a: poly64x2_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20795,6 +23881,8 @@ pub unsafe fn vreinterpret_s8_s32(a: int32x2_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20806,6 +23894,8 @@ pub unsafe fn vreinterpret_s8_u32(a: uint32x2_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20817,6 +23907,8 @@ pub unsafe fn vreinterpret_s16_s64(a: int64x1_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20828,6 +23920,8 @@ pub unsafe fn vreinterpret_s16_u64(a: uint64x1_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20839,6 +23933,8 @@ pub unsafe fn vreinterpretq_s8_s32(a: int32x4_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20850,6 +23946,8 @@ pub unsafe fn vreinterpretq_s8_u32(a: uint32x4_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20861,6 +23959,8 @@ pub unsafe fn vreinterpretq_s16_s64(a: int64x2_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20872,6 +23972,8 @@ pub unsafe fn vreinterpretq_s16_u64(a: uint64x2_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20883,6 +23985,8 @@ pub unsafe fn vreinterpret_u8_s32(a: int32x2_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20894,6 +23998,8 @@ pub unsafe fn vreinterpret_u8_u32(a: uint32x2_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20905,6 +24011,8 @@ pub unsafe fn vreinterpret_u16_s64(a: int64x1_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20916,6 +24024,8 @@ pub unsafe fn vreinterpret_u16_u64(a: uint64x1_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20927,6 +24037,8 @@ pub unsafe fn vreinterpretq_u8_s32(a: int32x4_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20938,6 +24050,8 @@ pub unsafe fn vreinterpretq_u8_u32(a: uint32x4_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20949,6 +24063,8 @@ pub unsafe fn vreinterpretq_u16_s64(a: int64x2_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20960,6 +24076,8 @@ pub unsafe fn vreinterpretq_u16_u64(a: uint64x2_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20971,6 +24089,8 @@ pub unsafe fn vreinterpret_p8_s32(a: int32x2_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20982,6 +24102,8 @@ pub unsafe fn vreinterpret_p8_u32(a: uint32x2_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -20993,6 +24115,8 @@ pub unsafe fn vreinterpret_p16_s64(a: int64x1_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21004,6 +24128,8 @@ pub unsafe fn vreinterpret_p16_u64(a: uint64x1_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21015,6 +24141,8 @@ pub unsafe fn vreinterpretq_p8_s32(a: int32x4_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21026,6 +24154,8 @@ pub unsafe fn vreinterpretq_p8_u32(a: uint32x4_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21037,6 +24167,8 @@ pub unsafe fn vreinterpretq_p16_s64(a: int64x2_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21048,6 +24180,8 @@ pub unsafe fn vreinterpretq_p16_u64(a: uint64x2_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21059,6 +24193,8 @@ pub unsafe fn vreinterpret_s16_p64(a: poly64x1_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21070,6 +24206,8 @@ pub unsafe fn vreinterpret_u16_p64(a: poly64x1_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21081,6 +24219,8 @@ pub unsafe fn vreinterpret_p16_p64(a: poly64x1_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21092,6 +24232,8 @@ pub unsafe fn vreinterpretq_s16_p64(a: poly64x2_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21103,6 +24245,8 @@ pub unsafe fn vreinterpretq_u16_p64(a: poly64x2_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21114,6 +24258,8 @@ pub unsafe fn vreinterpretq_p16_p64(a: poly64x2_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21125,6 +24271,8 @@ pub unsafe fn vreinterpretq_s32_p128(a: p128) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21136,6 +24284,8 @@ pub unsafe fn vreinterpretq_u32_p128(a: p128) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21147,6 +24297,8 @@ pub unsafe fn vreinterpret_s32_p8(a: poly8x8_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21158,6 +24310,8 @@ pub unsafe fn vreinterpret_s32_s8(a: int8x8_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21169,6 +24323,8 @@ pub unsafe fn vreinterpret_s32_u8(a: uint8x8_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21180,6 +24336,8 @@ pub unsafe fn vreinterpret_s64_p16(a: poly16x4_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21191,6 +24349,8 @@ pub unsafe fn vreinterpret_s64_s16(a: int16x4_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21202,6 +24362,8 @@ pub unsafe fn vreinterpret_s64_u16(a: uint16x4_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21213,6 +24375,8 @@ pub unsafe fn vreinterpretq_s32_p8(a: poly8x16_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21224,6 +24388,8 @@ pub unsafe fn vreinterpretq_s32_s8(a: int8x16_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21235,6 +24401,8 @@ pub unsafe fn vreinterpretq_s32_u8(a: uint8x16_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21246,6 +24414,8 @@ pub unsafe fn vreinterpretq_s64_p16(a: poly16x8_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21257,6 +24427,8 @@ pub unsafe fn vreinterpretq_s64_s16(a: int16x8_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21268,6 +24440,8 @@ pub unsafe fn vreinterpretq_s64_u16(a: uint16x8_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21279,6 +24453,8 @@ pub unsafe fn vreinterpret_u32_p8(a: poly8x8_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21290,6 +24466,8 @@ pub unsafe fn vreinterpret_u32_s8(a: int8x8_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21301,6 +24479,8 @@ pub unsafe fn vreinterpret_u32_u8(a: uint8x8_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21312,6 +24492,8 @@ pub unsafe fn vreinterpret_u64_p16(a: poly16x4_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21323,6 +24505,8 @@ pub unsafe fn vreinterpret_u64_s16(a: int16x4_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21334,6 +24518,8 @@ pub unsafe fn vreinterpret_u64_u16(a: uint16x4_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21345,6 +24531,8 @@ pub unsafe fn vreinterpretq_u32_p8(a: poly8x16_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21356,6 +24544,8 @@ pub unsafe fn vreinterpretq_u32_s8(a: int8x16_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21367,6 +24557,8 @@ pub unsafe fn vreinterpretq_u32_u8(a: uint8x16_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21378,6 +24570,8 @@ pub unsafe fn vreinterpretq_u64_p16(a: poly16x8_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21389,6 +24583,8 @@ pub unsafe fn vreinterpretq_u64_s16(a: int16x8_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21400,6 +24596,8 @@ pub unsafe fn vreinterpretq_u64_u16(a: uint16x8_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_p16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21411,6 +24609,8 @@ pub unsafe fn vreinterpret_p64_p16(a: poly16x4_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_s16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21422,6 +24622,8 @@ pub unsafe fn vreinterpret_p64_s16(a: int16x4_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_u16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21433,6 +24635,8 @@ pub unsafe fn vreinterpret_p64_u16(a: uint16x4_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_p16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21444,6 +24648,8 @@ pub unsafe fn vreinterpretq_p64_p16(a: poly16x8_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_s16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21455,6 +24661,8 @@ pub unsafe fn vreinterpretq_p64_s16(a: int16x8_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_u16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21466,6 +24674,8 @@ pub unsafe fn vreinterpretq_p64_u16(a: uint16x8_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_s32)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21477,6 +24687,8 @@ pub unsafe fn vreinterpretq_p128_s32(a: int32x4_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_u32)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21488,6 +24700,8 @@ pub unsafe fn vreinterpretq_p128_u32(a: uint32x4_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21499,6 +24713,8 @@ pub unsafe fn vreinterpret_s8_s64(a: int64x1_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21510,6 +24726,8 @@ pub unsafe fn vreinterpret_s8_u64(a: uint64x1_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21521,6 +24739,8 @@ pub unsafe fn vreinterpret_u8_s64(a: int64x1_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21532,6 +24752,8 @@ pub unsafe fn vreinterpret_u8_u64(a: uint64x1_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21543,6 +24765,8 @@ pub unsafe fn vreinterpret_p8_s64(a: int64x1_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21554,6 +24778,8 @@ pub unsafe fn vreinterpret_p8_u64(a: uint64x1_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21565,6 +24791,8 @@ pub unsafe fn vreinterpretq_s8_s64(a: int64x2_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21576,6 +24804,8 @@ pub unsafe fn vreinterpretq_s8_u64(a: uint64x2_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21587,6 +24817,8 @@ pub unsafe fn vreinterpretq_u8_s64(a: int64x2_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21598,6 +24830,8 @@ pub unsafe fn vreinterpretq_u8_u64(a: uint64x2_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21609,6 +24843,8 @@ pub unsafe fn vreinterpretq_p8_s64(a: int64x2_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21620,6 +24856,8 @@ pub unsafe fn vreinterpretq_p8_u64(a: uint64x2_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21631,6 +24869,8 @@ pub unsafe fn vreinterpret_s8_p64(a: poly64x1_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21642,6 +24882,8 @@ pub unsafe fn vreinterpret_u8_p64(a: poly64x1_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21653,6 +24895,8 @@ pub unsafe fn vreinterpret_p8_p64(a: poly64x1_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21664,6 +24908,8 @@ pub unsafe fn vreinterpretq_s8_p64(a: poly64x2_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21675,6 +24921,8 @@ pub unsafe fn vreinterpretq_u8_p64(a: poly64x2_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21686,6 +24934,8 @@ pub unsafe fn vreinterpretq_p8_p64(a: poly64x2_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21697,6 +24947,8 @@ pub unsafe fn vreinterpretq_s16_p128(a: p128) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21708,6 +24960,8 @@ pub unsafe fn vreinterpretq_u16_p128(a: p128) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21719,6 +24973,8 @@ pub unsafe fn vreinterpretq_p16_p128(a: p128) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21730,6 +24986,8 @@ pub unsafe fn vreinterpret_s64_p8(a: poly8x8_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21741,6 +24999,8 @@ pub unsafe fn vreinterpret_s64_s8(a: int8x8_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21752,6 +25012,8 @@ pub unsafe fn vreinterpret_s64_u8(a: uint8x8_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21763,6 +25025,8 @@ pub unsafe fn vreinterpret_u64_p8(a: poly8x8_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21774,6 +25038,8 @@ pub unsafe fn vreinterpret_u64_s8(a: int8x8_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21785,6 +25051,8 @@ pub unsafe fn vreinterpret_u64_u8(a: uint8x8_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21796,6 +25064,8 @@ pub unsafe fn vreinterpretq_s64_p8(a: poly8x16_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21807,6 +25077,8 @@ pub unsafe fn vreinterpretq_s64_s8(a: int8x16_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21818,6 +25090,8 @@ pub unsafe fn vreinterpretq_s64_u8(a: uint8x16_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21829,6 +25103,8 @@ pub unsafe fn vreinterpretq_u64_p8(a: poly8x16_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21840,6 +25116,8 @@ pub unsafe fn vreinterpretq_u64_s8(a: int8x16_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -21851,6 +25129,8 @@ pub unsafe fn vreinterpretq_u64_u8(a: uint8x16_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_p8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21862,6 +25142,8 @@ pub unsafe fn vreinterpret_p64_p8(a: poly8x8_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_s8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21873,6 +25155,8 @@ pub unsafe fn vreinterpret_p64_s8(a: int8x8_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p64_u8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21884,6 +25168,8 @@ pub unsafe fn vreinterpret_p64_u8(a: uint8x8_t) -> poly64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_p8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21895,6 +25181,8 @@ pub unsafe fn vreinterpretq_p64_p8(a: poly8x16_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_s8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21906,6 +25194,8 @@ pub unsafe fn vreinterpretq_p64_s8(a: int8x16_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p64_u8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21917,6 +25207,8 @@ pub unsafe fn vreinterpretq_p64_u8(a: uint8x16_t) -> poly64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_s16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21928,6 +25220,8 @@ pub unsafe fn vreinterpretq_p128_s16(a: int16x8_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_u16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21939,6 +25233,8 @@ pub unsafe fn vreinterpretq_p128_u16(a: uint16x8_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_p16)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21950,6 +25246,8 @@ pub unsafe fn vreinterpretq_p128_p16(a: poly16x8_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_s8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21961,6 +25259,8 @@ pub unsafe fn vreinterpretq_p128_s8(a: int8x16_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_u8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21972,6 +25272,8 @@ pub unsafe fn vreinterpretq_p128_u8(a: uint8x16_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_p8)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21983,6 +25285,8 @@ pub unsafe fn vreinterpretq_p128_p8(a: poly8x16_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -21994,6 +25298,8 @@ pub unsafe fn vreinterpretq_s8_p128(a: p128) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -22005,6 +25311,8 @@ pub unsafe fn vreinterpretq_u8_p128(a: p128) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_p128)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -22016,6 +25324,8 @@ pub unsafe fn vreinterpretq_p8_p128(a: p128) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s8_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22027,6 +25337,8 @@ pub unsafe fn vreinterpret_s8_f32(a: float32x2_t) -> int8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s16_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22038,6 +25350,8 @@ pub unsafe fn vreinterpret_s16_f32(a: float32x2_t) -> int16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22049,6 +25363,8 @@ pub unsafe fn vreinterpret_s32_f32(a: float32x2_t) -> int32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_s64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22060,6 +25376,8 @@ pub unsafe fn vreinterpret_s64_f32(a: float32x2_t) -> int64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s8_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22071,6 +25389,8 @@ pub unsafe fn vreinterpretq_s8_f32(a: float32x4_t) -> int8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s16_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22082,6 +25402,8 @@ pub unsafe fn vreinterpretq_s16_f32(a: float32x4_t) -> int16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22093,6 +25415,8 @@ pub unsafe fn vreinterpretq_s32_f32(a: float32x4_t) -> int32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_s64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22104,6 +25428,8 @@ pub unsafe fn vreinterpretq_s64_f32(a: float32x4_t) -> int64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u8_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22115,6 +25441,8 @@ pub unsafe fn vreinterpret_u8_f32(a: float32x2_t) -> uint8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u16_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22126,6 +25454,8 @@ pub unsafe fn vreinterpret_u16_f32(a: float32x2_t) -> uint16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22137,6 +25467,8 @@ pub unsafe fn vreinterpret_u32_f32(a: float32x2_t) -> uint32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_u64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22148,6 +25480,8 @@ pub unsafe fn vreinterpret_u64_f32(a: float32x2_t) -> uint64x1_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u8_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22159,6 +25493,8 @@ pub unsafe fn vreinterpretq_u8_f32(a: float32x4_t) -> uint8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u16_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22170,6 +25506,8 @@ pub unsafe fn vreinterpretq_u16_f32(a: float32x4_t) -> uint16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u32_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22181,6 +25519,8 @@ pub unsafe fn vreinterpretq_u32_f32(a: float32x4_t) -> uint32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_u64_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22192,6 +25532,8 @@ pub unsafe fn vreinterpretq_u64_f32(a: float32x4_t) -> uint64x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p8_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22203,6 +25545,8 @@ pub unsafe fn vreinterpret_p8_f32(a: float32x2_t) -> poly8x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_p16_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22214,6 +25558,8 @@ pub unsafe fn vreinterpret_p16_f32(a: float32x2_t) -> poly16x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p8_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22225,6 +25571,8 @@ pub unsafe fn vreinterpretq_p8_f32(a: float32x4_t) -> poly8x16_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p16_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22236,6 +25584,8 @@ pub unsafe fn vreinterpretq_p16_f32(a: float32x4_t) -> poly16x8_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_p128_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22247,6 +25597,8 @@ pub unsafe fn vreinterpretq_p128_f32(a: float32x4_t) -> p128 {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22258,6 +25610,8 @@ pub unsafe fn vreinterpret_f32_s8(a: int8x8_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22269,6 +25623,8 @@ pub unsafe fn vreinterpret_f32_s16(a: int16x4_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22280,6 +25636,8 @@ pub unsafe fn vreinterpret_f32_s32(a: int32x2_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22291,6 +25649,8 @@ pub unsafe fn vreinterpret_f32_s64(a: int64x1_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22302,6 +25662,8 @@ pub unsafe fn vreinterpretq_f32_s8(a: int8x16_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22313,6 +25675,8 @@ pub unsafe fn vreinterpretq_f32_s16(a: int16x8_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22324,6 +25688,8 @@ pub unsafe fn vreinterpretq_f32_s32(a: int32x4_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22335,6 +25701,8 @@ pub unsafe fn vreinterpretq_f32_s64(a: int64x2_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22346,6 +25714,8 @@ pub unsafe fn vreinterpret_f32_u8(a: uint8x8_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22357,6 +25727,8 @@ pub unsafe fn vreinterpret_f32_u16(a: uint16x4_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22368,6 +25740,8 @@ pub unsafe fn vreinterpret_f32_u32(a: uint32x2_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22379,6 +25753,8 @@ pub unsafe fn vreinterpret_f32_u64(a: uint64x1_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22390,6 +25766,8 @@ pub unsafe fn vreinterpretq_f32_u8(a: uint8x16_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22401,6 +25779,8 @@ pub unsafe fn vreinterpretq_f32_u16(a: uint16x8_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22412,6 +25792,8 @@ pub unsafe fn vreinterpretq_f32_u32(a: uint32x4_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22423,6 +25805,8 @@ pub unsafe fn vreinterpretq_f32_u64(a: uint64x2_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22434,6 +25818,8 @@ pub unsafe fn vreinterpret_f32_p8(a: poly8x8_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpret_f32_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22445,6 +25831,8 @@ pub unsafe fn vreinterpret_f32_p16(a: poly16x4_t) -> float32x2_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22456,6 +25844,8 @@ pub unsafe fn vreinterpretq_f32_p8(a: poly8x16_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22467,6 +25857,8 @@ pub unsafe fn vreinterpretq_f32_p16(a: poly16x8_t) -> float32x4_t {
 }
 
 /// Vector reinterpret cast operation
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vreinterpretq_f32_p128)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22478,6 +25870,8 @@ pub unsafe fn vreinterpretq_f32_p128(a: p128) -> float32x4_t {
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22495,6 +25889,8 @@ vrshl_s8_(a, b)
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22512,6 +25908,8 @@ vrshlq_s8_(a, b)
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22529,6 +25927,8 @@ vrshl_s16_(a, b)
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22546,6 +25946,8 @@ vrshlq_s16_(a, b)
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22563,6 +25965,8 @@ vrshl_s32_(a, b)
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22580,6 +25984,8 @@ vrshlq_s32_(a, b)
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22597,6 +26003,8 @@ vrshl_s64_(a, b)
 }
 
 /// Signed rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22614,6 +26022,8 @@ vrshlq_s64_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22631,6 +26041,8 @@ vrshl_u8_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22648,6 +26060,8 @@ vrshlq_u8_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22665,6 +26079,8 @@ vrshl_u16_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22682,6 +26098,8 @@ vrshlq_u16_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22699,6 +26117,8 @@ vrshl_u32_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22716,6 +26136,8 @@ vrshlq_u32_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshl_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22733,6 +26155,8 @@ vrshl_u64_(a, b)
 }
 
 /// Unsigned rounding shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshlq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22750,6 +26174,8 @@ vrshlq_u64_(a, b)
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22763,6 +26189,8 @@ pub unsafe fn vrshr_n_s8<const N: i32>(a: int8x8_t) -> int8x8_t {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22776,6 +26204,8 @@ pub unsafe fn vrshrq_n_s8<const N: i32>(a: int8x16_t) -> int8x16_t {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22789,6 +26219,8 @@ pub unsafe fn vrshr_n_s16<const N: i32>(a: int16x4_t) -> int16x4_t {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22802,6 +26234,8 @@ pub unsafe fn vrshrq_n_s16<const N: i32>(a: int16x8_t) -> int16x8_t {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22815,6 +26249,8 @@ pub unsafe fn vrshr_n_s32<const N: i32>(a: int32x2_t) -> int32x2_t {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22828,6 +26264,8 @@ pub unsafe fn vrshrq_n_s32<const N: i32>(a: int32x4_t) -> int32x4_t {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22841,6 +26279,8 @@ pub unsafe fn vrshr_n_s64<const N: i32>(a: int64x1_t) -> int64x1_t {
 }
 
