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
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512BWVL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vbmi,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VBMI
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vbmi,+avx512vl,+fast-variable-shuffle | FileCheck %s --check-prefixes=AVX512,AVX512VBMIVL
; PR31551
; Pairs of shufflevector:trunc functions with functional equivalence.
; Ideally, the shuffles should be lowered to code with the same quality as the truncates.
define void @shuffle_v64i8_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
; AVX512F-LABEL: shuffle_v64i8_to_v32i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512F-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
; AVX512F-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512F-NEXT: vmovdqa %ymm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v64i8_to_v32i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512VL-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,5,7]
; AVX512VL-NEXT: vpermi2q %ymm1, %ymm0, %ymm2
; AVX512VL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v64i8_to_v32i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512BW-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
; AVX512BW-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512BW-NEXT: vmovdqa %ymm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v64i8_to_v32i8:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512BWVL-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,5,7]
; AVX512BWVL-NEXT: vpermi2q %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: shuffle_v64i8_to_v32i8:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMI-NEXT: vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30]
; AVX512VBMI-NEXT: vpshufb {{.*#+}} ymm0 = ymm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u,16,18,20,22,24,26,28,30,u,u,u,u,u,u,u,u]
; AVX512VBMI-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
; AVX512VBMI-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512VBMI-NEXT: vmovdqa %ymm0, (%rsi)
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: shuffle_v64i8_to_v32i8:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62]
; AVX512VBMIVL-NEXT: vpermi2b %ymm1, %ymm0, %ymm2
; AVX512VBMIVL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%strided.vec = shufflevector <64 x i8> %vec, <64 x i8> undef, <32 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30, i32 32, i32 34, i32 36, i32 38, i32 40, i32 42, i32 44, i32 46, i32 48, i32 50, i32 52, i32 54, i32 56, i32 58, i32 60, i32 62>
store <32 x i8> %strided.vec, <32 x i8>* %S
ret void
}
define void @trunc_v32i16_to_v32i8(<64 x i8>* %L, <32 x i8>* %S) nounwind {
; AVX512F-LABEL: trunc_v32i16_to_v32i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpmovsxwd (%rdi), %zmm0
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
; AVX512F-NEXT: vpmovsxwd 32(%rdi), %zmm1
; AVX512F-NEXT: vpmovdb %zmm1, %xmm1
; AVX512F-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512F-NEXT: vmovdqa %ymm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc_v32i16_to_v32i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpmovsxwd (%rdi), %zmm0
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
; AVX512VL-NEXT: vpmovsxwd 32(%rdi), %zmm1
; AVX512VL-NEXT: vpmovdb %zmm1, %xmm1
; AVX512VL-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX512VL-NEXT: vmovdqa %ymm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc_v32i16_to_v32i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vpmovwb %zmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc_v32i16_to_v32i8:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vpmovwb %zmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: trunc_v32i16_to_v32i8:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMI-NEXT: vpmovwb %zmm0, (%rsi)
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: trunc_v32i16_to_v32i8:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vpmovwb %zmm0, (%rsi)
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%bc = bitcast <64 x i8> %vec to <32 x i16>
%strided.vec = trunc <32 x i16> %bc to <32 x i8>
store <32 x i8> %strided.vec, <32 x i8>* %S
ret void
}
define void @shuffle_v32i16_to_v16i16(<32 x i16>* %L, <16 x i16>* %S) nounwind {
; AVX512F-LABEL: shuffle_v32i16_to_v16i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpshuflw {{.*#+}} ymm0 = mem[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512F-NEXT: vpshufhw {{.*#+}} ymm0 = ymm0[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512F-NEXT: vpshuflw {{.*#+}} ymm1 = mem[0,2,2,3,4,5,6,7,8,10,10,11,12,13,14,15]
; AVX512F-NEXT: vpshufhw {{.*#+}} ymm1 = ymm1[0,1,2,3,4,6,6,7,8,9,10,11,12,14,14,15]
; AVX512F-NEXT: vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[0,2],ymm1[4,6],ymm0[4,6]
; AVX512F-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512F-NEXT: vmovaps %ymm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i16_to_v16i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,4,5,6,7,8,9,12,13,12,13,14,15,16,17,20,21,20,21,22,23,24,25,28,29,28,29,30,31]
; AVX512VL-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX512VL-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,8,10,12,14]
; AVX512VL-NEXT: vpermi2d %ymm1, %ymm0, %ymm2
; AVX512VL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i16_to_v16i16:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,4,5,6,7,8,9,12,13,12,13,14,15,16,17,20,21,20,21,22,23,24,25,28,29,28,29,30,31]
