llvm.org GIT mirror llvm / fcdf36f test / Transforms / LoopVectorize / induction.ll
fcdf36f

Tree @fcdf36f (Download .tar.gz)

induction.ll @fcdf36fraw · 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
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -S | FileCheck %s
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=IND
; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=2 -instcombine -S | FileCheck %s --check-prefix=UNROLL
; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=2 -S | FileCheck %s --check-prefix=UNROLL-NO-IC
; RUN: opt < %s -loop-vectorize -force-vector-interleave=2 -force-vector-width=4 -enable-interleaved-mem-accesses -instcombine -S | FileCheck %s --check-prefix=INTERLEAVE

target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"

; Make sure that we can handle multiple integer induction variables.
;
; CHECK-LABEL: @multi_int_induction(
; CHECK:       vector.body:
; CHECK-NEXT:    %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK-NEXT:    %vec.ind = phi <2 x i32> [ <i32 190, i32 191>, %vector.ph ], [ %vec.ind.next, %vector.body ]
; CHECK:         [[TMP3:%.*]] = add i64 %index, 0
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* %A, i64 [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i32, i32* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <2 x i32>*
; CHECK-NEXT:    store <2 x i32> %vec.ind, <2 x i32>* [[TMP6]], align 4
; CHECK:         %index.next = add i64 %index, 2
; CHECK-NEXT:    %vec.ind.next = add <2 x i32> %vec.ind, <i32 2, i32 2>
; CHECK:         br i1 {{.*}}, label %middle.block, label %vector.body
define void @multi_int_induction(i32* %A, i32 %N) {
for.body.lr.ph:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
  %count.09 = phi i32 [ 190, %for.body.lr.ph ], [ %inc, %for.body ]
  %arrayidx2 = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
  store i32 %count.09, i32* %arrayidx2, align 4
  %inc = add nsw i32 %count.09, 1
  %indvars.iv.next = add i64 %indvars.iv, 1
  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %exitcond = icmp ne i32 %lftr.wideiv, %N
  br i1 %exitcond, label %for.body, label %for.end

for.end:
  ret void
}

; Make sure we remove unneeded vectorization of induction variables.
; In order for instcombine to cleanup the vectorized induction variables that we
; create in the loop vectorizer we need to perform some form of redundancy
; elimination to get rid of multiple uses.

; IND-LABEL: scalar_use

; IND:     br label %vector.body
; IND:     vector.body:
;   Vectorized induction variable.
; IND-NOT:  insertelement <2 x i64>
; IND-NOT:  shufflevector <2 x i64>
; IND:     br {{.*}}, label %vector.body

define void @scalar_use(float* %a, float %b, i64 %offset, i64 %offset2, i64 %n) {
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %ind.sum = add i64 %iv, %offset
  %arr.idx = getelementptr inbounds float, float* %a, i64 %ind.sum
  %l1 = load float, float* %arr.idx, align 4
  %ind.sum2 = add i64 %iv, %offset2
  %arr.idx2 = getelementptr inbounds float, float* %a, i64 %ind.sum2
  %l2 = load float, float* %arr.idx2, align 4
  %m = fmul fast float %b, %l2
  %ad = fadd fast float %l1, %m
  store float %ad, float* %arr.idx, align 4
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond = icmp eq i64 %iv.next, %n
  br i1 %exitcond, label %loopexit, label %for.body

loopexit:
  ret void
}

; Make sure we don't create a vector induction phi node that is unused.
; Scalarize the step vectors instead.
;
; for (int i = 0; i < n; ++i)
;   sum += a[i];
;
; CHECK-LABEL: @scalarize_induction_variable_01(
; CHECK: vector.body:
; CHECK:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK:   %[[i0:.+]] = add i64 %index, 0
; CHECK:   getelementptr inbounds i64, i64* %a, i64 %[[i0]]
;
; UNROLL-NO-IC-LABEL: @scalarize_induction_variable_01(
; UNROLL-NO-IC: vector.body:
; UNROLL-NO-IC:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; UNROLL-NO-IC:   %[[i0:.+]] = add i64 %index, 0
; UNROLL-NO-IC:   %[[i2:.+]] = add i64 %index, 2
; UNROLL-NO-IC:   getelementptr inbounds i64, i64* %a, i64 %[[i0]]
; UNROLL-NO-IC:   getelementptr inbounds i64, i64* %a, i64 %[[i2]]
;
; IND-LABEL: @scalarize_induction_variable_01(
; IND:     vector.body:
; IND:       %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; IND-NOT:   add i64 {{.*}}, 2
; IND:       getelementptr inbounds i64, i64* %a, i64 %index
;
; UNROLL-LABEL: @scalarize_induction_variable_01(
; UNROLL:     vector.body:
; UNROLL:       %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; UNROLL-NOT:   add i64 {{.*}}, 4
; UNROLL:       %[[g1:.+]] = getelementptr inbounds i64, i64* %a, i64 %index
; UNROLL:       getelementptr i64, i64* %[[g1]], i64 2

define i64 @scalarize_induction_variable_01(i64 *%a, i64 %n) {
entry:
  br label %for.body

