llvm.org GIT mirror llvm / release_60 test / CodeGen / X86 / vector-shuffle-v1.ll
release_60

Tree @release_60 (Download .tar.gz)

vector-shuffle-v1.ll @release_60raw · history · blame

  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
; 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=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw -mattr=+avx512vl -mattr=+avx512dq| FileCheck %s --check-prefix=VL_BW_DQ

define <2 x i1> @shuf2i1_1_0(<2 x i1> %a) {
; AVX512F-LABEL: shuf2i1_1_0:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,3,0,1]
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf2i1_1_0:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpsllq $63, %xmm0, %xmm0
; AVX512VL-NEXT:    vptestmq %xmm0, %xmm0, %k1
; AVX512VL-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX512VL-NEXT:    vmovdqa64 %xmm0, %xmm1 {%k1} {z}
; AVX512VL-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; AVX512VL-NEXT:    vptestmq %xmm1, %xmm1, %k1
; AVX512VL-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf2i1_1_0:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    vpsllq $63, %xmm0, %xmm0
; VL_BW_DQ-NEXT:    vptestmq %xmm0, %xmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2q %k0, %xmm0
; VL_BW_DQ-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
; VL_BW_DQ-NEXT:    vpmovq2m %xmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2q %k0, %xmm0
; VL_BW_DQ-NEXT:    retq
  %b = shufflevector <2 x i1> %a, <2 x i1> undef, <2 x i32> <i32 1, i32 0>
  ret <2 x i1> %b
}

define <2 x i1> @shuf2i1_1_2(<2 x i1> %a) {
; AVX512F-LABEL: shuf2i1_1_2:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    movl $1, %eax
; AVX512F-NEXT:    vmovq %rax, %xmm1
; AVX512F-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7]
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf2i1_1_2:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpsllq $63, %xmm0, %xmm0
; AVX512VL-NEXT:    vptestmq %xmm0, %xmm0, %k1
; AVX512VL-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX512VL-NEXT:    vmovdqa64 %xmm0, %xmm1 {%k1} {z}
; AVX512VL-NEXT:    movq $-1, %rax
; AVX512VL-NEXT:    vmovq %rax, %xmm2
; AVX512VL-NEXT:    vpalignr {{.*#+}} xmm1 = xmm1[8,9,10,11,12,13,14,15],xmm2[0,1,2,3,4,5,6,7]
; AVX512VL-NEXT:    vptestmq %xmm1, %xmm1, %k1
; AVX512VL-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf2i1_1_2:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    vpsllq $63, %xmm0, %xmm0
; VL_BW_DQ-NEXT:    vptestmq %xmm0, %xmm0, %k0
; VL_BW_DQ-NEXT:    movq $-1, %rax
; VL_BW_DQ-NEXT:    vmovq %rax, %xmm0
; VL_BW_DQ-NEXT:    vpmovm2q %k0, %xmm1
; VL_BW_DQ-NEXT:    vpalignr {{.*#+}} xmm0 = xmm1[8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7]
; VL_BW_DQ-NEXT:    vpmovq2m %xmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2q %k0, %xmm0
; VL_BW_DQ-NEXT:    retq
  %b = shufflevector <2 x i1> %a, <2 x i1> <i1 1, i1 0>, <2 x i32> <i32 1, i32 2>
  ret <2 x i1> %b
}


define <4 x i1> @shuf4i1_3_2_10(<4 x i1> %a) {
; AVX512F-LABEL: shuf4i1_3_2_10:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf4i1_3_2_10:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpslld $31, %xmm0, %xmm0
; AVX512VL-NEXT:    vptestmd %xmm0, %xmm0, %k1
; AVX512VL-NEXT:    vpcmpeqd %xmm0, %xmm0, %xmm0
; AVX512VL-NEXT:    vmovdqa32 %xmm0, %xmm1 {%k1} {z}
; AVX512VL-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[3,2,1,0]
; AVX512VL-NEXT:    vptestmd %xmm1, %xmm1, %k1
; AVX512VL-NEXT:    vmovdqa32 %xmm0, %xmm0 {%k1} {z}
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf4i1_3_2_10:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    vpslld $31, %xmm0, %xmm0
; VL_BW_DQ-NEXT:    vptestmd %xmm0, %xmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %xmm0
; VL_BW_DQ-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[3,2,1,0]
; VL_BW_DQ-NEXT:    vpmovd2m %xmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %xmm0
; VL_BW_DQ-NEXT:    retq
  %b = shufflevector <4 x i1> %a, <4 x i1> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
  ret <4 x i1> %b
}

