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
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
|
/* Function sincos vectorized with AVX-512. KNL and SKX versions.
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
<http://www.gnu.org/licenses/>. */
#include <sysdep.h>
#include "svml_d_trig_data.h"
#include "svml_d_wrapper_impl.h"
/*
ALGORITHM DESCRIPTION:
( low accuracy ( < 4ulp ) or enhanced performance
( half of correct mantissa ) implementation )
Argument representation:
arg = N*Pi + R
Result calculation:
sin(arg) = sin(N*Pi + R) = (-1)^N * sin(R)
arg + Pi/2 = (N'*Pi + R')
cos(arg) = sin(arg+Pi/2) = sin(N'*Pi + R') = (-1)^N' * sin(R')
sin(R), sin(R') are approximated by corresponding polynomial. */
.text
ENTRY (_ZGVeN8vl8l8_sincos_knl)
#ifndef HAVE_AVX512DQ_ASM_SUPPORT
WRAPPER_IMPL_AVX512_fFF _ZGVdN4vl8l8_sincos
#else
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
cfi_def_cfa_register (%rbp)
andq $-64, %rsp
subq $1344, %rsp
movq __svml_d_trig_data@GOTPCREL(%rip), %rax
vmovaps %zmm0, %zmm4
movq $-1, %rdx
vmovups __dSignMask(%rax), %zmm12
vmovups __dInvPI(%rax), %zmm5
/* ARGUMENT RANGE REDUCTION:
Absolute argument: X' = |X| */
vpandnq %zmm4, %zmm12, %zmm3
vmovups __dPI1_FMA(%rax), %zmm7
vmovups __dPI3_FMA(%rax), %zmm9
/* SinR = X' - SinN*Pi1 */
vmovaps %zmm3, %zmm8
/* CosR = SinX - CosN*Pi1 */
vmovaps %zmm3, %zmm10
/* SinY = X'*InvPi + RS : right shifter add */
vfmadd213pd __dRShifter(%rax), %zmm3, %zmm5
vmovups __dC6(%rax), %zmm13
/* SinN = Y - RS : right shifter sub */
vsubpd __dRShifter(%rax), %zmm5, %zmm1
vmovaps %zmm13, %zmm14
/* SinSignRes = Y<<63 : shift LSB to MSB place for result sign */
vpsllq $63, %zmm5, %zmm2
vcmppd $22, __dRangeVal(%rax), %zmm3, %k1
/* Update CosRSign and CosSignRes signs */
vmovaps %zmm12, %zmm5
vfnmadd231pd %zmm1, %zmm7, %zmm8
/* SinR = SinR - SinN*Pi1 */
vfnmadd231pd __dPI2_FMA(%rax), %zmm1, %zmm8
/* Sine result sign: SinRSign = SignMask & SinR */
vpandq %zmm8, %zmm12, %zmm11
/* Set SinRSign to 0.5 */
vporq __dOneHalf(%rax), %zmm11, %zmm6
vpternlogq $150, %zmm2, %zmm11, %zmm5
/* Update sign SinSignRes */
vpternlogq $120, %zmm4, %zmm12, %zmm2
/* Polynomial approximation */
vmovups __dC7(%rax), %zmm11
/* CosN = SinN +(-)0.5 */
vaddpd %zmm6, %zmm1, %zmm0
/* SinR = SinR - SinN*Pi3 */
vfnmadd213pd %zmm8, %zmm9, %zmm1
vfnmadd231pd %zmm0, %zmm7, %zmm10
/* SinR2 = SinR^2 */
vmulpd %zmm1, %zmm1, %zmm15