; AVX512BW-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX512BW-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX512BW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX512BW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512BW-NEXT: vmovaps %ymm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i16_to_v16i16:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30]
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: shuffle_v32i16_to_v16i16:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} ymm2 = [0,1,4,5,4,5,6,7,8,9,12,13,12,13,14,15,16,17,20,21,20,21,22,23,24,25,28,29,28,29,30,31]
; AVX512VBMI-NEXT: vpshufb %ymm2, %ymm1, %ymm1
; AVX512VBMI-NEXT: vpshufb %ymm2, %ymm0, %ymm0
; AVX512VBMI-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX512VBMI-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512VBMI-NEXT: vmovaps %ymm0, (%rsi)
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: shuffle_v32i16_to_v16i16:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30]
; AVX512VBMIVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512VBMIVL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%vec = load <32 x i16>, <32 x i16>* %L
%strided.vec = shufflevector <32 x i16> %vec, <32 x i16> undef, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
store <16 x i16> %strided.vec, <16 x i16>* %S
ret void
}
define void @trunc_v16i32_to_v16i16(<32 x i16>* %L, <16 x i16>* %S) nounwind {
; AVX512-LABEL: trunc_v16i32_to_v16i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovdw %zmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <32 x i16>, <32 x i16>* %L
%bc = bitcast <32 x i16> %vec to <16 x i32>
%strided.vec = trunc <16 x i32> %bc to <16 x i16>
store <16 x i16> %strided.vec, <16 x i16>* %S
ret void
}
define void @shuffle_v16i32_to_v8i32(<16 x i32>* %L, <8 x i32>* %S) nounwind {
; AVX512F-LABEL: shuffle_v16i32_to_v8i32:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovaps (%rdi), %zmm0
; AVX512F-NEXT: vextractf64x4 $1, %zmm0, %ymm1
; AVX512F-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX512F-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512F-NEXT: vmovaps %ymm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v16i32_to_v8i32:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,8,10,12,14]
; AVX512VL-NEXT: vpermi2d %ymm1, %ymm0, %ymm2
; AVX512VL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v16i32_to_v8i32:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovaps (%rdi), %zmm0
; AVX512BW-NEXT: vextractf64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX512BW-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512BW-NEXT: vmovaps %ymm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v16i32_to_v8i32:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,8,10,12,14]
; AVX512BWVL-NEXT: vpermi2d %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: shuffle_v16i32_to_v8i32:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovaps (%rdi), %zmm0
; AVX512VBMI-NEXT: vextractf64x4 $1, %zmm0, %ymm1
; AVX512VBMI-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
; AVX512VBMI-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX512VBMI-NEXT: vmovaps %ymm0, (%rsi)
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: shuffle_v16i32_to_v8i32:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = [0,2,4,6,8,10,12,14]
; AVX512VBMIVL-NEXT: vpermi2d %ymm1, %ymm0, %ymm2
; AVX512VBMIVL-NEXT: vmovdqa %ymm2, (%rsi)
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%vec = load <16 x i32>, <16 x i32>* %L
%strided.vec = shufflevector <16 x i32> %vec, <16 x i32> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
store <8 x i32> %strided.vec, <8 x i32>* %S
ret void
}
define void @trunc_v8i64_to_v8i32(<16 x i32>* %L, <8 x i32>* %S) nounwind {
; AVX512-LABEL: trunc_v8i64_to_v8i32:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovqd %zmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <16 x i32>, <16 x i32>* %L
%bc = bitcast <16 x i32> %vec to <8 x i64>
%strided.vec = trunc <8 x i64> %bc to <8 x i32>
store <8 x i32> %strided.vec, <8 x i32>* %S
ret void
}
define void @shuffle_v64i8_to_v16i8(<64 x i8>* %L, <16 x i8>* %S) nounwind {
; AVX512F-LABEL: shuffle_v64i8_to_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v64i8_to_v16i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v64i8_to_v16i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BW-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v64i8_to_v16i8:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BWVL-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: shuffle_v64i8_to_v16i8:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMI-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,0,4,8,12,u,u,u,u,u,u,u,u>
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VBMI-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VBMI-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: shuffle_v64i8_to_v16i8:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,4,8,12,16,20,24,28,32,36,40,44,48,52,56,60,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMIVL-NEXT: vpermi2b %ymm1, %ymm0, %ymm2
; AVX512VBMIVL-NEXT: vmovdqa %xmm2, (%rsi)
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%strided.vec = shufflevector <64 x i8> %vec, <64 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28, i32 32, i32 36, i32 40, i32 44, i32 48, i32 52, i32 56, i32 60>
