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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
|
/* Copyright (C) 2017-2020 Free Software Foundation, Inc.
This file is part of GCC.
GCC is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.
GCC is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.
You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
<http://www.gnu.org/licenses/>. */
#ifndef _IMMINTRIN_H_INCLUDED
#error "Never use <gfniintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef _GFNIINTRIN_H_INCLUDED
#define _GFNIINTRIN_H_INCLUDED
#if !defined(__GFNI__) || !defined(__SSE2__)
#pragma GCC push_options
#pragma GCC target("gfni,sse2")
#define __DISABLE_GFNI__
#endif /* __GFNI__ */
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_gf2p8mul_epi8 (__m128i __A, __m128i __B)
{
return (__m128i) __builtin_ia32_vgf2p8mulb_v16qi((__v16qi) __A,
(__v16qi) __B);
}
#ifdef __OPTIMIZE__
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_gf2p8affineinv_epi64_epi8 (__m128i __A, __m128i __B, const int __C)
{
return (__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi ((__v16qi) __A,
(__v16qi) __B,
__C);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_gf2p8affine_epi64_epi8 (__m128i __A, __m128i __B, const int __C)
{
return (__m128i) __builtin_ia32_vgf2p8affineqb_v16qi ((__v16qi) __A,
(__v16qi) __B, __C);
}
#else
#define _mm_gf2p8affineinv_epi64_epi8(A, B, C) \
((__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi((__v16qi)(__m128i)(A), \
(__v16qi)(__m128i)(B), (int)(C)))
#define _mm_gf2p8affine_epi64_epi8(A, B, C) \
((__m128i) __builtin_ia32_vgf2p8affineqb_v16qi ((__v16qi)(__m128i)(A), \
(__v16qi)(__m128i)(B), (int)(C)))
#endif
#ifdef __DISABLE_GFNI__
#undef __DISABLE_GFNI__
#pragma GCC pop_options
#endif /* __DISABLE_GFNI__ */
#if !defined(__GFNI__) || !defined(__AVX__)
#pragma GCC push_options
#pragma GCC target("gfni,avx")
#define __DISABLE_GFNIAVX__
#endif /* __GFNIAVX__ */
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_gf2p8mul_epi8 (__m256i __A, __m256i __B)
{
return (__m256i) __builtin_ia32_vgf2p8mulb_v32qi ((__v32qi) __A,
(__v32qi) __B);
}
#ifdef __OPTIMIZE__
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_gf2p8affineinv_epi64_epi8 (__m256i __A, __m256i __B, const int __C)
{
return (__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi ((__v32qi) __A,
(__v32qi) __B,
__C);
}
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_gf2p8affine_epi64_epi8 (__m256i __A, __m256i __B, const int __C)
{
return (__m256i) __builtin_ia32_vgf2p8affineqb_v32qi ((__v32qi) __A,
(__v32qi) __B, __C);
}
#else
#define _mm256_gf2p8affineinv_epi64_epi8(A, B, C) \
((__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi((__v32qi)(__m256i)(A), \
(__v32qi)(__m256i)(B), \
(int)(C)))
#define _mm256_gf2p8affine_epi64_epi8(A, B, C) \
((__m256i) __builtin_ia32_vgf2p8affineqb_v32qi ((__v32qi)(__m256i)(A), \
( __v32qi)(__m256i)(B), (int)(C)))
#endif
#ifdef __DISABLE_GFNIAVX__
#undef __DISABLE_GFNIAVX__
#pragma GCC pop_options
#endif /* __GFNIAVX__ */
#if !defined(__GFNI__) || !defined(__AVX512VL__)
#pragma GCC push_options
#pragma GCC target("gfni,avx512vl")
#define __DISABLE_GFNIAVX512VL__