/* Grab SignX
CosR = CosR - CosN*Pi2 */
vfnmadd231pd __dPI2_FMA(%rax), %zmm0, %zmm10
vfmadd231pd __dC7(%rax), %zmm15, %zmm14
/* CosR = CosR - CosN*Pi3 */
vfnmadd213pd %zmm10, %zmm9, %zmm0
vfmadd213pd __dC5(%rax), %zmm15, %zmm14
/* CosR2 = CosR^2 */
vmulpd %zmm0, %zmm0, %zmm12
vfmadd213pd __dC4(%rax), %zmm15, %zmm14
vfmadd213pd %zmm13, %zmm12, %zmm11
/* SinPoly = C3 + SinR2*(C4 + SinR2*(C5 + SinR2*(C6 + SinR2*C7))) */
vfmadd213pd __dC3(%rax), %zmm15, %zmm14
vfmadd213pd __dC5(%rax), %zmm12, %zmm11
/* SinPoly = C2 + SinR2*SinPoly */
vfmadd213pd __dC2(%rax), %zmm15, %zmm14
vfmadd213pd __dC4(%rax), %zmm12, %zmm11
/* SinPoly = C1 + SinR2*SinPoly */
vfmadd213pd __dC1(%rax), %zmm15, %zmm14
/* CosPoly = C3 + CosR2*(C4 + CosR2*(C5 + CosR2*(C6 + CosR2*C7))) */
vfmadd213pd __dC3(%rax), %zmm12, %zmm11
/* SinPoly = SinR2*SinPoly */
vmulpd %zmm15, %zmm14, %zmm13
/* CosPoly = C2 + CosR2*CosPoly */
vfmadd213pd __dC2(%rax), %zmm12, %zmm11
/* SinPoly = SinR*SinPoly */
vfmadd213pd %zmm1, %zmm1, %zmm13
vpbroadcastq %rdx, %zmm1{%k1}{z}
/* CosPoly = C1 + CosR2*CosPoly */
vfmadd213pd __dC1(%rax), %zmm12, %zmm11
vptestmq %zmm1, %zmm1, %k0
kmovw %k0, %ecx
/* CosPoly = CosR2*CosPoly */
vmulpd %zmm12, %zmm11, %zmm14
movzbl %cl, %ecx
/* CosPoly = CosR*CosPoly */
vfmadd213pd %zmm0, %zmm0, %zmm14
/* Final reconstruction.
Update Sin result's sign */
vpxorq %zmm2, %zmm13, %zmm0
/* Update Cos result's sign */
vpxorq %zmm5, %zmm14, %zmm2
testl %ecx, %ecx
jne .LBL_1_3
.LBL_1_2:
cfi_remember_state
vmovups %zmm0, (%rdi)
vmovups %zmm2, (%rsi)
movq %rbp, %rsp
cfi_def_cfa_register (%rsp)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.LBL_1_3:
cfi_restore_state
vmovups %zmm4, 1152(%rsp)
vmovups %zmm0, 1216(%rsp)
vmovups %zmm2, 1280(%rsp)
je .LBL_1_2
xorb %dl, %dl
kmovw %k4, 1048(%rsp)
xorl %eax, %eax
kmovw %k5, 1040(%rsp)
kmovw %k6, 1032(%rsp)
kmovw %k7, 1024(%rsp)
vmovups %zmm16, 960(%rsp)
vmovups %zmm17, 896(%rsp)
vmovups %zmm18, 832(%rsp)
vmovups %zmm19, 768(%rsp)
vmovups %zmm20, 704(%rsp)
vmovups %zmm21, 640(%rsp)
vmovups %zmm22, 576(%rsp)
vmovups %zmm23, 512(%rsp)
vmovups %zmm24, 448(%rsp)
vmovups %zmm25, 384(%rsp)
vmovups %zmm26, 320(%rsp)
vmovups %zmm27, 256(%rsp)
vmovups %zmm28, 192(%rsp)
vmovups %zmm29, 128(%rsp)
vmovups %zmm30, 64(%rsp)
vmovups %zmm31, (%rsp)
movq %rsi, 1056(%rsp)
movq %r12, 1096(%rsp)
cfi_offset_rel_rsp (12, 1096)
movb %dl, %r12b
movq %r13, 1088(%rsp)
cfi_offset_rel_rsp (13, 1088)