define <8 x i1> @shuf8i1_3_6_1_0_3_7_7_0(<8 x i64> %a, <8 x i64> %b, <8 x i64> %a1, <8 x i64> %b1) {
; AVX512F-LABEL: shuf8i1_3_6_1_0_3_7_7_0:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vpcmpeqq %zmm2, %zmm0, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [3,6,1,0,3,7,7,0]
; AVX512F-NEXT:    vpermq %zmm0, %zmm1, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vpmovdw %zmm0, %ymm0
; AVX512F-NEXT:    # kill: def %xmm0 killed %xmm0 killed %ymm0
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1_3_6_1_0_3_7_7_0:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpcmpeqq %zmm2, %zmm0, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm1 {%k1} {z}
; AVX512VL-NEXT:    vmovdqa {{.*#+}} ymm2 = [3,6,1,0,3,7,7,0]
; AVX512VL-NEXT:    vpermd %ymm1, %ymm2, %ymm1
; AVX512VL-NEXT:    vptestmd %ymm1, %ymm1, %k1
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT:    vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1_3_6_1_0_3_7_7_0:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    vpcmpeqq %zmm2, %zmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vmovdqa {{.*#+}} ymm1 = [3,6,1,0,3,7,7,0]
; VL_BW_DQ-NEXT:    vpermd %ymm0, %ymm1, %ymm0
; VL_BW_DQ-NEXT:    vpmovd2m %ymm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2w %k0, %xmm0
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %a2 = icmp eq <8 x i64> %a, %a1
  %b2 = icmp eq <8 x i64> %b, %b1
  %c = shufflevector <8 x i1> %a2, <8 x i1> %b2, <8 x i32> <i32 3, i32 6, i32 1, i32 0, i32 3, i32 7, i32 7, i32 0>
  ret <8 x i1> %c
}

define <16 x i1> @shuf16i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0(<16 x i32> %a, <16 x i32> %b, <16 x i32> %a1, <16 x i32> %b1) {
; AVX512F-LABEL: shuf16i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vpcmpeqd %zmm2, %zmm0, %k1
; AVX512F-NEXT:    vpcmpeqd %zmm3, %zmm1, %k2
; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k2} {z}
; AVX512F-NEXT:    vpternlogd $255, %zmm1, %zmm1, %zmm1 {%k1} {z}
; AVX512F-NEXT:    vmovdqa32 {{.*#+}} zmm2 = [3,6,22,12,3,7,7,0,3,6,1,13,3,21,7,0]
; AVX512F-NEXT:    vpermi2d %zmm0, %zmm1, %zmm2
; AVX512F-NEXT:    vptestmd %zmm2, %zmm2, %k1
; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf16i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpcmpeqd %zmm2, %zmm0, %k1
; AVX512VL-NEXT:    vpcmpeqd %zmm3, %zmm1, %k2
; AVX512VL-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k2} {z}
; AVX512VL-NEXT:    vpternlogd $255, %zmm1, %zmm1, %zmm1 {%k1} {z}
; AVX512VL-NEXT:    vmovdqa32 {{.*#+}} zmm2 = [3,6,22,12,3,7,7,0,3,6,1,13,3,21,7,0]
; AVX512VL-NEXT:    vpermi2d %zmm0, %zmm1, %zmm2
; AVX512VL-NEXT:    vptestmd %zmm2, %zmm2, %k1
; AVX512VL-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf16i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    vpcmpeqd %zmm2, %zmm0, %k0
; VL_BW_DQ-NEXT:    vpcmpeqd %zmm3, %zmm1, %k1
; VL_BW_DQ-NEXT:    vpmovm2d %k1, %zmm0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %zmm1
; VL_BW_DQ-NEXT:    vmovdqa32 {{.*#+}} zmm2 = [3,6,22,12,3,7,7,0,3,6,1,13,3,21,7,0]
; VL_BW_DQ-NEXT:    vpermi2d %zmm0, %zmm1, %zmm2
; VL_BW_DQ-NEXT:    vpmovd2m %zmm2, %k0
; VL_BW_DQ-NEXT:    vpmovm2b %k0, %xmm0
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %a2 = icmp eq <16 x i32> %a, %a1
  %b2 = icmp eq <16 x i32> %b, %b1
  %c = shufflevector <16 x i1> %a2, <16 x i1> %b2, <16 x i32> <i32 3, i32 6, i32 22, i32 12, i32 3, i32 7, i32 7, i32 0, i32 3, i32 6, i32 1, i32 13, i32 3, i32 21, i32 7, i32 0>
  ret <16 x i1> %c
}