for.body:
  %i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
  %sum = phi i64 [ %2, %for.body ], [ 0, %entry ]
  %0 = getelementptr inbounds i64, i64* %a, i64 %i
  %1 = load i64, i64* %0, align 8
  %2 = add i64 %1, %sum
  %i.next = add nuw nsw i64 %i, 1
  %cond = icmp slt i64 %i.next, %n
  br i1 %cond, label %for.body, label %for.end

for.end:
  %3  = phi i64 [ %2, %for.body ]
  ret i64 %3
}

; Make sure we scalarize the step vectors used for the pointer arithmetic. We
; can't easily simplify vectorized step vectors.
;
; float s = 0;
; for (int i ; 0; i < n; i += 8)
;   s += (a[i] + b[i] + 1.0f);
;
; CHECK-LABEL: @scalarize_induction_variable_02(
; CHECK: vector.body:
; CHECK:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK:   %offset.idx = shl i64 %index, 3
; CHECK:   %[[i0:.+]] = add i64 %offset.idx, 0
; CHECK:   %[[i1:.+]] = add i64 %offset.idx, 8
; CHECK:   getelementptr inbounds float, float* %a, i64 %[[i0]]
; CHECK:   getelementptr inbounds float, float* %a, i64 %[[i1]]
; CHECK:   getelementptr inbounds float, float* %b, i64 %[[i0]]
; CHECK:   getelementptr inbounds float, float* %b, i64 %[[i1]]
;
; UNROLL-NO-IC-LABEL: @scalarize_induction_variable_02(
; UNROLL-NO-IC: vector.body:
; UNROLL-NO-IC:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; UNROLL-NO-IC:   %offset.idx = shl i64 %index, 3
; UNROLL-NO-IC:   %[[i0:.+]] = add i64 %offset.idx, 0
; UNROLL-NO-IC:   %[[i1:.+]] = add i64 %offset.idx, 8
; UNROLL-NO-IC:   %[[i2:.+]] = add i64 %offset.idx, 16
; UNROLL-NO-IC:   %[[i3:.+]] = add i64 %offset.idx, 24
; UNROLL-NO-IC:   getelementptr inbounds float, float* %a, i64 %[[i0]]
; UNROLL-NO-IC:   getelementptr inbounds float, float* %a, i64 %[[i1]]
; UNROLL-NO-IC:   getelementptr inbounds float, float* %a, i64 %[[i2]]
; UNROLL-NO-IC:   getelementptr inbounds float, float* %a, i64 %[[i3]]
; UNROLL-NO-IC:   getelementptr inbounds float, float* %b, i64 %[[i0]]
; UNROLL-NO-IC:   getelementptr inbounds float, float* %b, i64 %[[i1]]
; UNROLL-NO-IC:   getelementptr inbounds float, float* %b, i64 %[[i2]]
; UNROLL-NO-IC:   getelementptr inbounds float, float* %b, i64 %[[i3]]
;
; IND-LABEL: @scalarize_induction_variable_02(
; IND: vector.body:
; IND:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; IND:   %[[i0:.+]] = shl i64 %index, 3
; IND:   %[[i1:.+]] = or i64 %[[i0]], 8
; IND:   getelementptr inbounds float, float* %a, i64 %[[i0]]
; IND:   getelementptr inbounds float, float* %a, i64 %[[i1]]
;
; UNROLL-LABEL: @scalarize_induction_variable_02(
; UNROLL: vector.body:
; UNROLL:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; UNROLL:   %[[i0:.+]] = shl i64 %index, 3
; UNROLL:   %[[i1:.+]] = or i64 %[[i0]], 8
; UNROLL:   %[[i2:.+]] = or i64 %[[i0]], 16
; UNROLL:   %[[i3:.+]] = or i64 %[[i0]], 24
; UNROLL:   getelementptr inbounds float, float* %a, i64 %[[i0]]
; UNROLL:   getelementptr inbounds float, float* %a, i64 %[[i1]]
; UNROLL:   getelementptr inbounds float, float* %a, i64 %[[i2]]
; UNROLL:   getelementptr inbounds float, float* %a, i64 %[[i3]]

define float @scalarize_induction_variable_02(float* %a, float* %b, i64 %n) {
entry:
  br label %for.body

for.body:
  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
  %s = phi float [ 0.0, %entry ], [ %6, %for.body ]
  %0 = getelementptr inbounds float, float* %a, i64 %i
  %1 = load float, float* %0, align 4
  %2 = getelementptr inbounds float, float* %b, i64 %i
  %3 = load float, float* %2, align 4
  %4 = fadd fast float %s, 1.0
  %5 = fadd fast float %4, %1
  %6 = fadd fast float %5, %3
  %i.next = add nuw nsw i64 %i, 8
  %cond = icmp slt i64 %i.next, %n
  br i1 %cond, label %for.body, label %for.end

for.end:
  %s.lcssa = phi float [ %6, %for.body ]
  ret float %s.lcssa
}

; Make sure we scalarize the step vectors used for the pointer arithmetic. We
; can't easily simplify vectorized step vectors. (Interleaved accesses.)
;
; for (int i = 0; i < n; ++i)
;   a[i].f ^= y;
;
; INTERLEAVE-LABEL: @scalarize_induction_variable_03(
; INTERLEAVE: vector.body:
; INTERLEAVE:   %[[i0:.+]] = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; INTERLEAVE:   %[[i1:.+]] = or i64 %[[i0]], 1
; INTERLEAVE:   %[[i2:.+]] = or i64 %[[i0]], 2
; INTERLEAVE:   %[[i3:.+]] = or i64 %[[i0]], 3
; INTERLEAVE:   %[[i4:.+]] = or i64 %[[i0]], 4
; INTERLEAVE:   %[[i5:.+]] = or i64 %[[i0]], 5
; INTERLEAVE:   %[[i6:.+]] = or i64 %[[i0]], 6
; INTERLEAVE:   %[[i7:.+]] = or i64 %[[i0]], 7
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i0]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i1]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i2]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i3]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i4]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i5]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i6]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i7]], i32 1

