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
|
/* Copyright (C) 2013-2014 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 <avx512erintrin.h> directly; include <immintrin.h> instead."
#endif
#ifndef _AVX512ERINTRIN_H_INCLUDED
#define _AVX512ERINTRIN_H_INCLUDED
#ifndef __AVX512ER__
#pragma GCC push_options
#pragma GCC target("avx512er")
#define __DISABLE_AVX512ER__
#endif /* __AVX512ER__ */
/* Internal data types for implementing the intrinsics. */
typedef double __v8df __attribute__ ((__vector_size__ (64)));
typedef float __v16sf __attribute__ ((__vector_size__ (64)));
/* The Intel API is flexible enough that we must allow aliasing with other
vector types, and their scalar components. */
typedef float __m512 __attribute__ ((__vector_size__ (64), __may_alias__));
typedef double __m512d __attribute__ ((__vector_size__ (64), __may_alias__));
typedef unsigned char __mmask8;
typedef unsigned short __mmask16;
#ifdef __OPTIMIZE__
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_exp2a23_round_pd (__m512d __A, int __R)
{
__m512d __W;
return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
(__v8df) __W,
(__mmask8) -1, __R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_exp2a23_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
{
return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
(__v8df) __W,
(__mmask8) __U, __R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_exp2a23_round_pd (__mmask8 __U, __m512d __A, int __R)
{
return (__m512d) __builtin_ia32_exp2pd_mask ((__v8df) __A,
(__v8df) _mm512_setzero_pd (),
(__mmask8) __U, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_exp2a23_round_ps (__m512 __A, int __R)
{
__m512 __W;
return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
(__v16sf) __W,
(__mmask16) -1, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_exp2a23_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
{
return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
(__v16sf) __W,
(__mmask16) __U, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_exp2a23_round_ps (__mmask16 __U, __m512 __A, int __R)
{
return (__m512) __builtin_ia32_exp2ps_mask ((__v16sf) __A,
(__v16sf) _mm512_setzero_ps (),
(__mmask16) __U, __R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rcp28_round_pd (__m512d __A, int __R)
{
__m512d __W;
return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
(__v8df) __W,
(__mmask8) -1, __R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rcp28_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
{
return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
(__v8df) __W,
(__mmask8) __U, __R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rcp28_round_pd (__mmask8 __U, __m512d __A, int __R)
{
return (__m512d) __builtin_ia32_rcp28pd_mask ((__v8df) __A,
(__v8df) _mm512_setzero_pd (),
(__mmask8) __U, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rcp28_round_ps (__m512 __A, int __R)
{
__m512 __W;
return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
(__v16sf) __W,
(__mmask16) -1, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rcp28_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
{
return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
(__v16sf) __W,
(__mmask16) __U, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rcp28_round_ps (__mmask16 __U, __m512 __A, int __R)
{
return (__m512) __builtin_ia32_rcp28ps_mask ((__v16sf) __A,
(__v16sf) _mm512_setzero_ps (),
(__mmask16) __U, __R);
}
extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp28_round_sd (__m128d __A, __m128d __B, int __R)
{
return (__m128d) __builtin_ia32_rcp28sd_round ((__v2df) __B,
(__v2df) __A,
__R);
}
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rcp28_round_ss (__m128 __A, __m128 __B, int __R)
{
return (__m128) __builtin_ia32_rcp28ss_round ((__v4sf) __B,
(__v4sf) __A,
__R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rsqrt28_round_pd (__m512d __A, int __R)
{
__m512d __W;
return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
(__v8df) __W,
(__mmask8) -1, __R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rsqrt28_round_pd (__m512d __W, __mmask8 __U, __m512d __A, int __R)
{
return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
(__v8df) __W,
(__mmask8) __U, __R);
}
extern __inline __m512d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rsqrt28_round_pd (__mmask8 __U, __m512d __A, int __R)
{
return (__m512d) __builtin_ia32_rsqrt28pd_mask ((__v8df) __A,
(__v8df) _mm512_setzero_pd (),
(__mmask8) __U, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_rsqrt28_round_ps (__m512 __A, int __R)
{
__m512 __W;
return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
(__v16sf) __W,
(__mmask16) -1, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_mask_rsqrt28_round_ps (__m512 __W, __mmask16 __U, __m512 __A, int __R)
{
return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
(__v16sf) __W,
(__mmask16) __U, __R);
}
extern __inline __m512
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_maskz_rsqrt28_round_ps (__mmask16 __U, __m512 __A, int __R)
{
