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
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s --check-prefixes=AVX2
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx512f | FileCheck %s --check-prefixes=AVX512,AVX512F
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx512f,avx512vl | FileCheck %s --check-prefixes=AVX512,AVX512VL
define <4 x float> @fadd_v4f32(<4 x i1> %b, <4 x float> noundef %x, <4 x float> noundef %y) {
; AVX2-LABEL: fadd_v4f32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpslld $31, %xmm0, %xmm0
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm3 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX2-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
; AVX2-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fadd_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; AVX512F-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} xmm0 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fadd_v4f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmd %xmm0, %xmm0, %k1
; AVX512VL-NEXT: vaddps %xmm2, %xmm1, %xmm1 {%k1}
; AVX512VL-NEXT: vmovaps %xmm1, %xmm0
; AVX512VL-NEXT: retq
%s = select <4 x i1> %b, <4 x float> %y, <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>
%r = fadd <4 x float> %x, %s
ret <4 x float> %r
}
define <8 x float> @fadd_v8f32_commute(<8 x i1> %b, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fadd_v8f32_commute:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX2-NEXT: vblendvps %ymm0, %ymm2, %ymm3, %ymm0
; AVX2-NEXT: vaddps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fadd_v8f32_commute:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm2 killed $ymm2 def $zmm2
; AVX512F-NEXT: vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm0 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vaddps %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fadd_v8f32_commute:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovsxwd %xmm0, %ymm0
; AVX512VL-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vaddps %ymm2, %ymm1, %ymm1 {%k1}
; AVX512VL-NEXT: vmovaps %ymm1, %ymm0
; AVX512VL-NEXT: retq
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>
%r = fadd <8 x float> %s, %x
ret <8 x float> %r
}
define <16 x float> @fadd_v16f32_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fadd_v16f32_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vaddps %ymm3, %ymm1, %ymm0
; AVX2-NEXT: vaddps %ymm4, %ymm2, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fadd_v16f32_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vaddps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: vmovaps %zmm1, %zmm0 {%k1}
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, <16 x float> %y
%r = fadd <16 x float> %x, %s
ret <16 x float> %r
}
define <16 x float> @fadd_v16f32_commute_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fadd_v16f32_commute_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vaddps %ymm1, %ymm3, %ymm0
; AVX2-NEXT: vaddps %ymm2, %ymm4, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fadd_v16f32_commute_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vaddps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: vmovaps %zmm1, %zmm0 {%k1}
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, <16 x float> %y
%r = fadd <16 x float> %s, %x
ret <16 x float> %r
}
define <4 x float> @fsub_v4f32(<4 x i1> %b, <4 x float> noundef %x, <4 x float> noundef %y) {
; AVX2-LABEL: fsub_v4f32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpslld $31, %xmm0, %xmm0
; AVX2-NEXT: vpsrad $31, %xmm0, %xmm0
; AVX2-NEXT: vpand %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vsubps %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fsub_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; AVX512F-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1} {z}
; AVX512F-NEXT: vsubps %xmm0, %xmm1, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fsub_v4f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmd %xmm0, %xmm0, %k1
; AVX512VL-NEXT: vsubps %xmm2, %xmm1, %xmm1 {%k1}
; AVX512VL-NEXT: vmovaps %xmm1, %xmm0
; AVX512VL-NEXT: retq
%s = select <4 x i1> %b, <4 x float> %y, <4 x float> zeroinitializer
%r = fsub <4 x float> %x, %s
ret <4 x float> %r
}
; negative test - fsub is not commutative; there is no identity constant for operand 0