%pair.i32 = type { i32, i32 }
define void @scalarize_induction_variable_03(%pair.i32 *%p, i32 %y, i64 %n) {
entry:
  br label %for.body

for.body:
  %i  = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
  %f = getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %i, i32 1
  %0 = load i32, i32* %f, align 8
  %1 = xor i32 %0, %y
  store i32 %1, i32* %f, align 8
  %i.next = add nuw nsw i64 %i, 1
  %cond = icmp slt i64 %i.next, %n
  br i1 %cond, label %for.body, label %for.end

for.end:
  ret void
}

; Make sure we scalarize the step vectors used for the pointer arithmetic. We
; can't easily simplify vectorized step vectors. (Interleaved accesses.)
;
; for (int i = 0; i < n; ++i)
;   p[i].f = a[i * 4]
;
; INTERLEAVE-LABEL: @scalarize_induction_variable_04(
; INTERLEAVE: vector.body:
; INTERLEAVE:   %[[i0:.+]] = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; INTERLEAVE:   %[[i1:.+]] = or i64 %[[i0]], 1
; INTERLEAVE:   %[[i2:.+]] = or i64 %[[i0]], 2
; INTERLEAVE:   %[[i3:.+]] = or i64 %[[i0]], 3
; INTERLEAVE:   %[[i4:.+]] = or i64 %[[i0]], 4
; INTERLEAVE:   %[[i5:.+]] = or i64 %[[i0]], 5
; INTERLEAVE:   %[[i6:.+]] = or i64 %[[i0]], 6
; INTERLEAVE:   %[[i7:.+]] = or i64 %[[i0]], 7
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i0]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i1]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i2]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i3]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i4]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i5]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i6]], i32 1
; INTERLEAVE:   getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %[[i7]], i32 1

define void @scalarize_induction_variable_04(i32* %a, %pair.i32* %p, i32 %n) {
entry:
  br label %for.body

for.body:
  %i = phi i64 [ %i.next, %for.body ], [ 0, %entry]
  %0 = shl nsw i64 %i, 2
  %1 = getelementptr inbounds i32, i32* %a, i64 %0
  %2 = load i32, i32* %1, align 1
  %3 = getelementptr inbounds %pair.i32, %pair.i32* %p, i64 %i, i32 1
  store i32 %2, i32* %3, align 1
  %i.next = add nuw nsw i64 %i, 1
  %4 = trunc i64 %i.next to i32
  %cond = icmp eq i32 %4, %n
  br i1 %cond, label %for.end, label %for.body

for.end:
  ret void
}

; PR30542. Ensure we generate all the scalar steps for the induction variable.
; The scalar induction variable is used by a getelementptr instruction
; (uniform), and a udiv (non-uniform).
;
; int sum = 0;
; for (int i = 0; i < n; ++i) {
;   int x = a[i];
;   if (c)
;     x /= i;
;   sum += x;
; }
;
; CHECK-LABEL: @scalarize_induction_variable_05(
; CHECK: vector.body:
; CHECK:   %index = phi i32 [ 0, %vector.ph ], [ %index.next, %pred.udiv.continue2 ]
; CHECK:   %[[I0:.+]] = add i32 %index, 0
; CHECK:   getelementptr inbounds i32, i32* %a, i32 %[[I0]]
; CHECK: pred.udiv.if:
; CHECK:   udiv i32 {{.*}}, %[[I0]]
; CHECK: pred.udiv.if1:
; CHECK:   %[[I1:.+]] = add i32 %index, 1
; CHECK:   udiv i32 {{.*}}, %[[I1]]
;
; UNROLL-NO_IC-LABEL: @scalarize_induction_variable_05(
; UNROLL-NO-IC: vector.body:
; UNROLL-NO-IC:   %index = phi i32 [ 0, %vector.ph ], [ %index.next, %pred.udiv.continue11 ]
; UNROLL-NO-IC:   %[[I0:.+]] = add i32 %index, 0
; UNROLL-NO-IC:   %[[I2:.+]] = add i32 %index, 2
; UNROLL-NO-IC:   getelementptr inbounds i32, i32* %a, i32 %[[I0]]
; UNROLL-NO-IC:   getelementptr inbounds i32, i32* %a, i32 %[[I2]]
; UNROLL-NO-IC: pred.udiv.if:
; UNROLL-NO-IC:   udiv i32 {{.*}}, %[[I0]]
; UNROLL-NO-IC: pred.udiv.if6:
; UNROLL-NO-IC:   %[[I1:.+]] = add i32 %index, 1
; UNROLL-NO-IC:   udiv i32 {{.*}}, %[[I1]]
; UNROLL-NO-IC: pred.udiv.if8:
; UNROLL-NO-IC:   udiv i32 {{.*}}, %[[I2]]
; UNROLL-NO-IC: pred.udiv.if10:
; UNROLL-NO-IC:   %[[I3:.+]] = add i32 %index, 3
; UNROLL-NO-IC:   udiv i32 {{.*}}, %[[I3]]
;
; IND-LABEL: @scalarize_induction_variable_05(
; IND: vector.body:
; IND:   %index = phi i32 [ 0, %vector.ph ], [ %index.next, %pred.udiv.continue2 ]
; IND:   %[[E0:.+]] = sext i32 %index to i64
; IND:   getelementptr inbounds i32, i32* %a, i64 %[[E0]]
; IND: pred.udiv.if:
; IND:   udiv i32 {{.*}}, %index
; IND: pred.udiv.if1:
; IND:   %[[I1:.+]] = or i32 %index, 1
; IND:   udiv i32 {{.*}}, %[[I1]]
;
; UNROLL-LABEL: @scalarize_induction_variable_05(
; UNROLL: vector.body:
; UNROLL:   %index = phi i32 [ 0, %vector.ph ], [ %index.next, %pred.udiv.continue11 ]
; UNROLL:   %[[I2:.+]] = or i32 %index, 2
; UNROLL:   %[[E0:.+]] = sext i32 %index to i64
; UNROLL:   %[[G0:.+]] = getelementptr inbounds i32, i32* %a, i64 %[[E0]]
; UNROLL:   getelementptr i32, i32* %[[G0]], i64 2
; UNROLL: pred.udiv.if:
; UNROLL:   udiv i32 {{.*}}, %index
; UNROLL: pred.udiv.if6:
; UNROLL:   %[[I1:.+]] = or i32 %index, 1
; UNROLL:   udiv i32 {{.*}}, %[[I1]]
; UNROLL: pred.udiv.if8:
; UNROLL:   udiv i32 {{.*}}, %[[I2]]
; UNROLL: pred.udiv.if10:
; UNROLL:   %[[I3:.+]] = or i32 %index, 3
; UNROLL:   udiv i32 {{.*}}, %[[I3]]