movl %eax, %r13d
movq %r14, 1080(%rsp)
cfi_offset_rel_rsp (14, 1080)
movl %ecx, %r14d
movq %r15, 1072(%rsp)
cfi_offset_rel_rsp (15, 1072)
movq %rbx, 1064(%rsp)
movq %rdi, %rbx
cfi_remember_state
.LBL_1_6:
btl %r13d, %r14d
jc .LBL_1_13
.LBL_1_7:
lea 1(%r13), %esi
btl %esi, %r14d
jc .LBL_1_10
.LBL_1_8:
addb $1, %r12b
addl $2, %r13d
cmpb $16, %r12b
jb .LBL_1_6
movq %rbx, %rdi
kmovw 1048(%rsp), %k4
movq 1056(%rsp), %rsi
kmovw 1040(%rsp), %k5
movq 1096(%rsp), %r12
cfi_restore (%r12)
kmovw 1032(%rsp), %k6
movq 1088(%rsp), %r13
cfi_restore (%r13)
kmovw 1024(%rsp), %k7
vmovups 960(%rsp), %zmm16
vmovups 896(%rsp), %zmm17
vmovups 832(%rsp), %zmm18
vmovups 768(%rsp), %zmm19
vmovups 704(%rsp), %zmm20
vmovups 640(%rsp), %zmm21
vmovups 576(%rsp), %zmm22
vmovups 512(%rsp), %zmm23
vmovups 448(%rsp), %zmm24
vmovups 384(%rsp), %zmm25
vmovups 320(%rsp), %zmm26
vmovups 256(%rsp), %zmm27
vmovups 192(%rsp), %zmm28
vmovups 128(%rsp), %zmm29
vmovups 64(%rsp), %zmm30
vmovups (%rsp), %zmm31
movq 1080(%rsp), %r14
cfi_restore (%r14)
movq 1072(%rsp), %r15
cfi_restore (%r15)
movq 1064(%rsp), %rbx
vmovups 1216(%rsp), %zmm0
vmovups 1280(%rsp), %zmm2
jmp .LBL_1_2
.LBL_1_10:
cfi_restore_state
movzbl %r12b, %r15d
shlq $4, %r15
vmovsd 1160(%rsp,%r15), %xmm0
call JUMPTARGET(sin)
vmovsd %xmm0, 1224(%rsp,%r15)
vmovsd 1160(%rsp,%r15), %xmm0
call JUMPTARGET(cos)
vmovsd %xmm0, 1288(%rsp,%r15)
jmp .LBL_1_8
.LBL_1_13:
movzbl %r12b, %r15d
shlq $4, %r15
vmovsd 1152(%rsp,%r15), %xmm0
call JUMPTARGET(sin)
vmovsd %xmm0, 1216(%rsp,%r15)
vmovsd 1152(%rsp,%r15), %xmm0
call JUMPTARGET(cos)
vmovsd %xmm0, 1280(%rsp,%r15)
jmp .LBL_1_7
#endif
END (_ZGVeN8vl8l8_sincos_knl)
libmvec_hidden_def(_ZGVeN8vl8l8_sincos_knl)
ENTRY (_ZGVeN8vl8l8_sincos_skx)
#ifndef HAVE_AVX512DQ_ASM_SUPPORT
WRAPPER_IMPL_AVX512_fFF _ZGVdN4vl8l8_sincos
#else
pushq %rbp
cfi_adjust_cfa_offset (8)
cfi_rel_offset (%rbp, 0)
movq %rsp, %rbp
cfi_def_cfa_register (%rbp)
andq $-64, %rsp
subq $1344, %rsp
movq __svml_d_trig_data@GOTPCREL(%rip), %rax
vmovaps %zmm0, %zmm8
vmovups __dSignMask(%rax), %zmm4
vmovups __dInvPI(%rax), %zmm9
vmovups __dRShifter(%rax), %zmm10
vmovups __dPI1_FMA(%rax), %zmm13
vmovups __dPI2_FMA(%rax), %zmm14
vmovups __dOneHalf(%rax), %zmm11
vmovups __dPI3_FMA(%rax), %zmm2
/* ARGUMENT RANGE REDUCTION:
Absolute argument: X' = |X| */
vandnpd %zmm8, %zmm4, %zmm7
/* SinY = X'*InvPi + RS : right shifter add */
