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
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX2-SLOW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fast-variable-shuffle | FileCheck %s --check-prefix=AVX --check-prefix=AVX2 --check-prefix=AVX2-FAST
; 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 | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BWVL
define void @shuffle_v32i8_to_v16i8_1(<32 x i8>* %L, <16 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v16i8_1:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vmovdqa %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v16i8_1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vmovdqa %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: shuffle_v32i8_to_v16i8_1:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovdqa (%rdi), %ymm0
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
store <16 x i8> %strided.vec, <16 x i8>* %S
ret void
}
define void @shuffle_v16i16_to_v8i16_1(<16 x i16>* %L, <8 x i16>* %S) nounwind {
; AVX1-LABEL: shuffle_v16i16_to_v8i16_1:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT: vmovdqa %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v16i16_to_v8i16_1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT: vmovdqa %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512-LABEL: shuffle_v16i16_to_v8i16_1:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovdqa (%rdi), %ymm0
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512-NEXT: vmovdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
; AVX512-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512-NEXT: vmovdqa %xmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <16 x i16>, <16 x i16>* %L
%strided.vec = shufflevector <16 x i16> %vec, <16 x i16> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
store <8 x i16> %strided.vec, <8 x i16>* %S
ret void
}
define void @shuffle_v8i32_to_v4i32_1(<8 x i32>* %L, <4 x i32>* %S) nounwind {
; AVX-LABEL: shuffle_v8i32_to_v4i32_1:
; AVX: # %bb.0:
; AVX-NEXT: vmovaps (%rdi), %ymm0
; AVX-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX-NEXT: vmovaps %xmm0, (%rsi)
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq
;
; AVX512-LABEL: shuffle_v8i32_to_v4i32_1:
; AVX512: # %bb.0:
; AVX512-NEXT: vmovaps (%rdi), %ymm0
; AVX512-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX512-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX512-NEXT: vmovaps %xmm0, (%rsi)
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
%vec = load <8 x i32>, <8 x i32>* %L
%strided.vec = shufflevector <8 x i32> %vec, <8 x i32> undef, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
store <4 x i32> %strided.vec, <4 x i32>* %S
ret void
}
define void @shuffle_v32i8_to_v8i8_1(<32 x i8>* %L, <8 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v8i8_1:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v8i8_1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-NEXT: vmovq %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v8i8_1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v8i8_1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512VL-NEXT: vmovq %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v8i8_1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; 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, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v8i8_1:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [1,1,5,5,9,9,13,13,13,13,5,5,12,12,13,13]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovwb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v8i8_2(<32 x i8>* %L, <8 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v8i8_2:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v8i8_2:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-NEXT: vmovq %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v8i8_2:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v8i8_2:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = <2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512VL-NEXT: vmovq %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v8i8_2:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <2,6,10,14,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v8i8_2:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [2,3,6,7,10,11,14,15,14,15,10,11,12,13,14,15]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovwb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <8 x i32> <i32 2, i32 6, i32 10, i32 14, i32 18, i32 22, i32 26, i32 30>
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v8i8_3(<32 x i8>* %L, <8 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v8i8_3:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v8i8_3:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-NEXT: vmovq %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v8i8_3:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v8i8_3:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = <3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512VL-NEXT: vmovq %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v8i8_3:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v8i8_3:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [3,3,7,7,11,11,15,15,7,7,15,15,6,6,7,7]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovwb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <8 x i32> <i32 3, i32 7, i32 11, i32 15, i32 19, i32 23, i32 27, i32 31>
store <8 x i8> %strided.vec, <8 x i8>* %S
ret void
}
define void @shuffle_v16i16_to_v4i16_1(<16 x i16>* %L, <4 x i16>* %S) nounwind {
; AVX1-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,3,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,3,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-SLOW-NEXT: vmovq %xmm0, (%rsi)
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = [2,3,10,11,8,9,10,11,8,9,10,11,12,13,14,15]
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-FAST-NEXT: vmovq %xmm0, (%rsi)
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,3,2,3,4,5,6,7]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,1,3,3,4,5,6,7]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,1,3,3,4,5,6,7]
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdw %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,3,2,3,4,5,6,7]
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,3,2,3,4,5,6,7]