 /// Signed rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22854,6 +26294,8 @@ pub unsafe fn vrshrq_n_s64<const N: i32>(a: int64x2_t) -> int64x2_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22867,6 +26309,8 @@ pub unsafe fn vrshr_n_u8<const N: i32>(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22880,6 +26324,8 @@ pub unsafe fn vrshrq_n_u8<const N: i32>(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22893,6 +26339,8 @@ pub unsafe fn vrshr_n_u16<const N: i32>(a: uint16x4_t) -> uint16x4_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22906,6 +26354,8 @@ pub unsafe fn vrshrq_n_u16<const N: i32>(a: uint16x8_t) -> uint16x8_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22919,6 +26369,8 @@ pub unsafe fn vrshr_n_u32<const N: i32>(a: uint32x2_t) -> uint32x2_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22932,6 +26384,8 @@ pub unsafe fn vrshrq_n_u32<const N: i32>(a: uint32x4_t) -> uint32x4_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshr_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22945,6 +26399,8 @@ pub unsafe fn vrshr_n_u64<const N: i32>(a: uint64x1_t) -> uint64x1_t {
 }
 
 /// Unsigned rounding shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrq_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -22958,6 +26414,8 @@ pub unsafe fn vrshrq_n_u64<const N: i32>(a: uint64x2_t) -> uint64x2_t {
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_s16)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -22974,6 +26432,8 @@ vrshrn_n_s16_(a, int16x8_t(-N as i16, -N as i16, -N as i16, -N as i16, -N as i16
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_s16)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -22991,6 +26451,8 @@ vrshrn_n_s16_(a, N)
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_s32)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -23007,6 +26469,8 @@ vrshrn_n_s32_(a, int32x4_t(-N as i32, -N as i32, -N as i32, -N as i32))
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_s32)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -23024,6 +26488,8 @@ vrshrn_n_s32_(a, N)
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_s64)
 #[inline]
 #[cfg(target_arch = "arm")]
 #[target_feature(enable = "neon,v7")]
@@ -23040,6 +26506,8 @@ vrshrn_n_s64_(a, int64x2_t(-N as i64, -N as i64))
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_s64)
 #[inline]
 #[cfg(target_arch = "aarch64")]
 #[target_feature(enable = "neon")]
@@ -23057,6 +26525,8 @@ vrshrn_n_s64_(a, N)
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23070,6 +26540,8 @@ pub unsafe fn vrshrn_n_u16<const N: i32>(a: uint16x8_t) -> uint8x8_t {
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23083,6 +26555,8 @@ pub unsafe fn vrshrn_n_u32<const N: i32>(a: uint32x4_t) -> uint16x4_t {
 }
 
 /// Rounding shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrshrn_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23096,6 +26570,8 @@ pub unsafe fn vrshrn_n_u64<const N: i32>(a: uint64x2_t) -> uint32x2_t {
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23109,6 +26585,8 @@ pub unsafe fn vrsra_n_s8<const N: i32>(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23122,6 +26600,8 @@ pub unsafe fn vrsraq_n_s8<const N: i32>(a: int8x16_t, b: int8x16_t) -> int8x16_t
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23135,6 +26615,8 @@ pub unsafe fn vrsra_n_s16<const N: i32>(a: int16x4_t, b: int16x4_t) -> int16x4_t
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23148,6 +26630,8 @@ pub unsafe fn vrsraq_n_s16<const N: i32>(a: int16x8_t, b: int16x8_t) -> int16x8_
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23161,6 +26645,8 @@ pub unsafe fn vrsra_n_s32<const N: i32>(a: int32x2_t, b: int32x2_t) -> int32x2_t
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23174,6 +26660,8 @@ pub unsafe fn vrsraq_n_s32<const N: i32>(a: int32x4_t, b: int32x4_t) -> int32x4_
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23187,6 +26675,8 @@ pub unsafe fn vrsra_n_s64<const N: i32>(a: int64x1_t, b: int64x1_t) -> int64x1_t
 }
 
 /// Signed rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23200,6 +26690,8 @@ pub unsafe fn vrsraq_n_s64<const N: i32>(a: int64x2_t, b: int64x2_t) -> int64x2_
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23213,6 +26705,8 @@ pub unsafe fn vrsra_n_u8<const N: i32>(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23226,6 +26720,8 @@ pub unsafe fn vrsraq_n_u8<const N: i32>(a: uint8x16_t, b: uint8x16_t) -> uint8x1
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23239,6 +26735,8 @@ pub unsafe fn vrsra_n_u16<const N: i32>(a: uint16x4_t, b: uint16x4_t) -> uint16x
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23252,6 +26750,8 @@ pub unsafe fn vrsraq_n_u16<const N: i32>(a: uint16x8_t, b: uint16x8_t) -> uint16
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23265,6 +26765,8 @@ pub unsafe fn vrsra_n_u32<const N: i32>(a: uint32x2_t, b: uint32x2_t) -> uint32x
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23278,6 +26780,8 @@ pub unsafe fn vrsraq_n_u32<const N: i32>(a: uint32x4_t, b: uint32x4_t) -> uint32
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsra_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23291,6 +26795,8 @@ pub unsafe fn vrsra_n_u64<const N: i32>(a: uint64x1_t, b: uint64x1_t) -> uint64x
 }
 
 /// Unsigned rounding shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsraq_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23304,6 +26810,8 @@ pub unsafe fn vrsraq_n_u64<const N: i32>(a: uint64x2_t, b: uint64x2_t) -> uint64
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23321,6 +26829,8 @@ vrsubhn_s16_(a, b)
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23338,6 +26848,8 @@ vrsubhn_s32_(a, b)
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23355,6 +26867,8 @@ vrsubhn_s64_(a, b)
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23366,6 +26880,8 @@ pub unsafe fn vrsubhn_u16(a: uint16x8_t, b: uint16x8_t) -> uint8x8_t {
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23377,6 +26893,8 @@ pub unsafe fn vrsubhn_u32(a: uint32x4_t, b: uint32x4_t) -> uint16x4_t {
 }
 
 /// Rounding subtract returning high narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vrsubhn_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23388,6 +26906,8 @@ pub unsafe fn vrsubhn_u64(a: uint64x2_t, b: uint64x2_t) -> uint32x2_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23401,6 +26921,8 @@ pub unsafe fn vset_lane_s8<const LANE: i32>(a: i8, b: int8x8_t) -> int8x8_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23414,6 +26936,8 @@ pub unsafe fn vset_lane_s16<const LANE: i32>(a: i16, b: int16x4_t) -> int16x4_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23427,6 +26951,8 @@ pub unsafe fn vset_lane_s32<const LANE: i32>(a: i32, b: int32x2_t) -> int32x2_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23440,6 +26966,8 @@ pub unsafe fn vset_lane_s64<const LANE: i32>(a: i64, b: int64x1_t) -> int64x1_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23453,6 +26981,8 @@ pub unsafe fn vset_lane_u8<const LANE: i32>(a: u8, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23466,6 +26996,8 @@ pub unsafe fn vset_lane_u16<const LANE: i32>(a: u16, b: uint16x4_t) -> uint16x4_
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23479,6 +27011,8 @@ pub unsafe fn vset_lane_u32<const LANE: i32>(a: u32, b: uint32x2_t) -> uint32x2_
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23492,6 +27026,8 @@ pub unsafe fn vset_lane_u64<const LANE: i32>(a: u64, b: uint64x1_t) -> uint64x1_
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23505,6 +27041,8 @@ pub unsafe fn vset_lane_p8<const LANE: i32>(a: p8, b: poly8x8_t) -> poly8x8_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23518,6 +27056,8 @@ pub unsafe fn vset_lane_p16<const LANE: i32>(a: p16, b: poly16x4_t) -> poly16x4_
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -23531,6 +27071,8 @@ pub unsafe fn vset_lane_p64<const LANE: i32>(a: p64, b: poly64x1_t) -> poly64x1_
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23544,6 +27086,8 @@ pub unsafe fn vsetq_lane_s8<const LANE: i32>(a: i8, b: int8x16_t) -> int8x16_t {
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23557,6 +27101,8 @@ pub unsafe fn vsetq_lane_s16<const LANE: i32>(a: i16, b: int16x8_t) -> int16x8_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23570,6 +27116,8 @@ pub unsafe fn vsetq_lane_s32<const LANE: i32>(a: i32, b: int32x4_t) -> int32x4_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23583,6 +27131,8 @@ pub unsafe fn vsetq_lane_s64<const LANE: i32>(a: i64, b: int64x2_t) -> int64x2_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23596,6 +27146,8 @@ pub unsafe fn vsetq_lane_u8<const LANE: i32>(a: u8, b: uint8x16_t) -> uint8x16_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23609,6 +27161,8 @@ pub unsafe fn vsetq_lane_u16<const LANE: i32>(a: u16, b: uint16x8_t) -> uint16x8
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23622,6 +27176,8 @@ pub unsafe fn vsetq_lane_u32<const LANE: i32>(a: u32, b: uint32x4_t) -> uint32x4
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23635,6 +27191,8 @@ pub unsafe fn vsetq_lane_u64<const LANE: i32>(a: u64, b: uint64x2_t) -> uint64x2
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23648,6 +27206,8 @@ pub unsafe fn vsetq_lane_p8<const LANE: i32>(a: p8, b: poly8x16_t) -> poly8x16_t
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23661,6 +27221,8 @@ pub unsafe fn vsetq_lane_p16<const LANE: i32>(a: p16, b: poly16x8_t) -> poly16x8
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "aes,v8"))]
@@ -23674,6 +27236,8 @@ pub unsafe fn vsetq_lane_p64<const LANE: i32>(a: p64, b: poly64x2_t) -> poly64x2
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vset_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23687,6 +27251,8 @@ pub unsafe fn vset_lane_f32<const LANE: i32>(a: f32, b: float32x2_t) -> float32x
 }
 
 /// Insert vector element from another vector element
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsetq_lane_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23700,6 +27266,8 @@ pub unsafe fn vsetq_lane_f32<const LANE: i32>(a: f32, b: float32x4_t) -> float32
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23717,6 +27285,8 @@ vshl_s8_(a, b)
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23734,6 +27304,8 @@ vshlq_s8_(a, b)
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23751,6 +27323,8 @@ vshl_s16_(a, b)
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23768,6 +27342,8 @@ vshlq_s16_(a, b)
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23785,6 +27361,8 @@ vshl_s32_(a, b)
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23802,6 +27380,8 @@ vshlq_s32_(a, b)
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23819,6 +27399,8 @@ vshl_s64_(a, b)
 }
 
 /// Signed Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23836,6 +27418,8 @@ vshlq_s64_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23853,6 +27437,8 @@ vshl_u8_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23870,6 +27456,8 @@ vshlq_u8_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23887,6 +27475,8 @@ vshl_u16_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23904,6 +27494,8 @@ vshlq_u16_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23921,6 +27513,8 @@ vshl_u32_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23938,6 +27532,8 @@ vshlq_u32_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23955,6 +27551,8 @@ vshl_u64_(a, b)
 }
 
 /// Unsigned Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23972,6 +27570,8 @@ vshlq_u64_(a, b)
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23985,6 +27585,8 @@ pub unsafe fn vshl_n_s8<const N: i32>(a: int8x8_t) -> int8x8_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -23998,6 +27600,8 @@ pub unsafe fn vshlq_n_s8<const N: i32>(a: int8x16_t) -> int8x16_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24011,6 +27615,8 @@ pub unsafe fn vshl_n_s16<const N: i32>(a: int16x4_t) -> int16x4_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24024,6 +27630,8 @@ pub unsafe fn vshlq_n_s16<const N: i32>(a: int16x8_t) -> int16x8_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24037,6 +27645,8 @@ pub unsafe fn vshl_n_s32<const N: i32>(a: int32x2_t) -> int32x2_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24050,6 +27660,8 @@ pub unsafe fn vshlq_n_s32<const N: i32>(a: int32x4_t) -> int32x4_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24063,6 +27675,8 @@ pub unsafe fn vshl_n_u8<const N: i32>(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24076,6 +27690,8 @@ pub unsafe fn vshlq_n_u8<const N: i32>(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24089,6 +27705,8 @@ pub unsafe fn vshl_n_u16<const N: i32>(a: uint16x4_t) -> uint16x4_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24102,6 +27720,8 @@ pub unsafe fn vshlq_n_u16<const N: i32>(a: uint16x8_t) -> uint16x8_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24115,6 +27735,8 @@ pub unsafe fn vshl_n_u32<const N: i32>(a: uint32x2_t) -> uint32x2_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24128,6 +27750,8 @@ pub unsafe fn vshlq_n_u32<const N: i32>(a: uint32x4_t) -> uint32x4_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24141,6 +27765,8 @@ pub unsafe fn vshl_n_s64<const N: i32>(a: int64x1_t) -> int64x1_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24154,6 +27780,8 @@ pub unsafe fn vshlq_n_s64<const N: i32>(a: int64x2_t) -> int64x2_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshl_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24167,6 +27795,8 @@ pub unsafe fn vshl_n_u64<const N: i32>(a: uint64x1_t) -> uint64x1_t {
 }
 
 /// Shift left
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshlq_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24180,6 +27810,8 @@ pub unsafe fn vshlq_n_u64<const N: i32>(a: uint64x2_t) -> uint64x2_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24193,6 +27825,8 @@ pub unsafe fn vshll_n_s8<const N: i32>(a: int8x8_t) -> int16x8_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24206,6 +27840,8 @@ pub unsafe fn vshll_n_s16<const N: i32>(a: int16x4_t) -> int32x4_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24219,6 +27855,8 @@ pub unsafe fn vshll_n_s32<const N: i32>(a: int32x2_t) -> int64x2_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24232,6 +27870,8 @@ pub unsafe fn vshll_n_u8<const N: i32>(a: uint8x8_t) -> uint16x8_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24245,6 +27885,8 @@ pub unsafe fn vshll_n_u16<const N: i32>(a: uint16x4_t) -> uint32x4_t {
 }
 
 /// Signed shift left long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshll_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24258,6 +27900,8 @@ pub unsafe fn vshll_n_u32<const N: i32>(a: uint32x2_t) -> uint64x2_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24272,6 +27916,8 @@ pub unsafe fn vshr_n_s8<const N: i32>(a: int8x8_t) -> int8x8_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24286,6 +27932,8 @@ pub unsafe fn vshrq_n_s8<const N: i32>(a: int8x16_t) -> int8x16_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24300,6 +27948,8 @@ pub unsafe fn vshr_n_s16<const N: i32>(a: int16x4_t) -> int16x4_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24314,6 +27964,8 @@ pub unsafe fn vshrq_n_s16<const N: i32>(a: int16x8_t) -> int16x8_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24328,6 +27980,8 @@ pub unsafe fn vshr_n_s32<const N: i32>(a: int32x2_t) -> int32x2_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24342,6 +27996,8 @@ pub unsafe fn vshrq_n_s32<const N: i32>(a: int32x4_t) -> int32x4_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24356,6 +28012,8 @@ pub unsafe fn vshr_n_s64<const N: i32>(a: int64x1_t) -> int64x1_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24370,6 +28028,8 @@ pub unsafe fn vshrq_n_s64<const N: i32>(a: int64x2_t) -> int64x2_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24384,6 +28044,8 @@ pub unsafe fn vshr_n_u8<const N: i32>(a: uint8x8_t) -> uint8x8_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24398,6 +28060,8 @@ pub unsafe fn vshrq_n_u8<const N: i32>(a: uint8x16_t) -> uint8x16_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24412,6 +28076,8 @@ pub unsafe fn vshr_n_u16<const N: i32>(a: uint16x4_t) -> uint16x4_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24426,6 +28092,8 @@ pub unsafe fn vshrq_n_u16<const N: i32>(a: uint16x8_t) -> uint16x8_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24440,6 +28108,8 @@ pub unsafe fn vshr_n_u32<const N: i32>(a: uint32x2_t) -> uint32x2_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24454,6 +28124,8 @@ pub unsafe fn vshrq_n_u32<const N: i32>(a: uint32x4_t) -> uint32x4_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshr_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24468,6 +28140,8 @@ pub unsafe fn vshr_n_u64<const N: i32>(a: uint64x1_t) -> uint64x1_t {
 }
 
 /// Shift right
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrq_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24482,6 +28156,8 @@ pub unsafe fn vshrq_n_u64<const N: i32>(a: uint64x2_t) -> uint64x2_t {
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24495,6 +28171,8 @@ pub unsafe fn vshrn_n_s16<const N: i32>(a: int16x8_t) -> int8x8_t {
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24508,6 +28186,8 @@ pub unsafe fn vshrn_n_s32<const N: i32>(a: int32x4_t) -> int16x4_t {
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24521,6 +28201,8 @@ pub unsafe fn vshrn_n_s64<const N: i32>(a: int64x2_t) -> int32x2_t {
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24534,6 +28216,8 @@ pub unsafe fn vshrn_n_u16<const N: i32>(a: uint16x8_t) -> uint8x8_t {
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24547,6 +28231,8 @@ pub unsafe fn vshrn_n_u32<const N: i32>(a: uint32x4_t) -> uint16x4_t {
 }
 
 /// Shift right narrow
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vshrn_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24560,6 +28246,8 @@ pub unsafe fn vshrn_n_u64<const N: i32>(a: uint64x2_t) -> uint32x2_t {
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24573,6 +28261,8 @@ pub unsafe fn vsra_n_s8<const N: i32>(a: int8x8_t, b: int8x8_t) -> int8x8_t {
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24586,6 +28276,8 @@ pub unsafe fn vsraq_n_s8<const N: i32>(a: int8x16_t, b: int8x16_t) -> int8x16_t
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24599,6 +28291,8 @@ pub unsafe fn vsra_n_s16<const N: i32>(a: int16x4_t, b: int16x4_t) -> int16x4_t
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24612,6 +28306,8 @@ pub unsafe fn vsraq_n_s16<const N: i32>(a: int16x8_t, b: int16x8_t) -> int16x8_t
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24625,6 +28321,8 @@ pub unsafe fn vsra_n_s32<const N: i32>(a: int32x2_t, b: int32x2_t) -> int32x2_t
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24638,6 +28336,8 @@ pub unsafe fn vsraq_n_s32<const N: i32>(a: int32x4_t, b: int32x4_t) -> int32x4_t
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24651,6 +28351,8 @@ pub unsafe fn vsra_n_s64<const N: i32>(a: int64x1_t, b: int64x1_t) -> int64x1_t
 }
 
 /// Signed shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_s64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24664,6 +28366,8 @@ pub unsafe fn vsraq_n_s64<const N: i32>(a: int64x2_t, b: int64x2_t) -> int64x2_t
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24677,6 +28381,8 @@ pub unsafe fn vsra_n_u8<const N: i32>(a: uint8x8_t, b: uint8x8_t) -> uint8x8_t {
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24690,6 +28396,8 @@ pub unsafe fn vsraq_n_u8<const N: i32>(a: uint8x16_t, b: uint8x16_t) -> uint8x16
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24703,6 +28411,8 @@ pub unsafe fn vsra_n_u16<const N: i32>(a: uint16x4_t, b: uint16x4_t) -> uint16x4
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24716,6 +28426,8 @@ pub unsafe fn vsraq_n_u16<const N: i32>(a: uint16x8_t, b: uint16x8_t) -> uint16x
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24729,6 +28441,8 @@ pub unsafe fn vsra_n_u32<const N: i32>(a: uint32x2_t, b: uint32x2_t) -> uint32x2
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24742,6 +28456,8 @@ pub unsafe fn vsraq_n_u32<const N: i32>(a: uint32x4_t, b: uint32x4_t) -> uint32x
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsra_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24755,6 +28471,8 @@ pub unsafe fn vsra_n_u64<const N: i32>(a: uint64x1_t, b: uint64x1_t) -> uint64x1
 }
 
