llvm.org GIT mirror llvm / release_39 test / CodeGen / X86 / vector-trunc.ll
release_39

Tree @release_39 (Download .tar.gz)

vector-trunc.ll @release_39raw · 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
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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse2 | FileCheck %s --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 | FileCheck %s --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=AVX --check-prefix=AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx512bw | FileCheck %s --check-prefix=AVX512BW

define <8 x i32> @trunc8i64_8i32(<8 x i64> %a) {
; SSE2-LABEL: trunc8i64_8i32:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc8i64_8i32:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc8i64_8i32:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,1,0,2]
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE41-NEXT:    pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm3[4,5,6,7]
; SSE41-NEXT:    retq
;
; AVX1-LABEL: trunc8i64_8i32:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm2[4,5,6,7]
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc8i64_8i32:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc8i64_8i32:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <8 x i64> %a to <8 x i32>
  ret <8 x i32> %0
}

define <8 x i16> @trunc8i64_8i16(<8 x i64> %a) {
; SSE2-LABEL: trunc8i64_8i16:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pextrw $4, %xmm1, %eax
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
; SSE2-NEXT:    pextrw $4, %xmm0, %ecx
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE2-NEXT:    pextrw $4, %xmm3, %edx
; SSE2-NEXT:    movd %edx, %xmm1
; SSE2-NEXT:    movd %eax, %xmm3
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; SSE2-NEXT:    pextrw $4, %xmm2, %eax
; SSE2-NEXT:    movd %eax, %xmm1
; SSE2-NEXT:    movd %ecx, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc8i64_8i16:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    pextrw $4, %xmm1, %eax
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
; SSSE3-NEXT:    pextrw $4, %xmm0, %ecx
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSSE3-NEXT:    pextrw $4, %xmm3, %edx
; SSSE3-NEXT:    movd %edx, %xmm1
; SSSE3-NEXT:    movd %eax, %xmm3
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; SSSE3-NEXT:    pextrw $4, %xmm2, %eax
; SSSE3-NEXT:    movd %eax, %xmm1
; SSSE3-NEXT:    movd %ecx, %xmm2
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc8i64_8i16:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pxor %xmm4, %xmm4
; SSE41-NEXT:    pblendw {{.*#+}} xmm3 = xmm3[0],xmm4[1,2,3],xmm3[4],xmm4[5,6,7]
; SSE41-NEXT:    pblendw {{.*#+}} xmm2 = xmm2[0],xmm4[1,2,3],xmm2[4],xmm4[5,6,7]
; SSE41-NEXT:    packusdw %xmm3, %xmm2
; SSE41-NEXT:    pblendw {{.*#+}} xmm1 = xmm1[0],xmm4[1,2,3],xmm1[4],xmm4[5,6,7]
; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0],xmm4[1,2,3],xmm0[4],xmm4[5,6,7]
; SSE41-NEXT:    packusdw %xmm1, %xmm0
; SSE41-NEXT:    packusdw %xmm2, %xmm0
; SSE41-NEXT:    retq
;
; AVX1-LABEL: trunc8i64_8i16:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm3[1,2,3],xmm1[4],xmm3[5,6,7]
; AVX1-NEXT:    vpackusdw %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0],xmm3[1,2,3],xmm2[4],xmm3[5,6,7]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm3[1,2,3],xmm0[4],xmm3[5,6,7]
; AVX1-NEXT:    vpackusdw %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc8i64_8i16:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero,ymm0[16,17,20,21,24,25,28,29],zero,zero,zero,zero,zero,zero,zero,zero
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc8i64_8i16:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovqw %zmm0, %xmm0
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <8 x i64> %a to <8 x i16>
  ret <8 x i16> %0
}