define <8 x float> @fsub_v8f32_commute(<8 x i1> %b, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fsub_v8f32_commute:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vpsrad $31, %ymm0, %ymm0
; AVX2-NEXT: vpand %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vsubps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fsub_v8f32_commute:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm2 killed $ymm2 def $zmm2
; AVX512F-NEXT: vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1} {z}
; AVX512F-NEXT: vsubps %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fsub_v8f32_commute:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovsxwd %xmm0, %ymm0
; AVX512VL-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vmovaps %ymm2, %ymm0 {%k1} {z}
; AVX512VL-NEXT: vsubps %ymm1, %ymm0, %ymm0
; AVX512VL-NEXT: retq
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> zeroinitializer
%r = fsub <8 x float> %s, %x
ret <8 x float> %r
}
define <16 x float> @fsub_v16f32_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fsub_v16f32_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm5 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vpsrad $31, %ymm5, %ymm5
; AVX2-NEXT: vpandn %ymm4, %ymm5, %ymm4
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vpsrad $31, %ymm0, %ymm0
; AVX2-NEXT: vpandn %ymm3, %ymm0, %ymm0
; AVX2-NEXT: vsubps %ymm0, %ymm1, %ymm0
; AVX2-NEXT: vsubps %ymm4, %ymm2, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fsub_v16f32_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vsubps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: vmovaps %zmm1, %zmm0 {%k1}
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> zeroinitializer, <16 x float> %y
%r = fsub <16 x float> %x, %s
ret <16 x float> %r
}
; negative test - fsub is not commutative; there is no identity constant for operand 0
define <16 x float> @fsub_v16f32_commute_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fsub_v16f32_commute_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm5 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vpsrad $31, %ymm5, %ymm5
; AVX2-NEXT: vpandn %ymm4, %ymm5, %ymm4
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vpsrad $31, %ymm0, %ymm0
; AVX2-NEXT: vpandn %ymm3, %ymm0, %ymm0
; AVX2-NEXT: vsubps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vsubps %ymm2, %ymm4, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fsub_v16f32_commute_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestnmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vmovaps %zmm2, %zmm0 {%k1} {z}
; AVX512-NEXT: vsubps %zmm1, %zmm0, %zmm0
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> zeroinitializer, <16 x float> %y
%r = fsub <16 x float> %s, %x
ret <16 x float> %r
}
define <4 x float> @fmul_v4f32(<4 x i1> %b, <4 x float> noundef %x, <4 x float> noundef %y) {
; AVX2-LABEL: fmul_v4f32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpslld $31, %xmm0, %xmm0
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
; AVX2-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fmul_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; AVX512F-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} xmm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fmul_v4f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmd %xmm0, %xmm0, %k1
; AVX512VL-NEXT: vmulps %xmm2, %xmm1, %xmm1 {%k1}
; AVX512VL-NEXT: vmovaps %xmm1, %xmm0
; AVX512VL-NEXT: retq
%s = select <4 x i1> %b, <4 x float> %y, <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>
%r = fmul <4 x float> %x, %s
ret <4 x float> %r
}
define <8 x float> @fmul_v8f32_commute(<8 x i1> %b, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fmul_v8f32_commute:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm0, %ymm2, %ymm3, %ymm0
; AVX2-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fmul_v8f32_commute:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm2 killed $ymm2 def $zmm2
; AVX512F-NEXT: vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fmul_v8f32_commute:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovsxwd %xmm0, %ymm0
; AVX512VL-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vmulps %ymm2, %ymm1, %ymm1 {%k1}
; AVX512VL-NEXT: vmovaps %ymm1, %ymm0
; AVX512VL-NEXT: retq
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
%r = fmul <8 x float> %s, %x
ret <8 x float> %r