define <32 x i1> @shuf32i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0(<32 x i1> %a) {
; AVX512F-LABEL: shuf32i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vpshufb {{.*#+}} ymm1 = ymm0[3,6,u,12,3,7,7,0,3,6,1,13,3,u,7,0,u,u,22,u,u,u,u,u,u,u,u,u,u,21,u,u]
; AVX512F-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX512F-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,6,u,u,u,u,u,u,u,u,u,u,5,u,u,19,22,u,28,19,23,23,16,19,22,17,29,19,u,23,16]
; AVX512F-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,0,255,255,255,255,255,255,255,255,255,255,0,255,255,0,0,255,0,0,0,0,0,0,0,0,0,0,255,0,0]
; AVX512F-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf32i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpshufb {{.*#+}} ymm1 = ymm0[3,6,u,12,3,7,7,0,3,6,1,13,3,u,7,0,u,u,22,u,u,u,u,u,u,u,u,u,u,21,u,u]
; AVX512VL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX512VL-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,6,u,u,u,u,u,u,u,u,u,u,5,u,u,19,22,u,28,19,23,23,16,19,22,17,29,19,u,23,16]
; AVX512VL-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,0,255,255,255,255,255,255,255,255,255,255,0,255,255,0,0,255,0,0,0,0,0,0,0,0,0,0,255,0,0]
; AVX512VL-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf32i1_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0_3_6_22_12_3_7_7_0_3_6_1_13_3_21_7_0:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    vpsllw $7, %ymm0, %ymm0
; VL_BW_DQ-NEXT:    vpmovb2m %ymm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2w %k0, %zmm0
; VL_BW_DQ-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [3,6,22,12,3,7,7,0,3,6,1,13,3,21,7,0,3,6,22,12,3,7,7,0,3,6,1,13,3,21,7,0]
; VL_BW_DQ-NEXT:    vpermw %zmm0, %zmm1, %zmm0
; VL_BW_DQ-NEXT:    vpmovw2m %zmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2b %k0, %ymm0
; VL_BW_DQ-NEXT:    retq
  %b = shufflevector <32 x i1> %a, <32 x i1> undef, <32 x i32> <i32 3, i32 6, i32 22, i32 12, i32 3, i32 7, i32 7, i32 0, i32 3, i32 6, i32 1, i32 13, i32 3, i32 21, i32 7, i32 0, i32 3, i32 6, i32 22, i32 12, i32 3, i32 7, i32 7, i32 0, i32 3, i32 6, i32 1, i32 13, i32 3, i32 21, i32 7, i32 0>
  ret <32 x i1> %b
}

define <8 x i1> @shuf8i1_u_2_u_u_2_u_2_u(i8 %a) {
; AVX512F-LABEL: shuf8i1_u_2_u_u_2_u_2_u:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    kmovw %edi, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm0
; AVX512F-NEXT:    vpbroadcastq %xmm0, %zmm0
; AVX512F-NEXT:    vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vpmovdw %zmm0, %ymm0
; AVX512F-NEXT:    # kill: def %xmm0 killed %xmm0 killed %ymm0
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1_u_2_u_u_2_u_2_u:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    kmovw %edi, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm1 {%k1} {z}
; AVX512VL-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,2,3,3]
; AVX512VL-NEXT:    vpbroadcastq %xmm1, %ymm1
; AVX512VL-NEXT:    vpslld $31, %ymm1, %ymm1
; AVX512VL-NEXT:    vptestmd %ymm1, %ymm1, %k1
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT:    vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1_u_2_u_u_2_u_2_u:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovd %edi, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; VL_BW_DQ-NEXT:    vpbroadcastq %xmm0, %ymm0
; VL_BW_DQ-NEXT:    vpmovd2m %ymm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2w %k0, %xmm0
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i8 %a to <8 x i1>
  %c = shufflevector < 8 x i1> %b, <8 x i1>undef, <8 x i32> <i32 undef, i32 2, i32 undef, i32 undef, i32 2, i32 undef, i32 2, i32 undef>
  ret <8 x i1> %c
}