define void @trunc8i64_8i8(<8 x i64> %a) {
; SSE-LABEL: trunc8i64_8i8:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; SSE-NEXT:    pand %xmm4, %xmm3
; SSE-NEXT:    pand %xmm4, %xmm2
; SSE-NEXT:    packuswb %xmm3, %xmm2
; SSE-NEXT:    pand %xmm4, %xmm1
; SSE-NEXT:    pand %xmm4, %xmm0
; SSE-NEXT:    packuswb %xmm1, %xmm0
; SSE-NEXT:    packuswb %xmm2, %xmm0
; SSE-NEXT:    packuswb %xmm0, %xmm0
; SSE-NEXT:    movq %xmm0, (%rax)
; SSE-NEXT:    retq
;
; AVX1-LABEL: trunc8i64_8i8:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vmovaps {{.*#+}} xmm3 = [255,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0]
; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vpackuswb %xmm0, %xmm0, %xmm0
; AVX1-NEXT:    vmovq %xmm0, (%rax)
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc8i64_8i8:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,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, (%rax)
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc8i64_8i8:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovqb %zmm0, (%rax)
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <8 x i64> %a to <8 x i8>
  store <8 x i8> %0, <8 x i8>* undef, align 4
  ret void
}

define <8 x i16> @trunc8i32_8i16(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i16:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pslld $16, %xmm1
; SSE2-NEXT:    psrad $16, %xmm1
; SSE2-NEXT:    pslld $16, %xmm0
; SSE2-NEXT:    psrad $16, %xmm0
; SSE2-NEXT:    packssdw %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc8i32_8i16:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT:    pshufb %xmm2, %xmm1
; SSSE3-NEXT:    pshufb %xmm2, %xmm0
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc8i32_8i16:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT:    pshufb %xmm2, %xmm1
; SSE41-NEXT:    pshufb %xmm2, %xmm0
; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT:    retq
;
; AVX1-LABEL: trunc8i32_8i16:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc8i32_8i16:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero,ymm0[16,17,20,21,24,25,28,29],zero,zero,zero,zero,zero,zero,zero,zero
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc8i32_8i16:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
; AVX512BW-NEXT:    vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <8 x i32> %a to <8 x i16>
  ret <8 x i16> %0
}

define void @trunc8i32_8i8(<8 x i32> %a) {
; SSE2-LABEL: trunc8i32_8i8:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa {{.*#+}} xmm2 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE2-NEXT:    pand %xmm2, %xmm1
; SSE2-NEXT:    pand %xmm2, %xmm0
; SSE2-NEXT:    packuswb %xmm1, %xmm0
; SSE2-NEXT:    packuswb %xmm0, %xmm0
; SSE2-NEXT:    movq %xmm0, (%rax)
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc8i32_8i8:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSSE3-NEXT:    pshufb %xmm2, %xmm1
; SSSE3-NEXT:    pshufb %xmm2, %xmm0
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSSE3-NEXT:    movq %xmm0, (%rax)
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc8i32_8i8:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = <0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u>
; SSE41-NEXT:    pshufb %xmm2, %xmm1
; SSE41-NEXT:    pshufb %xmm2, %xmm0
; SSE41-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE41-NEXT:    movq %xmm0, (%rax)
; SSE41-NEXT:    retq
;
; AVX1-LABEL: trunc8i32_8i8:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,4,8,12,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, (%rax)
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc8i32_8i8:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,4,5,8,9,12,13],zero,zero,zero,zero,zero,zero,zero,zero,ymm0[16,17,20,21,24,25,28,29],zero,zero,zero,zero,zero,zero,zero,zero
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX2-NEXT:    vmovq %xmm0, (%rax)
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc8i32_8i8:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
; AVX512BW-NEXT:    vpmovdw %zmm0, %ymm0
; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT:    vmovq %xmm0, (%rax)
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <8 x i32> %a to <8 x i8>
  store <8 x i8> %0, <8 x i8>* undef, align 4
  ret void
}