define i32 @scalarize_induction_variable_05(i32* %a, i32 %x, i1 %c, i32 %n) {
entry:
  br label %for.body

for.body:
  %i = phi i32 [ 0, %entry ], [ %i.next, %if.end ]
  %sum = phi i32 [ 0, %entry ], [ %tmp4, %if.end ]
  %tmp0 = getelementptr inbounds i32, i32* %a, i32 %i
  %tmp1 = load i32, i32* %tmp0, align 4
  br i1 %c, label %if.then, label %if.end

if.then:
  %tmp2 = udiv i32 %tmp1, %i
  br label %if.end

if.end:
  %tmp3 = phi i32 [ %tmp2, %if.then ], [ %tmp1, %for.body ]
  %tmp4 = add i32 %tmp3, %sum
  %i.next = add nuw nsw i32 %i, 1
  %cond = icmp slt i32 %i.next, %n
  br i1 %cond, label %for.body, label %for.end

for.end:
  %tmp5  = phi i32 [ %tmp4, %if.end ]
  ret i32 %tmp5
}

; Ensure we generate both a vector and a scalar induction variable. In this
; test, the induction variable is used by an instruction that will be
; vectorized (trunc) as well as an instruction that will remain in scalar form
; (gepelementptr).
;
; CHECK-LABEL: @iv_vector_and_scalar_users(
; CHECK: vector.body:
; CHECK:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK:   %vec.ind = phi <2 x i64> [ <i64 0, i64 1>, %vector.ph ], [ %vec.ind.next, %vector.body ]
; CHECK:   %vec.ind1 = phi <2 x i32> [ <i32 0, i32 1>, %vector.ph ], [ %vec.ind.next2, %vector.body ]
; CHECK:   %[[i0:.+]] = add i64 %index, 0
; CHECK:   %[[i1:.+]] = add i64 %index, 1
; CHECK:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %[[i0]], i32 1
; CHECK:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %[[i1]], i32 1
; CHECK:   %index.next = add i64 %index, 2
; CHECK:   %vec.ind.next = add <2 x i64> %vec.ind, <i64 2, i64 2>
; CHECK:   %vec.ind.next2 = add <2 x i32> %vec.ind1, <i32 2, i32 2>
;
; IND-LABEL: @iv_vector_and_scalar_users(
; IND: vector.body:
; IND:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; IND:   %vec.ind1 = phi <2 x i32> [ <i32 0, i32 1>, %vector.ph ], [ %vec.ind.next2, %vector.body ]
; IND:   %[[i1:.+]] = or i64 %index, 1
; IND:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %index, i32 1
; IND:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %[[i1]], i32 1
; IND:   %index.next = add i64 %index, 2
; IND:   %vec.ind.next2 = add <2 x i32> %vec.ind1, <i32 2, i32 2>
;
; UNROLL-LABEL: @iv_vector_and_scalar_users(
; UNROLL: vector.body:
; UNROLL:   %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; UNROLL:   %vec.ind2 = phi <2 x i32> [ <i32 0, i32 1>, %vector.ph ], [ %vec.ind.next5, %vector.body ]
; UNROLL:   %[[i1:.+]] = or i64 %index, 1
; UNROLL:   %[[i2:.+]] = or i64 %index, 2
; UNROLL:   %[[i3:.+]] = or i64 %index, 3
; UNROLL:   %step.add3 = add <2 x i32> %vec.ind2, <i32 2, i32 2>
; UNROLL:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %index, i32 1
; UNROLL:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %[[i1]], i32 1
; UNROLL:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %[[i2]], i32 1
; UNROLL:   getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %[[i3]], i32 1
; UNROLL:   %index.next = add i64 %index, 4
; UNROLL:   %vec.ind.next5 = add <2 x i32> %vec.ind2, <i32 4, i32 4>