return (__m512) __builtin_ia32_rsqrt28ps_mask ((__v16sf) __A,
(__v16sf) _mm512_setzero_ps (),
(__mmask16) __U, __R);
}
extern __inline __m128d
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt28_round_sd (__m128d __A, __m128d __B, int __R)
{
return (__m128d) __builtin_ia32_rsqrt28sd_round ((__v2df) __B,
(__v2df) __A,
__R);
}
extern __inline __m128
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_rsqrt28_round_ss (__m128 __A, __m128 __B, int __R)
{
return (__m128) __builtin_ia32_rsqrt28ss_round ((__v4sf) __B,
(__v4sf) __A,
__R);
}
#else
#define _mm512_exp2a23_round_pd(A, C) \
__builtin_ia32_exp2pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
#define _mm512_mask_exp2a23_round_pd(W, U, A, C) \
__builtin_ia32_exp2pd_mask(A, W, U, C)
#define _mm512_maskz_exp2a23_round_pd(U, A, C) \
__builtin_ia32_exp2pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)
#define _mm512_exp2a23_round_ps(A, C) \
__builtin_ia32_exp2ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)
#define _mm512_mask_exp2a23_round_ps(W, U, A, C) \
__builtin_ia32_exp2ps_mask(A, W, U, C)
#define _mm512_maskz_exp2a23_round_ps(U, A, C) \
__builtin_ia32_exp2ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
#define _mm512_rcp28_round_pd(A, C) \
__builtin_ia32_rcp28pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
#define _mm512_mask_rcp28_round_pd(W, U, A, C) \
__builtin_ia32_rcp28pd_mask(A, W, U, C)
#define _mm512_maskz_rcp28_round_pd(U, A, C) \
__builtin_ia32_rcp28pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)
#define _mm512_rcp28_round_ps(A, C) \
__builtin_ia32_rcp28ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)
#define _mm512_mask_rcp28_round_ps(W, U, A, C) \
__builtin_ia32_rcp28ps_mask(A, W, U, C)
#define _mm512_maskz_rcp28_round_ps(U, A, C) \
__builtin_ia32_rcp28ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
#define _mm512_rsqrt28_round_pd(A, C) \
__builtin_ia32_rsqrt28pd_mask(A, (__v8df)_mm512_setzero_pd(), -1, C)
#define _mm512_mask_rsqrt28_round_pd(W, U, A, C) \
__builtin_ia32_rsqrt28pd_mask(A, W, U, C)
#define _mm512_maskz_rsqrt28_round_pd(U, A, C) \
__builtin_ia32_rsqrt28pd_mask(A, (__v8df)_mm512_setzero_pd(), U, C)
#define _mm512_rsqrt28_round_ps(A, C) \
__builtin_ia32_rsqrt28ps_mask(A, (__v16sf)_mm512_setzero_ps(), -1, C)
#define _mm512_mask_rsqrt28_round_ps(W, U, A, C) \
__builtin_ia32_rsqrt28ps_mask(A, W, U, C)
#define _mm512_maskz_rsqrt28_round_ps(U, A, C) \
__builtin_ia32_rsqrt28ps_mask(A, (__v16sf)_mm512_setzero_ps(), U, C)
#define _mm_rcp28_round_sd(A, B, R) \
__builtin_ia32_rcp28sd_round(A, B, R)
#define _mm_rcp28_round_ss(A, B, R) \
__builtin_ia32_rcp28ss_round(A, B, R)
#define _mm_rsqrt28_round_sd(A, B, R) \
__builtin_ia32_rsqrt28sd_round(A, B, R)
#define _mm_rsqrt28_round_ss(A, B, R) \
__builtin_ia32_rsqrt28ss_round(A, B, R)
#endif
#define _mm512_exp2a23_pd(A) \
_mm512_exp2a23_round_pd(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_exp2a23_pd(W, U, A) \
_mm512_mask_exp2a23_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_exp2a23_pd(U, A) \
_mm512_maskz_exp2a23_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_exp2a23_ps(A) \
_mm512_exp2a23_round_ps(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_exp2a23_ps(W, U, A) \
_mm512_mask_exp2a23_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_exp2a23_ps(U, A) \
_mm512_maskz_exp2a23_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_rcp28_pd(A) \
_mm512_rcp28_round_pd(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rcp28_pd(W, U, A) \
_mm512_mask_rcp28_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rcp28_pd(U, A) \
_mm512_maskz_rcp28_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_rcp28_ps(A) \
_mm512_rcp28_round_ps(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rcp28_ps(W, U, A) \
_mm512_mask_rcp28_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rcp28_ps(U, A) \
_mm512_maskz_rcp28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_rsqrt28_pd(A) \
_mm512_rsqrt28_round_pd(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rsqrt28_pd(W, U, A) \
_mm512_mask_rsqrt28_round_pd(W, U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rsqrt28_pd(U, A) \
_mm512_maskz_rsqrt28_round_pd(U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_rsqrt28_ps(A) \
_mm512_rsqrt28_round_ps(A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_mask_rsqrt28_ps(W, U, A) \
_mm512_mask_rsqrt28_round_ps(W, U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm512_maskz_rsqrt28_ps(U, A) \
_mm512_maskz_rsqrt28_round_ps(U, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rcp28_sd(A, B) \
__builtin_ia32_rcp28sd_round(B, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rcp28_ss(A, B) \
__builtin_ia32_rcp28ss_round(B, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rsqrt28_sd(A, B) \
__builtin_ia32_rsqrt28sd_round(B, A, _MM_FROUND_CUR_DIRECTION)
#define _mm_rsqrt28_ss(A, B) \
__builtin_ia32_rsqrt28ss_round(B, A, _MM_FROUND_CUR_DIRECTION)
#ifdef __DISABLE_AVX512ER__
#undef __DISABLE_AVX512ER__
#pragma GCC pop_options
#endif /* __DISABLE_AVX512ER__ */
#endif /* _AVX512ERINTRIN_H_INCLUDED */
|