}
define <16 x float> @fmul_v16f32_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fmul_v16f32_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vmulps %ymm3, %ymm1, %ymm0
; AVX2-NEXT: vmulps %ymm4, %ymm2, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fmul_v16f32_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vmulps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: vmovaps %zmm1, %zmm0 {%k1}
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fmul <16 x float> %x, %s
ret <16 x float> %r
}
define <16 x float> @fmul_v16f32_commute_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fmul_v16f32_commute_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vmulps %ymm1, %ymm3, %ymm0
; AVX2-NEXT: vmulps %ymm2, %ymm4, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fmul_v16f32_commute_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vmulps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: vmovaps %zmm1, %zmm0 {%k1}
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fmul <16 x float> %s, %x
ret <16 x float> %r
}
define <4 x float> @fdiv_v4f32(<4 x i1> %b, <4 x float> noundef %x, <4 x float> noundef %y) {
; AVX2-LABEL: fdiv_v4f32:
; AVX2: # %bb.0:
; AVX2-NEXT: vpslld $31, %xmm0, %xmm0
; AVX2-NEXT: vbroadcastss {{.*#+}} xmm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %xmm0, %xmm2, %xmm3, %xmm0
; AVX2-NEXT: vdivps %xmm0, %xmm1, %xmm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fdiv_v4f32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $xmm2 killed $xmm2 def $zmm2
; AVX512F-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} xmm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vdivps %xmm0, %xmm1, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fdiv_v4f32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT: vptestmd %xmm0, %xmm0, %k1
; AVX512VL-NEXT: vdivps %xmm2, %xmm1, %xmm1 {%k1}
; AVX512VL-NEXT: vmovaps %xmm1, %xmm0
; AVX512VL-NEXT: retq
%s = select <4 x i1> %b, <4 x float> %y, <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>
%r = fdiv <4 x float> %x, %s
ret <4 x float> %r
}
define <8 x float> @fdiv_v8f32_commute(<8 x i1> %b, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fdiv_v8f32_commute:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm0, %ymm2, %ymm3, %ymm0
; AVX2-NEXT: vdivps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fdiv_v8f32_commute:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm2 killed $ymm2 def $zmm2
; AVX512F-NEXT: vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT: vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT: vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm2, %zmm0 {%k1}
; AVX512F-NEXT: vdivps %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fdiv_v8f32_commute:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovsxwd %xmm0, %ymm0
; AVX512VL-NEXT: vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT: vptestmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vbroadcastss {{.*#+}} ymm0 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512VL-NEXT: vmovaps %ymm2, %ymm0 {%k1}
; AVX512VL-NEXT: vdivps %ymm1, %ymm0, %ymm0
; AVX512VL-NEXT: retq
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
%r = fdiv <8 x float> %s, %x
ret <8 x float> %r
}
define <16 x float> @fdiv_v16f32_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fdiv_v16f32_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vdivps %ymm3, %ymm1, %ymm0
; AVX2-NEXT: vdivps %ymm4, %ymm2, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fdiv_v16f32_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vdivps %zmm2, %zmm1, %zmm0
; AVX512-NEXT: vmovaps %zmm1, %zmm0 {%k1}
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fdiv <16 x float> %x, %s
ret <16 x float> %r
}
define <16 x float> @fdiv_v16f32_commute_swap(<16 x i1> %b, <16 x float> noundef %x, <16 x float> noundef %y) {
; AVX2-LABEL: fdiv_v16f32_commute_swap:
; AVX2: # %bb.0:
; AVX2-NEXT: vpmovzxbw {{.*#+}} xmm5 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm5 = xmm5[0],zero,xmm5[1],zero,xmm5[2],zero,xmm5[3],zero,xmm5[4],zero,xmm5[5],zero,xmm5[6],zero,xmm5[7],zero
; AVX2-NEXT: vpslld $31, %ymm5, %ymm5
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm5, %ymm6, %ymm3, %ymm3
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