#endif /* __GFNIAVX512VL__ */
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_gf2p8mul_epi8 (__m128i __A, __mmask16 __B, __m128i __C, __m128i __D)
{
return (__m128i) __builtin_ia32_vgf2p8mulb_v16qi_mask ((__v16qi) __C,
(__v16qi) __D,
(__v16qi)__A, __B);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_gf2p8mul_epi8 (__mmask16 __A, __m128i __B, __m128i __C)
{
return (__m128i) __builtin_ia32_vgf2p8mulb_v16qi_mask ((__v16qi) __B,
(__v16qi) __C, (__v16qi) _mm_setzero_si128 (), __A);
}
#ifdef __OPTIMIZE__
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_gf2p8affineinv_epi64_epi8 (__m128i __A, __mmask16 __B, __m128i __C,
__m128i __D, const int __E)
{
return (__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask ((__v16qi) __C,
(__v16qi) __D,
__E,
(__v16qi)__A,
__B);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_gf2p8affineinv_epi64_epi8 (__mmask16 __A, __m128i __B, __m128i __C,
const int __D)
{
return (__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask ((__v16qi) __B,
(__v16qi) __C, __D,
(__v16qi) _mm_setzero_si128 (),
__A);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_mask_gf2p8affine_epi64_epi8 (__m128i __A, __mmask16 __B, __m128i __C,
__m128i __D, const int __E)
{
return (__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask ((__v16qi) __C,
(__v16qi) __D, __E, (__v16qi)__A, __B);
}
extern __inline __m128i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm_maskz_gf2p8affine_epi64_epi8 (__mmask16 __A, __m128i __B, __m128i __C,
const int __D)
{
return (__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask ((__v16qi) __B,
(__v16qi) __C, __D, (__v16qi) _mm_setzero_si128 (), __A);
}
#else
#define _mm_mask_gf2p8affineinv_epi64_epi8(A, B, C, D, E) \
((__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask( \
(__v16qi)(__m128i)(C), (__v16qi)(__m128i)(D), \
(int)(E), (__v16qi)(__m128i)(A), (__mmask16)(B)))
#define _mm_maskz_gf2p8affineinv_epi64_epi8(A, B, C, D) \
((__m128i) __builtin_ia32_vgf2p8affineinvqb_v16qi_mask( \
(__v16qi)(__m128i)(B), (__v16qi)(__m128i)(C), \
(int)(D), (__v16qi)(__m128i) _mm_setzero_si128 (), \
(__mmask16)(A)))
#define _mm_mask_gf2p8affine_epi64_epi8(A, B, C, D, E) \
((__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask((__v16qi)(__m128i)(C),\
(__v16qi)(__m128i)(D), (int)(E), (__v16qi)(__m128i)(A), (__mmask16)(B)))
#define _mm_maskz_gf2p8affine_epi64_epi8(A, B, C, D) \
((__m128i) __builtin_ia32_vgf2p8affineqb_v16qi_mask((__v16qi)(__m128i)(B),\
(__v16qi)(__m128i)(C), (int)(D), \
(__v16qi)(__m128i) _mm_setzero_si128 (), (__mmask16)(A)))
#endif
#ifdef __DISABLE_GFNIAVX512VL__
#undef __DISABLE_GFNIAVX512VL__
#pragma GCC pop_options
#endif /* __GFNIAVX512VL__ */
#if !defined(__GFNI__) || !defined(__AVX512VL__) || !defined(__AVX512BW__)
#pragma GCC push_options
#pragma GCC target("gfni,avx512vl,avx512bw")
#define __DISABLE_GFNIAVX512VLBW__
#endif /* __GFNIAVX512VLBW__ */
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_gf2p8mul_epi8 (__m256i __A, __mmask32 __B, __m256i __C,
__m256i __D)
{
return (__m256i) __builtin_ia32_vgf2p8mulb_v32qi_mask ((__v32qi) __C,
(__v32qi) __D,
(__v32qi)__A, __B);
}