 /// Unsigned shift right and accumulate
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vsraq_n_u64)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24768,6 +28486,8 @@ pub unsafe fn vsraq_n_u64<const N: i32>(a: uint64x2_t, b: uint64x2_t) -> uint64x
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24781,6 +28501,8 @@ pub unsafe fn vtrn_s8(a: int8x8_t, b: int8x8_t) -> int8x8x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24794,6 +28516,8 @@ pub unsafe fn vtrn_s16(a: int16x4_t, b: int16x4_t) -> int16x4x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24807,6 +28531,8 @@ pub unsafe fn vtrnq_s8(a: int8x16_t, b: int8x16_t) -> int8x16x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24820,6 +28546,8 @@ pub unsafe fn vtrnq_s16(a: int16x8_t, b: int16x8_t) -> int16x8x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24833,6 +28561,8 @@ pub unsafe fn vtrnq_s32(a: int32x4_t, b: int32x4_t) -> int32x4x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24846,6 +28576,8 @@ pub unsafe fn vtrn_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24859,6 +28591,8 @@ pub unsafe fn vtrn_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24872,6 +28606,8 @@ pub unsafe fn vtrnq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24885,6 +28621,8 @@ pub unsafe fn vtrnq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24898,6 +28636,8 @@ pub unsafe fn vtrnq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24911,6 +28651,8 @@ pub unsafe fn vtrn_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24924,6 +28666,8 @@ pub unsafe fn vtrn_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24937,6 +28681,8 @@ pub unsafe fn vtrnq_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24950,6 +28696,8 @@ pub unsafe fn vtrnq_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24963,6 +28711,8 @@ pub unsafe fn vtrn_s32(a: int32x2_t, b: int32x2_t) -> int32x2x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24976,6 +28726,8 @@ pub unsafe fn vtrn_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrn_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -24989,6 +28741,8 @@ pub unsafe fn vtrn_f32(a: float32x2_t, b: float32x2_t) -> float32x2x2_t {
 }
 
 /// Transpose elements
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vtrnq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25002,6 +28756,8 @@ pub unsafe fn vtrnq_f32(a: float32x4_t, b: float32x4_t) -> float32x4x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25015,6 +28771,8 @@ pub unsafe fn vzip_s8(a: int8x8_t, b: int8x8_t) -> int8x8x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25028,6 +28786,8 @@ pub unsafe fn vzip_s16(a: int16x4_t, b: int16x4_t) -> int16x4x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25041,6 +28801,8 @@ pub unsafe fn vzip_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25054,6 +28816,8 @@ pub unsafe fn vzip_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25067,6 +28831,8 @@ pub unsafe fn vzip_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25080,6 +28846,8 @@ pub unsafe fn vzip_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25093,6 +28861,8 @@ pub unsafe fn vzip_s32(a: int32x2_t, b: int32x2_t) -> int32x2x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25106,6 +28876,8 @@ pub unsafe fn vzip_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25119,6 +28891,8 @@ pub unsafe fn vzipq_s8(a: int8x16_t, b: int8x16_t) -> int8x16x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25132,6 +28906,8 @@ pub unsafe fn vzipq_s16(a: int16x8_t, b: int16x8_t) -> int16x8x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25145,6 +28921,8 @@ pub unsafe fn vzipq_s32(a: int32x4_t, b: int32x4_t) -> int32x4x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25158,6 +28936,8 @@ pub unsafe fn vzipq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25171,6 +28951,8 @@ pub unsafe fn vzipq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25184,6 +28966,8 @@ pub unsafe fn vzipq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25197,6 +28981,8 @@ pub unsafe fn vzipq_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25210,6 +28996,8 @@ pub unsafe fn vzipq_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzip_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25223,6 +29011,8 @@ pub unsafe fn vzip_f32(a: float32x2_t, b: float32x2_t) -> float32x2x2_t {
 }
 
 /// Zip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vzipq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25236,6 +29026,8 @@ pub unsafe fn vzipq_f32(a: float32x4_t, b: float32x4_t) -> float32x4x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25249,6 +29041,8 @@ pub unsafe fn vuzp_s8(a: int8x8_t, b: int8x8_t) -> int8x8x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25262,6 +29056,8 @@ pub unsafe fn vuzp_s16(a: int16x4_t, b: int16x4_t) -> int16x4x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25275,6 +29071,8 @@ pub unsafe fn vuzpq_s8(a: int8x16_t, b: int8x16_t) -> int8x16x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25288,6 +29086,8 @@ pub unsafe fn vuzpq_s16(a: int16x8_t, b: int16x8_t) -> int16x8x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25301,6 +29101,8 @@ pub unsafe fn vuzpq_s32(a: int32x4_t, b: int32x4_t) -> int32x4x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25314,6 +29116,8 @@ pub unsafe fn vuzp_u8(a: uint8x8_t, b: uint8x8_t) -> uint8x8x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25327,6 +29131,8 @@ pub unsafe fn vuzp_u16(a: uint16x4_t, b: uint16x4_t) -> uint16x4x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25340,6 +29146,8 @@ pub unsafe fn vuzpq_u8(a: uint8x16_t, b: uint8x16_t) -> uint8x16x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25353,6 +29161,8 @@ pub unsafe fn vuzpq_u16(a: uint16x8_t, b: uint16x8_t) -> uint16x8x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25366,6 +29176,8 @@ pub unsafe fn vuzpq_u32(a: uint32x4_t, b: uint32x4_t) -> uint32x4x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25379,6 +29191,8 @@ pub unsafe fn vuzp_p8(a: poly8x8_t, b: poly8x8_t) -> poly8x8x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25392,6 +29206,8 @@ pub unsafe fn vuzp_p16(a: poly16x4_t, b: poly16x4_t) -> poly16x4x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_p8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25405,6 +29221,8 @@ pub unsafe fn vuzpq_p8(a: poly8x16_t, b: poly8x16_t) -> poly8x16x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_p16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25418,6 +29236,8 @@ pub unsafe fn vuzpq_p16(a: poly16x8_t, b: poly16x8_t) -> poly16x8x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25431,6 +29251,8 @@ pub unsafe fn vuzp_s32(a: int32x2_t, b: int32x2_t) -> int32x2x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25444,6 +29266,8 @@ pub unsafe fn vuzp_u32(a: uint32x2_t, b: uint32x2_t) -> uint32x2x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzp_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25457,6 +29281,8 @@ pub unsafe fn vuzp_f32(a: float32x2_t, b: float32x2_t) -> float32x2x2_t {
 }
 
 /// Unzip vectors
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vuzpq_f32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25470,6 +29296,8 @@ pub unsafe fn vuzpq_f32(a: float32x4_t, b: float32x4_t) -> float32x4x2_t {
 }
 
 /// Unsigned Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_u8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25482,6 +29310,8 @@ pub unsafe fn vabal_u8(a: uint16x8_t, b: uint8x8_t, c: uint8x8_t) -> uint16x8_t
 }
 
 /// Unsigned Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_u16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25494,6 +29324,8 @@ pub unsafe fn vabal_u16(a: uint32x4_t, b: uint16x4_t, c: uint16x4_t) -> uint32x4
 }
 
 /// Unsigned Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_u32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25506,6 +29338,8 @@ pub unsafe fn vabal_u32(a: uint64x2_t, b: uint32x2_t, c: uint32x2_t) -> uint64x2
 }
 
 /// Signed Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25519,6 +29353,8 @@ pub unsafe fn vabal_s8(a: int16x8_t, b: int8x8_t, c: int8x8_t) -> int16x8_t {
 }
 
 /// Signed Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25532,6 +29368,8 @@ pub unsafe fn vabal_s16(a: int32x4_t, b: int16x4_t, c: int16x4_t) -> int32x4_t {
 }
 
 /// Signed Absolute difference and Accumulate Long
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vabal_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25545,6 +29383,8 @@ pub unsafe fn vabal_s32(a: int64x2_t, b: int32x2_t, c: int32x2_t) -> int64x2_t {
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabs_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25562,6 +29402,8 @@ vqabs_s8_(a)
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabsq_s8)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25579,6 +29421,8 @@ vqabsq_s8_(a)
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabs_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25596,6 +29440,8 @@ vqabs_s16_(a)
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabsq_s16)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25613,6 +29459,8 @@ vqabsq_s16_(a)
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabs_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -25630,6 +29478,8 @@ vqabs_s32_(a)
 }
 
 /// Singned saturating Absolute value
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vqabsq_s32)
 #[inline]
 #[target_feature(enable = "neon")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -28096,181 +31946,181 @@ mod test {
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_s8() {
-        let a: i8x8 = i8x8::new(0, 8, 8, 9, 8, 9, 9, 11);
-        let b: i8x8 = i8x8::new(9, 11, 14, 15, 16, 17, 18, 19);
-        let e: i8x8 = i8x8::new(8, 9, 9, 11, 9, 11, 14, 15);
-        let r: i8x8 = transmute(vext_s8::<4>(transmute(a), transmute(b)));
+        let a: i8x8 = i8x8::new(1, 1, 1, 1, 1, 1, 1, 1);
+        let b: i8x8 = i8x8::new(2, 2, 2, 2, 2, 2, 2, 2);
+        let e: i8x8 = i8x8::new(1, 2, 2, 2, 2, 2, 2, 2);
+        let r: i8x8 = transmute(vext_s8::<7>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_s8() {
-        let a: i8x16 = i8x16::new(0, 8, 8, 9, 8, 9, 9, 11, 8, 9, 9, 11, 9, 11, 14, 15);
-        let b: i8x16 = i8x16::new(9, 11, 14, 15, 16, 17, 18, 19, 0, 8, 8, 9, 8, 9, 9, 11);
-        let e: i8x16 = i8x16::new(8, 9, 9, 11, 9, 11, 14, 15, 9, 11, 14, 15, 16, 17, 18, 19);
-        let r: i8x16 = transmute(vextq_s8::<8>(transmute(a), transmute(b)));
+        let a: i8x16 = i8x16::new(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1);
+        let b: i8x16 = i8x16::new(2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2);
+        let e: i8x16 = i8x16::new(1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2);
+        let r: i8x16 = transmute(vextq_s8::<15>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_s16() {
-        let a: i16x4 = i16x4::new(0, 8, 8, 9);
-        let b: i16x4 = i16x4::new(9, 11, 14, 15);
-        let e: i16x4 = i16x4::new(8, 9, 9, 11);
-        let r: i16x4 = transmute(vext_s16::<2>(transmute(a), transmute(b)));
+        let a: i16x4 = i16x4::new(1, 1, 1, 1);
+        let b: i16x4 = i16x4::new(2, 2, 2, 2);
+        let e: i16x4 = i16x4::new(1, 2, 2, 2);
+        let r: i16x4 = transmute(vext_s16::<3>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_s16() {
-        let a: i16x8 = i16x8::new(0, 8, 8, 9, 8, 9, 9, 11);
-        let b: i16x8 = i16x8::new(9, 11, 14, 15, 16, 17, 18, 19);
-        let e: i16x8 = i16x8::new(8, 9, 9, 11, 9, 11, 14, 15);
-        let r: i16x8 = transmute(vextq_s16::<4>(transmute(a), transmute(b)));
+        let a: i16x8 = i16x8::new(1, 1, 1, 1, 1, 1, 1, 1);
+        let b: i16x8 = i16x8::new(2, 2, 2, 2, 2, 2, 2, 2);
+        let e: i16x8 = i16x8::new(1, 2, 2, 2, 2, 2, 2, 2);
+        let r: i16x8 = transmute(vextq_s16::<7>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_s32() {
-        let a: i32x2 = i32x2::new(0, 8);
-        let b: i32x2 = i32x2::new(9, 11);
-        let e: i32x2 = i32x2::new(8, 9);
+        let a: i32x2 = i32x2::new(1, 1);
+        let b: i32x2 = i32x2::new(2, 2);
+        let e: i32x2 = i32x2::new(1, 2);
         let r: i32x2 = transmute(vext_s32::<1>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_s32() {
-        let a: i32x4 = i32x4::new(0, 8, 8, 9);
-        let b: i32x4 = i32x4::new(9, 11, 14, 15);
-        let e: i32x4 = i32x4::new(8, 9, 9, 11);
-        let r: i32x4 = transmute(vextq_s32::<2>(transmute(a), transmute(b)));
+        let a: i32x4 = i32x4::new(1, 1, 1, 1);
+        let b: i32x4 = i32x4::new(2, 2, 2, 2);
+        let e: i32x4 = i32x4::new(1, 2, 2, 2);
+        let r: i32x4 = transmute(vextq_s32::<3>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_u8() {
-        let a: u8x8 = u8x8::new(0, 8, 8, 9, 8, 9, 9, 11);
-        let b: u8x8 = u8x8::new(9, 11, 14, 15, 16, 17, 18, 19);
-        let e: u8x8 = u8x8::new(8, 9, 9, 11, 9, 11, 14, 15);
-        let r: u8x8 = transmute(vext_u8::<4>(transmute(a), transmute(b)));
+        let a: u8x8 = u8x8::new(1, 1, 1, 1, 1, 1, 1, 1);
+        let b: u8x8 = u8x8::new(2, 2, 2, 2, 2, 2, 2, 2);
+        let e: u8x8 = u8x8::new(1, 2, 2, 2, 2, 2, 2, 2);
+        let r: u8x8 = transmute(vext_u8::<7>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_u8() {
-        let a: u8x16 = u8x16::new(0, 8, 8, 9, 8, 9, 9, 11, 8, 9, 9, 11, 9, 11, 14, 15);
-        let b: u8x16 = u8x16::new(9, 11, 14, 15, 16, 17, 18, 19, 0, 8, 8, 9, 8, 9, 9, 11);
-        let e: u8x16 = u8x16::new(8, 9, 9, 11, 9, 11, 14, 15, 9, 11, 14, 15, 16, 17, 18, 19);
-        let r: u8x16 = transmute(vextq_u8::<8>(transmute(a), transmute(b)));
+        let a: u8x16 = u8x16::new(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1);
+        let b: u8x16 = u8x16::new(2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2);
+        let e: u8x16 = u8x16::new(1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2);
+        let r: u8x16 = transmute(vextq_u8::<15>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_u16() {
-        let a: u16x4 = u16x4::new(0, 8, 8, 9);
-        let b: u16x4 = u16x4::new(9, 11, 14, 15);
-        let e: u16x4 = u16x4::new(8, 9, 9, 11);
-        let r: u16x4 = transmute(vext_u16::<2>(transmute(a), transmute(b)));
+        let a: u16x4 = u16x4::new(1, 1, 1, 1);
+        let b: u16x4 = u16x4::new(2, 2, 2, 2);
+        let e: u16x4 = u16x4::new(1, 2, 2, 2);
+        let r: u16x4 = transmute(vext_u16::<3>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_u16() {
-        let a: u16x8 = u16x8::new(0, 8, 8, 9, 8, 9, 9, 11);
-        let b: u16x8 = u16x8::new(9, 11, 14, 15, 16, 17, 18, 19);
-        let e: u16x8 = u16x8::new(8, 9, 9, 11, 9, 11, 14, 15);
-        let r: u16x8 = transmute(vextq_u16::<4>(transmute(a), transmute(b)));
+        let a: u16x8 = u16x8::new(1, 1, 1, 1, 1, 1, 1, 1);
+        let b: u16x8 = u16x8::new(2, 2, 2, 2, 2, 2, 2, 2);
+        let e: u16x8 = u16x8::new(1, 2, 2, 2, 2, 2, 2, 2);
+        let r: u16x8 = transmute(vextq_u16::<7>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_u32() {
-        let a: u32x2 = u32x2::new(0, 8);
-        let b: u32x2 = u32x2::new(9, 11);
-        let e: u32x2 = u32x2::new(8, 9);
+        let a: u32x2 = u32x2::new(1, 1);
+        let b: u32x2 = u32x2::new(2, 2);
+        let e: u32x2 = u32x2::new(1, 2);
         let r: u32x2 = transmute(vext_u32::<1>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_u32() {
-        let a: u32x4 = u32x4::new(0, 8, 8, 9);
-        let b: u32x4 = u32x4::new(9, 11, 14, 15);
-        let e: u32x4 = u32x4::new(8, 9, 9, 11);
-        let r: u32x4 = transmute(vextq_u32::<2>(transmute(a), transmute(b)));
+        let a: u32x4 = u32x4::new(1, 1, 1, 1);
+        let b: u32x4 = u32x4::new(2, 2, 2, 2);
+        let e: u32x4 = u32x4::new(1, 2, 2, 2);
+        let r: u32x4 = transmute(vextq_u32::<3>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_p8() {
-        let a: i8x8 = i8x8::new(0, 8, 8, 9, 8, 9, 9, 11);
-        let b: i8x8 = i8x8::new(9, 11, 14, 15, 16, 17, 18, 19);
-        let e: i8x8 = i8x8::new(8, 9, 9, 11, 9, 11, 14, 15);
-        let r: i8x8 = transmute(vext_p8::<4>(transmute(a), transmute(b)));
+        let a: i8x8 = i8x8::new(1, 1, 1, 1, 1, 1, 1, 1);
+        let b: i8x8 = i8x8::new(2, 2, 2, 2, 2, 2, 2, 2);
+        let e: i8x8 = i8x8::new(1, 2, 2, 2, 2, 2, 2, 2);
+        let r: i8x8 = transmute(vext_p8::<7>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_p8() {
-        let a: i8x16 = i8x16::new(0, 8, 8, 9, 8, 9, 9, 11, 8, 9, 9, 11, 9, 11, 14, 15);
-        let b: i8x16 = i8x16::new(9, 11, 14, 15, 16, 17, 18, 19, 0, 8, 8, 9, 8, 9, 9, 11);
-        let e: i8x16 = i8x16::new(8, 9, 9, 11, 9, 11, 14, 15, 9, 11, 14, 15, 16, 17, 18, 19);
-        let r: i8x16 = transmute(vextq_p8::<8>(transmute(a), transmute(b)));
+        let a: i8x16 = i8x16::new(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1);
+        let b: i8x16 = i8x16::new(2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2);
+        let e: i8x16 = i8x16::new(1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2);
+        let r: i8x16 = transmute(vextq_p8::<15>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_p16() {
-        let a: i16x4 = i16x4::new(0, 8, 8, 9);
-        let b: i16x4 = i16x4::new(9, 11, 14, 15);
-        let e: i16x4 = i16x4::new(8, 9, 9, 11);
-        let r: i16x4 = transmute(vext_p16::<2>(transmute(a), transmute(b)));
+        let a: i16x4 = i16x4::new(1, 1, 1, 1);
+        let b: i16x4 = i16x4::new(2, 2, 2, 2);
+        let e: i16x4 = i16x4::new(1, 2, 2, 2);
+        let r: i16x4 = transmute(vext_p16::<3>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_p16() {
-        let a: i16x8 = i16x8::new(0, 8, 8, 9, 8, 9, 9, 11);
-        let b: i16x8 = i16x8::new(9, 11, 14, 15, 16, 17, 18, 19);
-        let e: i16x8 = i16x8::new(8, 9, 9, 11, 9, 11, 14, 15);
-        let r: i16x8 = transmute(vextq_p16::<4>(transmute(a), transmute(b)));
+        let a: i16x8 = i16x8::new(1, 1, 1, 1, 1, 1, 1, 1);
+        let b: i16x8 = i16x8::new(2, 2, 2, 2, 2, 2, 2, 2);
+        let e: i16x8 = i16x8::new(1, 2, 2, 2, 2, 2, 2, 2);
+        let r: i16x8 = transmute(vextq_p16::<7>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_s64() {
-        let a: i64x2 = i64x2::new(0, 8);
-        let b: i64x2 = i64x2::new(9, 11);
-        let e: i64x2 = i64x2::new(8, 9);
+        let a: i64x2 = i64x2::new(1, 1);
+        let b: i64x2 = i64x2::new(2, 2);
+        let e: i64x2 = i64x2::new(1, 2);
         let r: i64x2 = transmute(vextq_s64::<1>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_u64() {
-        let a: u64x2 = u64x2::new(0, 8);
-        let b: u64x2 = u64x2::new(9, 11);
-        let e: u64x2 = u64x2::new(8, 9);
+        let a: u64x2 = u64x2::new(1, 1);
+        let b: u64x2 = u64x2::new(2, 2);
+        let e: u64x2 = u64x2::new(1, 2);
         let r: u64x2 = transmute(vextq_u64::<1>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vext_f32() {
-        let a: f32x2 = f32x2::new(0., 2.);
-        let b: f32x2 = f32x2::new(3., 4.);
-        let e: f32x2 = f32x2::new(2., 3.);
+        let a: f32x2 = f32x2::new(1., 1.);
+        let b: f32x2 = f32x2::new(2., 2.);
+        let e: f32x2 = f32x2::new(1., 2.);
         let r: f32x2 = transmute(vext_f32::<1>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vextq_f32() {
-        let a: f32x4 = f32x4::new(0., 2., 2., 3.);
-        let b: f32x4 = f32x4::new(3., 4., 5., 6.);
-        let e: f32x4 = f32x4::new(2., 3., 3., 4.);
-        let r: f32x4 = transmute(vextq_f32::<2>(transmute(a), transmute(b)));
+        let a: f32x4 = f32x4::new(1., 1., 1., 1.);
+        let b: f32x4 = f32x4::new(2., 2., 2., 2.);
+        let e: f32x4 = f32x4::new(1., 2., 2., 2.);
+        let r: f32x4 = transmute(vextq_f32::<3>(transmute(a), transmute(b)));
         assert_eq!(r, e);
     }
 
diff --git a/library/stdarch/crates/core_arch/src/arm_shared/neon/mod.rs b/library/stdarch/crates/core_arch/src/arm_shared/neon/mod.rs
index 952d1ca2e..043f7ed51 100644
--- a/library/stdarch/crates/core_arch/src/arm_shared/neon/mod.rs
+++ b/library/stdarch/crates/core_arch/src/arm_shared/neon/mod.rs
@@ -106,6 +106,7 @@ types! {
 }
 