; AVX2-NEXT: vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; AVX2-NEXT: vpslld $31, %ymm0, %ymm0
; AVX2-NEXT: vblendvps %ymm0, %ymm6, %ymm4, %ymm4
; AVX2-NEXT: vdivps %ymm1, %ymm3, %ymm0
; AVX2-NEXT: vdivps %ymm2, %ymm4, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fdiv_v16f32_commute_swap:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovsxbd %xmm0, %zmm0
; AVX512-NEXT: vpslld $31, %zmm0, %zmm0
; AVX512-NEXT: vptestmd %zmm0, %zmm0, %k1
; AVX512-NEXT: vbroadcastss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %zmm2 {%k1}
; AVX512-NEXT: vdivps %zmm1, %zmm2, %zmm0
; AVX512-NEXT: retq
%s = select <16 x i1> %b, <16 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, <16 x float> %y
%r = fdiv <16 x float> %s, %x
ret <16 x float> %r
}
define <8 x float> @fadd_v8f32_cast_cond(i8 noundef zeroext %pb, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fadd_v8f32_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovd %edi, %xmm2
; AVX2-NEXT: vpbroadcastb %xmm2, %ymm2
; AVX2-NEXT: vmovdqa {{.*#+}} ymm3 = [1,2,4,8,16,32,64,128]
; AVX2-NEXT: vpand %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX2-NEXT: vblendvps %ymm2, %ymm1, %ymm3, %ymm1
; AVX2-NEXT: vaddps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fadd_v8f32_cast_cond:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: kmovw %edi, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm2 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX512F-NEXT: vmovaps %zmm1, %zmm2 {%k1}
; AVX512F-NEXT: vaddps %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fadd_v8f32_cast_cond:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: kmovw %edi, %k1
; AVX512VL-NEXT: vaddps %ymm1, %ymm0, %ymm0 {%k1}
; AVX512VL-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>
%r = fadd <8 x float> %x, %s
ret <8 x float> %r
}
define <8 x double> @fadd_v8f64_cast_cond(i8 noundef zeroext %pb, <8 x double> noundef %x, <8 x double> noundef %y) {
; AVX2-LABEL: fadd_v8f64_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: movl %edi, %ecx
; AVX2-NEXT: andb $1, %cl
; AVX2-NEXT: movzbl %cl, %ecx
; AVX2-NEXT: vmovd %ecx, %xmm4
; AVX2-NEXT: vpinsrb $2, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $2, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $4, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $3, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $6, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $4, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $8, %eax, %xmm4, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $5, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $10, %eax, %xmm5, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $6, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $12, %eax, %xmm5, %xmm5
; AVX2-NEXT: shrb $7, %dil
; AVX2-NEXT: movzbl %dil, %eax
; AVX2-NEXT: vpinsrb $14, %eax, %xmm5, %xmm5
; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm5[4,4,5,5,6,6,7,7]
; AVX2-NEXT: vpslld $31, %xmm5, %xmm5
; AVX2-NEXT: vpmovsxdq %xmm5, %ymm5
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; AVX2-NEXT: vblendvpd %ymm5, %ymm3, %ymm6, %ymm3
; AVX2-NEXT: vpmovzxwd {{.*#+}} xmm4 = xmm4[0],zero,xmm4[1],zero,xmm4[2],zero,xmm4[3],zero
; AVX2-NEXT: vpslld $31, %xmm4, %xmm4
; AVX2-NEXT: vpmovsxdq %xmm4, %ymm4
; AVX2-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-NEXT: vaddpd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vaddpd %ymm3, %ymm1, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fadd_v8f64_cast_cond:
; AVX512: # %bb.0:
; AVX512-NEXT: kmovw %edi, %k1
; AVX512-NEXT: vaddpd %zmm1, %zmm0, %zmm0 {%k1}
; AVX512-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x double> %y, <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>
%r = fadd <8 x double> %x, %s
ret <8 x double> %r
}
define <8 x float> @fsub_v8f32_cast_cond(i8 noundef zeroext %pb, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fsub_v8f32_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovd %edi, %xmm2
; AVX2-NEXT: vpbroadcastb %xmm2, %ymm2
; AVX2-NEXT: vmovdqa {{.*#+}} ymm3 = [1,2,4,8,16,32,64,128]
; AVX2-NEXT: vpand %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpxor %xmm3, %xmm3, %xmm3
; AVX2-NEXT: vblendvps %ymm2, %ymm1, %ymm3, %ymm1
; AVX2-NEXT: vsubps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fsub_v8f32_cast_cond:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: kmovw %edi, %k1