define i8 @shuf8i1_10_2_9_u_3_u_2_u(i8 %a) {
; AVX512F-LABEL: shuf8i1_10_2_9_u_3_u_2_u:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    kmovw %edi, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT:    vmovdqa64 {{.*#+}} zmm2 = <8,2,10,u,3,u,2,u>
; AVX512F-NEXT:    vpermi2q %zmm1, %zmm0, %zmm2
; AVX512F-NEXT:    vpsllq $63, %zmm2, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k0
; AVX512F-NEXT:    kmovw %k0, %eax
; AVX512F-NEXT:    # kill: def %al killed %al killed %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1_10_2_9_u_3_u_2_u:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    kmovw %edi, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[3,2,2,3]
; AVX512VL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX512VL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3,4,5,6,7]
; AVX512VL-NEXT:    vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT:    vptestmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT:    kmovw %k0, %eax
; AVX512VL-NEXT:    # kill: def %al killed %al killed %eax
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1_10_2_9_u_3_u_2_u:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovd %edi, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[3,2,2,3]
; VL_BW_DQ-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
; VL_BW_DQ-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; VL_BW_DQ-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3,4,5,6,7]
; VL_BW_DQ-NEXT:    vpmovd2m %ymm0, %k0
; VL_BW_DQ-NEXT:    kmovd %k0, %eax
; VL_BW_DQ-NEXT:    # kill: def %al killed %al killed %eax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i8 %a to <8 x i1>
  %c = shufflevector < 8 x i1> %b, <8 x i1> zeroinitializer, <8 x i32> <i32 10, i32 2, i32 9, i32 undef, i32 3, i32 undef, i32 2, i32 undef>
  %d = bitcast <8 x i1> %c to i8
  ret i8 %d
}

define i8 @shuf8i1_0_1_4_5_u_u_u_u(i8 %a) {
; AVX512F-LABEL: shuf8i1_0_1_4_5_u_u_u_u:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    kmovw %edi, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,4,5,0,1,0,1]
; AVX512F-NEXT:    vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k0
; AVX512F-NEXT:    kmovw %k0, %eax
; AVX512F-NEXT:    # kill: def %al killed %al killed %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1_0_1_4_5_u_u_u_u:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    kmovw %edi, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX512VL-NEXT:    vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT:    vptestmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT:    kmovw %k0, %eax
; AVX512VL-NEXT:    # kill: def %al killed %al killed %eax
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1_0_1_4_5_u_u_u_u:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovd %edi, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; VL_BW_DQ-NEXT:    vpmovd2m %ymm0, %k0
; VL_BW_DQ-NEXT:    kmovd %k0, %eax
; VL_BW_DQ-NEXT:    # kill: def %al killed %al killed %eax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i8 %a to <8 x i1>
  %c = shufflevector < 8 x i1> %b, <8 x i1> undef, <8 x i32> <i32 0, i32 1, i32 4, i32 5, i32 undef, i32 undef, i32 undef, i32 undef>
  %d = bitcast <8 x i1> %c to i8
  ret i8 %d
}

define i8 @shuf8i1_9_6_1_0_3_7_7_0(i8 %a) {
; AVX512F-LABEL: shuf8i1_9_6_1_0_3_7_7_0:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    kmovw %edi, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512F-NEXT:    vmovdqa64 {{.*#+}} zmm2 = [8,6,1,0,3,7,7,0]
; AVX512F-NEXT:    vpermi2q %zmm1, %zmm0, %zmm2
; AVX512F-NEXT:    vptestmq %zmm2, %zmm2, %k0
; AVX512F-NEXT:    kmovw %k0, %eax
; AVX512F-NEXT:    # kill: def %al killed %al killed %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1_9_6_1_0_3_7_7_0:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    kmovw %edi, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT:    vmovdqa {{.*#+}} ymm2 = [8,6,1,0,3,7,7,0]
; AVX512VL-NEXT:    vpermi2d %ymm1, %ymm0, %ymm2
; AVX512VL-NEXT:    vptestmd %ymm2, %ymm2, %k0
; AVX512VL-NEXT:    kmovw %k0, %eax
; AVX512VL-NEXT:    # kill: def %al killed %al killed %eax
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1_9_6_1_0_3_7_7_0:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovd %edi, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; VL_BW_DQ-NEXT:    vmovdqa {{.*#+}} ymm2 = [8,6,1,0,3,7,7,0]
; VL_BW_DQ-NEXT:    vpermi2d %ymm1, %ymm0, %ymm2
; VL_BW_DQ-NEXT:    vpmovd2m %ymm2, %k0
; VL_BW_DQ-NEXT:    kmovd %k0, %eax
; VL_BW_DQ-NEXT:    # kill: def %al killed %al killed %eax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i8 %a to <8 x i1>
  %c = shufflevector <8 x i1> %b, <8 x i1> zeroinitializer, <8 x i32> <i32 9, i32 6, i32 1, i32 0, i32 3, i32 7, i32 7, i32 0>
  %d = bitcast <8 x i1>%c to i8
  ret i8 %d
}