define void @trunc16i32_16i8(<16 x i32> %a) {
; SSE-LABEL: trunc16i32_16i8:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    movdqa {{.*#+}} xmm4 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; SSE-NEXT:    pand %xmm4, %xmm3
; SSE-NEXT:    pand %xmm4, %xmm2
; SSE-NEXT:    packuswb %xmm3, %xmm2
; SSE-NEXT:    pand %xmm4, %xmm1
; SSE-NEXT:    pand %xmm4, %xmm0
; SSE-NEXT:    packuswb %xmm1, %xmm0
; SSE-NEXT:    packuswb %xmm2, %xmm0
; SSE-NEXT:    movdqu %xmm0, (%rax)
; SSE-NEXT:    retq
;
; AVX1-LABEL: trunc16i32_16i8:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vmovaps {{.*#+}} xmm3 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vandps %xmm3, %xmm1, %xmm1
; AVX1-NEXT:    vpackuswb %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vandps %xmm3, %xmm2, %xmm2
; AVX1-NEXT:    vandps %xmm3, %xmm0, %xmm0
; AVX1-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0
; AVX1-NEXT:    vmovdqu %xmm0, (%rax)
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc16i32_16i8:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,1,4,5,8,9,12,13,128,128,128,128,128,128,128,128,0,1,4,5,8,9,12,13,128,128,128,128,128,128,128,128]
; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX2-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
; AVX2-NEXT:    vpshufb %ymm2, %ymm0, %ymm0
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT:    vmovdqu %xmm0, (%rax)
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc16i32_16i8:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpmovdb %zmm0, (%rax)
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <16 x i32> %a to <16 x i8>
  store <16 x i8> %0, <16 x i8>* undef, align 4
  ret void
}

define <8 x i32> @trunc2x4i64_8i32(<4 x i64> %a, <4 x i64> %b) {
; SSE2-LABEL: trunc2x4i64_8i32:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc2x4i64_8i32:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc2x4i64_8i32:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,1,0,2]
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm2[0,2,2,3]
; SSE41-NEXT:    pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm3[4,5,6,7]
; SSE41-NEXT:    retq
;
; AVX1-LABEL: trunc2x4i64_8i32:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm2[4,5,6,7]
; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc2x4i64_8i32:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm0
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc2x4i64_8i32:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    # kill: %YMM1<def> %YMM1<kill> %ZMM1<def>
; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
; AVX512BW-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <4 x i64> %a to <4 x i32>
  %1 = trunc <4 x i64> %b to <4 x i32>
  %2 = shufflevector <4 x i32> %0, <4 x i32> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  ret <8 x i32> %2
}

define <8 x i16> @trunc2x4i64_8i16(<4 x i64> %a, <4 x i64> %b) {
; SSE2-LABEL: trunc2x4i64_8i16:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pextrw $4, %xmm1, %eax
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
; SSE2-NEXT:    pextrw $4, %xmm0, %ecx
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE2-NEXT:    pextrw $4, %xmm3, %edx
; SSE2-NEXT:    movd %edx, %xmm1
; SSE2-NEXT:    movd %eax, %xmm3
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; SSE2-NEXT:    pextrw $4, %xmm2, %eax
; SSE2-NEXT:    movd %eax, %xmm1
; SSE2-NEXT:    movd %ecx, %xmm2
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc2x4i64_8i16:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    pextrw $4, %xmm1, %eax
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
; SSSE3-NEXT:    pextrw $4, %xmm0, %ecx
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSSE3-NEXT:    pextrw $4, %xmm3, %edx
; SSSE3-NEXT:    movd %edx, %xmm1
; SSSE3-NEXT:    movd %eax, %xmm3
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3]
; SSSE3-NEXT:    pextrw $4, %xmm2, %eax
; SSSE3-NEXT:    movd %eax, %xmm1
; SSSE3-NEXT:    movd %ecx, %xmm2
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc2x4i64_8i16:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pextrw $4, %xmm0, %eax
; SSE41-NEXT:    pinsrw $1, %eax, %xmm0
; SSE41-NEXT:    movd %xmm1, %eax
; SSE41-NEXT:    pinsrw $2, %eax, %xmm0
; SSE41-NEXT:    pextrw $4, %xmm1, %eax
; SSE41-NEXT:    pinsrw $3, %eax, %xmm0
; SSE41-NEXT:    movd %xmm2, %eax
; SSE41-NEXT:    pinsrw $4, %eax, %xmm0
; SSE41-NEXT:    pextrw $4, %xmm2, %eax
; SSE41-NEXT:    pinsrw $5, %eax, %xmm0
; SSE41-NEXT:    movd %xmm3, %eax
; SSE41-NEXT:    pinsrw $6, %eax, %xmm0
; SSE41-NEXT:    pextrw $4, %xmm3, %eax
; SSE41-NEXT:    pinsrw $7, %eax, %xmm0
; SSE41-NEXT:    retq
;
; AVX1-LABEL: trunc2x4i64_8i16:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm2[4,5,6,7]
; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,1,0,2]
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm2[4,5,6,7]
; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX1-NEXT:    vzeroupper
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc2x4i64_8i16:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,2,3]
; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,2,2,3,4,6,6,7]
; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
; AVX2-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX2-NEXT:    vzeroupper
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc2x4i64_8i16:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    # kill: %YMM1<def> %YMM1<kill> %ZMM1<def>
; AVX512BW-NEXT:    # kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
; AVX512BW-NEXT:    vpmovqd %zmm0, %ymm0
; AVX512BW-NEXT:    vpmovqd %zmm1, %ymm1
; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512BW-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <4 x i64> %a to <4 x i16>
  %1 = trunc <4 x i64> %b to <4 x i16>
  %2 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  ret <8 x i16> %2
}