store <16 x i8> %strided.vec, <16 x i8>* %S
ret void
}
define void @trunc_v16i32_to_v16i8(<64 x i8>* %L, <16 x i8>* %S) nounwind {
; AVX512-LABEL: trunc_v16i32_to_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovdb %zmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%bc = bitcast <64 x i8> %vec to <16 x i32>
%strided.vec = trunc <16 x i32> %bc to <16 x i8>
store <16 x i8> %strided.vec, <16 x i8>* %S
ret void
}
define void @shuffle_v32i16_to_v8i16(<32 x i16>* %L, <8 x i16>* %S) nounwind {
; AVX512F-LABEL: shuffle_v32i16_to_v8i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,1,0,2,4,5,6,7]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[0,1,0,2,4,5,6,7]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vpshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm2 = xmm2[0,2,2,3,4,5,6,7]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i16_to_v8i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,2,3,0,1,8,9,8,9,10,11,12,13,14,15]
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,8,9,8,9,10,11,8,9,10,11,12,13,14,15]
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i16_to_v8i16:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,2,3,0,1,8,9,8,9,10,11,12,13,14,15]
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,8,9,8,9,10,11,8,9,10,11,12,13,14,15]
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BW-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i16_to_v8i16:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,4,8,12,16,20,24,28,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vmovdqa %xmm2, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: shuffle_v32i16_to_v8i16:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMI-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,2,3,0,1,8,9,8,9,10,11,12,13,14,15]
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = [0,1,8,9,8,9,10,11,8,9,10,11,12,13,14,15]
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VBMI-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VBMI-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: shuffle_v32i16_to_v8i16:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,4,8,12,16,20,24,28,u,u,u,u,u,u,u,u>
; AVX512VBMIVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512VBMIVL-NEXT: vmovdqa %xmm2, (%rsi)
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%vec = load <32 x i16>, <32 x i16>* %L
%strided.vec = shufflevector <32 x i16> %vec, <32 x i16> undef, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
store <8 x i16> %strided.vec, <8 x i16>* %S
ret void
}
define void @trunc_v8i64_to_v8i16(<32 x i16>* %L, <8 x i16>* %S) nounwind {
; AVX512-LABEL: trunc_v8i64_to_v8i16:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovqw %zmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <32 x i16>, <32 x i16>* %L
%bc = bitcast <32 x i16> %vec to <8 x i64>
%strided.vec = trunc <8 x i64> %bc to <8 x i16>
store <8 x i16> %strided.vec, <8 x i16>* %S
ret void
}
define void @shuffle_v64i8_to_v8i8(<64 x i8>* %L, <8 x i8>* %S) nounwind {
; AVX512F-LABEL: shuffle_v64i8_to_v8i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v64i8_to_v8i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqa 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512VL-NEXT: vmovq %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v64i8_to_v8i8:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v64i8_to_v8i8:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,4,8,12,16,20,24,28,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vpmovwb %xmm2, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: shuffle_v64i8_to_v8i8:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMI-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VBMI-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VBMI-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512VBMI-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512VBMI-NEXT: vmovq %xmm0, (%rsi)
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: shuffle_v64i8_to_v8i8:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,4,8,12,16,20,24,28,u,u,u,u,u,u,u,u>
; AVX512VBMIVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512VBMIVL-NEXT: vpmovwb %xmm2, (%rsi)
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%strided.vec = shufflevector <64 x i8> %vec, <64 x i8> undef, <8 x i32> <i32 0, i32 8, i32 16, i32 24, i32 32, i32 40, i32 48, i32 56>
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
define void @trunc_v8i64_to_v8i8(<64 x i8>* %L, <8 x i8>* %S) nounwind {
; AVX512-LABEL: trunc_v8i64_to_v8i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovdqa64 (%rdi), %zmm0
; AVX512-NEXT: vpmovqb %zmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <64 x i8>, <64 x i8>* %L
%bc = bitcast <64 x i8> %vec to <8 x i64>
%strided.vec = trunc <8 x i64> %bc to <8 x i8>
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
define <16 x i8> @trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61(<64 x i8> %x) {
; AVX512F-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BW-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BW-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512BWVL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMI-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u>
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm1, %xmm1