%pair.i16 = type { i16, i16 }
define void @iv_vector_and_scalar_users(%pair.i16* %p, i32 %a, i32 %n) {
entry:
  br label %for.body

for.body:
  %i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
  %0 = trunc i64 %i to i32
  %1 = add i32 %a, %0
  %2 = trunc i32 %1 to i16
  %3 = getelementptr inbounds %pair.i16, %pair.i16* %p, i64 %i, i32 1
  store i16 %2, i16* %3, align 2
  %i.next = add nuw nsw i64 %i, 1
  %4 = trunc i64 %i.next to i32
  %cond = icmp eq i32 %4, %n
  br i1 %cond, label %for.end, label %for.body

for.end:
  ret void
}

; Make sure that the loop exit count computation does not overflow for i8 and
; i16. The exit count of these loops is i8/i16 max + 1. If we don't cast the
; induction variable to a bigger type the exit count computation will overflow
; to 0.
; PR17532

; CHECK-LABEL: i8_loop
; CHECK: icmp eq i32 {{.*}}, 256
define i32 @i8_loop() nounwind readnone ssp uwtable {
  br label %1

; <label>:1                                       ; preds = %1, %0
  %a.0 = phi i32 [ 1, %0 ], [ %2, %1 ]
  %b.0 = phi i8 [ 0, %0 ], [ %3, %1 ]
  %2 = and i32 %a.0, 4
  %3 = add i8 %b.0, -1
  %4 = icmp eq i8 %3, 0
  br i1 %4, label %5, label %1

; <label>:5                                       ; preds = %1
  ret i32 %2
}

; CHECK-LABEL: i16_loop
; CHECK: icmp eq i32 {{.*}}, 65536

define i32 @i16_loop() nounwind readnone ssp uwtable {
  br label %1

; <label>:1                                       ; preds = %1, %0
  %a.0 = phi i32 [ 1, %0 ], [ %2, %1 ]
  %b.0 = phi i16 [ 0, %0 ], [ %3, %1 ]
  %2 = and i32 %a.0, 4
  %3 = add i16 %b.0, -1
  %4 = icmp eq i16 %3, 0
  br i1 %4, label %5, label %1

; <label>:5                                       ; preds = %1
  ret i32 %2
}

; This loop has a backedge taken count of i32_max. We need to check for this
; condition and branch directly to the scalar loop.

; CHECK-LABEL: max_i32_backedgetaken
; CHECK:  br i1 true, label %scalar.ph, label %min.iters.checked

; CHECK: middle.block:
; CHECK:  %[[v9:.+]] = extractelement <2 x i32> %bin.rdx, i32 0
; CHECK: scalar.ph:
; CHECK:  %bc.resume.val = phi i32 [ 0, %middle.block ], [ 0, %[[v0:.+]] ]
; CHECK:  %bc.merge.rdx = phi i32 [ 1, %[[v0:.+]] ], [ 1, %min.iters.checked ], [ %[[v9]], %middle.block ]

define i32 @max_i32_backedgetaken() nounwind readnone ssp uwtable {

  br label %1

; <label>:1                                       ; preds = %1, %0
  %a.0 = phi i32 [ 1, %0 ], [ %2, %1 ]
  %b.0 = phi i32 [ 0, %0 ], [ %3, %1 ]
  %2 = and i32 %a.0, 4
  %3 = add i32 %b.0, -1
  %4 = icmp eq i32 %3, 0
  br i1 %4, label %5, label %1

; <label>:5                                       ; preds = %1
  ret i32 %2
}

; When generating the overflow check we must sure that the induction start value
; is defined before the branch to the scalar preheader.

; CHECK-LABEL: testoverflowcheck
; CHECK: entry
; CHECK: %[[LOAD:.*]] = load i8
; CHECK: br

; CHECK: scalar.ph
; CHECK: phi i8 [ %{{.*}}, %middle.block ], [ %[[LOAD]], %entry ]

@e = global i8 1, align 1
@d = common global i32 0, align 4
@c = common global i32 0, align 4
define i32 @testoverflowcheck() {
entry:
  %.pr.i = load i8, i8* @e, align 1
  %0 = load i32, i32* @d, align 4
  %c.promoted.i = load i32, i32* @c, align 4
  br label %cond.end.i

cond.end.i:
  %inc4.i = phi i8 [ %.pr.i, %entry ], [ %inc.i, %cond.end.i ]
  %and3.i = phi i32 [ %c.promoted.i, %entry ], [ %and.i, %cond.end.i ]
  %and.i = and i32 %0, %and3.i
  %inc.i = add i8 %inc4.i, 1
  %tobool.i = icmp eq i8 %inc.i, 0
  br i1 %tobool.i, label %loopexit, label %cond.end.i

loopexit:
  ret i32 %and.i
}

; The SCEV expression of %sphi is (zext i8 {%t,+,1}<%loop> to i32)
; In order to recognize %sphi as an induction PHI and vectorize this loop,
; we need to convert the SCEV expression into an AddRecExpr.
; The expression gets converted to {zext i8 %t to i32,+,1}.