 /// ARM-specific type containing two `int8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -113,6 +114,7 @@ types! {
 )]
 pub struct int8x8x2_t(pub int8x8_t, pub int8x8_t);
 /// ARM-specific type containing three `int8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -120,6 +122,7 @@ pub struct int8x8x2_t(pub int8x8_t, pub int8x8_t);
 )]
 pub struct int8x8x3_t(pub int8x8_t, pub int8x8_t, pub int8x8_t);
 /// ARM-specific type containing four `int8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -128,6 +131,7 @@ pub struct int8x8x3_t(pub int8x8_t, pub int8x8_t, pub int8x8_t);
 pub struct int8x8x4_t(pub int8x8_t, pub int8x8_t, pub int8x8_t, pub int8x8_t);
 
 /// ARM-specific type containing two `int8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -135,6 +139,7 @@ pub struct int8x8x4_t(pub int8x8_t, pub int8x8_t, pub int8x8_t, pub int8x8_t);
 )]
 pub struct int8x16x2_t(pub int8x16_t, pub int8x16_t);
 /// ARM-specific type containing three `int8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -142,6 +147,7 @@ pub struct int8x16x2_t(pub int8x16_t, pub int8x16_t);
 )]
 pub struct int8x16x3_t(pub int8x16_t, pub int8x16_t, pub int8x16_t);
 /// ARM-specific type containing four `int8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -150,6 +156,7 @@ pub struct int8x16x3_t(pub int8x16_t, pub int8x16_t, pub int8x16_t);
 pub struct int8x16x4_t(pub int8x16_t, pub int8x16_t, pub int8x16_t, pub int8x16_t);
 
 /// ARM-specific type containing two `uint8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -157,6 +164,7 @@ pub struct int8x16x4_t(pub int8x16_t, pub int8x16_t, pub int8x16_t, pub int8x16_
 )]
 pub struct uint8x8x2_t(pub uint8x8_t, pub uint8x8_t);
 /// ARM-specific type containing three `uint8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -164,6 +172,7 @@ pub struct uint8x8x2_t(pub uint8x8_t, pub uint8x8_t);
 )]
 pub struct uint8x8x3_t(pub uint8x8_t, pub uint8x8_t, pub uint8x8_t);
 /// ARM-specific type containing four `uint8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -172,6 +181,7 @@ pub struct uint8x8x3_t(pub uint8x8_t, pub uint8x8_t, pub uint8x8_t);
 pub struct uint8x8x4_t(pub uint8x8_t, pub uint8x8_t, pub uint8x8_t, pub uint8x8_t);
 
 /// ARM-specific type containing two `uint8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -179,6 +189,7 @@ pub struct uint8x8x4_t(pub uint8x8_t, pub uint8x8_t, pub uint8x8_t, pub uint8x8_
 )]
 pub struct uint8x16x2_t(pub uint8x16_t, pub uint8x16_t);
 /// ARM-specific type containing three `uint8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -186,6 +197,7 @@ pub struct uint8x16x2_t(pub uint8x16_t, pub uint8x16_t);
 )]
 pub struct uint8x16x3_t(pub uint8x16_t, pub uint8x16_t, pub uint8x16_t);
 /// ARM-specific type containing four `uint8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -199,6 +211,7 @@ pub struct uint8x16x4_t(
 );
 
 /// ARM-specific type containing two `poly8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -206,6 +219,7 @@ pub struct uint8x16x4_t(
 )]
 pub struct poly8x8x2_t(pub poly8x8_t, pub poly8x8_t);
 /// ARM-specific type containing three `poly8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -213,6 +227,7 @@ pub struct poly8x8x2_t(pub poly8x8_t, pub poly8x8_t);
 )]
 pub struct poly8x8x3_t(pub poly8x8_t, pub poly8x8_t, pub poly8x8_t);
 /// ARM-specific type containing four `poly8x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -221,6 +236,7 @@ pub struct poly8x8x3_t(pub poly8x8_t, pub poly8x8_t, pub poly8x8_t);
 pub struct poly8x8x4_t(pub poly8x8_t, pub poly8x8_t, pub poly8x8_t, pub poly8x8_t);
 
 /// ARM-specific type containing two `poly8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -228,6 +244,7 @@ pub struct poly8x8x4_t(pub poly8x8_t, pub poly8x8_t, pub poly8x8_t, pub poly8x8_
 )]
 pub struct poly8x16x2_t(pub poly8x16_t, pub poly8x16_t);
 /// ARM-specific type containing three `poly8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -235,6 +252,7 @@ pub struct poly8x16x2_t(pub poly8x16_t, pub poly8x16_t);
 )]
 pub struct poly8x16x3_t(pub poly8x16_t, pub poly8x16_t, pub poly8x16_t);
 /// ARM-specific type containing four `poly8x16_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -248,6 +266,7 @@ pub struct poly8x16x4_t(
 );
 
 /// ARM-specific type containing two `int16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -255,6 +274,7 @@ pub struct poly8x16x4_t(
 )]
 pub struct int16x4x2_t(pub int16x4_t, pub int16x4_t);
 /// ARM-specific type containing three `int16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -262,6 +282,7 @@ pub struct int16x4x2_t(pub int16x4_t, pub int16x4_t);
 )]
 pub struct int16x4x3_t(pub int16x4_t, pub int16x4_t, pub int16x4_t);
 /// ARM-specific type containing four `int16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -270,6 +291,7 @@ pub struct int16x4x3_t(pub int16x4_t, pub int16x4_t, pub int16x4_t);
 pub struct int16x4x4_t(pub int16x4_t, pub int16x4_t, pub int16x4_t, pub int16x4_t);
 
 /// ARM-specific type containing two `int16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -277,6 +299,7 @@ pub struct int16x4x4_t(pub int16x4_t, pub int16x4_t, pub int16x4_t, pub int16x4_
 )]
 pub struct int16x8x2_t(pub int16x8_t, pub int16x8_t);
 /// ARM-specific type containing three `int16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -284,6 +307,7 @@ pub struct int16x8x2_t(pub int16x8_t, pub int16x8_t);
 )]
 pub struct int16x8x3_t(pub int16x8_t, pub int16x8_t, pub int16x8_t);
 /// ARM-specific type containing four `int16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -292,6 +316,7 @@ pub struct int16x8x3_t(pub int16x8_t, pub int16x8_t, pub int16x8_t);
 pub struct int16x8x4_t(pub int16x8_t, pub int16x8_t, pub int16x8_t, pub int16x8_t);
 
 /// ARM-specific type containing two `uint16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -299,6 +324,7 @@ pub struct int16x8x4_t(pub int16x8_t, pub int16x8_t, pub int16x8_t, pub int16x8_
 )]
 pub struct uint16x4x2_t(pub uint16x4_t, pub uint16x4_t);
 /// ARM-specific type containing three `uint16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -306,6 +332,7 @@ pub struct uint16x4x2_t(pub uint16x4_t, pub uint16x4_t);
 )]
 pub struct uint16x4x3_t(pub uint16x4_t, pub uint16x4_t, pub uint16x4_t);
 /// ARM-specific type containing four `uint16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -319,6 +346,7 @@ pub struct uint16x4x4_t(
 );
 
 /// ARM-specific type containing two `uint16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -326,6 +354,7 @@ pub struct uint16x4x4_t(
 )]
 pub struct uint16x8x2_t(pub uint16x8_t, pub uint16x8_t);
 /// ARM-specific type containing three `uint16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -333,6 +362,7 @@ pub struct uint16x8x2_t(pub uint16x8_t, pub uint16x8_t);
 )]
 pub struct uint16x8x3_t(pub uint16x8_t, pub uint16x8_t, pub uint16x8_t);
 /// ARM-specific type containing four `uint16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -346,6 +376,7 @@ pub struct uint16x8x4_t(
 );
 
 /// ARM-specific type containing two `poly16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -353,6 +384,7 @@ pub struct uint16x8x4_t(
 )]
 pub struct poly16x4x2_t(pub poly16x4_t, pub poly16x4_t);
 /// ARM-specific type containing three `poly16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -360,6 +392,7 @@ pub struct poly16x4x2_t(pub poly16x4_t, pub poly16x4_t);
 )]
 pub struct poly16x4x3_t(pub poly16x4_t, pub poly16x4_t, pub poly16x4_t);
 /// ARM-specific type containing four `poly16x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -373,6 +406,7 @@ pub struct poly16x4x4_t(
 );
 
 /// ARM-specific type containing two `poly16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -380,6 +414,7 @@ pub struct poly16x4x4_t(
 )]
 pub struct poly16x8x2_t(pub poly16x8_t, pub poly16x8_t);
 /// ARM-specific type containing three `poly16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -387,6 +422,7 @@ pub struct poly16x8x2_t(pub poly16x8_t, pub poly16x8_t);
 )]
 pub struct poly16x8x3_t(pub poly16x8_t, pub poly16x8_t, pub poly16x8_t);
 /// ARM-specific type containing four `poly16x8_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -400,6 +436,7 @@ pub struct poly16x8x4_t(
 );
 
 /// ARM-specific type containing two `int32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -407,6 +444,7 @@ pub struct poly16x8x4_t(
 )]
 pub struct int32x2x2_t(pub int32x2_t, pub int32x2_t);
 /// ARM-specific type containing three `int32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -414,6 +452,7 @@ pub struct int32x2x2_t(pub int32x2_t, pub int32x2_t);
 )]
 pub struct int32x2x3_t(pub int32x2_t, pub int32x2_t, pub int32x2_t);
 /// ARM-specific type containing four `int32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -422,6 +461,7 @@ pub struct int32x2x3_t(pub int32x2_t, pub int32x2_t, pub int32x2_t);
 pub struct int32x2x4_t(pub int32x2_t, pub int32x2_t, pub int32x2_t, pub int32x2_t);
 
 /// ARM-specific type containing two `int32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -429,6 +469,7 @@ pub struct int32x2x4_t(pub int32x2_t, pub int32x2_t, pub int32x2_t, pub int32x2_
 )]
 pub struct int32x4x2_t(pub int32x4_t, pub int32x4_t);
 /// ARM-specific type containing three `int32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -436,6 +477,7 @@ pub struct int32x4x2_t(pub int32x4_t, pub int32x4_t);
 )]
 pub struct int32x4x3_t(pub int32x4_t, pub int32x4_t, pub int32x4_t);
 /// ARM-specific type containing four `int32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -444,6 +486,7 @@ pub struct int32x4x3_t(pub int32x4_t, pub int32x4_t, pub int32x4_t);
 pub struct int32x4x4_t(pub int32x4_t, pub int32x4_t, pub int32x4_t, pub int32x4_t);
 
 /// ARM-specific type containing two `uint32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -451,6 +494,7 @@ pub struct int32x4x4_t(pub int32x4_t, pub int32x4_t, pub int32x4_t, pub int32x4_
 )]
 pub struct uint32x2x2_t(pub uint32x2_t, pub uint32x2_t);
 /// ARM-specific type containing three `uint32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -458,6 +502,7 @@ pub struct uint32x2x2_t(pub uint32x2_t, pub uint32x2_t);
 )]
 pub struct uint32x2x3_t(pub uint32x2_t, pub uint32x2_t, pub uint32x2_t);
 /// ARM-specific type containing four `uint32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -471,6 +516,7 @@ pub struct uint32x2x4_t(
 );
 
 /// ARM-specific type containing two `uint32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -478,6 +524,7 @@ pub struct uint32x2x4_t(
 )]
 pub struct uint32x4x2_t(pub uint32x4_t, pub uint32x4_t);
 /// ARM-specific type containing three `uint32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -485,6 +532,7 @@ pub struct uint32x4x2_t(pub uint32x4_t, pub uint32x4_t);
 )]
 pub struct uint32x4x3_t(pub uint32x4_t, pub uint32x4_t, pub uint32x4_t);
 /// ARM-specific type containing four `uint32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -498,6 +546,7 @@ pub struct uint32x4x4_t(
 );
 
 /// ARM-specific type containing two `float32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -505,6 +554,7 @@ pub struct uint32x4x4_t(
 )]
 pub struct float32x2x2_t(pub float32x2_t, pub float32x2_t);
 /// ARM-specific type containing three `float32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -512,6 +562,7 @@ pub struct float32x2x2_t(pub float32x2_t, pub float32x2_t);
 )]
 pub struct float32x2x3_t(pub float32x2_t, pub float32x2_t, pub float32x2_t);
 /// ARM-specific type containing four `float32x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -525,6 +576,7 @@ pub struct float32x2x4_t(
 );
 
 /// ARM-specific type containing two `float32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -532,6 +584,7 @@ pub struct float32x2x4_t(
 )]
 pub struct float32x4x2_t(pub float32x4_t, pub float32x4_t);
 /// ARM-specific type containing three `float32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -539,6 +592,7 @@ pub struct float32x4x2_t(pub float32x4_t, pub float32x4_t);
 )]
 pub struct float32x4x3_t(pub float32x4_t, pub float32x4_t, pub float32x4_t);
 /// ARM-specific type containing four `float32x4_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -552,6 +606,7 @@ pub struct float32x4x4_t(
 );
 
 /// ARM-specific type containing four `int64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -559,6 +614,7 @@ pub struct float32x4x4_t(
 )]
 pub struct int64x1x2_t(pub int64x1_t, pub int64x1_t);
 /// ARM-specific type containing four `int64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -566,6 +622,7 @@ pub struct int64x1x2_t(pub int64x1_t, pub int64x1_t);
 )]
 pub struct int64x1x3_t(pub int64x1_t, pub int64x1_t, pub int64x1_t);
 /// ARM-specific type containing four `int64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -574,6 +631,7 @@ pub struct int64x1x3_t(pub int64x1_t, pub int64x1_t, pub int64x1_t);
 pub struct int64x1x4_t(pub int64x1_t, pub int64x1_t, pub int64x1_t, pub int64x1_t);
 
 /// ARM-specific type containing four `int64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -581,6 +639,7 @@ pub struct int64x1x4_t(pub int64x1_t, pub int64x1_t, pub int64x1_t, pub int64x1_
 )]
 pub struct int64x2x2_t(pub int64x2_t, pub int64x2_t);
 /// ARM-specific type containing four `int64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -588,6 +647,7 @@ pub struct int64x2x2_t(pub int64x2_t, pub int64x2_t);
 )]
 pub struct int64x2x3_t(pub int64x2_t, pub int64x2_t, pub int64x2_t);
 /// ARM-specific type containing four `int64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -596,6 +656,7 @@ pub struct int64x2x3_t(pub int64x2_t, pub int64x2_t, pub int64x2_t);
 pub struct int64x2x4_t(pub int64x2_t, pub int64x2_t, pub int64x2_t, pub int64x2_t);
 
 /// ARM-specific type containing four `uint64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -603,6 +664,7 @@ pub struct int64x2x4_t(pub int64x2_t, pub int64x2_t, pub int64x2_t, pub int64x2_
 )]
 pub struct uint64x1x2_t(pub uint64x1_t, pub uint64x1_t);
 /// ARM-specific type containing four `uint64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -610,6 +672,7 @@ pub struct uint64x1x2_t(pub uint64x1_t, pub uint64x1_t);
 )]
 pub struct uint64x1x3_t(pub uint64x1_t, pub uint64x1_t, pub uint64x1_t);
 /// ARM-specific type containing four `uint64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -623,6 +686,7 @@ pub struct uint64x1x4_t(
 );
 
 /// ARM-specific type containing four `uint64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -630,6 +694,7 @@ pub struct uint64x1x4_t(
 )]
 pub struct uint64x2x2_t(pub uint64x2_t, pub uint64x2_t);
 /// ARM-specific type containing four `uint64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -637,6 +702,7 @@ pub struct uint64x2x2_t(pub uint64x2_t, pub uint64x2_t);
 )]
 pub struct uint64x2x3_t(pub uint64x2_t, pub uint64x2_t, pub uint64x2_t);
 /// ARM-specific type containing four `uint64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -650,6 +716,7 @@ pub struct uint64x2x4_t(
 );
 
 /// ARM-specific type containing four `poly64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -657,6 +724,7 @@ pub struct uint64x2x4_t(
 )]
 pub struct poly64x1x2_t(pub poly64x1_t, pub poly64x1_t);
 /// ARM-specific type containing four `poly64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -664,6 +732,7 @@ pub struct poly64x1x2_t(pub poly64x1_t, pub poly64x1_t);
 )]
 pub struct poly64x1x3_t(pub poly64x1_t, pub poly64x1_t, pub poly64x1_t);
 /// ARM-specific type containing four `poly64x1_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -677,6 +746,7 @@ pub struct poly64x1x4_t(
 );
 
 /// ARM-specific type containing four `poly64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -684,6 +754,7 @@ pub struct poly64x1x4_t(
 )]
 pub struct poly64x2x2_t(pub poly64x2_t, pub poly64x2_t);
 /// ARM-specific type containing four `poly64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -691,6 +762,7 @@ pub struct poly64x2x2_t(pub poly64x2_t, pub poly64x2_t);
 )]
 pub struct poly64x2x3_t(pub poly64x2_t, pub poly64x2_t, pub poly64x2_t);
 /// ARM-specific type containing four `poly64x2_t` vectors.
+#[repr(C)]
 #[derive(Copy, Clone, Debug)]
 #[cfg_attr(
     target_arch = "aarch64",
@@ -1212,6 +1284,8 @@ pub unsafe fn vld1q_lane_p16<const LANE: i32>(ptr: *const p16, src: poly16x8_t)
 }
 