vfmadd213pd %zmm10, %zmm7, %zmm9
vcmppd $18, __dRangeVal(%rax), %zmm7, %k1
/* SinSignRes = Y<<63 : shift LSB to MSB place for result sign */
vpsllq $63, %zmm9, %zmm6
/* SinN = Y - RS : right shifter sub */
vsubpd %zmm10, %zmm9, %zmm5
vmovups __dC5(%rax), %zmm9
vmovups __dC4(%rax), %zmm10
/* SinR = X' - SinN*Pi1 */
vmovaps %zmm7, %zmm15
vfnmadd231pd %zmm5, %zmm13, %zmm15
/* SinR = SinR - SinN*Pi1 */
vfnmadd231pd %zmm5, %zmm14, %zmm15
/* Sine result sign: SinRSign = SignMask & SinR */
vandpd %zmm15, %zmm4, %zmm1
/* Set SinRSign to 0.5 */
vorpd %zmm1, %zmm11, %zmm12
vmovups __dC3(%rax), %zmm11
/* CosN = SinN +(-)0.5 */
vaddpd %zmm12, %zmm5, %zmm3
/* SinR = SinR - SinN*Pi3 */
vfnmadd213pd %zmm15, %zmm2, %zmm5
vmovups __dC2(%rax), %zmm12
/* SinR2 = SinR^2 */
vmulpd %zmm5, %zmm5, %zmm15
/* CosR = SinX - CosN*Pi1 */
vmovaps %zmm7, %zmm0
vfnmadd231pd %zmm3, %zmm13, %zmm0
vmovups __dC1(%rax), %zmm13
/* Grab SignX
CosR = CosR - CosN*Pi2 */
vfnmadd231pd %zmm3, %zmm14, %zmm0
/* CosR = CosR - CosN*Pi3 */
vfnmadd213pd %zmm0, %zmm2, %zmm3
/* Polynomial approximation */
vmovups __dC7(%rax), %zmm0
/* Update CosRSign and CosSignRes signs */
vmovaps %zmm4, %zmm2
vpternlogq $150, %zmm6, %zmm1, %zmm2
/* Update sign SinSignRes */
vpternlogq $120, %zmm8, %zmm4, %zmm6
/* CosR2 = CosR^2 */
vmulpd %zmm3, %zmm3, %zmm1
vmovups __dC6(%rax), %zmm4
vmovaps %zmm0, %zmm14
vfmadd213pd %zmm4, %zmm1, %zmm0
vfmadd213pd %zmm4, %zmm15, %zmm14
vfmadd213pd %zmm9, %zmm1, %zmm0
vfmadd213pd %zmm9, %zmm15, %zmm14
vfmadd213pd %zmm10, %zmm1, %zmm0
vfmadd213pd %zmm10, %zmm15, %zmm14
/* CosPoly = C3 + CosR2*(C4 + CosR2*(C5 + CosR2*(C6 + CosR2*C7))) */
vfmadd213pd %zmm11, %zmm1, %zmm0
/* SinPoly = C3 + SinR2*(C4 + SinR2*(C5 + SinR2*(C6 + SinR2*C7))) */
vfmadd213pd %zmm11, %zmm15, %zmm14
/* CosPoly = C2 + CosR2*CosPoly */
vfmadd213pd %zmm12, %zmm1, %zmm0
/* SinPoly = C2 + SinR2*SinPoly */
vfmadd213pd %zmm12, %zmm15, %zmm14
/* CosPoly = C1 + CosR2*CosPoly */
vfmadd213pd %zmm13, %zmm1, %zmm0
/* SinPoly = C1 + SinR2*SinPoly */
vfmadd213pd %zmm13, %zmm15, %zmm14
/* CosPoly = CosR2*CosPoly */
vmulpd %zmm1, %zmm0, %zmm1
/* SinPoly = SinR2*SinPoly */
vmulpd %zmm15, %zmm14, %zmm4
/* CosPoly = CosR*CosPoly */
vfmadd213pd %zmm3, %zmm3, %zmm1
/* SinPoly = SinR*SinPoly */
vfmadd213pd %zmm5, %zmm5, %zmm4
vpbroadcastq .L_2il0floatpacket.15(%rip), %zmm3
/* Update Cos result's sign */
vxorpd %zmm2, %zmm1, %zmm1
/* Final reconstruction.
