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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
|
/*===----------------- gfniintrin.h - GFNI intrinsics ----------------------===
*
*
* Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
* See https://llvm.org/LICENSE.txt for license information.
* SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
*
*===-----------------------------------------------------------------------===
*/
#ifndef __IMMINTRIN_H
#error "Never use <gfniintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef __GFNIINTRIN_H
#define __GFNIINTRIN_H
/* Default attributes for simple form (no masking). */
#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("gfni"), __min_vector_width__(128)))
/* Default attributes for YMM unmasked form. */
#define __DEFAULT_FN_ATTRS_Y __attribute__((__always_inline__, __nodebug__, __target__("avx,gfni"), __min_vector_width__(256)))
/* Default attributes for ZMM forms. */
#define __DEFAULT_FN_ATTRS_Z __attribute__((__always_inline__, __nodebug__, __target__("avx512bw,gfni"), __min_vector_width__(512)))
/* Default attributes for VLX forms. */
#define __DEFAULT_FN_ATTRS_VL128 __attribute__((__always_inline__, __nodebug__, __target__("avx512bw,avx512vl,gfni"), __min_vector_width__(128)))
#define __DEFAULT_FN_ATTRS_VL256 __attribute__((__always_inline__, __nodebug__, __target__("avx512bw,avx512vl,gfni"), __min_vector_width__(256)))
#define _mm_gf2p8affineinv_epi64_epi8(A, B, I) \
((__m128i)__builtin_ia32_vgf2p8affineinvqb_v16qi((__v16qi)(__m128i)(A), \
(__v16qi)(__m128i)(B), \
(char)(I)))
#define _mm_gf2p8affine_epi64_epi8(A, B, I) \
((__m128i)__builtin_ia32_vgf2p8affineqb_v16qi((__v16qi)(__m128i)(A), \
(__v16qi)(__m128i)(B), \
(char)(I)))
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_gf2p8mul_epi8(__m128i __A, __m128i __B)
{
return (__m128i) __builtin_ia32_vgf2p8mulb_v16qi((__v16qi) __A,
(__v16qi) __B);
}
#ifdef __AVXINTRIN_H
#define _mm256_gf2p8affineinv_epi64_epi8(A, B, I) \
((__m256i)__builtin_ia32_vgf2p8affineinvqb_v32qi((__v32qi)(__m256i)(A), \
(__v32qi)(__m256i)(B), \
(char)(I)))
#define _mm256_gf2p8affine_epi64_epi8(A, B, I) \
((__m256i)__builtin_ia32_vgf2p8affineqb_v32qi((__v32qi)(__m256i)(A), \
(__v32qi)(__m256i)(B), \
(char)(I)))
static __inline__ __m256i __DEFAULT_FN_ATTRS_Y
_mm256_gf2p8mul_epi8(__m256i __A, __m256i __B)
{
return (__m256i) __builtin_ia32_vgf2p8mulb_v32qi((__v32qi) __A,
(__v32qi) __B);
}
#endif /* __AVXINTRIN_H */
#ifdef __AVX512BWINTRIN_H
#define _mm512_gf2p8affineinv_epi64_epi8(A, B, I) \
((__m512i)__builtin_ia32_vgf2p8affineinvqb_v64qi((__v64qi)(__m512i)(A), \
(__v64qi)(__m512i)(B), \
(char)(I)))
#define _mm512_mask_gf2p8affineinv_epi64_epi8(S, U, A, B, I) \
((__m512i)__builtin_ia32_selectb_512((__mmask64)(U), \
(__v64qi)_mm512_gf2p8affineinv_epi64_epi8(A, B, I), \
(__v64qi)(__m512i)(S)))
#define _mm512_maskz_gf2p8affineinv_epi64_epi8(U, A, B, I) \
_mm512_mask_gf2p8affineinv_epi64_epi8((__m512i)_mm512_setzero_si512(), \
U, A, B, I)
#define _mm512_gf2p8affine_epi64_epi8(A, B, I) \
((__m512i)__builtin_ia32_vgf2p8affineqb_v64qi((__v64qi)(__m512i)(A), \
(__v64qi)(__m512i)(B), \
(char)(I)))
#define _mm512_mask_gf2p8affine_epi64_epi8(S, U, A, B, I) \
((__m512i)__builtin_ia32_selectb_512((__mmask64)(U), \