 /// Load one single-element structure to one lane of one register.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1228,6 +1302,8 @@ pub unsafe fn vld1_lane_p64<const LANE: i32>(ptr: *const p64, src: poly64x1_t) -
 }
 
 /// Load one single-element structure to one lane of one register.
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_lane_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1603,6 +1679,8 @@ pub unsafe fn vld1_dup_f32(ptr: *const f32) -> float32x2_t {
 }
 
 /// Load one single-element structure and Replicate to all lanes (of one register).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -1624,6 +1702,8 @@ pub unsafe fn vld1_dup_p64(ptr: *const p64) -> poly64x1_t {
 }
 
 /// Load one single-element structure and Replicate to all lanes (of one register).
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/vld1q_dup_p64)
 #[inline]
 #[target_feature(enable = "neon,aes")]
 #[cfg_attr(target_arch = "arm", target_feature(enable = "v7"))]
@@ -3733,7 +3813,11 @@ pub unsafe fn vbicq_u64(a: uint64x2_t, b: uint64x2_t) -> uint64x2_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_s8(a: uint8x8_t, b: int8x8_t, c: int8x8_t) -> int8x8_t {
-    simd_select(transmute::<_, int8x8_t>(a), b, c)
+    let not = int8x8_t(-1, -1, -1, -1, -1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3747,7 +3831,11 @@ pub unsafe fn vbsl_s8(a: uint8x8_t, b: int8x8_t, c: int8x8_t) -> int8x8_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_s16(a: uint16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_t {
-    simd_select(transmute::<_, int16x4_t>(a), b, c)
+    let not = int16x4_t(-1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3761,7 +3849,11 @@ pub unsafe fn vbsl_s16(a: uint16x4_t, b: int16x4_t, c: int16x4_t) -> int16x4_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_s32(a: uint32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_t {
-    simd_select(transmute::<_, int32x2_t>(a), b, c)
+    let not = int32x2_t(-1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3775,7 +3867,11 @@ pub unsafe fn vbsl_s32(a: uint32x2_t, b: int32x2_t, c: int32x2_t) -> int32x2_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_s64(a: uint64x1_t, b: int64x1_t, c: int64x1_t) -> int64x1_t {
-    simd_select(transmute::<_, int64x1_t>(a), b, c)
+    let not = int64x1_t(-1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3789,7 +3885,11 @@ pub unsafe fn vbsl_s64(a: uint64x1_t, b: int64x1_t, c: int64x1_t) -> int64x1_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_u8(a: uint8x8_t, b: uint8x8_t, c: uint8x8_t) -> uint8x8_t {
-    simd_select(transmute::<_, int8x8_t>(a), b, c)
+    let not = int8x8_t(-1, -1, -1, -1, -1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3803,7 +3903,11 @@ pub unsafe fn vbsl_u8(a: uint8x8_t, b: uint8x8_t, c: uint8x8_t) -> uint8x8_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_u16(a: uint16x4_t, b: uint16x4_t, c: uint16x4_t) -> uint16x4_t {
-    simd_select(transmute::<_, int16x4_t>(a), b, c)
+    let not = int16x4_t(-1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3817,7 +3921,11 @@ pub unsafe fn vbsl_u16(a: uint16x4_t, b: uint16x4_t, c: uint16x4_t) -> uint16x4_
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_u32(a: uint32x2_t, b: uint32x2_t, c: uint32x2_t) -> uint32x2_t {
-    simd_select(transmute::<_, int32x2_t>(a), b, c)
+    let not = int32x2_t(-1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3831,7 +3939,11 @@ pub unsafe fn vbsl_u32(a: uint32x2_t, b: uint32x2_t, c: uint32x2_t) -> uint32x2_
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_u64(a: uint64x1_t, b: uint64x1_t, c: uint64x1_t) -> uint64x1_t {
-    simd_select(transmute::<_, int64x1_t>(a), b, c)
+    let not = int64x1_t(-1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3845,7 +3957,11 @@ pub unsafe fn vbsl_u64(a: uint64x1_t, b: uint64x1_t, c: uint64x1_t) -> uint64x1_
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_f32(a: uint32x2_t, b: float32x2_t, c: float32x2_t) -> float32x2_t {
-    simd_select(transmute::<_, int32x2_t>(a), b, c)
+    let not = int32x2_t(-1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3859,7 +3975,11 @@ pub unsafe fn vbsl_f32(a: uint32x2_t, b: float32x2_t, c: float32x2_t) -> float32
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_p8(a: uint8x8_t, b: poly8x8_t, c: poly8x8_t) -> poly8x8_t {
-    simd_select(transmute::<_, int8x8_t>(a), b, c)
+    let not = int8x8_t(-1, -1, -1, -1, -1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select.
@@ -3873,7 +3993,11 @@ pub unsafe fn vbsl_p8(a: uint8x8_t, b: poly8x8_t, c: poly8x8_t) -> poly8x8_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbsl_p16(a: uint16x4_t, b: poly16x4_t, c: poly16x4_t) -> poly16x4_t {
-    simd_select(transmute::<_, int16x4_t>(a), b, c)
+    let not = int16x4_t(-1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3887,7 +4011,13 @@ pub unsafe fn vbsl_p16(a: uint16x4_t, b: poly16x4_t, c: poly16x4_t) -> poly16x4_
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_s8(a: uint8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
-    simd_select(transmute::<_, int8x16_t>(a), b, c)
+    let not = int8x16_t(
+        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    );
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3901,7 +4031,11 @@ pub unsafe fn vbslq_s8(a: uint8x16_t, b: int8x16_t, c: int8x16_t) -> int8x16_t {
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_s16(a: uint16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t {
-    simd_select(transmute::<_, int16x8_t>(a), b, c)
+    let not = int16x8_t(-1, -1, -1, -1, -1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3915,7 +4049,11 @@ pub unsafe fn vbslq_s16(a: uint16x8_t, b: int16x8_t, c: int16x8_t) -> int16x8_t
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_s32(a: uint32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t {
-    simd_select(transmute::<_, int32x4_t>(a), b, c)
+    let not = int32x4_t(-1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3929,7 +4067,11 @@ pub unsafe fn vbslq_s32(a: uint32x4_t, b: int32x4_t, c: int32x4_t) -> int32x4_t
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_s64(a: uint64x2_t, b: int64x2_t, c: int64x2_t) -> int64x2_t {
-    simd_select(transmute::<_, int64x2_t>(a), b, c)
+    let not = int64x2_t(-1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3943,7 +4085,13 @@ pub unsafe fn vbslq_s64(a: uint64x2_t, b: int64x2_t, c: int64x2_t) -> int64x2_t
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16_t {
-    simd_select(transmute::<_, int8x16_t>(a), b, c)
+    let not = int8x16_t(
+        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    );
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3957,7 +4105,11 @@ pub unsafe fn vbslq_u8(a: uint8x16_t, b: uint8x16_t, c: uint8x16_t) -> uint8x16_
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x8_t {
-    simd_select(transmute::<_, int16x8_t>(a), b, c)
+    let not = int16x8_t(-1, -1, -1, -1, -1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3971,7 +4123,11 @@ pub unsafe fn vbslq_u16(a: uint16x8_t, b: uint16x8_t, c: uint16x8_t) -> uint16x8
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x4_t {
-    simd_select(transmute::<_, int32x4_t>(a), b, c)
+    let not = int32x4_t(-1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3985,7 +4141,11 @@ pub unsafe fn vbslq_u32(a: uint32x4_t, b: uint32x4_t, c: uint32x4_t) -> uint32x4
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> uint64x2_t {
-    simd_select(transmute::<_, int64x2_t>(a), b, c)
+    let not = int64x2_t(-1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -3999,7 +4159,13 @@ pub unsafe fn vbslq_u64(a: uint64x2_t, b: uint64x2_t, c: uint64x2_t) -> uint64x2
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_p8(a: uint8x16_t, b: poly8x16_t, c: poly8x16_t) -> poly8x16_t {
-    simd_select(transmute::<_, int8x16_t>(a), b, c)
+    let not = int8x16_t(
+        -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    );
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -4013,7 +4179,11 @@ pub unsafe fn vbslq_p8(a: uint8x16_t, b: poly8x16_t, c: poly8x16_t) -> poly8x16_
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_p16(a: uint16x8_t, b: poly16x8_t, c: poly16x8_t) -> poly16x8_t {
-    simd_select(transmute::<_, int16x8_t>(a), b, c)
+    let not = int16x8_t(-1, -1, -1, -1, -1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Bitwise Select. (128-bit)
@@ -4027,7 +4197,11 @@ pub unsafe fn vbslq_p16(a: uint16x8_t, b: poly16x8_t, c: poly16x8_t) -> poly16x8
     stable(feature = "neon_intrinsics", since = "1.59.0")
 )]
 pub unsafe fn vbslq_f32(a: uint32x4_t, b: float32x4_t, c: float32x4_t) -> float32x4_t {
-    simd_select(transmute::<_, int32x4_t>(a), b, c)
+    let not = int32x4_t(-1, -1, -1, -1);
+    transmute(simd_or(
+        simd_and(a, transmute(b)),
+        simd_and(simd_xor(a, transmute(not)), transmute(c)),
+    ))
 }
 
 /// Vector bitwise inclusive OR NOT
@@ -9206,7 +9380,7 @@ mod tests {
 
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_s8() {
-        let a = u8x8::new(u8::MAX, 0, u8::MAX, 0, u8::MAX, 0, u8::MAX, 0);
+        let a = u8x8::new(u8::MAX, 1, u8::MAX, 2, u8::MAX, 0, u8::MAX, 0);
         let b = i8x8::new(
             i8::MAX,
             i8::MAX,
@@ -9229,9 +9403,9 @@ mod tests {
         );
         let e = i8x8::new(
             i8::MAX,
-            i8::MIN,
+            i8::MIN | 1,
             i8::MAX,
-            i8::MIN,
+            i8::MIN | 2,
             i8::MAX,
             i8::MIN,
             i8::MAX,
@@ -9242,34 +9416,34 @@ mod tests {
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_s16() {
-        let a = u16x4::new(u16::MAX, 0, u16::MAX, 0);
+        let a = u16x4::new(u16::MAX, 0, 1, 2);
         let b = i16x4::new(i16::MAX, i16::MAX, i16::MAX, i16::MAX);
         let c = i16x4::new(i16::MIN, i16::MIN, i16::MIN, i16::MIN);
-        let e = i16x4::new(i16::MAX, i16::MIN, i16::MAX, i16::MIN);
+        let e = i16x4::new(i16::MAX, i16::MIN, i16::MIN | 1, i16::MIN | 2);
         let r: i16x4 = transmute(vbsl_s16(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_s32() {
-        let a = u32x2::new(u32::MAX, u32::MIN);
+        let a = u32x2::new(u32::MAX, 1);
         let b = i32x2::new(i32::MAX, i32::MAX);
         let c = i32x2::new(i32::MIN, i32::MIN);
-        let e = i32x2::new(i32::MAX, i32::MIN);
+        let e = i32x2::new(i32::MAX, i32::MIN | 1);
         let r: i32x2 = transmute(vbsl_s32(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_s64() {
-        let a = u64x1::new(u64::MAX);
+        let a = u64x1::new(1);
         let b = i64x1::new(i64::MAX);
         let c = i64x1::new(i64::MIN);
-        let e = i64x1::new(i64::MAX);
+        let e = i64x1::new(i64::MIN | 1);
         let r: i64x1 = transmute(vbsl_s64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_u8() {
-        let a = u8x8::new(u8::MAX, 0, u8::MAX, 0, u8::MAX, 0, u8::MAX, 0);
+        let a = u8x8::new(u8::MAX, 1, u8::MAX, 2, u8::MAX, 0, u8::MAX, 0);
         let b = u8x8::new(
             u8::MAX,
             u8::MAX,
@@ -9290,58 +9464,49 @@ mod tests {
             u8::MIN,
             u8::MIN,
         );
-        let e = u8x8::new(
-            u8::MAX,
-            u8::MIN,
-            u8::MAX,
-            u8::MIN,
-            u8::MAX,
-            u8::MIN,
-            u8::MAX,
-            u8::MIN,
-        );
+        let e = u8x8::new(u8::MAX, 1, u8::MAX, 2, u8::MAX, u8::MIN, u8::MAX, u8::MIN);
         let r: u8x8 = transmute(vbsl_u8(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_u16() {
-        let a = u16x4::new(u16::MAX, 0, u16::MAX, 0);
+        let a = u16x4::new(u16::MAX, 0, 1, 2);
         let b = u16x4::new(u16::MAX, u16::MAX, u16::MAX, u16::MAX);
         let c = u16x4::new(u16::MIN, u16::MIN, u16::MIN, u16::MIN);
-        let e = u16x4::new(u16::MAX, u16::MIN, u16::MAX, u16::MIN);
+        let e = u16x4::new(u16::MAX, 0, 1, 2);
         let r: u16x4 = transmute(vbsl_u16(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_u32() {
-        let a = u32x2::new(u32::MAX, 0);
+        let a = u32x2::new(u32::MAX, 2);
         let b = u32x2::new(u32::MAX, u32::MAX);
         let c = u32x2::new(u32::MIN, u32::MIN);
-        let e = u32x2::new(u32::MAX, u32::MIN);
+        let e = u32x2::new(u32::MAX, 2);
         let r: u32x2 = transmute(vbsl_u32(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_u64() {
-        let a = u64x1::new(u64::MAX);
+        let a = u64x1::new(2);
         let b = u64x1::new(u64::MAX);
         let c = u64x1::new(u64::MIN);
-        let e = u64x1::new(u64::MAX);
+        let e = u64x1::new(2);
         let r: u64x1 = transmute(vbsl_u64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_f32() {
-        let a = u32x2::new(u32::MAX, 0);
-        let b = f32x2::new(f32::MAX, f32::MAX);
-        let c = f32x2::new(f32::MIN, f32::MIN);
-        let e = f32x2::new(f32::MAX, f32::MIN);
+        let a = u32x2::new(1, 0x80000000);
+        let b = f32x2::new(8388609f32, -1.23f32);
+        let c = f32x2::new(2097152f32, 2.34f32);
+        let e = f32x2::new(2097152.25f32, -2.34f32);
         let r: f32x2 = transmute(vbsl_f32(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_p8() {
-        let a = u8x8::new(u8::MAX, 0, u8::MAX, 0, u8::MAX, 0, u8::MAX, 0);
+        let a = u8x8::new(u8::MAX, 1, u8::MAX, 2, u8::MAX, 0, u8::MAX, 0);
         let b = u8x8::new(
             u8::MAX,
             u8::MAX,
@@ -9362,25 +9527,16 @@ mod tests {
             u8::MIN,
             u8::MIN,
         );
-        let e = u8x8::new(
-            u8::MAX,
-            u8::MIN,
-            u8::MAX,
-            u8::MIN,
-            u8::MAX,
-            u8::MIN,
-            u8::MAX,
-            u8::MIN,
-        );
+        let e = u8x8::new(u8::MAX, 1, u8::MAX, 2, u8::MAX, u8::MIN, u8::MAX, u8::MIN);
         let r: u8x8 = transmute(vbsl_p8(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbsl_p16() {
-        let a = u16x4::new(u16::MAX, 0, u16::MAX, 0);
+        let a = u16x4::new(u16::MAX, 0, 1, 2);
         let b = u16x4::new(u16::MAX, u16::MAX, u16::MAX, u16::MAX);
         let c = u16x4::new(u16::MIN, u16::MIN, u16::MIN, u16::MIN);
-        let e = u16x4::new(u16::MAX, u16::MIN, u16::MAX, u16::MIN);
+        let e = u16x4::new(u16::MAX, 0, 1, 2);
         let r: u16x4 = transmute(vbsl_p16(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
@@ -9388,9 +9544,9 @@ mod tests {
     unsafe fn test_vbslq_s8() {
         let a = u8x16::new(
             u8::MAX,
-            0,
+            1,
             u8::MAX,
-            0,
+            2,
             u8::MAX,
             0,
             u8::MAX,
@@ -9442,9 +9598,9 @@ mod tests {
         );
         let e = i8x16::new(
             i8::MAX,
-            i8::MIN,
+            i8::MIN | 1,
             i8::MAX,
-            i8::MIN,
+            i8::MIN | 2,
             i8::MAX,
             i8::MIN,
             i8::MAX,
@@ -9463,7 +9619,7 @@ mod tests {
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_s16() {
-        let a = u16x8::new(u16::MAX, 0, u16::MAX, 0, u16::MAX, 0, u16::MAX, 0);
+        let a = u16x8::new(u16::MAX, 1, u16::MAX, 2, u16::MAX, 0, u16::MAX, 0);
         let b = i16x8::new(
             i16::MAX,
             i16::MAX,
@@ -9486,9 +9642,9 @@ mod tests {
         );
         let e = i16x8::new(
             i16::MAX,
-            i16::MIN,
+            i16::MIN | 1,
             i16::MAX,
-            i16::MIN,
+            i16::MIN | 2,
             i16::MAX,
             i16::MIN,
             i16::MAX,
@@ -9499,19 +9655,19 @@ mod tests {
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_s32() {
-        let a = u32x4::new(u32::MAX, 0, u32::MAX, 0);
+        let a = u32x4::new(u32::MAX, 1, u32::MAX, 2);
         let b = i32x4::new(i32::MAX, i32::MAX, i32::MAX, i32::MAX);
         let c = i32x4::new(i32::MIN, i32::MIN, i32::MIN, i32::MIN);
-        let e = i32x4::new(i32::MAX, i32::MIN, i32::MAX, i32::MIN);
+        let e = i32x4::new(i32::MAX, i32::MIN | 1, i32::MAX, i32::MIN | 2);
         let r: i32x4 = transmute(vbslq_s32(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_s64() {
-        let a = u64x2::new(u64::MAX, 0);
+        let a = u64x2::new(u64::MAX, 1);
         let b = i64x2::new(i64::MAX, i64::MAX);
         let c = i64x2::new(i64::MIN, i64::MIN);
-        let e = i64x2::new(i64::MAX, i64::MIN);
+        let e = i64x2::new(i64::MAX, i64::MIN | 1);
         let r: i64x2 = transmute(vbslq_s64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
@@ -9519,9 +9675,9 @@ mod tests {
     unsafe fn test_vbslq_u8() {
         let a = u8x16::new(
             u8::MAX,
-            0,
+            1,
             u8::MAX,
-            0,
+            2,
             u8::MAX,
             0,
             u8::MAX,
@@ -9573,9 +9729,9 @@ mod tests {
         );
         let e = u8x16::new(
             u8::MAX,
-            u8::MIN,
+            1,
             u8::MAX,
-            u8::MIN,
+            2,
             u8::MAX,
             u8::MIN,
             u8::MAX,
@@ -9594,7 +9750,7 @@ mod tests {
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_u16() {
-        let a = u16x8::new(u16::MAX, 0, u16::MAX, 0, u16::MAX, 0, u16::MAX, 0);
+        let a = u16x8::new(u16::MAX, 1, u16::MAX, 2, u16::MAX, 0, u16::MAX, 0);
         let b = u16x8::new(
             u16::MAX,
             u16::MAX,
@@ -9617,9 +9773,9 @@ mod tests {
         );
         let e = u16x8::new(
             u16::MAX,
-            u16::MIN,
+            1,
             u16::MAX,
-            u16::MIN,
+            2,
             u16::MAX,
             u16::MIN,
             u16::MAX,
@@ -9630,28 +9786,28 @@ mod tests {
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_u32() {
-        let a = u32x4::new(u32::MAX, 0, u32::MAX, 0);
+        let a = u32x4::new(u32::MAX, 1, u32::MAX, 2);
         let b = u32x4::new(u32::MAX, u32::MAX, u32::MAX, u32::MAX);
         let c = u32x4::new(u32::MIN, u32::MIN, u32::MIN, u32::MIN);
-        let e = u32x4::new(u32::MAX, u32::MIN, u32::MAX, u32::MIN);
+        let e = u32x4::new(u32::MAX, 1, u32::MAX, 2);
         let r: u32x4 = transmute(vbslq_u32(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_u64() {
-        let a = u64x2::new(u64::MAX, 0);
+        let a = u64x2::new(u64::MAX, 1);
         let b = u64x2::new(u64::MAX, u64::MAX);
         let c = u64x2::new(u64::MIN, u64::MIN);
-        let e = u64x2::new(u64::MAX, u64::MIN);
+        let e = u64x2::new(u64::MAX, 1);
         let r: u64x2 = transmute(vbslq_u64(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_f32() {
-        let a = u32x4::new(u32::MAX, 0, u32::MAX, 0);
-        let b = f32x4::new(f32::MAX, f32::MAX, f32::MAX, f32::MAX);
-        let c = f32x4::new(f32::MIN, f32::MIN, f32::MIN, f32::MIN);
-        let e = f32x4::new(f32::MAX, f32::MIN, f32::MAX, f32::MIN);
+        let a = u32x4::new(u32::MAX, 0, 1, 0x80000000);
+        let b = f32x4::new(-1.23f32, -1.23f32, 8388609f32, -1.23f32);
+        let c = f32x4::new(2.34f32, 2.34f32, 2097152f32, 2.34f32);
+        let e = f32x4::new(-1.23f32, 2.34f32, 2097152.25f32, -2.34f32);
         let r: f32x4 = transmute(vbslq_f32(transmute(a), transmute(b), transmute(c)));
         assert_eq!(r, e);
     }
@@ -9659,9 +9815,9 @@ mod tests {
     unsafe fn test_vbslq_p8() {
         let a = u8x16::new(
             u8::MAX,
-            0,
+            1,
             u8::MAX,
-            0,
+            2,
             u8::MAX,
             0,
             u8::MAX,
@@ -9713,9 +9869,9 @@ mod tests {
         );
         let e = u8x16::new(
             u8::MAX,
-            u8::MIN,
+            1,
             u8::MAX,
-            u8::MIN,
+            2,
             u8::MAX,
             u8::MIN,
             u8::MAX,
@@ -9734,7 +9890,7 @@ mod tests {
     }
     #[simd_test(enable = "neon")]
     unsafe fn test_vbslq_p16() {
-        let a = u16x8::new(u16::MAX, 0, u16::MAX, 0, u16::MAX, 0, u16::MAX, 0);
+        let a = u16x8::new(u16::MAX, 1, u16::MAX, 2, u16::MAX, 0, u16::MAX, 0);
         let b = u16x8::new(
             u16::MAX,
             u16::MAX,
@@ -9757,9 +9913,9 @@ mod tests {
         );
         let e = u16x8::new(
             u16::MAX,
-            u16::MIN,
+            1,
             u16::MAX,
-            u16::MIN,
+            2,
             u16::MAX,
             u16::MIN,
             u16::MAX,
diff --git a/library/stdarch/crates/core_arch/src/powerpc/altivec.rs b/library/stdarch/crates/core_arch/src/powerpc/altivec.rs
index 8b2be39dc..70344c88b 100644
--- a/library/stdarch/crates/core_arch/src/powerpc/altivec.rs
+++ b/library/stdarch/crates/core_arch/src/powerpc/altivec.rs
@@ -51,6 +51,8 @@ types! {
 