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v16i16_to_v4i16_1:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,1,3,3,4,5,6,7]
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,1,3,3,4,5,6,7]
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdw %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <16 x i16>, <16 x i16>* %L
%strided.vec = shufflevector <16 x i16> %vec, <16 x i16> undef, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
store <4 x i16> %strided.vec, <4 x i16>* %S
ret void
}
define void @shuffle_v16i16_to_v4i16_2(<16 x i16>* %L, <4 x i16>* %S) nounwind {
; AVX1-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[2,0,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[2,0,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-SLOW-NEXT: vmovq %xmm0, (%rsi)
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = [4,5,12,13,4,5,6,7,8,9,10,11,12,13,14,15]
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-FAST-NEXT: vmovq %xmm0, (%rsi)
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[2,0,2,3,4,5,6,7]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovaps (%rdi), %ymm0
; AVX512VL-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX512VL-NEXT: vpmovdw %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[2,0,2,3,4,5,6,7]
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7]
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v16i16_to_v4i16_2:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovaps (%rdi), %ymm0
; AVX512BWVL-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX512BWVL-NEXT: vpmovdw %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <16 x i16>, <16 x i16>* %L
%strided.vec = shufflevector <16 x i16> %vec, <16 x i16> undef, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
store <4 x i16> %strided.vec, <4 x i16>* %S
ret void
}
define void @shuffle_v16i16_to_v4i16_3(<16 x i16>* %L, <4 x i16>* %S) nounwind {
; AVX1-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX1-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
; AVX1-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX1-NEXT: vmovq %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-SLOW-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX2-SLOW: # %bb.0:
; AVX2-SLOW-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-SLOW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX2-SLOW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
; AVX2-SLOW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-SLOW-NEXT: vmovq %xmm0, (%rsi)
; AVX2-SLOW-NEXT: vzeroupper
; AVX2-SLOW-NEXT: retq
;
; AVX2-FAST-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX2-FAST: # %bb.0:
; AVX2-FAST-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-FAST-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-FAST-NEXT: vmovdqa {{.*#+}} xmm2 = [6,7,14,15,4,5,6,7,8,9,10,11,12,13,14,15]
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-FAST-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-FAST-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-FAST-NEXT: vmovq %xmm0, (%rsi)
; AVX2-FAST-NEXT: vzeroupper
; AVX2-FAST-NEXT: retq
;
; AVX512F-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
; AVX512F-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512F-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
; AVX512F-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512F-NEXT: vmovq %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdw %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,2,3,4,5,6,7]
; AVX512BW-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512BW-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,3,4,5,6,7]
; AVX512BW-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX512BW-NEXT: vmovq %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v16i16_to_v4i16_3:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdw %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <16 x i16>, <16 x i16>* %L
%strided.vec = shufflevector <16 x i16> %vec, <16 x i16> undef, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
store <4 x i16> %strided.vec, <4 x i16>* %S
ret void
}
define void @shuffle_v32i8_to_v4i8_1(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v4i8_1:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vmovd %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v4i8_1:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vmovd %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v4i8_1:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v4i8_1:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [1,1,255,255,9,9,255,255,9,9,255,255,11,11,255,255]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v4i8_1:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <1,9,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v4i8_1:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [1,1,255,255,9,9,255,255,9,9,255,255,11,11,255,255]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <4 x i32> <i32 1, i32 9, i32 17, i32 25>
store <4 x i8> %strided.vec, <4 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v4i8_2(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v4i8_2:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vmovd %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v4i8_2:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vmovd %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v4i8_2:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v4i8_2:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,1,3,3,4,5,6,7]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,1,3,3,4,5,6,7]
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v4i8_2:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <2,10,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v4i8_2:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[1,1,3,3,4,5,6,7]
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[1,1,3,3,4,5,6,7]
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <4 x i32> <i32 2, i32 10, i32 18, i32 26>