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VBMI-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VBMI-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_61:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm1 = <1,5,9,13,17,21,25,29,33,37,41,45,49,53,57,61,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMIVL-NEXT: vpermi2b %ymm2, %ymm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa %xmm1, %xmm0
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 61>
ret <16 x i8> %res
}
define <16 x i8> @trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62(<64 x i8> %x) {
; AVX512F-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512F-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm3, %xmm2, %xmm2
; AVX512VL-NEXT: vpshufb %xmm3, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm2
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm2
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512BWVL-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512BWVL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512BWVL-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VBMI-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMI-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VBMI-NEXT: vpshufb %xmm2, %xmm0, %xmm2
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VBMI-NEXT: vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
; AVX512VBMI-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
; AVX512VBMI-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; AVX512VBMI-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX512VBMI-NEXT: vzeroupper
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm2
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm1 = <1,5,9,13,17,21,25,29,33,37,41,45,49,53,57,62,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMIVL-NEXT: vpermi2b %ymm2, %ymm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa %xmm1, %xmm0
; AVX512VBMIVL-NEXT: vzeroupper
; AVX512VBMIVL-NEXT: retq
%res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 62>
ret <16 x i8> %res
}
define <4 x double> @PR34175(<32 x i16>* %p) {
; AVX512F-LABEL: PR34175:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqu (%rdi), %ymm0
; AVX512F-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512F-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512F-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512F-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512F-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX512F-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: PR34175:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqu (%rdi), %ymm0
; AVX512VL-NEXT: vmovdqu 32(%rdi), %ymm1
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512VL-NEXT: vextracti128 $1, %ymm1, %xmm2
; AVX512VL-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3]
; AVX512VL-NEXT: vpbroadcastd %xmm1, %xmm1
; AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
; AVX512VL-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX512VL-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: PR34175:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqu64 (%rdi), %zmm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512BW-NEXT: vpbroadcastd %xmm0, %xmm0
; AVX512BW-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
; AVX512BW-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX512BW-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: PR34175:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqu64 (%rdi), %zmm0
; AVX512BWVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,8,16,24,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BWVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512BWVL-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
; AVX512BWVL-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512BWVL-NEXT: retq
;
; AVX512VBMI-LABEL: PR34175:
; AVX512VBMI: # %bb.0:
; AVX512VBMI-NEXT: vmovdqu64 (%rdi), %zmm0
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VBMI-NEXT: vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512VBMI-NEXT: vextracti64x4 $1, %zmm0, %ymm0
; AVX512VBMI-NEXT: vextracti128 $1, %ymm0, %xmm2
; AVX512VBMI-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; AVX512VBMI-NEXT: vpbroadcastd %xmm0, %xmm0
; AVX512VBMI-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
; AVX512VBMI-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX512VBMI-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512VBMI-NEXT: retq
;
; AVX512VBMIVL-LABEL: PR34175:
; AVX512VBMIVL: # %bb.0:
; AVX512VBMIVL-NEXT: vmovdqu64 (%rdi), %zmm0
; AVX512VBMIVL-NEXT: vextracti64x4 $1, %zmm0, %ymm1
; AVX512VBMIVL-NEXT: vmovdqa {{.*#+}} ymm2 = <0,8,16,24,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VBMIVL-NEXT: vpermi2w %ymm1, %ymm0, %ymm2
; AVX512VBMIVL-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm2[0],zero,xmm2[1],zero,xmm2[2],zero,xmm2[3],zero
; AVX512VBMIVL-NEXT: vcvtdq2pd %xmm0, %ymm0
; AVX512VBMIVL-NEXT: retq
%v = load <32 x i16>, <32 x i16>* %p, align 2
%shuf = shufflevector <32 x i16> %v, <32 x i16> undef, <4 x i32> <i32 0, i32 8, i32 16, i32 24>
%tofp = uitofp <4 x i16> %shuf to <4 x double>
ret <4 x double> %tofp
}
define <16 x i8> @trunc_v8i64_to_v8i8_return_v16i8(<8 x i64> %vec) nounwind {
; AVX512-LABEL: trunc_v8i64_to_v8i8_return_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: vpmovqb %zmm0, %xmm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%truncated = trunc <8 x i64> %vec to <8 x i8>
%result = shufflevector <8 x i8> %truncated, <8 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
ret <16 x i8> %result
}
|