 #[allow(improper_ctypes)]
 extern "C" {
+    #[link_name = "llvm.ppc.altivec.lvx"]
+    fn lvx(p: *const i8) -> vector_unsigned_int;
     #[link_name = "llvm.ppc.altivec.vperm"]
     fn vperm(
         a: vector_signed_int,
@@ -442,8 +444,7 @@ mod sealed {
     #[inline(always)]
     unsafe fn load(off: i32, p: *const i8) -> u32x4 {
         let addr = p.offset(off as isize);
-
-        *(addr as *const u32x4)
+        transmute(lvx(addr))
     }
 
     pub trait VectorLd {
diff --git a/library/stdarch/crates/core_arch/src/x86/avx2.rs b/library/stdarch/crates/core_arch/src/x86/avx2.rs
index 081609ece..24f9c0301 100644
--- a/library/stdarch/crates/core_arch/src/x86/avx2.rs
+++ b/library/stdarch/crates/core_arch/src/x86/avx2.rs
@@ -1195,7 +1195,7 @@ pub unsafe fn _mm_mask_i32gather_epi64<const SCALE: i32>(
 
 /// Returns values from `slice` at offsets determined by `offsets * scale`,
 /// where
-/// `scale` should be 1, 2, 4 and 8.
+/// `scale` should be 1, 2, 4 or 8.
 ///
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_mm256_i32gather_epi64)
 #[inline]
diff --git a/library/stdarch/crates/core_arch/src/x86/avx512bw.rs b/library/stdarch/crates/core_arch/src/x86/avx512bw.rs
index 47d565cea..49d78ed60 100644
--- a/library/stdarch/crates/core_arch/src/x86/avx512bw.rs
+++ b/library/stdarch/crates/core_arch/src/x86/avx512bw.rs
@@ -8545,9 +8545,6 @@ pub unsafe fn _mm_movm_epi8(k: __mmask16) -> __m128i {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kadd_mask32&expand=3207)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(all(test, target_arch = "x86"), assert_instr(add))]
-#[cfg_attr(all(test, target_arch = "x86_64"), assert_instr(lea))] // generate normal lea/add code instead of kaddd
-                                                                  //llvm.x86.avx512.kadd.d
 pub unsafe fn _kadd_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
     transmute(a + b)
 }
@@ -8557,9 +8554,6 @@ pub unsafe fn _kadd_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kadd_mask64&expand=3208)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(all(test, target_arch = "x86"), assert_instr(add))]
-#[cfg_attr(all(test, target_arch = "x86_64"), assert_instr(lea))] // generate normal lea/add code instead of kaddd
-                                                                  //llvm.x86.avx512.kadd.d
 pub unsafe fn _kadd_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
     transmute(a + b)
 }
@@ -8569,7 +8563,6 @@ pub unsafe fn _kadd_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kand_mask32&expand=3213)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(and))] // generate normal and code instead of kandd
 pub unsafe fn _kand_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
     transmute(a & b)
 }
@@ -8579,7 +8572,6 @@ pub unsafe fn _kand_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kand_mask64&expand=3214)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(and))] // generate normal and code instead of kandq
 pub unsafe fn _kand_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
     transmute(a & b)
 }
@@ -8607,7 +8599,6 @@ pub unsafe fn _knot_mask64(a: __mmask64) -> __mmask64 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kandn_mask32&expand=3219)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(not))] // generate normal and code instead of kandnd
 pub unsafe fn _kandn_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
     transmute(_knot_mask32(a) & b)
 }
@@ -8617,7 +8608,6 @@ pub unsafe fn _kandn_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kandn_mask64&expand=3220)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(not))] // generate normal and code instead of kandnq
 pub unsafe fn _kandn_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
     transmute(_knot_mask64(a) & b)
 }
@@ -8627,7 +8617,6 @@ pub unsafe fn _kandn_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kor_mask32&expand=3240)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(or))] // generate normal and code instead of kord
 pub unsafe fn _kor_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
     transmute(a | b)
 }
@@ -8637,7 +8626,6 @@ pub unsafe fn _kor_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kor_mask64&expand=3241)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(or))] // generate normal and code instead of korq
 pub unsafe fn _kor_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
     transmute(a | b)
 }
@@ -8647,7 +8635,6 @@ pub unsafe fn _kor_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kxor_mask32&expand=3292)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(xor))] // generate normal and code instead of kxord
 pub unsafe fn _kxor_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
     transmute(a ^ b)
 }
@@ -8657,7 +8644,6 @@ pub unsafe fn _kxor_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kxor_mask64&expand=3293)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(xor))] // generate normal and code instead of kxorq
 pub unsafe fn _kxor_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
     transmute(a ^ b)
 }
@@ -8667,7 +8653,6 @@ pub unsafe fn _kxor_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kxnor_mask32&expand=3286)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(xor))] // generate normal and code instead of kxnord
 pub unsafe fn _kxnor_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
     transmute(_knot_mask32(a ^ b))
 }
@@ -8677,7 +8662,6 @@ pub unsafe fn _kxnor_mask32(a: __mmask32, b: __mmask32) -> __mmask32 {
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_kxnor_mask64&expand=3287)
 #[inline]
 #[target_feature(enable = "avx512bw")]
-#[cfg_attr(test, assert_instr(xor))] // generate normal and code instead of kxnorq
 pub unsafe fn _kxnor_mask64(a: __mmask64, b: __mmask64) -> __mmask64 {
     transmute(_knot_mask64(a ^ b))
 }
diff --git a/library/stdarch/crates/core_arch/src/x86/avx512gfni.rs b/library/stdarch/crates/core_arch/src/x86/avx512gfni.rs
index d8ac5c29c..66fd1c2e1 100644
--- a/library/stdarch/crates/core_arch/src/x86/avx512gfni.rs
+++ b/library/stdarch/crates/core_arch/src/x86/avx512gfni.rs
@@ -829,21 +829,21 @@ mod tests {
     #[target_feature(enable = "sse2")]
     unsafe fn load_m128i_word<T>(data: &[T], word_index: usize) -> __m128i {
         let byte_offset = word_index * 16 / size_of::<T>();
-        let pointer = data.as_ptr().offset(byte_offset as isize) as *const __m128i;
+        let pointer = data.as_ptr().add(byte_offset) as *const __m128i;
         _mm_loadu_si128(black_box(pointer))
     }
 
     #[target_feature(enable = "avx")]
     unsafe fn load_m256i_word<T>(data: &[T], word_index: usize) -> __m256i {
         let byte_offset = word_index * 32 / size_of::<T>();
-        let pointer = data.as_ptr().offset(byte_offset as isize) as *const __m256i;
+        let pointer = data.as_ptr().add(byte_offset) as *const __m256i;
         _mm256_loadu_si256(black_box(pointer))
     }
 
     #[target_feature(enable = "avx512f")]
     unsafe fn load_m512i_word<T>(data: &[T], word_index: usize) -> __m512i {
         let byte_offset = word_index * 64 / size_of::<T>();
-        let pointer = data.as_ptr().offset(byte_offset as isize) as *const i32;
+        let pointer = data.as_ptr().add(byte_offset) as *const i32;
         _mm512_loadu_si512(black_box(pointer))
     }
 
diff --git a/library/stdarch/crates/core_arch/src/x86/sse.rs b/library/stdarch/crates/core_arch/src/x86/sse.rs
index 2c4295ef6..03c3a14a5 100644
--- a/library/stdarch/crates/core_arch/src/x86/sse.rs
+++ b/library/stdarch/crates/core_arch/src/x86/sse.rs
@@ -1185,9 +1185,9 @@ pub unsafe fn _mm_loadu_ps(p: *const f32) -> __m128 {
 ///
 /// ```text
 /// let a0 = *p;
-/// let a1 = *p.offset(1);
-/// let a2 = *p.offset(2);
-/// let a3 = *p.offset(3);
+/// let a1 = *p.add(1);
+/// let a2 = *p.add(2);
+/// let a3 = *p.add(3);
 /// __m128::new(a3, a2, a1, a0)
 /// ```
 ///
@@ -1241,9 +1241,9 @@ pub unsafe fn _mm_store_ss(p: *mut f32, a: __m128) {
 /// ```text
 /// let x = a.extract(0);
 /// *p = x;
-/// *p.offset(1) = x;
-/// *p.offset(2) = x;
-/// *p.offset(3) = x;
+/// *p.add(1) = x;
+/// *p.add(2) = x;
+/// *p.add(3) = x;
 /// ```
 ///
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_mm_store1_ps)
@@ -1317,9 +1317,9 @@ pub unsafe fn _mm_storeu_ps(p: *mut f32, a: __m128) {
 ///
 /// ```text
 /// *p = a.extract(3);
-/// *p.offset(1) = a.extract(2);
-/// *p.offset(2) = a.extract(1);
-/// *p.offset(3) = a.extract(0);
+/// *p.add(1) = a.extract(2);
+/// *p.add(2) = a.extract(1);
+/// *p.add(3) = a.extract(0);
 /// ```
 ///
 /// [Intel's documentation](https://software.intel.com/sites/landingpage/IntrinsicsGuide/#text=_mm_storer_ps)
@@ -3006,9 +3006,9 @@ mod tests {
 
         let unalignment = (p as usize) & 0xf;
         if unalignment != 0 {
-            let delta = ((16 - unalignment) >> 2) as isize;
+            let delta = (16 - unalignment) >> 2;
             fixup = delta as f32;
-            p = p.offset(delta);
+            p = p.add(delta);
         }
 
         let r = _mm_load_ps(p);
@@ -3019,7 +3019,7 @@ mod tests {
     #[simd_test(enable = "sse")]
     unsafe fn test_mm_loadu_ps() {
         let vals = &[1.0f32, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0];
-        let p = vals.as_ptr().offset(3);
+        let p = vals.as_ptr().add(3);
         let r = _mm_loadu_ps(black_box(p));
         assert_eq_m128(r, _mm_setr_ps(4.0, 5.0, 6.0, 7.0));
     }
@@ -3036,9 +3036,9 @@ mod tests {
 
         let unalignment = (p as usize) & 0xf;
         if unalignment != 0 {
-            let delta = ((16 - unalignment) >> 2) as isize;
+            let delta = (16 - unalignment) >> 2;
             fixup = delta as f32;
-            p = p.offset(delta);
+            p = p.add(delta);
         }
 
         let r = _mm_loadr_ps(p);
@@ -3057,7 +3057,7 @@ mod tests {
     unsafe fn test_mm_store_ss() {
         let mut vals = [0.0f32; 8];
         let a = _mm_setr_ps(1.0, 2.0, 3.0, 4.0);
-        _mm_store_ss(vals.as_mut_ptr().offset(1), a);
+        _mm_store_ss(vals.as_mut_ptr().add(1), a);
 
         assert_eq!(vals[0], 0.0);
         assert_eq!(vals[1], 1.0);
@@ -3152,7 +3152,7 @@ mod tests {
         // Make sure p is **not** aligned to 16-byte boundary
         if (p as usize) & 0xf == 0 {
             ofs = 1;
-            p = p.offset(1);
+            p = p.add(1);
         }
 
         _mm_storeu_ps(p, *black_box(&a));
diff --git a/library/stdarch/crates/core_arch/src/x86/sse2.rs b/library/stdarch/crates/core_arch/src/x86/sse2.rs
index 5a9120042..d82b8641f 100644
--- a/library/stdarch/crates/core_arch/src/x86/sse2.rs
+++ b/library/stdarch/crates/core_arch/src/x86/sse2.rs
@@ -4518,7 +4518,7 @@ mod tests {
         // Make sure p is **not** aligned to 16-byte boundary
         if (p as usize) & 0xf == 0 {
             ofs = 1;
-            p = p.offset(1);
+            p = p.add(1);
         }
 
         _mm_storeu_pd(p, *black_box(&a));
@@ -4606,7 +4606,7 @@ mod tests {
         let mut offset = 0;
         if (d as usize) & 0xf == 0 {
             offset = 1;
-            d = d.offset(offset as isize);
+            d = d.add(offset);
         }
 
         let r = _mm_loadu_pd(d);
diff --git a/library/stdarch/crates/core_arch/src/x86_64/cmpxchg16b.rs b/library/stdarch/crates/core_arch/src/x86_64/cmpxchg16b.rs
index 391daed20..a262932af 100644
--- a/library/stdarch/crates/core_arch/src/x86_64/cmpxchg16b.rs
+++ b/library/stdarch/crates/core_arch/src/x86_64/cmpxchg16b.rs
@@ -34,11 +34,11 @@ use stdarch_test::assert_instr;
 /// support `cmpxchg16b` and the program enters an execution path that
 /// eventually would reach this function the behavior is undefined.
 ///
-/// The `success` ordering must also be stronger or equal to `failure`, or this
-/// function call is undefined. See the `Atomic*` documentation's
-/// `compare_exchange` function for more information. When `compare_exchange`
-/// panics, this is undefined behavior. Currently this function aborts the
-/// process with an undefined instruction.
+/// The failure ordering must be [`Ordering::SeqCst`], [`Ordering::Acquire`] or
+/// [`Ordering::Relaxed`], or this function call is undefined. See the `Atomic*`
+/// documentation's `compare_exchange` function for more information. When
+/// `compare_exchange` panics, this is undefined behavior. Currently this
+/// function aborts the process with an undefined instruction.
 #[inline]
 #[cfg_attr(test, assert_instr(cmpxchg16b, success = Ordering::SeqCst, failure = Ordering::SeqCst))]
 #[target_feature(enable = "cmpxchg16b")]
@@ -54,15 +54,21 @@ pub unsafe fn cmpxchg16b(
     debug_assert!(dst as usize % 16 == 0);
 
     let (val, _ok) = match (success, failure) {
-        (Acquire, Acquire) => intrinsics::atomic_cxchg_acq(dst, old, new),
-        (Release, Relaxed) => intrinsics::atomic_cxchg_rel(dst, old, new),
-        (AcqRel, Acquire) => intrinsics::atomic_cxchg_acqrel(dst, old, new),
-        (Relaxed, Relaxed) => intrinsics::atomic_cxchg_relaxed(dst, old, new),
-        (SeqCst, SeqCst) => intrinsics::atomic_cxchg(dst, old, new),
-        (Acquire, Relaxed) => intrinsics::atomic_cxchg_acq_failrelaxed(dst, old, new),
-        (AcqRel, Relaxed) => intrinsics::atomic_cxchg_acqrel_failrelaxed(dst, old, new),
-        (SeqCst, Relaxed) => intrinsics::atomic_cxchg_failrelaxed(dst, old, new),
-        (SeqCst, Acquire) => intrinsics::atomic_cxchg_failacq(dst, old, new),
+        (Relaxed, Relaxed) => intrinsics::atomic_cxchg_relaxed_relaxed(dst, old, new),
+        (Relaxed, Acquire) => intrinsics::atomic_cxchg_relaxed_acquire(dst, old, new),
+        (Relaxed, SeqCst) => intrinsics::atomic_cxchg_relaxed_seqcst(dst, old, new),
+        (Acquire, Relaxed) => intrinsics::atomic_cxchg_acquire_relaxed(dst, old, new),
+        (Acquire, Acquire) => intrinsics::atomic_cxchg_acquire_acquire(dst, old, new),
+        (Acquire, SeqCst) => intrinsics::atomic_cxchg_acquire_seqcst(dst, old, new),
+        (Release, Relaxed) => intrinsics::atomic_cxchg_release_relaxed(dst, old, new),
+        (Release, Acquire) => intrinsics::atomic_cxchg_release_acquire(dst, old, new),
+        (Release, SeqCst) => intrinsics::atomic_cxchg_release_seqcst(dst, old, new),
+        (AcqRel, Relaxed) => intrinsics::atomic_cxchg_acqrel_relaxed(dst, old, new),
+        (AcqRel, Acquire) => intrinsics::atomic_cxchg_acqrel_acquire(dst, old, new),
+        (AcqRel, SeqCst) => intrinsics::atomic_cxchg_acqrel_seqcst(dst, old, new),
+        (SeqCst, Relaxed) => intrinsics::atomic_cxchg_seqcst_relaxed(dst, old, new),
+        (SeqCst, Acquire) => intrinsics::atomic_cxchg_seqcst_acquire(dst, old, new),
+        (SeqCst, SeqCst) => intrinsics::atomic_cxchg_seqcst_seqcst(dst, old, new),
 