store <4 x i8> %strided.vec, <4 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v4i8_3(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v4i8_3:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vmovd %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v4i8_3:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vmovd %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v4i8_3:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v4i8_3:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [3,3,11,11,11,11,3,3,8,8,9,9,10,10,11,11]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v4i8_3:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <3,11,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v4i8_3:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [3,3,11,11,11,11,3,3,8,8,9,9,10,10,11,11]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <4 x i32> <i32 3, i32 11, i32 19, i32 27>
store <4 x i8> %strided.vec, <4 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v4i8_4(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v4i8_4:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vmovd %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v4i8_4:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vmovd %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v4i8_4:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v4i8_4:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovaps (%rdi), %ymm0
; AVX512VL-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v4i8_4:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <4,12,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v4i8_4:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovaps (%rdi), %ymm0
; AVX512BWVL-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm1[1,3]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <4 x i32> <i32 4, i32 12, i32 20, i32 28>
store <4 x i8> %strided.vec, <4 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v4i8_5(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v4i8_5:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vmovd %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v4i8_5:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vmovd %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v4i8_5:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v4i8_5:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [5,5,13,13,13,13,5,5,4,4,5,5,6,6,7,7]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v4i8_5:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <5,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v4i8_5:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [5,5,13,13,13,13,5,5,4,4,5,5,6,6,7,7]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <4 x i32> <i32 5, i32 13, i32 21, i32 29>
store <4 x i8> %strided.vec, <4 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v4i8_6(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v4i8_6:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vmovd %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v4i8_6:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vmovd %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v4i8_6:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v4i8_6:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
; AVX512VL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512VL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v4i8_6:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <6,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v4i8_6:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm1 = xmm1[3,1,1,3,4,5,6,7]
; AVX512BWVL-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,1,2,3]
; AVX512BWVL-NEXT: vpshuflw {{.*#+}} xmm0 = xmm0[3,1,1,3,4,5,6,7]
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <4 x i32> <i32 6, i32 14, i32 22, i32 30>
store <4 x i8> %strided.vec, <4 x i8>* %S
ret void
}
define void @shuffle_v32i8_to_v4i8_7(<32 x i8>* %L, <4 x i8>* %S) nounwind {
; AVX1-LABEL: shuffle_v32i8_to_v4i8_7:
; AVX1: # %bb.0:
; AVX1-NEXT: vmovdqa (%rdi), %ymm0
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = <7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX1-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX1-NEXT: vmovd %xmm0, (%rsi)
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v32i8_to_v4i8_7:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa (%rdi), %ymm0
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX2-NEXT: vmovdqa {{.*#+}} xmm2 = <7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX2-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX2-NEXT: vmovd %xmm0, (%rsi)
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
; AVX512F-LABEL: shuffle_v32i8_to_v4i8_7:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT: vmovdqa {{.*#+}} xmm2 = <7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512F-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512F-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512F-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512F-NEXT: vmovd %xmm0, (%rsi)
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: shuffle_v32i8_to_v4i8_7:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT: vmovdqa {{.*#+}} xmm2 = [7,7,14,14,15,15,14,14,15,15,4,4,5,5,6,6]
; AVX512VL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512VL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512VL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512VL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512BW-LABEL: shuffle_v32i8_to_v4i8_7:
; AVX512BW: # %bb.0:
; AVX512BW-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BW-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BW-NEXT: vmovdqa {{.*#+}} xmm2 = <7,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX512BW-NEXT: vmovd %xmm0, (%rsi)
; AVX512BW-NEXT: vzeroupper
; AVX512BW-NEXT: retq
;
; AVX512BWVL-LABEL: shuffle_v32i8_to_v4i8_7:
; AVX512BWVL: # %bb.0:
; AVX512BWVL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512BWVL-NEXT: vextracti128 $1, %ymm0, %xmm1
; AVX512BWVL-NEXT: vmovdqa {{.*#+}} xmm2 = [7,7,14,14,15,15,14,14,15,15,4,4,5,5,6,6]
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm1, %xmm1
; AVX512BWVL-NEXT: vpshufb %xmm2, %xmm0, %xmm0
; AVX512BWVL-NEXT: vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BWVL-NEXT: vpmovdb %xmm0, (%rsi)
; AVX512BWVL-NEXT: vzeroupper
; AVX512BWVL-NEXT: retq
%vec = load <32 x i8>, <32 x i8>* %L
%strided.vec = shufflevector <32 x i8> %vec, <32 x i8> undef, <4 x i32> <i32 7, i32 15, i32 23, i32 31>
store <4 x i8> %strided.vec, <4 x i8>* %S
ret void
}
|