Update Sin result's sign */
vxorpd %zmm6, %zmm4, %zmm0
vpandnq %zmm7, %zmm7, %zmm3{%k1}
vcmppd $3, %zmm3, %zmm3, %k0
kmovw %k0, %ecx
testl %ecx, %ecx
jne .LBL_2_3
.LBL_2_2:
cfi_remember_state
vmovups %zmm0, (%rdi)
vmovups %zmm1, (%rsi)
movq %rbp, %rsp
cfi_def_cfa_register (%rsp)
popq %rbp
cfi_adjust_cfa_offset (-8)
cfi_restore (%rbp)
ret
.LBL_2_3:
cfi_restore_state
vmovups %zmm8, 1152(%rsp)
vmovups %zmm0, 1216(%rsp)
vmovups %zmm1, 1280(%rsp)
je .LBL_2_2
xorb %dl, %dl
xorl %eax, %eax
kmovw %k4, 1048(%rsp)
kmovw %k5, 1040(%rsp)
kmovw %k6, 1032(%rsp)
kmovw %k7, 1024(%rsp)
vmovups %zmm16, 960(%rsp)
vmovups %zmm17, 896(%rsp)
vmovups %zmm18, 832(%rsp)
vmovups %zmm19, 768(%rsp)
vmovups %zmm20, 704(%rsp)
vmovups %zmm21, 640(%rsp)
vmovups %zmm22, 576(%rsp)
vmovups %zmm23, 512(%rsp)
vmovups %zmm24, 448(%rsp)
vmovups %zmm25, 384(%rsp)
vmovups %zmm26, 320(%rsp)
vmovups %zmm27, 256(%rsp)
vmovups %zmm28, 192(%rsp)
vmovups %zmm29, 128(%rsp)
vmovups %zmm30, 64(%rsp)
vmovups %zmm31, (%rsp)
movq %rsi, 1056(%rsp)
movq %r12, 1096(%rsp)
cfi_offset_rel_rsp (12, 1096)
movb %dl, %r12b
movq %r13, 1088(%rsp)
cfi_offset_rel_rsp (13, 1088)
movl %eax, %r13d
movq %r14, 1080(%rsp)
cfi_offset_rel_rsp (14, 1080)
movl %ecx, %r14d
movq %r15, 1072(%rsp)
cfi_offset_rel_rsp (15, 1072)
movq %rbx, 1064(%rsp)
movq %rdi, %rbx
cfi_remember_state
.LBL_2_6:
btl %r13d, %r14d
jc .LBL_2_13
.LBL_2_7:
lea 1(%r13), %esi
btl %esi, %r14d
jc .LBL_2_10
.LBL_2_8:
incb %r12b
addl $2, %r13d
cmpb $16, %r12b
jb .LBL_2_6
kmovw 1048(%rsp), %k4
movq %rbx, %rdi
kmovw 1040(%rsp), %k5
kmovw 1032(%rsp), %k6
kmovw 1024(%rsp), %k7
vmovups 960(%rsp), %zmm16
vmovups 896(%rsp), %zmm17
vmovups 832(%rsp), %zmm18
vmovups 768(%rsp), %zmm19
vmovups 704(%rsp), %zmm20
vmovups 640(%rsp), %zmm21
vmovups 576(%rsp), %zmm22
vmovups 512(%rsp), %zmm23
vmovups 448(%rsp), %zmm24
vmovups 384(%rsp), %zmm25
vmovups 320(%rsp), %zmm26
vmovups 256(%rsp), %zmm27
vmovups 192(%rsp), %zmm28
vmovups 128(%rsp), %zmm29
vmovups 64(%rsp), %zmm30
vmovups (%rsp), %zmm31
vmovups 1216(%rsp), %zmm0
vmovups 1280(%rsp), %zmm1
movq 1056(%rsp), %rsi
movq 1096(%rsp), %r12
cfi_restore (%r12)
movq 1088(%rsp), %r13
cfi_restore (%r13)
movq 1080(%rsp), %r14
cfi_restore (%r14)
movq 1072(%rsp), %r15
cfi_restore (%r15)
movq 1064(%rsp), %rbx
jmp .LBL_2_2
.LBL_2_10:
cfi_restore_state
movzbl %r12b, %r15d
shlq $4, %r15
vmovsd 1160(%rsp,%r15), %xmm0
vzeroupper
vmovsd 1160(%rsp,%r15), %xmm0
call JUMPTARGET(sin)
vmovsd %xmm0, 1224(%rsp,%r15)
vmovsd 1160(%rsp,%r15), %xmm0
call JUMPTARGET(cos)
vmovsd %xmm0, 1288(%rsp,%r15)
jmp .LBL_2_8
.LBL_2_13:
movzbl %r12b, %r15d
shlq $4, %r15
vmovsd 1152(%rsp,%r15), %xmm0
vzeroupper
vmovsd 1152(%rsp,%r15), %xmm0
call JUMPTARGET(sin)
vmovsd %xmm0, 1216(%rsp,%r15)
vmovsd 1152(%rsp,%r15), %xmm0
call JUMPTARGET(cos)
vmovsd %xmm0, 1280(%rsp,%r15)
jmp .LBL_2_7
#endif
END (_ZGVeN8vl8l8_sincos_skx)
libmvec_hidden_def(_ZGVeN8vl8l8_sincos_skx)