define i8 @shuf8i1_9_6_1_10_3_7_7_0(i8 %a) {
; AVX512F-LABEL: shuf8i1_9_6_1_10_3_7_7_0:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    kmovw %edi, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [9,1,2,10,4,5,6,7]
; AVX512F-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; AVX512F-NEXT:    vpermt2q %zmm0, %zmm1, %zmm2
; AVX512F-NEXT:    vptestmq %zmm2, %zmm2, %k0
; AVX512F-NEXT:    kmovw %k0, %eax
; AVX512F-NEXT:    # kill: def %al killed %al killed %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1_9_6_1_10_3_7_7_0:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    kmovw %edi, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,2]
; AVX512VL-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX512VL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2],ymm0[3],ymm1[4,5,6,7]
; AVX512VL-NEXT:    vptestmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT:    kmovw %k0, %eax
; AVX512VL-NEXT:    # kill: def %al killed %al killed %eax
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1_9_6_1_10_3_7_7_0:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovd %edi, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,2]
; VL_BW_DQ-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; VL_BW_DQ-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2],ymm0[3],ymm1[4,5,6,7]
; VL_BW_DQ-NEXT:    vpmovd2m %ymm0, %k0
; VL_BW_DQ-NEXT:    kmovd %k0, %eax
; VL_BW_DQ-NEXT:    # kill: def %al killed %al killed %eax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i8 %a to <8 x i1>
  %c = shufflevector <8 x i1> zeroinitializer, <8 x i1> %b, <8 x i32> <i32 9, i32 6, i32 1, i32 10, i32 3, i32 7, i32 7, i32 0>
  %d = bitcast <8 x i1>%c to i8
  ret i8 %d
}

define i8 @shuf8i1__9_6_1_10_3_7_7_1(i8 %a) {
; AVX512F-LABEL: shuf8i1__9_6_1_10_3_7_7_1:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    kmovw %edi, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [9,6,1,0,3,7,7,1]
; AVX512F-NEXT:    vmovdqa64 {{.*#+}} zmm2 = [18446744073709551615,18446744073709551615,0,0,18446744073709551615,18446744073709551615,0,0]
; AVX512F-NEXT:    vpermt2q %zmm0, %zmm1, %zmm2
; AVX512F-NEXT:    vptestmq %zmm2, %zmm2, %k0
; AVX512F-NEXT:    kmovw %k0, %eax
; AVX512F-NEXT:    # kill: def %al killed %al killed %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1__9_6_1_10_3_7_7_1:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    kmovw %edi, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; AVX512VL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],mem[1,2,3,4,5,6,7]
; AVX512VL-NEXT:    vptestmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT:    kmovw %k0, %eax
; AVX512VL-NEXT:    # kill: def %al killed %al killed %eax
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1__9_6_1_10_3_7_7_1:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovd %edi, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; VL_BW_DQ-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],mem[1,2,3,4,5,6,7]
; VL_BW_DQ-NEXT:    vpmovd2m %ymm0, %k0
; VL_BW_DQ-NEXT:    kmovd %k0, %eax
; VL_BW_DQ-NEXT:    # kill: def %al killed %al killed %eax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i8 %a to <8 x i1>
  %c = shufflevector <8 x i1> <i1 1, i1 1, i1 0, i1 0, i1 1, i1 1, i1 0, i1 0>, <8 x i1> %b, <8 x i32> <i32 9, i32 6, i32 1, i32 0, i32 3, i32 7, i32 7, i32 1>
  %c1 = bitcast <8 x i1>%c to i8
  ret i8 %c1
}