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_gf2p8mul_epi8 (__mmask32 __A, __m256i __B, __m256i __C)
{
return (__m256i) __builtin_ia32_vgf2p8mulb_v32qi_mask ((__v32qi) __B,
(__v32qi) __C, (__v32qi) _mm256_setzero_si256 (), __A);
}
#ifdef __OPTIMIZE__
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_gf2p8affineinv_epi64_epi8 (__m256i __A, __mmask32 __B,
__m256i __C, __m256i __D, const int __E)
{
return (__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask ((__v32qi) __C,
(__v32qi) __D,
__E,
(__v32qi)__A,
__B);
}
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_gf2p8affineinv_epi64_epi8 (__mmask32 __A, __m256i __B,
__m256i __C, const int __D)
{
return (__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask ((__v32qi) __B,
(__v32qi) __C, __D,
(__v32qi) _mm256_setzero_si256 (), __A);
}
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_mask_gf2p8affine_epi64_epi8 (__m256i __A, __mmask32 __B, __m256i __C,
__m256i __D, const int __E)
{
return (__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask ((__v32qi) __C,
(__v32qi) __D,
__E,
(__v32qi)__A,
__B);
}
extern __inline __m256i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm256_maskz_gf2p8affine_epi64_epi8 (__mmask32 __A, __m256i __B,
__m256i __C, const int __D)
{
return (__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask ((__v32qi) __B,
(__v32qi) __C, __D, (__v32qi)_mm256_setzero_si256 (), __A);
}
#else
#define _mm256_mask_gf2p8affineinv_epi64_epi8(A, B, C, D, E) \
((__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask( \
(__v32qi)(__m256i)(C), (__v32qi)(__m256i)(D), (int)(E), \
(__v32qi)(__m256i)(A), (__mmask32)(B)))
#define _mm256_maskz_gf2p8affineinv_epi64_epi8(A, B, C, D) \
((__m256i) __builtin_ia32_vgf2p8affineinvqb_v32qi_mask( \
(__v32qi)(__m256i)(B), (__v32qi)(__m256i)(C), (int)(D), \
(__v32qi)(__m256i) _mm256_setzero_si256 (), (__mmask32)(A)))
#define _mm256_mask_gf2p8affine_epi64_epi8(A, B, C, D, E) \
((__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask((__v32qi)(__m256i)(C),\
(__v32qi)(__m256i)(D), (int)(E), (__v32qi)(__m256i)(A), (__mmask32)(B)))
#define _mm256_maskz_gf2p8affine_epi64_epi8(A, B, C, D) \
((__m256i) __builtin_ia32_vgf2p8affineqb_v32qi_mask((__v32qi)(__m256i)(B),\
(__v32qi)(__m256i)(C), (int)(D), \
(__v32qi)(__m256i) _mm256_setzero_si256 (), (__mmask32)(A)))
#endif
#ifdef __DISABLE_GFNIAVX512VLBW__
#undef __DISABLE_GFNIAVX512VLBW__
#pragma GCC pop_options
#endif /* __GFNIAVX512VLBW__ */
#if !defined(__GFNI__) || !defined(__AVX512F__) || !defined(__AVX512BW__)
#pragma GCC push_options
#pragma GCC target("gfni,avx512f,avx512bw")
#define __DISABLE_GFNIAVX512FBW__
#endif /* __GFNIAVX512FBW__ */
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_gf2p8mul_epi8 (__m512i __A, __mmask64 __B, __m512i __C,
__m512i __D)
{
return (__m512i) __builtin_ia32_vgf2p8mulb_v64qi_mask ((__v64qi) __C,
(__v64qi) __D, (__v64qi)__A, __B);
}
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_gf2p8mul_epi8 (__mmask64 __A, __m512i __B, __m512i __C)
{
return (__m512i) __builtin_ia32_vgf2p8mulb_v64qi_mask ((__v64qi) __B,
(__v64qi) __C, (__v64qi) _mm512_setzero_si512 (), __A);
}
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_gf2p8mul_epi8 (__m512i __A, __m512i __B)
