From 76cb841cb886eef6b3bee341a2266c76578724ad Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Mon, 6 May 2024 03:02:30 +0200 Subject: Adding upstream version 4.19.249. Signed-off-by: Daniel Baumann --- arch/arm/lib/xor-neon.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100644 arch/arm/lib/xor-neon.c (limited to 'arch/arm/lib/xor-neon.c') diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c new file mode 100644 index 000000000..c691b9010 --- /dev/null +++ b/arch/arm/lib/xor-neon.c @@ -0,0 +1,46 @@ +/* + * linux/arch/arm/lib/xor-neon.c + * + * Copyright (C) 2013 Linaro Ltd + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +MODULE_LICENSE("GPL"); + +#ifndef __ARM_NEON__ +#error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon' +#endif + +/* + * Pull in the reference implementations while instructing GCC (through + * -ftree-vectorize) to attempt to exploit implicit parallelism and emit + * NEON instructions. + */ +#if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 6) +#pragma GCC optimize "tree-vectorize" +#else +/* + * While older versions of GCC do not generate incorrect code, they fail to + * recognize the parallel nature of these functions, and emit plain ARM code, + * which is known to be slower than the optimized ARM code in asm-arm/xor.h. + */ +#warning This code requires at least version 4.6 of GCC +#endif + +#pragma GCC diagnostic ignored "-Wunused-variable" +#include + +struct xor_block_template const xor_block_neon_inner = { + .name = "__inner_neon__", + .do_2 = xor_8regs_2, + .do_3 = xor_8regs_3, + .do_4 = xor_8regs_4, + .do_5 = xor_8regs_5, +}; +EXPORT_SYMBOL(xor_block_neon_inner); -- cgit v1.2.3