1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
/* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy,
* modify, merge, publish, distribute, sublicense, and/or sell copies
* of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
* Copyright:
* 2021 Atharva Nimbalkar <atharvakn@gmail.com>
*/
#if !defined(SIMDE_ARM_NEON_CMLA_H)
#define SIMDE_ARM_NEON_CMLA_H
#include "types.h"
HEDLEY_DIAGNOSTIC_PUSH
SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
SIMDE_BEGIN_DECLS_
SIMDE_FUNCTION_ATTRIBUTES
simde_float32x2_t
simde_vcmla_f32(simde_float32x2_t r, simde_float32x2_t a, simde_float32x2_t b) {
#if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && SIMDE_ARCH_ARM_CHECK(8,3) && \
(!defined(HEDLEY_GCC_VERSION) || HEDLEY_GCC_VERSION_CHECK(9,0,0)) && \
(!defined(__clang__) || SIMDE_DETECT_CLANG_VERSION_CHECK(12,0,0))
return vcmla_f32(r, a, b);
#else
simde_float32x2_private
r_ = simde_float32x2_to_private(r),
a_ = simde_float32x2_to_private(a),
b_ = simde_float32x2_to_private(b);
#if defined(SIMDE_SHUFFLE_VECTOR_)
a_.values = SIMDE_SHUFFLE_VECTOR_(32, 8, a_.values, a_.values, 0, 0);
r_.values += b_.values * a_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] += b_.values[i] * a_.values[i & 2];
}
#endif
return simde_float32x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#undef vcmla_f32
#define vcmla_f32(r, a, b) simde_vcmla_f32(r, a, b)
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_float32x4_t
simde_vcmlaq_f32(simde_float32x4_t r, simde_float32x4_t a, simde_float32x4_t b) {
#if defined(SIMDE_ARM_NEON_A32V8_NATIVE) && SIMDE_ARCH_ARM_CHECK(8,3) && \
(!defined(HEDLEY_GCC_VERSION) || HEDLEY_GCC_VERSION_CHECK(9,0,0)) && \
(!defined(__clang__) || SIMDE_DETECT_CLANG_VERSION_CHECK(12,0,0))
return vcmlaq_f32(r, a, b);
#else
simde_float32x4_private
r_ = simde_float32x4_to_private(r),
a_ = simde_float32x4_to_private(a),
b_ = simde_float32x4_to_private(b);
#if defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_f32x4_add(r_.v128, wasm_f32x4_mul(b_.v128, wasm_i32x4_shuffle(a_.v128, a_.v128, 0, 0, 2, 2)));
#elif defined(SIMDE_SHUFFLE_VECTOR_)
a_.values = SIMDE_SHUFFLE_VECTOR_(32, 16, a_.values, a_.values, 0, 0, 2, 2);
r_.values += b_.values * a_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] += b_.values[i] * a_.values[i & 2];
}
#endif
return simde_float32x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#undef vcmlaq_f32
#define vcmlaq_f32(r, a, b) simde_vcmlaq_f32(r, a, b)
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_float64x2_t
simde_vcmlaq_f64(simde_float64x2_t r, simde_float64x2_t a, simde_float64x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE) && SIMDE_ARCH_ARM_CHECK(8,3) && \
(!defined(HEDLEY_GCC_VERSION) || HEDLEY_GCC_VERSION_CHECK(9,0,0)) && \
(!defined(__clang__) || SIMDE_DETECT_CLANG_VERSION_CHECK(12,0,0))
return vcmlaq_f64(r, a, b);
#else
simde_float64x2_private
r_ = simde_float64x2_to_private(r),
a_ = simde_float64x2_to_private(a),
b_ = simde_float64x2_to_private(b);
#if defined(SIMDE_WASM_SIMD128_NATIVE)
r_.v128 = wasm_f64x2_add(r_.v128, wasm_f64x2_mul(b_.v128, wasm_i64x2_shuffle(a_.v128, a_.v128, 0, 0)));
#elif defined(SIMDE_SHUFFLE_VECTOR_)
a_.values = SIMDE_SHUFFLE_VECTOR_(64, 16, a_.values, a_.values, 0, 0);
r_.values += b_.values * a_.values;
#else
SIMDE_VECTORIZE
for (size_t i = 0 ; i < (sizeof(r_.values) / sizeof(r_.values[0])) ; i++) {
r_.values[i] += b_.values[i] * a_.values[i & 2];
}
#endif
return simde_float64x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A32V8_ENABLE_NATIVE_ALIASES)
#undef vcmlaq_f64
#define vcmlaq_f64(r, a, b) simde_vcmlaq_f64(r, a, b)
#endif
SIMDE_END_DECLS_
HEDLEY_DIAGNOSTIC_POP
#endif /* !defined(SIMDE_ARM_NEON_CMLA_H) */
|