define i8 @shuf8i1_9_6_1_10_3_7_7_0_all_ones(<8 x i1> %a) {
; AVX512F-LABEL: shuf8i1_9_6_1_10_3_7_7_0_all_ones:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    vpmovsxwq %xmm0, %zmm0
; AVX512F-NEXT:    vpsllq $63, %zmm0, %zmm0
; AVX512F-NEXT:    vptestmq %zmm0, %zmm0, %k1
; AVX512F-NEXT:    vpternlogq $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vmovdqa64 {{.*#+}} zmm1 = [9,1,2,3,4,5,6,7]
; AVX512F-NEXT:    vpternlogd $255, %zmm2, %zmm2, %zmm2
; AVX512F-NEXT:    vpermt2q %zmm0, %zmm1, %zmm2
; AVX512F-NEXT:    vptestmq %zmm2, %zmm2, %k0
; AVX512F-NEXT:    kmovw %k0, %eax
; AVX512F-NEXT:    # kill: def %al killed %al killed %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf8i1_9_6_1_10_3_7_7_0_all_ones:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    vpmovsxwd %xmm0, %ymm0
; AVX512VL-NEXT:    vpslld $31, %ymm0, %ymm0
; AVX512VL-NEXT:    vptestmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT:    vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT:    vmovdqa32 %ymm0, %ymm1 {%k1} {z}
; AVX512VL-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[1,1,2,3]
; AVX512VL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5,6,7]
; AVX512VL-NEXT:    vptestmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT:    kmovw %k0, %eax
; AVX512VL-NEXT:    # kill: def %al killed %al killed %eax
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf8i1_9_6_1_10_3_7_7_0_all_ones:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    vpsllw $15, %xmm0, %xmm0
; VL_BW_DQ-NEXT:    vpmovw2m %xmm0, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %ymm0
; VL_BW_DQ-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
; VL_BW_DQ-NEXT:    vpcmpeqd %ymm1, %ymm1, %ymm1
; VL_BW_DQ-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4,5,6,7]
; VL_BW_DQ-NEXT:    vpmovd2m %ymm0, %k0
; VL_BW_DQ-NEXT:    kmovd %k0, %eax
; VL_BW_DQ-NEXT:    # kill: def %al killed %al killed %eax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %c = shufflevector <8 x i1> <i1 1, i1 1, i1 1, i1 1, i1 1, i1 1, i1 1, i1 1>, <8 x i1> %a, <8 x i32> <i32 9, i32 6, i32 1, i32 0, i32 3, i32 7, i32 7, i32 0>
  %c1 = bitcast <8 x i1>%c to i8
  ret i8 %c1
}


define i16 @shuf16i1_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0(i16 %a) {
; AVX512F-LABEL: shuf16i1_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    kmovw %edi, %k1
; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vpbroadcastd %xmm0, %zmm0
; AVX512F-NEXT:    vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT:    kmovw %k0, %eax
; AVX512F-NEXT:    # kill: def %ax killed %ax killed %eax
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf16i1_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    kmovw %edi, %k1
; AVX512VL-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512VL-NEXT:    vpbroadcastd %xmm0, %zmm0
; AVX512VL-NEXT:    vptestmd %zmm0, %zmm0, %k0
; AVX512VL-NEXT:    kmovw %k0, %eax
; AVX512VL-NEXT:    # kill: def %ax killed %ax killed %eax
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf16i1_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0_0:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovd %edi, %k0
; VL_BW_DQ-NEXT:    vpmovm2d %k0, %zmm0
; VL_BW_DQ-NEXT:    vpbroadcastd %xmm0, %zmm0
; VL_BW_DQ-NEXT:    vpmovd2m %zmm0, %k0
; VL_BW_DQ-NEXT:    kmovd %k0, %eax
; VL_BW_DQ-NEXT:    # kill: def %ax killed %ax killed %eax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i16 %a to <16 x i1>
  %c = shufflevector < 16 x i1> %b, <16 x i1> undef, <16 x i32> zeroinitializer
  %d = bitcast <16 x i1> %c to i16
  ret i16 %d
}