         // The above block is all copied from libcore, and this statement is
         // also copied from libcore except that it's a panic in libcore and we
diff --git a/library/stdarch/crates/intrinsic-test/missing_aarch64.txt b/library/stdarch/crates/intrinsic-test/missing_aarch64.txt
index 56ec274b5..93fc126e5 100644
--- a/library/stdarch/crates/intrinsic-test/missing_aarch64.txt
+++ b/library/stdarch/crates/intrinsic-test/missing_aarch64.txt
@@ -67,20 +67,6 @@ vrnd64xq_f64
 vrnd64z_f64
 vrnd64zq_f64
 
-# Takes too long to compile tests
-vcopyq_laneq_u8
-vcopyq_laneq_s8
-vcopyq_laneq_p8
-vcopyq_lane_u8
-vcopyq_lane_s8
-vcopyq_lane_p8
-vcopy_laneq_u8
-vcopy_laneq_s8
-vcopy_laneq_p8
-vcopy_lane_u8
-vcopy_lane_s8
-vcopy_lane_p8
-
 # QEMU 6.0 doesn't support these instructions
 vmmlaq_s32
 vmmlaq_u32
diff --git a/library/stdarch/crates/intrinsic-test/src/argument.rs b/library/stdarch/crates/intrinsic-test/src/argument.rs
index f4cb77992..798854c03 100644
--- a/library/stdarch/crates/intrinsic-test/src/argument.rs
+++ b/library/stdarch/crates/intrinsic-test/src/argument.rs
@@ -1,6 +1,6 @@
 use std::ops::Range;
 
-use crate::types::IntrinsicType;
+use crate::types::{IntrinsicType, TypeKind};
 use crate::Language;
 
 /// An argument for the intrinsic.
@@ -90,49 +90,108 @@ impl ArgumentList {
             .join(", ")
     }
 
-    /// Creates a line that initializes this argument for C code.
-    /// e.g. `int32x2_t a = { 0x1, 0x2 };`
-    pub fn init_random_values_c(&self, pass: usize) -> String {
+    /// Creates a line for each argument that initializes an array for C from which `loads` argument
+    /// values can be loaded  as a sliding window.
+    /// e.g `const int32x2_t a_vals = {0x3effffff, 0x3effffff, 0x3f7fffff}`, if loads=2.
+    pub fn gen_arglists_c(&self, loads: u32) -> String {
         self.iter()
             .filter_map(|arg| {
                 (!arg.has_constraint()).then(|| {
                     format!(
-                        "{ty} {name} = {{ {values} }};",
-                        ty = arg.to_c_type(),
+                        "const {ty} {name}_vals[] = {{ {values} }};",
+                        ty = arg.ty.c_scalar_type(),
                         name = arg.name,
-                        values = arg.ty.populate_random(pass, &Language::C)
+                        values = arg.ty.populate_random(loads, &Language::C)
                     )
                 })
             })
             .collect::<Vec<_>>()
-            .join("\n    ")
+            .join("\n")
     }
 
-    /// Creates a line that initializes this argument for Rust code.
-    /// e.g. `let a = transmute([0x1, 0x2]);`
-    pub fn init_random_values_rust(&self, pass: usize) -> String {
+    /// Creates a line for each argument that initializes an array for Rust from which `loads` argument
+    /// values can be loaded as a sliding window, e.g `const A_VALS: [u32; 20]  = [...];`
+    pub fn gen_arglists_rust(&self, loads: u32) -> String {
         self.iter()
             .filter_map(|arg| {
                 (!arg.has_constraint()).then(|| {
-                    if arg.is_simd() {
-                        format!(
-                            "let {name} = ::std::mem::transmute([{values}]);",
-                            name = arg.name,
-                            values = arg.ty.populate_random(pass, &Language::Rust),
-                        )
-                    } else {
-                        format!(
-                            "let {name} = {value};",
-                            name = arg.name,
-                            value = arg.ty.populate_random(pass, &Language::Rust)
-                        )
-                    }
+                    format!(
+                        "const {upper_name}_VALS: [{ty}; {load_size}] = unsafe{{ [{values}] }};",
+                        upper_name = arg.name.to_uppercase(),
+                        ty = arg.ty.rust_scalar_type(),
+                        load_size = arg.ty.num_lanes() * arg.ty.num_vectors() + loads - 1,
+                        values = arg.ty.populate_random(loads, &Language::Rust)
+                    )
+                })
+            })
+            .collect::<Vec<_>>()
+            .join("\n")
+    }
+
+    /// Creates a line for each argument that initalizes the argument from an array [arg]_vals at
+    /// an offset i using a load intrinsic, in C.
+    /// e.g `uint8x8_t a = vld1_u8(&a_vals[i]);`
+    pub fn load_values_c(&self, p64_armv7_workaround: bool) -> String {
+        self.iter()
+            .filter_map(|arg| {
+                // The ACLE doesn't support 64-bit polynomial loads on Armv7
+                // This and the cast are a workaround for this
+                let armv7_p64 = if let TypeKind::Poly = arg.ty.kind() {
+                    p64_armv7_workaround
+                } else {
+                    false
+                };
+
+                (!arg.has_constraint()).then(|| {
+                    format!(
+                        "{ty} {name} = {open_cast}{load}(&{name}_vals[i]){close_cast};",
+                        ty = arg.to_c_type(),
+                        name = arg.name,
+                        load = if arg.is_simd() {
+                            arg.ty.get_load_function(p64_armv7_workaround)
+                        } else {
+                            "*".to_string()
+                        },
+                        open_cast = if armv7_p64 {
+                            format!("cast<{}>(", arg.to_c_type())
+                        } else {
+                            "".to_string()
+                        },
+                        close_cast = if armv7_p64 {
+                            ")".to_string()
+                        } else {
+                            "".to_string()
+                        }
+                    )
                 })
             })
             .collect::<Vec<_>>()
             .join("\n        ")
     }
 
+    /// Creates a line for each argument that initalizes the argument from array [ARG]_VALS at
+    /// an offset i using a load intrinsic, in Rust.
+    /// e.g `let a = vld1_u8(A_VALS.as_ptr().offset(i));`
+    pub fn load_values_rust(&self) -> String {
+        self.iter()
+            .filter_map(|arg| {
+                (!arg.has_constraint()).then(|| {
+                    format!(
+                        "let {name} = {load}({upper_name}_VALS.as_ptr().offset(i));",
+                        name = arg.name,
+                        upper_name = arg.name.to_uppercase(),
+                        load = if arg.is_simd() {
+                            arg.ty.get_load_function(false)
+                        } else {
+                            "*".to_string()
+                        },
+                    )
+                })
+            })
+            .collect::<Vec<_>>()
+            .join("\n            ")
+    }
+
     pub fn iter(&self) -> std::slice::Iter<'_, Argument> {
         self.args.iter()
     }
diff --git a/library/stdarch/crates/intrinsic-test/src/intrinsic.rs b/library/stdarch/crates/intrinsic-test/src/intrinsic.rs
index 2b7130440..e0645a36b 100644
--- a/library/stdarch/crates/intrinsic-test/src/intrinsic.rs
+++ b/library/stdarch/crates/intrinsic-test/src/intrinsic.rs
@@ -20,8 +20,9 @@ pub struct Intrinsic {
 
 impl Intrinsic {
     /// Generates a std::cout for the intrinsics results that will match the
-    /// rust debug output format for the return type.
-    pub fn print_result_c(&self, index: usize, additional: &str) -> String {
+    /// rust debug output format for the return type. The generated line assumes
+    /// there is an int i in scope which is the current pass number.
+    pub fn print_result_c(&self, additional: &str) -> String {
         let lanes = if self.results.num_vectors() > 1 {
             (0..self.results.num_vectors())
                 .map(|vector| {
@@ -72,7 +73,7 @@ impl Intrinsic {
         };
 
         format!(
-            r#"std::cout << "Result {additional}-{idx}: {ty}" << std::fixed << std::setprecision(150) <<  {lanes} << "{close}" << std::endl;"#,
+            r#"std::cout << "Result {additional}-" << i+1 << ": {ty}" << std::fixed << std::setprecision(150) <<  {lanes} << "{close}" << std::endl;"#,
             ty = if self.results.is_simd() {
                 format!("{}(", self.results.c_type())
             } else {
@@ -81,11 +82,31 @@ impl Intrinsic {
             close = if self.results.is_simd() { ")" } else { "" },
             lanes = lanes,
             additional = additional,
-            idx = index,
         )
     }
 
-    pub fn generate_pass_rust(&self, index: usize, additional: &str) -> String {
+    pub fn generate_loop_c(
+        &self,
+        additional: &str,
+        passes: u32,
+        p64_armv7_workaround: bool,
+    ) -> String {
+        format!(
+            r#"  {{
+    for (int i=0; i<{passes}; i++) {{
+        {loaded_args}
+        auto __return_value = {intrinsic_call}({args});
+        {print_result}
+    }}
+  }}"#,
+            loaded_args = self.arguments.load_values_c(p64_armv7_workaround),
+            intrinsic_call = self.name,
+            args = self.arguments.as_call_param_c(),
+            print_result = self.print_result_c(additional)
+        )
+    }
+
+    pub fn generate_loop_rust(&self, additional: &str, passes: u32) -> String {
         let constraints = self.arguments.as_constraint_parameters_rust();
         let constraints = if !constraints.is_empty() {
             format!("::<{}>", constraints)
@@ -94,32 +115,20 @@ impl Intrinsic {
         };
 
         format!(
-            r#"
-    unsafe {{
-        {initialized_args}
-        let res = {intrinsic_call}{const}({args});
-        println!("Result {additional}-{idx}: {{:.150?}}", res);
-    }}"#,
-            initialized_args = self.arguments.init_random_values_rust(index),
-            intrinsic_call = self.name,
-            args = self.arguments.as_call_param_rust(),
-            additional = additional,
-            idx = index,
-            const = constraints,
-        )
-    }
-
-    pub fn generate_pass_c(&self, index: usize, additional: &str) -> String {
-        format!(
             r#"  {{
-    {initialized_args}
-    auto __return_value = {intrinsic_call}({args});
-    {print_result}
+    for i in 0..{passes} {{
+        unsafe {{
+            {loaded_args}
+            let __return_value = {intrinsic_call}{const}({args});
+            println!("Result {additional}-{{}}: {{:.150?}}", i+1, __return_value);
+        }}
+    }}
   }}"#,
-            initialized_args = self.arguments.init_random_values_c(index),
+            loaded_args = self.arguments.load_values_rust(),
             intrinsic_call = self.name,
-            args = self.arguments.as_call_param_c(),
-            print_result = self.print_result_c(index, additional)
+            const = constraints,
+            args = self.arguments.as_call_param_rust(),
+            additional = additional,
         )
     }
 }
diff --git a/library/stdarch/crates/intrinsic-test/src/main.rs b/library/stdarch/crates/intrinsic-test/src/main.rs
index 1b58da2fd..43f2df08b 100644
--- a/library/stdarch/crates/intrinsic-test/src/main.rs
+++ b/library/stdarch/crates/intrinsic-test/src/main.rs
@@ -23,13 +23,21 @@ mod intrinsic;
 mod types;
 mod values;
 
+// The number of times each intrinsic will be called.
+const PASSES: u32 = 20;
+
 #[derive(Debug, PartialEq)]
 pub enum Language {
     Rust,
     C,
 }
 
-fn gen_code_c(intrinsic: &Intrinsic, constraints: &[&Argument], name: String) -> String {
+fn gen_code_c(
+    intrinsic: &Intrinsic,
+    constraints: &[&Argument],
+    name: String,
+    p64_armv7_workaround: bool,
+) -> String {
     if let Some((current, constraints)) = constraints.split_last() {
         let range = current
             .constraints
@@ -47,19 +55,25 @@ fn gen_code_c(intrinsic: &Intrinsic, constraints: &[&Argument], name: String) ->
                     name = current.name,
                     ty = current.ty.c_type(),
                     val = i,
-                    pass = gen_code_c(intrinsic, constraints, format!("{}-{}", name, i))
+                    pass = gen_code_c(
+                        intrinsic,
+                        constraints,
+                        format!("{}-{}", name, i),
+                        p64_armv7_workaround
+                    )
                 )
             })
             .collect()
     } else {
-        (1..20)
-            .map(|idx| intrinsic.generate_pass_c(idx, &name))
-            .collect::<Vec<_>>()
-            .join("\n")
+        intrinsic.generate_loop_c(&name, PASSES, p64_armv7_workaround)
     }
 }
 
-fn generate_c_program(header_files: &[&str], intrinsic: &Intrinsic) -> String {
+fn generate_c_program(
+    header_files: &[&str],
+    intrinsic: &Intrinsic,
+    p64_armv7_workaround: bool,
+) -> String {
     let constraints = intrinsic
         .arguments
         .iter()
@@ -75,7 +89,7 @@ fn generate_c_program(header_files: &[&str], intrinsic: &Intrinsic) -> String {
 
 template<typename T1, typename T2> T1 cast(T2 x) {{
   static_assert(sizeof(T1) == sizeof(T2), "sizeof T1 and T2 must be the same");
-  T1 ret = 0;
+  T1 ret{{}};
   memcpy(&ret, &x, sizeof(T1));
   return ret;
 }}
@@ -95,6 +109,8 @@ std::ostream& operator<<(std::ostream& os, poly128_t value) {{
 }}
 #endif
 
+{arglists}
+
 int main(int argc, char **argv) {{
 {passes}
     return 0;
@@ -104,7 +120,13 @@ int main(int argc, char **argv) {{
             .map(|header| format!("#include <{}>", header))
             .collect::<Vec<_>>()
             .join("\n"),
-        passes = gen_code_c(intrinsic, constraints.as_slice(), Default::default()),
+        arglists = intrinsic.arguments.gen_arglists_c(PASSES),
+        passes = gen_code_c(
+            intrinsic,
+            constraints.as_slice(),
+            Default::default(),
+            p64_armv7_workaround
+        ),
     )
 }
 
@@ -131,10 +153,7 @@ fn gen_code_rust(intrinsic: &Intrinsic, constraints: &[&Argument], name: String)
             })
             .collect()
     } else {
-        (1..20)
-            .map(|idx| intrinsic.generate_pass_rust(idx, &name))
-            .collect::<Vec<_>>()
-            .join("\n")
+        intrinsic.generate_loop_rust(&name, PASSES)
     }
 }
 
@@ -153,11 +172,14 @@ fn generate_rust_program(intrinsic: &Intrinsic, a32: bool) -> String {
 #![allow(non_upper_case_globals)]
 use core_arch::arch::{target_arch}::*;
 
+{arglists}
+
 fn main() {{
 {passes}
 }}
 "#,
         target_arch = if a32 { "arm" } else { "aarch64" },
+        arglists = intrinsic.arguments.gen_arglists_rust(PASSES),
         passes = gen_code_rust(intrinsic, &constraints, Default::default())
     )
 }
@@ -203,7 +225,7 @@ fn build_c(intrinsics: &Vec<Intrinsic>, compiler: &str, a32: bool) -> bool {
             let c_filename = format!(r#"c_programs/{}.cpp"#, i.name);
             let mut file = File::create(&c_filename).unwrap();
 
-            let c_code = generate_c_program(&["arm_neon.h", "arm_acle.h"], &i);
+            let c_code = generate_c_program(&["arm_neon.h", "arm_acle.h"], &i, a32);
             file.write_all(c_code.into_bytes().as_slice()).unwrap();
             compile_c(&c_filename, &i, compiler, a32)
         })
@@ -259,7 +281,7 @@ path = "{intrinsic}/main.rs""#,
         .current_dir("rust_programs")
         .arg("-c")
         .arg(format!(
-            "cargo {toolchain} build --target {target}",
+            "cargo {toolchain} build --target {target} --release",
             toolchain = toolchain,
             target = if a32 {
                 "armv7-unknown-linux-gnueabihf"
@@ -407,7 +429,7 @@ fn compare_outputs(intrinsics: &Vec<Intrinsic>, toolchain: &str, runner: &str, a
                 .current_dir("rust_programs")
                 .arg("-c")
                 .arg(format!(
-                    "cargo {toolchain} run --target {target} --bin {intrinsic}",
+                    "cargo {toolchain} run --target {target} --bin {intrinsic} --release",
                     intrinsic = intrinsic.name,
                     toolchain = toolchain,
                     target = if a32 {
diff --git a/library/stdarch/crates/intrinsic-test/src/types.rs b/library/stdarch/crates/intrinsic-test/src/types.rs
index e51e61649..dd23586e7 100644
--- a/library/stdarch/crates/intrinsic-test/src/types.rs
+++ b/library/stdarch/crates/intrinsic-test/src/types.rs
@@ -1,7 +1,7 @@
 use std::fmt;
 use std::str::FromStr;
 
-use crate::values::values_for_pass;
+use crate::values::value_for_array;
 use crate::Language;
 
 #[derive(Debug, PartialEq, Copy, Clone)]
@@ -160,8 +160,7 @@ impl IntrinsicType {
         }
     }
 
-    #[allow(unused)]
-    fn c_scalar_type(&self) -> String {
+    pub fn c_scalar_type(&self) -> String {
         format!(
             "{prefix}{bits}_t",
             prefix = self.kind().c_prefix(),
@@ -169,7 +168,7 @@ impl IntrinsicType {
         )
     }
 
-    fn rust_scalar_type(&self) -> String {
+    pub fn rust_scalar_type(&self) -> String {
         format!(
             "{prefix}{bits}",
             prefix = self.kind().rust_prefix(),
@@ -289,18 +288,19 @@ impl IntrinsicType {
         }
     }
 
-    /// Generates a comma list of values that can be used to initialize an
-    /// argument for the intrinsic call.
+    /// Generates a comma list of values that can be used to initialize the array that
+    /// an argument for the intrinsic call is loaded from.
     /// This is determistic based on the pass number.
     ///
-    /// * `pass`: The pass index, i.e. the iteration index for the call to an intrinsic
+    /// * `loads`: The number of values that need to be loaded from the argument array
+    /// * e.g for argument type uint32x2, loads=2 results in a string representing 4 32-bit values
     ///
     /// Returns a string such as
     /// * `0x1, 0x7F, 0xFF` if `language` is `Language::C`
     /// * `0x1 as _, 0x7F as _, 0xFF as _` if `language` is `Language::Rust`
-    pub fn populate_random(&self, pass: usize, language: &Language) -> String {
+    pub fn populate_random(&self, loads: u32, language: &Language) -> String {
         match self {
-            IntrinsicType::Ptr { child, .. } => child.populate_random(pass, language),
+            IntrinsicType::Ptr { child, .. } => child.populate_random(loads, language),
             IntrinsicType::Type {
                 bit_len: Some(bit_len),
                 kind,
@@ -308,11 +308,11 @@ impl IntrinsicType {
                 vec_len,
                 ..
             } if kind == &TypeKind::Int || kind == &TypeKind::UInt || kind == &TypeKind::Poly => (0
-                ..(simd_len.unwrap_or(1) * vec_len.unwrap_or(1)))
+                ..(simd_len.unwrap_or(1) * vec_len.unwrap_or(1) + loads - 1))
                 .map(|i| {
                     format!(
                         "{}{}",
-                        values_for_pass(*bit_len, i, pass),
+                        value_for_array(*bit_len, i),
                         match language {
                             &Language::Rust => format!(" as {ty} ", ty = self.rust_scalar_type()),
                             &Language::C => String::from(""),
@@ -327,15 +327,15 @@ impl IntrinsicType {
                 simd_len,
                 vec_len,
                 ..
-            } => (0..(simd_len.unwrap_or(1) * vec_len.unwrap_or(1)))
+            } => (0..(simd_len.unwrap_or(1) * vec_len.unwrap_or(1) + loads - 1))
                 .map(|i| {
                     format!(
                         "{}({})",
                         match language {
-                            &Language::Rust => "f32::from_bits",
+                            &Language::Rust => "std::mem::transmute",
                             &Language::C => "cast<float, uint32_t>",
                         },
-                        values_for_pass(32, i, pass),
+                        value_for_array(32, i),
                     )
                 })
                 .collect::<Vec<_>>()
@@ -346,15 +346,15 @@ impl IntrinsicType {
                 simd_len,
                 vec_len,
                 ..
-            } => (0..(simd_len.unwrap_or(1) * vec_len.unwrap_or(1)))
+            } => (0..(simd_len.unwrap_or(1) * vec_len.unwrap_or(1) + loads - 1))
                 .map(|i| {
                     format!(
                         "{}({}{})",
                         match language {
-                            &Language::Rust => "f64::from_bits",
+                            &Language::Rust => "std::mem::transmute",
                             &Language::C => "cast<double, uint64_t>",
                         },
-                        values_for_pass(64, i, pass),
+                        value_for_array(64, i),
                         match language {
                             &Language::Rust => " as u64",
                             &Language::C => "",
@@ -368,10 +368,9 @@ impl IntrinsicType {
     }
 
