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
|
/* Function sincosf vectorized with AVX-512. Wrapper to AVX2 version.
Copyright (C) 2014-2019 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<https://www.gnu.org/licenses/>. */
#include <sysdep.h>
#include "svml_s_wrapper_impl.h"
.text
ENTRY (_ZGVeN16vl4l4_sincosf)
WRAPPER_IMPL_AVX512_fFF _ZGVdN8vl4l4_sincosf
END (_ZGVeN16vl4l4_sincosf)
/* AVX512 ISA version as wrapper to AVX2 ISA version (for vector
function declared with #pragma omp declare simd notinbranch). */
.macro WRAPPER_IMPL_AVX512_fFF_vvv callee
#ifndef __ILP32__
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
cfi_def_cfa_register (%rbp)
andq $-64, %rsp
subq $448, %rsp
vmovups %zmm0, 384(%rsp)
lea (%rsp), %rdi
vmovups %zmm1, 128(%rdi)
vmovups %zmm2, 192(%rdi)
vmovups %zmm3, 256(%rdi)
vmovups %zmm4, 320(%rdi)
lea 64(%rsp), %rsi
call HIDDEN_JUMPTARGET(\callee)
vmovdqu 416(%rsp), %ymm0
lea 32(%rsp), %rdi
lea 96(%rsp), %rsi
call HIDDEN_JUMPTARGET(\callee)
movq 128(%rsp), %rdx
movq 136(%rsp), %rsi
movq 144(%rsp), %r8
movq 152(%rsp), %r10
movl (%rsp), %eax
movl 4(%rsp), %ecx
movl 8(%rsp), %edi
movl 12(%rsp), %r9d
movl %eax, (%rdx)
movl %ecx, (%rsi)
movq 160(%rsp), %rax
movq 168(%rsp), %rcx
movl %edi, (%r8)
movl %r9d, (%r10)
movq 176(%rsp), %rdi
movq 184(%rsp), %r9
movl 16(%rsp), %r11d
movl 20(%rsp), %edx
movl 24(%rsp), %esi
movl 28(%rsp), %r8d
movl %r11d, (%rax)
movl %edx, (%rcx)
movq 192(%rsp), %r11
movq 200(%rsp), %rdx
movl %esi, (%rdi)
movl %r8d, (%r9)
movq 208(%rsp), %rsi
movq 216(%rsp), %r8
movl 32(%rsp), %r10d
movl 36(%rsp), %eax
movl 40(%rsp), %ecx
movl 44(%rsp), %edi
movl %r10d, (%r11)
movl %eax, (%rdx)
movq 224(%rsp), %r10
movq 232(%rsp), %rax
movl %ecx, (%rsi)
movl %edi, (%r8)
movq 240(%rsp), %rcx
movq 248(%rsp), %rdi
movl 48(%rsp), %r9d
movl 52(%rsp), %r11d
movl 56(%rsp), %edx
movl 60(%rsp), %esi
movl %r9d, (%r10)
movl %r11d, (%rax)
movq 256(%rsp), %r9
movq 264(%rsp), %r11
movl %edx, (%rcx)
movl %esi, (%rdi)
movq 272(%rsp), %rdx
movq 280(%rsp), %rsi
movl 64(%rsp), %r8d
movl 68(%rsp), %r10d
movl 72(%rsp), %eax
movl 76(%rsp), %ecx
movl %r8d, (%r9)
movl %r10d, (%r11)
movq 288(%rsp), %r8
movq 296(%rsp), %r10
movl %eax, (%rdx)
movl %ecx, (%rsi)
movq 304(%rsp), %rax
movq 312(%rsp), %rcx
movl 80(%rsp), %edi
movl 84(%rsp), %r9d
movl 88(%rsp), %r11d
movl 92(%rsp), %edx
movl %edi, (%r8)
movl %r9d, (%r10)
movq 320(%rsp), %rdi
movq 328(%rsp), %r9
movl %r11d, (%rax)
movl %edx, (%rcx)
movq 336(%rsp), %r11
movq 344(%rsp), %rdx
movl 96(%rsp), %esi
movl 100(%rsp), %r8d
movl 104(%rsp), %r10d
movl 108(%rsp), %eax
movl %esi, (%rdi)
movl %r8d, (%r9)
movq 352(%rsp), %rsi
movq 360(%rsp), %r8
movl %r10d, (%r11)
movl %eax, (%rdx)
movq 368(%rsp), %r10
movq 376(%rsp), %rax
movl 112(%rsp), %ecx
movl 116(%rsp), %edi
movl 120(%rsp), %r9d
movl 124(%rsp), %r11d
movl %ecx, (%rsi)
movl %edi, (%r8)
movl %r9d, (%r10)
movl %r11d, (%rax)
movq %rbp, %rsp
cfi_def_cfa_register (%rsp)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
#else
leal 8(%rsp), %r10d
.cfi_def_cfa 10, 0
andl $-64, %esp
pushq -8(%r10d)
pushq %rbp
.cfi_escape 0x10,0x6,0x2,0x76,0
movl %esp, %ebp
pushq %r12
leal -112(%rbp), %esi
pushq %r10
.cfi_escape 0xf,0x3,0x76,0x70,0x6