define i64 @shuf64i1_zero(i64 %a) {
; AVX512F-LABEL: shuf64i1_zero:
; AVX512F:       # %bb.0:
; AVX512F-NEXT:    pushq %rbp
; AVX512F-NEXT:    .cfi_def_cfa_offset 16
; AVX512F-NEXT:    .cfi_offset %rbp, -16
; AVX512F-NEXT:    movq %rsp, %rbp
; AVX512F-NEXT:    .cfi_def_cfa_register %rbp
; AVX512F-NEXT:    andq $-32, %rsp
; AVX512F-NEXT:    subq $96, %rsp
; AVX512F-NEXT:    movl %edi, {{[0-9]+}}(%rsp)
; AVX512F-NEXT:    kmovw {{[0-9]+}}(%rsp), %k1
; AVX512F-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512F-NEXT:    vpbroadcastb %xmm0, %ymm0
; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512F-NEXT:    vpmovsxbd %xmm1, %zmm1
; AVX512F-NEXT:    vpslld $31, %zmm1, %zmm1
; AVX512F-NEXT:    vptestmd %zmm1, %zmm1, %k0
; AVX512F-NEXT:    kmovw %k0, {{[0-9]+}}(%rsp)
; AVX512F-NEXT:    vpmovsxbd %xmm0, %zmm0
; AVX512F-NEXT:    vpslld $31, %zmm0, %zmm0
; AVX512F-NEXT:    vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT:    kmovw %k0, (%rsp)
; AVX512F-NEXT:    movl (%rsp), %ecx
; AVX512F-NEXT:    movq %rcx, %rax
; AVX512F-NEXT:    shlq $32, %rax
; AVX512F-NEXT:    orq %rcx, %rax
; AVX512F-NEXT:    movq %rbp, %rsp
; AVX512F-NEXT:    popq %rbp
; AVX512F-NEXT:    vzeroupper
; AVX512F-NEXT:    retq
;
; AVX512VL-LABEL: shuf64i1_zero:
; AVX512VL:       # %bb.0:
; AVX512VL-NEXT:    pushq %rbp
; AVX512VL-NEXT:    .cfi_def_cfa_offset 16
; AVX512VL-NEXT:    .cfi_offset %rbp, -16
; AVX512VL-NEXT:    movq %rsp, %rbp
; AVX512VL-NEXT:    .cfi_def_cfa_register %rbp
; AVX512VL-NEXT:    andq $-32, %rsp
; AVX512VL-NEXT:    subq $96, %rsp
; AVX512VL-NEXT:    movl %edi, {{[0-9]+}}(%rsp)
; AVX512VL-NEXT:    kmovw {{[0-9]+}}(%rsp), %k1
; AVX512VL-NEXT:    vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
; AVX512VL-NEXT:    vpbroadcastb %xmm0, %ymm0
; AVX512VL-NEXT:    vextracti128 $1, %ymm0, %xmm1
; AVX512VL-NEXT:    vpmovsxbd %xmm1, %zmm1
; AVX512VL-NEXT:    vpslld $31, %zmm1, %zmm1
; AVX512VL-NEXT:    vptestmd %zmm1, %zmm1, %k0
; AVX512VL-NEXT:    kmovw %k0, {{[0-9]+}}(%rsp)
; AVX512VL-NEXT:    vpmovsxbd %xmm0, %zmm0
; AVX512VL-NEXT:    vpslld $31, %zmm0, %zmm0
; AVX512VL-NEXT:    vptestmd %zmm0, %zmm0, %k0
; AVX512VL-NEXT:    kmovw %k0, (%rsp)
; AVX512VL-NEXT:    movl (%rsp), %ecx
; AVX512VL-NEXT:    movq %rcx, %rax
; AVX512VL-NEXT:    shlq $32, %rax
; AVX512VL-NEXT:    orq %rcx, %rax
; AVX512VL-NEXT:    movq %rbp, %rsp
; AVX512VL-NEXT:    popq %rbp
; AVX512VL-NEXT:    vzeroupper
; AVX512VL-NEXT:    retq
;
; VL_BW_DQ-LABEL: shuf64i1_zero:
; VL_BW_DQ:       # %bb.0:
; VL_BW_DQ-NEXT:    kmovq %rdi, %k0
; VL_BW_DQ-NEXT:    vpmovm2b %k0, %zmm0
; VL_BW_DQ-NEXT:    vpbroadcastb %xmm0, %zmm0
; VL_BW_DQ-NEXT:    vpmovb2m %zmm0, %k0
; VL_BW_DQ-NEXT:    kmovq %k0, %rax
; VL_BW_DQ-NEXT:    vzeroupper
; VL_BW_DQ-NEXT:    retq
  %b = bitcast i64 %a to <64 x i1>
  %c = shufflevector < 64 x i1> %b, <64 x i1> undef, <64 x i32> zeroinitializer
  %d = bitcast <64 x i1> %c to i64
  ret i64 %d
}