/* Wrapper between vvv and vl8l8 vector variants. */
.macro WRAPPER_AVX512_vvv_vl8l8 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 $256, %rsp
vmovups %zmm1, 128(%rsp)
lea (%rsp), %rdi
vmovups %zmm2, 192(%rdi)
lea 64(%rsp), %rsi
call HIDDEN_JUMPTARGET(\callee)
movq 128(%rsp), %rdx
movq 136(%rsp), %rsi
movq 144(%rsp), %r8
movq 152(%rsp), %r10
movq (%rsp), %rax
movq 8(%rsp), %rcx
movq 16(%rsp), %rdi
movq 24(%rsp), %r9
movq %rax, (%rdx)
movq %rcx, (%rsi)
movq 160(%rsp), %rax
movq 168(%rsp), %rcx
movq %rdi, (%r8)
movq %r9, (%r10)
movq 176(%rsp), %rdi
movq 184(%rsp), %r9
movq 32(%rsp), %r11
movq 40(%rsp), %rdx
movq 48(%rsp), %rsi
movq 56(%rsp), %r8
movq %r11, (%rax)
movq %rdx, (%rcx)
movq 192(%rsp), %r11
movq 200(%rsp), %rdx
movq %rsi, (%rdi)
movq %r8, (%r9)
movq 208(%rsp), %rsi
movq 216(%rsp), %r8
movq 64(%rsp), %r10
movq 72(%rsp), %rax
movq 80(%rsp), %rcx
movq 88(%rsp), %rdi
movq %r10, (%r11)
movq %rax, (%rdx)
movq 224(%rsp), %r10
movq 232(%rsp), %rax
movq %rcx, (%rsi)
movq %rdi, (%r8)
movq 240(%rsp), %rcx
movq 248(%rsp), %rdi
movq 96(%rsp), %r9
movq 104(%rsp), %r11
movq 112(%rsp), %rdx
movq 120(%rsp), %rsi
movq %r9, (%r10)
movq %r11, (%rax)
movq %rdx, (%rcx)
movq %rsi, (%rdi)
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 %r10
.cfi_escape 0xf,0x3,0x76,0x78,0x6
leal -112(%rbp), %esi
leal -176(%rbp), %edi
subl $232, %esp
vmovdqa %ymm1, -208(%ebp)
vmovdqa %ymm2, -240(%ebp)
call HIDDEN_JUMPTARGET(\callee)
vmovdqa -208(%ebp), %xmm0
vmovq %xmm0, %rax
vmovsd -176(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -168(%ebp), %xmm0
vmovsd %xmm0, (%eax)
movq -200(%ebp), %rax
vmovsd -160(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -152(%ebp), %xmm0
vmovsd %xmm0, (%eax)
movq -192(%ebp), %rax
vmovsd -144(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -136(%ebp), %xmm0
vmovsd %xmm0, (%eax)
movq -184(%ebp), %rax
vmovsd -128(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -120(%ebp), %xmm0
vmovsd %xmm0, (%eax)
vmovdqa -240(%ebp), %xmm0
vmovq %xmm0, %rax
vmovsd -112(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -104(%ebp), %xmm0
vmovsd %xmm0, (%eax)
movq -232(%ebp), %rax
vmovsd -96(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -88(%ebp), %xmm0
vmovsd %xmm0, (%eax)
movq -224(%ebp), %rax
vmovsd -80(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -72(%ebp), %xmm0
vmovsd %xmm0, (%eax)
movq -216(%ebp), %rax
vmovsd -64(%ebp), %xmm0
vmovsd %xmm0, (%eax)
shrq $32, %rax
vmovsd -56(%ebp), %xmm0
vmovsd %xmm0, (%eax)
addl $232, %esp
popq %r10
.cfi_def_cfa 10, 0
popq %rbp
leal -8(%r10), %esp
.cfi_def_cfa 7, 8
ret
#endif
.endm
ENTRY (_ZGVeN8vvv_sincos_knl)
WRAPPER_AVX512_vvv_vl8l8 _ZGVeN8vl8l8_sincos_knl
END (_ZGVeN8vvv_sincos_knl)
ENTRY (_ZGVeN8vvv_sincos_skx)
WRAPPER_AVX512_vvv_vl8l8 _ZGVeN8vl8l8_sincos_skx
END (_ZGVeN8vvv_sincos_skx)
.section .rodata, "a"
.L_2il0floatpacket.15:
.long 0xffffffff,0xffffffff
.type .L_2il0floatpacket.15,@object
|