define <4 x i32> @trunc2x2i64_4i32(<2 x i64> %a, <2 x i64> %b) {
; SSE2-LABEL: trunc2x2i64_4i32:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc2x2i64_4i32:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc2x2i64_4i32:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT:    retq
;
; AVX1-LABEL: trunc2x2i64_4i32:
; AVX1:       # BB#0: # %entry
; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
; AVX1-NEXT:    retq
;
; AVX2-LABEL: trunc2x2i64_4i32:
; AVX2:       # BB#0: # %entry
; AVX2-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX2-NEXT:    retq
;
; AVX512BW-LABEL: trunc2x2i64_4i32:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,1,0,2]
; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512BW-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <2 x i64> %a to <2 x i32>
  %1 = trunc <2 x i64> %b to <2 x i32>
  %2 = shufflevector <2 x i32> %0, <2 x i32> %1, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  ret <4 x i32> %2
}

define i64 @trunc2i64_i64(<2 x i64> %inval) {
; SSE-LABEL: trunc2i64_i64:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE-NEXT:    movd %xmm0, %rax
; SSE-NEXT:    retq
;
; AVX-LABEL: trunc2i64_i64:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX-NEXT:    vmovq %xmm0, %rax
; AVX-NEXT:    retq
;
; AVX512BW-LABEL: trunc2i64_i64:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; AVX512BW-NEXT:    vmovq %xmm0, %rax
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <2 x i64> %inval to <2 x i32>
  %1 = bitcast <2 x i32> %0 to i64
  ret i64 %1
}

define <8 x i16> @trunc2x4i32_8i16(<4 x i32> %a, <4 x i32> %b) {
; SSE2-LABEL: trunc2x4i32_8i16:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
; SSE2-NEXT:    pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,6,6,7]
; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc2x4i32_8i16:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT:    pshufb %xmm2, %xmm1
; SSSE3-NEXT:    pshufb %xmm2, %xmm0
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc2x4i32_8i16:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT:    pshufb %xmm2, %xmm1
; SSE41-NEXT:    pshufb %xmm2, %xmm0
; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT:    retq
;
; AVX-LABEL: trunc2x4i32_8i16:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-NEXT:    retq
;
; AVX512BW-LABEL: trunc2x4i32_8i16:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512BW-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <4 x i32> %a to <4 x i16>
  %1 = trunc <4 x i32> %b to <4 x i16>
  %2 = shufflevector <4 x i16> %0, <4 x i16> %1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  ret <8 x i16> %2
}