(__v64qi)_mm512_gf2p8affine_epi64_epi8((A), (B), (I)), \
(__v64qi)(__m512i)(S)))
#define _mm512_maskz_gf2p8affine_epi64_epi8(U, A, B, I) \
_mm512_mask_gf2p8affine_epi64_epi8((__m512i)_mm512_setzero_si512(), \
U, A, B, I)
static __inline__ __m512i __DEFAULT_FN_ATTRS_Z
_mm512_gf2p8mul_epi8(__m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_vgf2p8mulb_v64qi((__v64qi) __A,
(__v64qi) __B);
}
static __inline__ __m512i __DEFAULT_FN_ATTRS_Z
_mm512_mask_gf2p8mul_epi8(__m512i __S, __mmask64 __U, __m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_selectb_512(__U,
(__v64qi) _mm512_gf2p8mul_epi8(__A, __B),
(__v64qi) __S);
}
static __inline__ __m512i __DEFAULT_FN_ATTRS_Z
_mm512_maskz_gf2p8mul_epi8(__mmask64 __U, __m512i __A, __m512i __B)
{
return _mm512_mask_gf2p8mul_epi8((__m512i)_mm512_setzero_si512(),
__U, __A, __B);
}
#endif /* __AVX512BWINTRIN_H */
#ifdef __AVX512VLBWINTRIN_H
#define _mm_mask_gf2p8affineinv_epi64_epi8(S, U, A, B, I) \
((__m128i)__builtin_ia32_selectb_128((__mmask16)(U), \
(__v16qi)_mm_gf2p8affineinv_epi64_epi8(A, B, I), \
(__v16qi)(__m128i)(S)))
#define _mm_maskz_gf2p8affineinv_epi64_epi8(U, A, B, I) \
_mm_mask_gf2p8affineinv_epi64_epi8((__m128i)_mm_setzero_si128(), \
U, A, B, I)
#define _mm256_mask_gf2p8affineinv_epi64_epi8(S, U, A, B, I) \
((__m256i)__builtin_ia32_selectb_256((__mmask32)(U), \
(__v32qi)_mm256_gf2p8affineinv_epi64_epi8(A, B, I), \
(__v32qi)(__m256i)(S)))
#define _mm256_maskz_gf2p8affineinv_epi64_epi8(U, A, B, I) \
_mm256_mask_gf2p8affineinv_epi64_epi8((__m256i)_mm256_setzero_si256(), \
U, A, B, I)
#define _mm_mask_gf2p8affine_epi64_epi8(S, U, A, B, I) \
((__m128i)__builtin_ia32_selectb_128((__mmask16)(U), \
(__v16qi)_mm_gf2p8affine_epi64_epi8(A, B, I), \
(__v16qi)(__m128i)(S)))
#define _mm_maskz_gf2p8affine_epi64_epi8(U, A, B, I) \
_mm_mask_gf2p8affine_epi64_epi8((__m128i)_mm_setzero_si128(), U, A, B, I)
#define _mm256_mask_gf2p8affine_epi64_epi8(S, U, A, B, I) \
((__m256i)__builtin_ia32_selectb_256((__mmask32)(U), \
(__v32qi)_mm256_gf2p8affine_epi64_epi8(A, B, I), \
(__v32qi)(__m256i)(S)))
#define _mm256_maskz_gf2p8affine_epi64_epi8(U, A, B, I) \
_mm256_mask_gf2p8affine_epi64_epi8((__m256i)_mm256_setzero_si256(), \
U, A, B, I)
static __inline__ __m128i __DEFAULT_FN_ATTRS_VL128
_mm_mask_gf2p8mul_epi8(__m128i __S, __mmask16 __U, __m128i __A, __m128i __B)
{
return (__m128i) __builtin_ia32_selectb_128(__U,
(__v16qi) _mm_gf2p8mul_epi8(__A, __B),
(__v16qi) __S);
}
static __inline__ __m128i __DEFAULT_FN_ATTRS_VL128
_mm_maskz_gf2p8mul_epi8(__mmask16 __U, __m128i __A, __m128i __B)
{
return _mm_mask_gf2p8mul_epi8((__m128i)_mm_setzero_si128(),
__U, __A, __B);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS_VL256
_mm256_mask_gf2p8mul_epi8(__m256i __S, __mmask32 __U, __m256i __A, __m256i __B)
{
return (__m256i) __builtin_ia32_selectb_256(__U,
(__v32qi) _mm256_gf2p8mul_epi8(__A, __B),
(__v32qi) __S);
}
static __inline__ __m256i __DEFAULT_FN_ATTRS_VL256
_mm256_maskz_gf2p8mul_epi8(__mmask32 __U, __m256i __A, __m256i __B)
{
return _mm256_mask_gf2p8mul_epi8((__m256i)_mm256_setzero_si256(),
__U, __A, __B);
}
#endif /* __AVX512VLBWINTRIN_H */
#undef __DEFAULT_FN_ATTRS
#undef __DEFAULT_FN_ATTRS_Y
#undef __DEFAULT_FN_ATTRS_Z
#undef __DEFAULT_FN_ATTRS_VL128
#undef __DEFAULT_FN_ATTRS_VL256
#endif /* __GFNIINTRIN_H */
|