     /// Determines the load function for this type.
-    #[allow(unused)]
-    pub fn get_load_function(&self) -> String {
+    pub fn get_load_function(&self, armv7_p64_workaround: bool) -> String {
         match self {
-            IntrinsicType::Ptr { child, .. } => child.get_load_function(),
+            IntrinsicType::Ptr { child, .. } => child.get_load_function(armv7_p64_workaround),
             IntrinsicType::Type {
                 kind: k,
                 bit_len: Some(bl),
@@ -379,7 +378,7 @@ impl IntrinsicType {
                 vec_len,
                 ..
             } => {
-                let quad = if (simd_len.unwrap_or(1) * bl) > 64 {
+                let quad = if simd_len.unwrap_or(1) * bl > 64 {
                     "q"
                 } else {
                     ""
@@ -390,7 +389,8 @@ impl IntrinsicType {
                         TypeKind::UInt => "u",
                         TypeKind::Int => "s",
                         TypeKind::Float => "f",
-                        TypeKind::Poly => "p",
+                        // The ACLE doesn't support 64-bit polynomial loads on Armv7
+                        TypeKind::Poly => if armv7_p64_workaround && *bl == 64 {"s"} else {"p"},
                         x => todo!("get_load_function TypeKind: {:#?}", x),
                     },
                     size = bl,
diff --git a/library/stdarch/crates/intrinsic-test/src/values.rs b/library/stdarch/crates/intrinsic-test/src/values.rs
index 4565edca0..64b4d9fc9 100644
--- a/library/stdarch/crates/intrinsic-test/src/values.rs
+++ b/library/stdarch/crates/intrinsic-test/src/values.rs
@@ -1,9 +1,8 @@
-/// Gets a hex constant value for a single lane in in a determistic way
+/// Gets a hex constant value for a single value in the argument values array in a determistic way
 /// * `bits`: The number of bits for the type, only 8, 16, 32, 64 are valid values
-/// * `simd`: The index of the simd lane we are generating for
-/// * `pass`: The index of the pass we are generating the values for
-pub fn values_for_pass(bits: u32, simd: u32, pass: usize) -> String {
-    let index = pass + (simd as usize);
+/// * `index`: The position in the array we are generating for
+pub fn value_for_array(bits: u32, index: u32) -> String {
+    let index = index as usize;
 
     if bits == 8 {
         format!("{:#X}", VALUES_8[index % VALUES_8.len()])
diff --git a/library/stdarch/crates/std_detect/src/detect/arch/aarch64.rs b/library/stdarch/crates/std_detect/src/detect/arch/aarch64.rs
index f32f961ae..5f46c7696 100644
--- a/library/stdarch/crates/std_detect/src/detect/arch/aarch64.rs
+++ b/library/stdarch/crates/std_detect/src/detect/arch/aarch64.rs
@@ -72,7 +72,8 @@ features! {
     @FEATURE: #[stable(feature = "simd_aarch64", since = "1.60.0")] pmull: "pmull";
     /// FEAT_PMULL (Polynomial Multiply)
     @FEATURE: #[stable(feature = "simd_aarch64", since = "1.60.0")] fp: "fp";
-    /// FEAT_FP (Floating point support)
+    implied by target_features: ["neon"];
+    /// FEAT_FP (Floating point support) - Implied by `neon` target_feature
     @FEATURE: #[stable(feature = "simd_aarch64", since = "1.60.0")] fp16: "fp16";
     /// FEAT_FP16 (Half-float support)
     @FEATURE: #[stable(feature = "simd_aarch64", since = "1.60.0")] sve: "sve";
diff --git a/library/stdarch/crates/std_detect/src/detect/macros.rs b/library/stdarch/crates/std_detect/src/detect/macros.rs
index 7548c9780..a467f9db6 100644
--- a/library/stdarch/crates/std_detect/src/detect/macros.rs
+++ b/library/stdarch/crates/std_detect/src/detect/macros.rs
@@ -1,3 +1,15 @@
+#[macro_export]
+#[allow_internal_unstable(stdsimd)]
+macro_rules! detect_feature {
+    ($feature:tt, $feature_lit:tt) => {
+        $crate::detect_feature!($feature, $feature_lit : $feature_lit)
+    };
+    ($feature:tt, $feature_lit:tt : $($target_feature_lit:tt),*) => {
+        $(cfg!(target_feature = $target_feature_lit) ||)*
+            $crate::detect::__is_feature_detected::$feature()
+    };
+}
+
 #[allow(unused)]
 macro_rules! features {
     (
@@ -7,7 +19,9 @@ macro_rules! features {
       @MACRO_ATTRS: $(#[$macro_attrs:meta])*
       $(@BIND_FEATURE_NAME: $bind_feature:tt; $feature_impl:tt; )*
       $(@NO_RUNTIME_DETECTION: $nort_feature:tt; )*
-      $(@FEATURE: #[$stability_attr:meta] $feature:ident: $feature_lit:tt; $(#[$feature_comment:meta])*)*
+      $(@FEATURE: #[$stability_attr:meta] $feature:ident: $feature_lit:tt;
+          $(implied by target_features: [$($target_feature_lit:tt),*];)?
+          $(#[$feature_comment:meta])*)*
     ) => {
         #[macro_export]
         $(#[$macro_attrs])*
@@ -17,12 +31,11 @@ macro_rules! features {
         macro_rules! $macro_name {
             $(
                 ($feature_lit) => {
-                    cfg!(target_feature = $feature_lit) ||
-                        $crate::detect::__is_feature_detected::$feature()
+                    $crate::detect_feature!($feature, $feature_lit $(: $($target_feature_lit),*)?)
                 };
             )*
             $(
-                ($bind_feature) => { $macro_name!($feature_impl) };
+                ($bind_feature) => { $crate::$macro_name!($feature_impl) };
             )*
             $(
                 ($nort_feature) => {
@@ -35,7 +48,7 @@ macro_rules! features {
                 };
             )*
             ($t:tt,) => {
-                    $macro_name!($t);
+                    $crate::$macro_name!($t);
             };
             ($t:tt) => {
                 compile_error!(
@@ -66,7 +79,7 @@ macro_rules! features {
                 };
             )*
             $(
-                ($bind_feature) => { $macro_name!($feature_impl) };
+                ($bind_feature) => { $crate::$macro_name!($feature_impl) };
             )*
             $(
                 ($nort_feature) => {
@@ -79,7 +92,7 @@ macro_rules! features {
                 };
             )*
             ($t:tt,) => {
-                    $macro_name!($t);
+                    $crate::$macro_name!($t);
             };
             ($t:tt) => {
                 compile_error!(
diff --git a/library/stdarch/crates/stdarch-gen/neon.spec b/library/stdarch/crates/stdarch-gen/neon.spec
index 68a50fbe9..95fbc354c 100644
--- a/library/stdarch/crates/stdarch-gen/neon.spec
+++ b/library/stdarch/crates/stdarch-gen/neon.spec
@@ -1570,10 +1570,10 @@ name = vext
 constn = N
 multi_fn = static_assert_imm-out_exp_len-N
 multi_fn = matchn-out_exp_len-N, simd_shuffle-out_len-!, a, b, {asc-n-out_len}
-a = 0, 8, 8, 9, 8, 9, 9, 11, 8, 9, 9, 11, 9, 11, 14, 15
-b = 9, 11, 14, 15, 16, 17, 18, 19, 0, 8, 8, 9, 8, 9, 9, 11
-n = HFLEN
-validate 8, 9, 9, 11, 9, 11, 14, 15, 9, 11, 14, 15, 16, 17, 18, 19
+a = 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
+b = 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
+n = LEN_M1
+validate 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
 
 arm = "vext.8"
 aarch64 = ext
@@ -1584,10 +1584,10 @@ name = vext
 constn = N
 multi_fn = static_assert_imm-out_exp_len-N
 multi_fn = matchn-out_exp_len-N, simd_shuffle-out_len-!, a, b, {asc-n-out_len}
-a = 0, 8, 8, 9, 8, 9, 9, 11, 8, 9, 9, 11, 9, 11, 14, 15
-b = 9, 11, 14, 15, 16, 17, 18, 19, 0, 8, 8, 9, 8, 9, 9, 11
-n = HFLEN
-validate 8, 9, 9, 11, 9, 11, 14, 15, 9, 11, 14, 15, 16, 17, 18, 19
+a = 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
+b = 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
+n = LEN_M1
+validate 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2
 
 aarch64 = ext
 generate poly64x2_t
@@ -1600,10 +1600,10 @@ name = vext
 constn = N
 multi_fn = static_assert_imm-out_exp_len-N
 multi_fn = matchn-out_exp_len-N, simd_shuffle-out_len-!, a, b, {asc-n-out_len}
-a = 0., 2., 2., 3.
-b = 3., 4., 5., 6.,
-n = HFLEN
-validate 2., 3., 3., 4.
+a = 1., 1., 1., 1.
+b = 2., 2., 2., 2.,
+n = LEN_M1
+validate 1., 2., 2., 2.
 
 aarch64 = ext
 generate float64x2_t
diff --git a/library/stdarch/crates/stdarch-gen/src/main.rs b/library/stdarch/crates/stdarch-gen/src/main.rs
index a2ae250a7..d2f865753 100644
--- a/library/stdarch/crates/stdarch-gen/src/main.rs
+++ b/library/stdarch/crates/stdarch-gen/src/main.rs
@@ -856,6 +856,40 @@ fn type_len_str(t: &str) -> &'static str {
     }
 }
 
+fn type_len_minus_one_str(t: &str) -> &'static str {
+    match t {
+        "int8x8_t" => "7",
+        "int8x16_t" => "15",
+        "int16x4_t" => "3",
+        "int16x8_t" => "7",
+        "int32x2_t" => "1",
+        "int32x4_t" => "3",
+        "int64x1_t" => "0",
+        "int64x2_t" => "1",
+        "uint8x8_t" => "7",
+        "uint8x16_t" => "15",
+        "uint16x4_t" => "3",
+        "uint16x8_t" => "7",
+        "uint32x2_t" => "1",
+        "uint32x4_t" => "3",
+        "uint64x1_t" => "0",
+        "uint64x2_t" => "1",
+        "float16x4_t" => "3",
+        "float16x8_t" => "7",
+        "float32x2_t" => "1",
+        "float32x4_t" => "3",
+        "float64x1_t" => "0",
+        "float64x2_t" => "1",
+        "poly8x8_t" => "7",
+        "poly8x16_t" => "15",
+        "poly16x4_t" => "3",
+        "poly16x8_t" => "7",
+        "poly64x1_t" => "0",
+        "poly64x2_t" => "1",
+        _ => panic!("unknown type: {}", t),
+    }
+}
+
 fn type_half_len_str(t: &str) -> &'static str {
     match t {
         "int8x8_t" => "4",
@@ -901,6 +935,7 @@ fn map_val<'v>(t: &str, v: &'v str) -> &'v str {
         "BITS_M1" => bits_minus_one(t),
         "HFBITS" => half_bits(t),
         "LEN" => type_len_str(t),
+        "LEN_M1" => type_len_minus_one_str(t),
         "HFLEN" => type_half_len_str(t),
         o => o,
     }
@@ -971,6 +1006,15 @@ fn is_vstx(name: &str) -> bool {
         && (s[1].starts_with("s") || s[1].starts_with("f"))
 }
 
+fn create_doc_string(comment_string: &str, fn_name: &str) -> String {
+    format!(
+        r#"{}
+///
+/// [Arm's documentation](https://developer.arm.com/architectures/instruction-sets/intrinsics/{})"#,
+        comment_string, fn_name
+    )
+}
+
 #[allow(clippy::too_many_arguments)]
 fn gen_aarch64(
     current_comment: &str,
@@ -1374,6 +1418,7 @@ fn gen_aarch64(
         RDM => String::from("\n#[stable(feature = \"rdm_intrinsics\", since = \"1.62.0\")]"),
         _ => String::new(),
     };
+    let function_doc = create_doc_string(current_comment, &name);
     let function = format!(
         r#"
 {}
@@ -1384,7 +1429,7 @@ fn gen_aarch64(
     {}
 }}
 "#,
-        current_comment,
+        function_doc,
         current_target,
         current_aarch64,
         const_assert,
@@ -2342,6 +2387,7 @@ fn gen_arm(
             RDM => String::from("\n#[stable(feature = \"rdm_intrinsics\", since = \"1.62.0\")]"),
             _ => String::new(),
         };
+        let function_doc = create_doc_string(current_comment, &name);
         format!(
             r#"
 {}
@@ -2358,13 +2404,13 @@ fn gen_arm(
 #[cfg_attr(test, assert_instr({}{}))]{}{}
 {}
 "#,
-            current_comment,
+            function_doc,
             current_target_arm,
             expand_intrinsic(&current_arm, in_t[1]),
             const_assert,
             const_legacy,
             call_arm,
-            current_comment,
+            function_doc,
             current_target_aarch64,
             expand_intrinsic(&current_aarch64, in_t[1]),
             const_assert,
@@ -2410,6 +2456,7 @@ fn gen_arm(
             RDM => String::from("\n#[cfg_attr(target_arch = \"aarch64\", stable(feature = \"rdm_intrinsics\", since = \"1.62.0\"))]"),
             _ => String::new(),
         };
+        let function_doc = create_doc_string(current_comment, &name);
         format!(
             r#"
 {}
@@ -2420,7 +2467,7 @@ fn gen_arm(
 #[cfg_attr(all(test, target_arch = "aarch64"), assert_instr({}{}))]{}{}
 {}
 "#,
-            current_comment,
+            function_doc,
             current_target_aarch64,
             current_target_arm,
             expand_intrinsic(&current_arm, in_t[1]),
diff --git a/library/stdarch/examples/hex.rs b/library/stdarch/examples/hex.rs
index 812836d66..d982a71b9 100644
--- a/library/stdarch/examples/hex.rs
+++ b/library/stdarch/examples/hex.rs
@@ -76,7 +76,7 @@ unsafe fn hex_encode_avx2<'a>(mut src: &[u8], dst: &'a mut [u8]) -> Result<&'a s
     let ascii_a = _mm256_set1_epi8((b'a' - 9 - 1) as i8);
     let and4bits = _mm256_set1_epi8(0xf);
 
-    let mut i = 0_isize;
+    let mut i = 0_usize;
     while src.len() >= 32 {
         let invec = _mm256_loadu_si256(src.as_ptr() as *const _);
 
@@ -96,18 +96,17 @@ unsafe fn hex_encode_avx2<'a>(mut src: &[u8], dst: &'a mut [u8]) -> Result<&'a s
         let res2 = _mm256_unpackhi_epi8(masked2, masked1);
 
         // Store everything into the right destination now
-        let base = dst.as_mut_ptr().offset(i * 2);
-        let base1 = base.offset(0) as *mut _;
-        let base2 = base.offset(16) as *mut _;
-        let base3 = base.offset(32) as *mut _;
-        let base4 = base.offset(48) as *mut _;
+        let base = dst.as_mut_ptr().add(i * 2);
+        let base1 = base.add(0) as *mut _;
+        let base2 = base.add(16) as *mut _;
+        let base3 = base.add(32) as *mut _;
+        let base4 = base.add(48) as *mut _;
         _mm256_storeu2_m128i(base3, base1, res1);
         _mm256_storeu2_m128i(base4, base2, res2);
         src = &src[32..];
         i += 32;
     }
 
-    let i = i as usize;
     let _ = hex_encode_sse41(src, &mut dst[i * 2..]);
 
     Ok(str::from_utf8_unchecked(&dst[..src.len() * 2 + i * 2]))
@@ -122,7 +121,7 @@ unsafe fn hex_encode_sse41<'a>(mut src: &[u8], dst: &'a mut [u8]) -> Result<&'a
     let ascii_a = _mm_set1_epi8((b'a' - 9 - 1) as i8);
     let and4bits = _mm_set1_epi8(0xf);
 
-    let mut i = 0_isize;
+    let mut i = 0_usize;
     while src.len() >= 16 {
         let invec = _mm_loadu_si128(src.as_ptr() as *const _);
 
@@ -141,13 +140,12 @@ unsafe fn hex_encode_sse41<'a>(mut src: &[u8], dst: &'a mut [u8]) -> Result<&'a
         let res1 = _mm_unpacklo_epi8(masked2, masked1);
         let res2 = _mm_unpackhi_epi8(masked2, masked1);
 
-        _mm_storeu_si128(dst.as_mut_ptr().offset(i * 2) as *mut _, res1);
-        _mm_storeu_si128(dst.as_mut_ptr().offset(i * 2 + 16) as *mut _, res2);
+        _mm_storeu_si128(dst.as_mut_ptr().add(i * 2) as *mut _, res1);
+        _mm_storeu_si128(dst.as_mut_ptr().add(i * 2 + 16) as *mut _, res2);
         src = &src[16..];
         i += 16;
     }
 
-    let i = i as usize;
     let _ = hex_encode_fallback(src, &mut dst[i * 2..]);
 
     Ok(str::from_utf8_unchecked(&dst[..src.len() * 2 + i * 2]))
@@ -163,7 +161,7 @@ unsafe fn hex_encode_simd128<'a>(mut src: &[u8], dst: &'a mut [u8]) -> Result<&'
     let ascii_a = u8x16_splat(b'a' - 9 - 1);
     let and4bits = u8x16_splat(0xf);
 
-    let mut i = 0_isize;
+    let mut i = 0_usize;
     while src.len() >= 16 {
         let invec = v128_load(src.as_ptr() as *const _);
 
@@ -189,13 +187,12 @@ unsafe fn hex_encode_simd128<'a>(mut src: &[u8], dst: &'a mut [u8]) -> Result<&'
             masked2, masked1,
         );
 
-        v128_store(dst.as_mut_ptr().offset(i * 2) as *mut _, res1);
-        v128_store(dst.as_mut_ptr().offset(i * 2 + 16) as *mut _, res2);
+        v128_store(dst.as_mut_ptr().add(i * 2) as *mut _, res1);
+        v128_store(dst.as_mut_ptr().add(i * 2 + 16) as *mut _, res2);
         src = &src[16..];
         i += 16;
     }
 
-    let i = i as usize;
     let _ = hex_encode_fallback(src, &mut dst[i * 2..]);
 
     Ok(str::from_utf8_unchecked(&dst[..src.len() * 2 + i * 2]))