.cfi_escape 0x10,0xc,0x2,0x76,0x78
leal -176(%rbp), %edi
movq %rsi, %r12
pushq %rbx
.cfi_escape 0x10,0x3,0x2,0x76,0x68
movq %rdi, %rbx
subl $344, %esp
vmovdqa64 %zmm1, -240(%ebp)
vmovdqa64 %zmm2, -304(%ebp)
vmovaps %zmm0, -368(%ebp)
call HIDDEN_JUMPTARGET(\callee)
leal 32(%r12), %esi
vmovups -336(%ebp), %ymm0
leal 32(%rbx), %edi
call HIDDEN_JUMPTARGET(\callee)
movl -240(%ebp), %eax
vmovss -176(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -236(%ebp), %eax
vmovss -172(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -232(%ebp), %eax
vmovss -168(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -228(%ebp), %eax
vmovss -164(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -224(%ebp), %eax
vmovss -160(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -220(%ebp), %eax
vmovss -156(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -216(%ebp), %eax
vmovss -152(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -212(%ebp), %eax
vmovss -148(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -208(%ebp), %eax
vmovss -144(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -204(%ebp), %eax
vmovss -140(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -200(%ebp), %eax
vmovss -136(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -196(%ebp), %eax
vmovss -132(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -192(%ebp), %eax
vmovss -128(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -188(%ebp), %eax
vmovss -124(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -184(%ebp), %eax
vmovss -120(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -180(%ebp), %eax
vmovss -116(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -304(%ebp), %eax
vmovss -112(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -300(%ebp), %eax
vmovss -108(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -296(%ebp), %eax
vmovss -104(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -292(%ebp), %eax
vmovss -100(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -288(%ebp), %eax
vmovss -96(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -284(%ebp), %eax
vmovss -92(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -280(%ebp), %eax
vmovss -88(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -276(%ebp), %eax
vmovss -84(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -272(%ebp), %eax
vmovss -80(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -268(%ebp), %eax
vmovss -76(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -264(%ebp), %eax
vmovss -72(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -260(%ebp), %eax
vmovss -68(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -256(%ebp), %eax
vmovss -64(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -252(%ebp), %eax
vmovss -60(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -248(%ebp), %eax
vmovss -56(%ebp), %xmm0
vmovss %xmm0, (%eax)
movl -244(%ebp), %eax
vmovss -52(%ebp), %xmm0
vmovss %xmm0, (%eax)
addl $344, %esp
popq %rbx
popq %r10
.cfi_def_cfa 10, 0
popq %r12
popq %rbp
leal -8(%r10), %esp
.cfi_def_cfa 7, 8
ret
#endif
.endm
ENTRY (_ZGVeN16vvv_sincosf)
WRAPPER_IMPL_AVX512_fFF_vvv _ZGVdN8vl4l4_sincosf
END (_ZGVeN16vvv_sincosf)
|