; CHECK-LABEL: wrappingindvars1
; CHECK-LABEL: vector.scevcheck
; CHECK-LABEL: vector.ph
; CHECK: %[[START:.*]] = add <2 x i32> %{{.*}}, <i32 0, i32 1>
; CHECK-LABEL: vector.body
; CHECK: %[[PHI:.*]] = phi <2 x i32> [ %[[START]], %vector.ph ], [ %[[STEP:.*]], %vector.body ]
; CHECK: %[[STEP]] = add <2 x i32> %[[PHI]], <i32 2, i32 2>
define void @wrappingindvars1(i8 %t, i32 %len, i32 *%A) {
 entry:
  %st = zext i8 %t to i16
  %ext = zext i8 %t to i32
  %ecmp = icmp ult i16 %st, 42
  br i1 %ecmp, label %loop, label %exit

 loop:

  %idx = phi i8 [ %t, %entry ], [ %idx.inc, %loop ]
  %idx.b = phi i32 [ 0, %entry ], [ %idx.b.inc, %loop ]
  %sphi = phi i32 [ %ext, %entry ], [%idx.inc.ext, %loop]

  %ptr = getelementptr inbounds i32, i32* %A, i8 %idx
  store i32 %sphi, i32* %ptr

  %idx.inc = add i8 %idx, 1
  %idx.inc.ext = zext i8 %idx.inc to i32
  %idx.b.inc = add nuw nsw i32 %idx.b, 1

  %c = icmp ult i32 %idx.b, %len
  br i1 %c, label %loop, label %exit

 exit:
  ret void
}

; The SCEV expression of %sphi is (4 * (zext i8 {%t,+,1}<%loop> to i32))
; In order to recognize %sphi as an induction PHI and vectorize this loop,
; we need to convert the SCEV expression into an AddRecExpr.
; The expression gets converted to ({4 * (zext %t to i32),+,4}).
; CHECK-LABEL: wrappingindvars2
; CHECK-LABEL: vector.scevcheck
; CHECK-LABEL: vector.ph
; CHECK: %[[START:.*]] = add <2 x i32> %{{.*}}, <i32 0, i32 4>
; CHECK-LABEL: vector.body
; CHECK: %[[PHI:.*]] = phi <2 x i32> [ %[[START]], %vector.ph ], [ %[[STEP:.*]], %vector.body ]
; CHECK: %[[STEP]] = add <2 x i32> %[[PHI]], <i32 8, i32 8>
define void @wrappingindvars2(i8 %t, i32 %len, i32 *%A) {

entry:
  %st = zext i8 %t to i16
  %ext = zext i8 %t to i32
  %ext.mul = mul i32 %ext, 4

  %ecmp = icmp ult i16 %st, 42
  br i1 %ecmp, label %loop, label %exit

 loop:

  %idx = phi i8 [ %t, %entry ], [ %idx.inc, %loop ]
  %sphi = phi i32 [ %ext.mul, %entry ], [%mul, %loop]
  %idx.b = phi i32 [ 0, %entry ], [ %idx.b.inc, %loop ]

  %ptr = getelementptr inbounds i32, i32* %A, i8 %idx
  store i32 %sphi, i32* %ptr

  %idx.inc = add i8 %idx, 1
  %idx.inc.ext = zext i8 %idx.inc to i32
  %mul = mul i32 %idx.inc.ext, 4
  %idx.b.inc = add nuw nsw i32 %idx.b, 1

  %c = icmp ult i32 %idx.b, %len
  br i1 %c, label %loop, label %exit

 exit:
  ret void
}

; Check that we generate vectorized IVs in the pre-header
; instead of widening the scalar IV inside the loop, when
; we know how to do that.
; IND-LABEL: veciv
; IND: vector.body:
; IND: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; IND: %vec.ind = phi <2 x i32> [ <i32 0, i32 1>, %vector.ph ], [ %vec.ind.next, %vector.body ]
; IND: %index.next = add i32 %index, 2
; IND: %vec.ind.next = add <2 x i32> %vec.ind, <i32 2, i32 2>
; IND: %[[CMP:.*]] = icmp eq i32 %index.next
; IND: br i1 %[[CMP]]
; UNROLL-LABEL: veciv
; UNROLL: vector.body:
; UNROLL: %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; UNROLL: %vec.ind = phi <2 x i32> [ <i32 0, i32 1>, %vector.ph ], [ %vec.ind.next, %vector.body ]
; UNROLL: %step.add = add <2 x i32> %vec.ind, <i32 2, i32 2>
; UNROLL: %index.next = add i32 %index, 4
; UNROLL: %vec.ind.next = add <2 x i32> %vec.ind, <i32 4, i32 4>
; UNROLL: %[[CMP:.*]] = icmp eq i32 %index.next
; UNROLL: br i1 %[[CMP]]
define void @veciv(i32* nocapture %a, i32 %start, i32 %k) {
for.body.preheader:
  br label %for.body