; AVX512F-NEXT: vmovaps %zmm1, %zmm1 {%k1} {z}
; AVX512F-NEXT: vsubps %ymm1, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fsub_v8f32_cast_cond:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: kmovw %edi, %k1
; AVX512VL-NEXT: vsubps %ymm1, %ymm0, %ymm0 {%k1}
; AVX512VL-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> zeroinitializer
%r = fsub <8 x float> %x, %s
ret <8 x float> %r
}
define <8 x double> @fsub_v8f64_cast_cond(i8 noundef zeroext %pb, <8 x double> noundef %x, <8 x double> noundef %y) {
; AVX2-LABEL: fsub_v8f64_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: movl %edi, %ecx
; AVX2-NEXT: andb $1, %cl
; AVX2-NEXT: movzbl %cl, %ecx
; AVX2-NEXT: vmovd %ecx, %xmm4
; AVX2-NEXT: vpinsrb $2, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $2, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $4, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $3, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $6, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $4, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $8, %eax, %xmm4, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $5, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $10, %eax, %xmm5, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $6, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $12, %eax, %xmm5, %xmm5
; AVX2-NEXT: shrb $7, %dil
; AVX2-NEXT: movzbl %dil, %eax
; AVX2-NEXT: vpinsrb $14, %eax, %xmm5, %xmm5
; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm5[4,4,5,5,6,6,7,7]
; AVX2-NEXT: vpslld $31, %xmm5, %xmm5
; AVX2-NEXT: vpsrad $31, %xmm5, %xmm5
; AVX2-NEXT: vpmovsxdq %xmm5, %ymm5
; AVX2-NEXT: vpand %ymm3, %ymm5, %ymm3
; AVX2-NEXT: vpmovzxwd {{.*#+}} xmm4 = xmm4[0],zero,xmm4[1],zero,xmm4[2],zero,xmm4[3],zero
; AVX2-NEXT: vpslld $31, %xmm4, %xmm4
; AVX2-NEXT: vpsrad $31, %xmm4, %xmm4
; AVX2-NEXT: vpmovsxdq %xmm4, %ymm4
; AVX2-NEXT: vpand %ymm2, %ymm4, %ymm2
; AVX2-NEXT: vsubpd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vsubpd %ymm3, %ymm1, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fsub_v8f64_cast_cond:
; AVX512: # %bb.0:
; AVX512-NEXT: kmovw %edi, %k1
; AVX512-NEXT: vsubpd %zmm1, %zmm0, %zmm0 {%k1}
; AVX512-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x double> %y, <8 x double> zeroinitializer
%r = fsub <8 x double> %x, %s
ret <8 x double> %r
}
define <8 x float> @fmul_v8f32_cast_cond(i8 noundef zeroext %pb, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fmul_v8f32_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovd %edi, %xmm2
; AVX2-NEXT: vpbroadcastb %xmm2, %ymm2
; AVX2-NEXT: vmovdqa {{.*#+}} ymm3 = [1,2,4,8,16,32,64,128]
; AVX2-NEXT: vpand %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm2, %ymm1, %ymm3, %ymm1
; AVX2-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fmul_v8f32_cast_cond:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: kmovw %edi, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm1, %zmm2 {%k1}
; AVX512F-NEXT: vmulps %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fmul_v8f32_cast_cond:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: kmovw %edi, %k1
; AVX512VL-NEXT: vmulps %ymm1, %ymm0, %ymm0 {%k1}
; AVX512VL-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
%r = fmul <8 x float> %x, %s
ret <8 x float> %r
}
define <8 x double> @fmul_v8f64_cast_cond(i8 noundef zeroext %pb, <8 x double> noundef %x, <8 x double> noundef %y) {
; AVX2-LABEL: fmul_v8f64_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: movl %edi, %ecx
; AVX2-NEXT: andb $1, %cl
; AVX2-NEXT: movzbl %cl, %ecx
; AVX2-NEXT: vmovd %ecx, %xmm4
; AVX2-NEXT: vpinsrb $2, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $2, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $4, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $3, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $6, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $4, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $8, %eax, %xmm4, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $5, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $10, %eax, %xmm5, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $6, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $12, %eax, %xmm5, %xmm5
; AVX2-NEXT: shrb $7, %dil
; AVX2-NEXT: movzbl %dil, %eax
; AVX2-NEXT: vpinsrb $14, %eax, %xmm5, %xmm5
; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm5[4,4,5,5,6,6,7,7]
; AVX2-NEXT: vpslld $31, %xmm5, %xmm5
; AVX2-NEXT: vpmovsxdq %xmm5, %ymm5
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvpd %ymm5, %ymm3, %ymm6, %ymm3
; AVX2-NEXT: vpmovzxwd {{.*#+}} xmm4 = xmm4[0],zero,xmm4[1],zero,xmm4[2],zero,xmm4[3],zero
; AVX2-NEXT: vpslld $31, %xmm4, %xmm4
; AVX2-NEXT: vpmovsxdq %xmm4, %ymm4
; AVX2-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-NEXT: vmulpd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vmulpd %ymm3, %ymm1, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fmul_v8f64_cast_cond:
; AVX512: # %bb.0:
; AVX512-NEXT: kmovw %edi, %k1
; AVX512-NEXT: vmulpd %zmm1, %zmm0, %zmm0 {%k1}
; AVX512-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x double> %y, <8 x double> <double 1.0, double 1.0, double 1.0, double 1.0, double 1.0, double 1.0, double 1.0, double 1.0>
%r = fmul <8 x double> %x, %s
ret <8 x double> %r
}
define <8 x float> @fdiv_v8f32_cast_cond(i8 noundef zeroext %pb, <8 x float> noundef %x, <8 x float> noundef %y) {
; AVX2-LABEL: fdiv_v8f32_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovd %edi, %xmm2
; AVX2-NEXT: vpbroadcastb %xmm2, %ymm2
; AVX2-NEXT: vmovdqa {{.*#+}} ymm3 = [1,2,4,8,16,32,64,128]
; AVX2-NEXT: vpand %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vpcmpeqd %ymm3, %ymm2, %ymm2
; AVX2-NEXT: vbroadcastss {{.*#+}} ymm3 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvps %ymm2, %ymm1, %ymm3, %ymm1
; AVX2-NEXT: vdivps %ymm1, %ymm0, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: fdiv_v8f32_cast_cond:
; AVX512F: # %bb.0:
; AVX512F-NEXT: # kill: def $ymm1 killed $ymm1 def $zmm1
; AVX512F-NEXT: kmovw %edi, %k1
; AVX512F-NEXT: vbroadcastss {{.*#+}} ymm2 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX512F-NEXT: vmovaps %zmm1, %zmm2 {%k1}
; AVX512F-NEXT: vdivps %ymm2, %ymm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: fdiv_v8f32_cast_cond:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: kmovw %edi, %k1
; AVX512VL-NEXT: vdivps %ymm1, %ymm0, %ymm0 {%k1}
; AVX512VL-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x float> %y, <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>
%r = fdiv <8 x float> %x, %s
ret <8 x float> %r
}
define <8 x double> @fdiv_v8f64_cast_cond(i8 noundef zeroext %pb, <8 x double> noundef %x, <8 x double> noundef %y) {
; AVX2-LABEL: fdiv_v8f64_cast_cond:
; AVX2: # %bb.0:
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: movl %edi, %ecx
; AVX2-NEXT: andb $1, %cl
; AVX2-NEXT: movzbl %cl, %ecx
; AVX2-NEXT: vmovd %ecx, %xmm4
; AVX2-NEXT: vpinsrb $2, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $2, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $4, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $3, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $6, %eax, %xmm4, %xmm4
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $4, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $8, %eax, %xmm4, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $5, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $10, %eax, %xmm5, %xmm5
; AVX2-NEXT: movl %edi, %eax
; AVX2-NEXT: shrb $6, %al
; AVX2-NEXT: andb $1, %al
; AVX2-NEXT: movzbl %al, %eax
; AVX2-NEXT: vpinsrb $12, %eax, %xmm5, %xmm5
; AVX2-NEXT: shrb $7, %dil
; AVX2-NEXT: movzbl %dil, %eax
; AVX2-NEXT: vpinsrb $14, %eax, %xmm5, %xmm5
; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm5[4,4,5,5,6,6,7,7]
; AVX2-NEXT: vpslld $31, %xmm5, %xmm5
; AVX2-NEXT: vpmovsxdq %xmm5, %ymm5
; AVX2-NEXT: vbroadcastsd {{.*#+}} ymm6 = [1.0E+0,1.0E+0,1.0E+0,1.0E+0]
; AVX2-NEXT: vblendvpd %ymm5, %ymm3, %ymm6, %ymm3
; AVX2-NEXT: vpmovzxwd {{.*#+}} xmm4 = xmm4[0],zero,xmm4[1],zero,xmm4[2],zero,xmm4[3],zero
; AVX2-NEXT: vpslld $31, %xmm4, %xmm4
; AVX2-NEXT: vpmovsxdq %xmm4, %ymm4
; AVX2-NEXT: vblendvpd %ymm4, %ymm2, %ymm6, %ymm2
; AVX2-NEXT: vdivpd %ymm2, %ymm0, %ymm0
; AVX2-NEXT: vdivpd %ymm3, %ymm1, %ymm1
; AVX2-NEXT: retq
;
; AVX512-LABEL: fdiv_v8f64_cast_cond:
; AVX512: # %bb.0:
; AVX512-NEXT: kmovw %edi, %k1
; AVX512-NEXT: vdivpd %zmm1, %zmm0, %zmm0 {%k1}
; AVX512-NEXT: retq
%b = bitcast i8 %pb to <8 x i1>
%s = select <8 x i1> %b, <8 x double> %y, <8 x double> <double 1.0, double 1.0, double 1.0, double 1.0, double 1.0, double 1.0, double 1.0, double 1.0>
%r = fdiv <8 x double> %x, %s
ret <8 x double> %r
}
|