{
return (__m512i) __builtin_ia32_vgf2p8mulb_v64qi ((__v64qi) __A,
(__v64qi) __B);
}
#ifdef __OPTIMIZE__
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_gf2p8affineinv_epi64_epi8 (__m512i __A, __mmask64 __B, __m512i __C,
__m512i __D, const int __E)
{
return (__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask ((__v64qi) __C,
(__v64qi) __D,
__E,
(__v64qi)__A,
__B);
}
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_gf2p8affineinv_epi64_epi8 (__mmask64 __A, __m512i __B,
__m512i __C, const int __D)
{
return (__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask ((__v64qi) __B,
(__v64qi) __C, __D,
(__v64qi) _mm512_setzero_si512 (), __A);
}
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_gf2p8affineinv_epi64_epi8 (__m512i __A, __m512i __B, const int __C)
{
return (__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi ((__v64qi) __A,
(__v64qi) __B, __C);
}
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_gf2p8affine_epi64_epi8 (__m512i __A, __mmask64 __B, __m512i __C,
__m512i __D, const int __E)
{
return (__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask ((__v64qi) __C,
(__v64qi) __D, __E, (__v64qi)__A, __B);
}
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_gf2p8affine_epi64_epi8 (__mmask64 __A, __m512i __B, __m512i __C,
const int __D)
{
return (__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask ((__v64qi) __B,
(__v64qi) __C, __D, (__v64qi) _mm512_setzero_si512 (), __A);
}
extern __inline __m512i
__attribute__((__gnu_inline__, __always_inline__, __artificial__))
_mm512_gf2p8affine_epi64_epi8 (__m512i __A, __m512i __B, const int __C)
{
return (__m512i) __builtin_ia32_vgf2p8affineqb_v64qi ((__v64qi) __A,
(__v64qi) __B, __C);
}
#else
#define _mm512_mask_gf2p8affineinv_epi64_epi8(A, B, C, D, E) \
((__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask( \
(__v64qi)(__m512i)(C), (__v64qi)(__m512i)(D), (int)(E), \
(__v64qi)(__m512i)(A), (__mmask64)(B)))
#define _mm512_maskz_gf2p8affineinv_epi64_epi8(A, B, C, D) \
((__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi_mask( \
(__v64qi)(__m512i)(B), (__v64qi)(__m512i)(C), (int)(D), \
(__v64qi)(__m512i) _mm512_setzero_si512 (), (__mmask64)(A)))
#define _mm512_gf2p8affineinv_epi64_epi8(A, B, C) \
((__m512i) __builtin_ia32_vgf2p8affineinvqb_v64qi ( \
(__v64qi)(__m512i)(A), (__v64qi)(__m512i)(B), (int)(C)))
#define _mm512_mask_gf2p8affine_epi64_epi8(A, B, C, D, E) \
((__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask((__v64qi)(__m512i)(C),\
(__v64qi)(__m512i)(D), (int)(E), (__v64qi)(__m512i)(A), (__mmask64)(B)))
#define _mm512_maskz_gf2p8affine_epi64_epi8(A, B, C, D) \
((__m512i) __builtin_ia32_vgf2p8affineqb_v64qi_mask((__v64qi)(__m512i)(B),\
(__v64qi)(__m512i)(C), (int)(D), \
(__v64qi)(__m512i) _mm512_setzero_si512 (), (__mmask64)(A)))
#define _mm512_gf2p8affine_epi64_epi8(A, B, C) \
((__m512i) __builtin_ia32_vgf2p8affineqb_v64qi ((__v64qi)(__m512i)(A), \
(__v64qi)(__m512i)(B), (int)(C)))
#endif
#ifdef __DISABLE_GFNIAVX512FBW__
#undef __DISABLE_GFNIAVX512FBW__
#pragma GCC pop_options
#endif /* __GFNIAVX512FBW__ */
#endif /* _GFNIINTRIN_H_INCLUDED */
|