for.body:
  %indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
  %arrayidx = getelementptr inbounds i32, i32* %a, i32 %indvars.iv
  store i32 %indvars.iv, i32* %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i32 %indvars.iv, 1
  %exitcond = icmp eq i32 %indvars.iv.next, %k
  br i1 %exitcond, label %exit, label %for.body

exit:
  ret void
}

; IND-LABEL: trunciv
; IND: vector.body:
; IND: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; IND: %[[VECIND:.*]] = phi <2 x i32> [ <i32 0, i32 1>, %vector.ph ], [ %[[STEPADD:.*]], %vector.body ]
; IND: %index.next = add i64 %index, 2
; IND: %[[STEPADD]] = add <2 x i32> %[[VECIND]], <i32 2, i32 2>
; IND: %[[CMP:.*]] = icmp eq i64 %index.next
; IND: br i1 %[[CMP]]
define void @trunciv(i32* nocapture %a, i32 %start, i64 %k) {
for.body.preheader:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
  %trunc.iv = trunc i64 %indvars.iv to i32
  %arrayidx = getelementptr inbounds i32, i32* %a, i32 %trunc.iv
  store i32 %trunc.iv, i32* %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  %exitcond = icmp eq i64 %indvars.iv.next, %k
  br i1 %exitcond, label %exit, label %for.body

exit:
  ret void
}

; CHECK-LABEL: @nonprimary(
; CHECK: vector.ph:
; CHECK:   %[[INSERT:.*]] = insertelement <2 x i32> undef, i32 %i, i32 0
; CHECK:   %[[SPLAT:.*]] = shufflevector <2 x i32> %[[INSERT]], <2 x i32> undef, <2 x i32> zeroinitializer
; CHECK:   %[[START:.*]] = add <2 x i32> %[[SPLAT]], <i32 0, i32 1>
; CHECK: vector.body:
; CHECK:   %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK:   %vec.ind = phi <2 x i32> [ %[[START]], %vector.ph ], [ %vec.ind.next, %vector.body ]
; CHECK:   %offset.idx = add i32 %i, %index
; CHECK:   %[[A1:.*]] = add i32 %offset.idx, 0
; CHECK:   %[[G1:.*]] = getelementptr inbounds i32, i32* %a, i32 %[[A1]]
; CHECK:   %[[G3:.*]] = getelementptr i32, i32* %[[G1]], i32 0
; CHECK:   %[[B1:.*]] = bitcast i32* %[[G3]] to <2 x i32>*
; CHECK:   store <2 x i32> %vec.ind, <2 x i32>* %[[B1]]
; CHECK:   %index.next = add i32 %index, 2
; CHECK:   %vec.ind.next = add <2 x i32> %vec.ind, <i32 2, i32 2>
; CHECK:   %[[CMP:.*]] = icmp eq i32 %index.next, %n.vec
; CHECK:   br i1 %[[CMP]]
;
; IND-LABEL: @nonprimary(
; IND: vector.ph:
; IND:   %[[INSERT:.*]] = insertelement <2 x i32> undef, i32 %i, i32 0
; IND:   %[[SPLAT:.*]] = shufflevector <2 x i32> %[[INSERT]], <2 x i32> undef, <2 x i32> zeroinitializer
; IND:   %[[START:.*]] = add <2 x i32> %[[SPLAT]], <i32 0, i32 1>
; IND: vector.body:
; IND:   %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; IND:   %vec.ind = phi <2 x i32> [ %[[START]], %vector.ph ], [ %vec.ind.next, %vector.body ]
; IND:   %[[A1:.*]] = add i32 %index, %i
; IND:   %[[S1:.*]] = sext i32 %[[A1]] to i64
; IND:   %[[G1:.*]] = getelementptr inbounds i32, i32* %a, i64 %[[S1]]
; IND:   %[[B1:.*]] = bitcast i32* %[[G1]] to <2 x i32>*
; IND:   store <2 x i32> %vec.ind, <2 x i32>* %[[B1]]
; IND:   %index.next = add i32 %index, 2
; IND:   %vec.ind.next = add <2 x i32> %vec.ind, <i32 2, i32 2>
; IND:   %[[CMP:.*]] = icmp eq i32 %index.next, %n.vec
; IND:   br i1 %[[CMP]]
;
; UNROLL-LABEL: @nonprimary(
; UNROLL: vector.ph:
; UNROLL:   %[[INSERT:.*]] = insertelement <2 x i32> undef, i32 %i, i32 0
; UNROLL:   %[[SPLAT:.*]] = shufflevector <2 x i32> %[[INSERT]], <2 x i32> undef, <2 x i32> zeroinitializer
; UNROLL:   %[[START:.*]] = add <2 x i32> %[[SPLAT]], <i32 0, i32 1>
; UNROLL: vector.body:
; UNROLL:   %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; UNROLL:   %vec.ind = phi <2 x i32> [ %[[START]], %vector.ph ], [ %vec.ind.next, %vector.body ]
; UNROLL:   %step.add = add <2 x i32> %vec.ind, <i32 2, i32 2>
; UNROLL:   %[[A1:.*]] = add i32 %index, %i
; UNROLL:   %[[S1:.*]] = sext i32 %[[A1]] to i64
; UNROLL:   %[[G1:.*]] = getelementptr inbounds i32, i32* %a, i64 %[[S1]]
; UNROLL:   %[[B1:.*]] = bitcast i32* %[[G1]] to <2 x i32>*
; UNROLL:   store <2 x i32> %vec.ind, <2 x i32>* %[[B1]]
; UNROLL:   %[[G2:.*]] = getelementptr i32, i32* %[[G1]], i64 2
; UNROLL:   %[[B2:.*]] = bitcast i32* %[[G2]] to <2 x i32>*
; UNROLL:   store <2 x i32> %step.add, <2 x i32>* %[[B2]]
; UNROLL:   %index.next = add i32 %index, 4
; UNROLL:   %vec.ind.next = add <2 x i32> %vec.ind, <i32 4, i32 4>
; UNROLL:   %[[CMP:.*]] = icmp eq i32 %index.next, %n.vec
; UNROLL:   br i1 %[[CMP]]
define void @nonprimary(i32* nocapture %a, i32 %start, i32 %i, i32 %k) {
for.body.preheader:
  br label %for.body