; PR15524 http://llvm.org/bugs/show_bug.cgi?id=15524
define i64 @trunc4i32_i64(<4 x i32> %inval) {
; SSE2-LABEL: trunc4i32_i64:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,3,4,5,6,7]
; SSE2-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
; SSE2-NEXT:    movd %xmm0, %rax
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc4i32_i64:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSSE3-NEXT:    movd %xmm0, %rax
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc4i32_i64:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; SSE41-NEXT:    movd %xmm0, %rax
; SSE41-NEXT:    retq
;
; AVX-LABEL: trunc4i32_i64:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX-NEXT:    vmovq %xmm0, %rax
; AVX-NEXT:    retq
;
; AVX512BW-LABEL: trunc4i32_i64:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
; AVX512BW-NEXT:    vmovq %xmm0, %rax
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <4 x i32> %inval to <4 x i16>
  %1 = bitcast <4 x i16> %0 to i64
  ret i64 %1
}

define <16 x i8> @trunc2x8i16_16i8(<8 x i16> %a, <8 x i16> %b) {
; SSE2-LABEL: trunc2x8i16_16i8:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT:    pand %xmm2, %xmm1
; SSE2-NEXT:    pand %xmm2, %xmm0
; SSE2-NEXT:    packuswb %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc2x8i16_16i8:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSSE3-NEXT:    pshufb %xmm2, %xmm1
; SSSE3-NEXT:    pshufb %xmm2, %xmm0
; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc2x8i16_16i8:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; SSE41-NEXT:    pshufb %xmm2, %xmm1
; SSE41-NEXT:    pshufb %xmm2, %xmm0
; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE41-NEXT:    retq
;
; AVX-LABEL: trunc2x8i16_16i8:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX-NEXT:    retq
;
; AVX512BW-LABEL: trunc2x8i16_16i8:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm2 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
; AVX512BW-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
; AVX512BW-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
; AVX512BW-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <8 x i16> %a to <8 x i8>
  %1 = trunc <8 x i16> %b to <8 x i8>
  %2 = shufflevector <8 x i8> %0, <8 x i8> %1, <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> %2
}

; PR15524 http://llvm.org/bugs/show_bug.cgi?id=15524
define i64 @trunc8i16_i64(<8 x i16> %inval) {
; SSE2-LABEL: trunc8i16_i64:
; SSE2:       # BB#0: # %entry
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm0
; SSE2-NEXT:    packuswb %xmm0, %xmm0
; SSE2-NEXT:    movd %xmm0, %rax
; SSE2-NEXT:    retq
;
; SSSE3-LABEL: trunc8i16_i64:
; SSSE3:       # BB#0: # %entry
; SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; SSSE3-NEXT:    movd %xmm0, %rax
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: trunc8i16_i64:
; SSE41:       # BB#0: # %entry
; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; SSE41-NEXT:    movd %xmm0, %rax
; SSE41-NEXT:    retq
;
; AVX-LABEL: trunc8i16_i64:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX-NEXT:    vmovq %xmm0, %rax
; AVX-NEXT:    retq
;
; AVX512BW-LABEL: trunc8i16_i64:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
; AVX512BW-NEXT:    vmovq %xmm0, %rax
; AVX512BW-NEXT:    retq
entry:
  %0 = trunc <8 x i16> %inval to <8 x i8>
  %1 = bitcast <8 x i8> %0 to i64
  ret i64 %1
}

define <16 x i8> @trunc16i64_16i8_const() {
; SSE-LABEL: trunc16i64_16i8_const:
; SSE:       # BB#0: # %entry
; SSE-NEXT:    xorps %xmm0, %xmm0
; SSE-NEXT:    retq
;
; AVX-LABEL: trunc16i64_16i8_const:
; AVX:       # BB#0: # %entry
; AVX-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; AVX-NEXT:    retq
;
; AVX512BW-LABEL: trunc16i64_16i8_const:
; AVX512BW:       # BB#0: # %entry
; AVX512BW-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; AVX512BW-NEXT:    retq

entry:
  %0 = trunc <16 x i64> zeroinitializer to <16 x i8>
  %1 = shufflevector <16 x i8> %0, <16 x i8> %0, <16 x i32> <i32 28, i32 30, i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 undef, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26>
  ret <16 x i8> %1
}