for.body:
  %indvars.iv = phi i32 [ %indvars.iv.next, %for.body ], [ %i, %for.body.preheader ]
  %arrayidx = getelementptr inbounds i32, i32* %a, i32 %indvars.iv
  store i32 %indvars.iv, i32* %arrayidx, align 4
  %indvars.iv.next = add nuw nsw i32 %indvars.iv, 1
  %exitcond = icmp eq i32 %indvars.iv.next, %k
  br i1 %exitcond, label %exit, label %for.body

exit:
  ret void
}

; CHECK-LABEL: @non_primary_iv_trunc(
; CHECK:       vector.body:
; CHECK-NEXT:    %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
; CHECK:         [[VEC_IND:%.*]] = phi <2 x i32> [ <i32 0, i32 2>, %vector.ph ], [ [[VEC_IND_NEXT:%.*]], %vector.body ]
; CHECK:         [[TMP3:%.*]] = add i64 %index, 0
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, i32* %a, i64 [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i32, i32* [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i32* [[TMP5]] to <2 x i32>*
; CHECK-NEXT:    store <2 x i32> [[VEC_IND]], <2 x i32>* [[TMP6]], align 4
; CHECK-NEXT:    %index.next = add i64 %index, 2
; CHECK:         [[VEC_IND_NEXT]] = add <2 x i32> [[VEC_IND]], <i32 4, i32 4>
; CHECK:         br i1 {{.*}}, label %middle.block, label %vector.body
define void @non_primary_iv_trunc(i32* %a, i64 %n) {
entry:
  br label %for.body

for.body:
  %i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
  %j = phi i64 [ %j.next, %for.body ], [ 0, %entry ]
  %tmp0 = getelementptr inbounds i32, i32* %a, i64 %i
  %tmp1 = trunc i64 %j to i32
  store i32 %tmp1, i32* %tmp0, align 4
  %i.next = add nuw nsw i64 %i, 1
  %j.next = add nuw nsw i64 %j, 2
  %cond = icmp slt i64 %i.next, %n
  br i1 %cond, label %for.body, label %for.end

for.end:
  ret void
}

; PR32419. Ensure we transform truncated non-primary induction variables. In
; the test case below we replace %tmp1 with a new induction variable. Because
; the truncated value is non-primary, we must compute an offset from the
; primary induction variable.
;
; CHECK-LABEL: @PR32419(
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %vector.ph ], [ [[INDEX_NEXT:%.*]], %[[PRED_UREM_CONTINUE4:.*]] ]
; CHECK:         [[OFFSET_IDX:%.*]] = add i32 -20, [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = trunc i32 [[OFFSET_IDX]] to i16
; CHECK:         [[TMP8:%.*]] = add i16 [[TMP1]], 0
; CHECK-NEXT:    [[TMP9:%.*]] = urem i16 %b, [[TMP8]]
; CHECK:         [[TMP15:%.*]] = add i16 [[TMP1]], 1
; CHECK-NEXT:    [[TMP16:%.*]] = urem i16 %b, [[TMP15]]
; CHECK:       [[PRED_UREM_CONTINUE4]]:
; CHECK:         br i1 {{.*}}, label %middle.block, label %vector.body
;
define i32 @PR32419(i32 %a, i16 %b) {
entry:
  br label %for.body

for.body:
  %i = phi i32 [ -20, %entry ], [ %i.next, %for.inc ]
  %tmp0 = phi i32 [ %a, %entry ], [ %tmp6, %for.inc ]
  %tmp1 = trunc i32 %i to i16
  %tmp2 = icmp eq i16 %tmp1, 0
  br i1 %tmp2, label %for.inc, label %for.cond

for.cond:
  %tmp3 = urem i16 %b, %tmp1
  br label %for.inc

for.inc:
  %tmp4 = phi i16 [ %tmp3, %for.cond ], [ 0, %for.body ]
  %tmp5 = sext i16 %tmp4 to i32
  %tmp6 = or i32 %tmp0, %tmp5
  %i.next = add nsw i32 %i, 1
  %cond = icmp eq i32 %i.next, 0
  br i1 %cond, label %for.end, label %for.body

for.end:
  %tmp7 = phi i32 [ %tmp6, %for.inc ]
  ret i32 %tmp7
}