llvm.org GIT mirror llvm / release_38 test / CodeGen / AArch64 / arm64-shrink-wrapping.ll
release_38

Tree @release_38 (Download .tar.gz)

arm64-shrink-wrapping.ll @release_38raw · 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
; RUN: llc %s -o - -enable-shrink-wrap=true -disable-post-ra | FileCheck %s --check-prefix=CHECK --check-prefix=ENABLE
; RUN: llc %s -o - -enable-shrink-wrap=false -disable-post-ra | FileCheck %s --check-prefix=CHECK --check-prefix=DISABLE
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "arm64-apple-ios"


; Initial motivating example: Simple diamond with a call just on one side.
; CHECK-LABEL: foo:
;
; Compare the arguments and jump to exit.
; No prologue needed.
; ENABLE: cmp w0, w1
; ENABLE-NEXT: b.ge [[EXIT_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; CHECK: stp [[SAVE_SP:x[0-9]+]], [[CSR:x[0-9]+]], [sp, #-16]!
; CHECK-NEXT: mov [[SAVE_SP]], sp
; CHECK-NEXT: sub sp, sp, #16
;
; Compare the arguments and jump to exit.
; After the prologue is set.
; DISABLE: cmp w0, w1
; DISABLE-NEXT: b.ge [[EXIT_LABEL:LBB[0-9_]+]]
;
; Store %a in the alloca.
; CHECK: stur w0, {{\[}}[[SAVE_SP]], #-4]
; Set the alloca address in the second argument.
; CHECK-NEXT: sub x1, [[SAVE_SP]], #4
; Set the first argument to zero.
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: bl _doSomething
; 
; Without shrink-wrapping, epilogue is in the exit block.
; DISABLE: [[EXIT_LABEL]]:
; Epilogue code.
; CHECK-NEXT: mov sp, [[SAVE_SP]]
; CHECK-NEXT: ldp [[SAVE_SP]], [[CSR]], [sp], #16
;
; With shrink-wrapping, exit block is a simple return.
; ENABLE: [[EXIT_LABEL]]:
; CHECK-NEXT: ret
define i32 @foo(i32 %a, i32 %b) {
  %tmp = alloca i32, align 4
  %tmp2 = icmp slt i32 %a, %b
  br i1 %tmp2, label %true, label %false

true:
  store i32 %a, i32* %tmp, align 4
  %tmp4 = call i32 @doSomething(i32 0, i32* %tmp)
  br label %false

false:
  %tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ]
  ret i32 %tmp.0
}

; Function Attrs: optsize
declare i32 @doSomething(i32, i32*)


; Check that we do not perform the restore inside the loop whereas the save
; is outside.
; CHECK-LABEL: freqSaveAndRestoreOutsideLoop:
;
; Shrink-wrapping allows to skip the prologue in the else case.
; ENABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; CHECK: stp [[CSR1:x[0-9]+]], [[CSR2:x[0-9]+]], [sp, #-32]!
; CHECK-NEXT: stp [[CSR3:x[0-9]+]], [[CSR4:x[0-9]+]], [sp, #16]
; CHECK-NEXT: add [[NEW_SP:x[0-9]+]], sp, #16
;
; DISABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: mov [[SUM:w[0-9]+]], wzr
; CHECK-NEXT: movz [[IV:w[0-9]+]], #0xa
;
; Next BB.
; CHECK: [[LOOP:LBB[0-9_]+]]: ; %for.body
; CHECK: bl _something
; CHECK-NEXT: add [[SUM]], w0, [[SUM]]
; CHECK-NEXT: sub [[IV]], [[IV]], #1
; CHECK-NEXT: cbnz [[IV]], [[LOOP]]
;
; Next BB.
; Copy SUM into the returned register + << 3.
; CHECK: lsl w0, [[SUM]], #3
;
; Jump to epilogue.
; DISABLE: b [[EPILOG_BB:LBB[0-9_]+]]
;
; DISABLE: [[ELSE_LABEL]]: ; %if.else
; Shift second argument by one and store into returned register.
; DISABLE: lsl w0, w1, #1
; DISABLE: [[EPILOG_BB]]: ; %if.end
;
; Epilogue code.
; CHECK: ldp [[CSR3]], [[CSR4]], [sp, #16]
; CHECK-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #32
; CHECK-NEXT: ret
;
; ENABLE: [[ELSE_LABEL]]: ; %if.else
; Shift second argument by one and store into returned register.
; ENABLE: lsl w0, w1, #1
; ENABLE: ret
define i32 @freqSaveAndRestoreOutsideLoop(i32 %cond, i32 %N) {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.05 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %sum.04 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %call = tail call i32 bitcast (i32 (...)* @something to i32 ()*)()
  %add = add nsw i32 %call, %sum.04
  %inc = add nuw nsw i32 %i.05, 1
  %exitcond = icmp eq i32 %inc, 10
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  %shl = shl i32 %add, 3
  br label %if.end

if.else:                                          ; preds = %entry
  %mul = shl nsw i32 %N, 1
  br label %if.end

if.end:                                           ; preds = %if.else, %for.end
  %sum.1 = phi i32 [ %shl, %for.end ], [ %mul, %if.else ]
  ret i32 %sum.1
}

declare i32 @something(...)

; Check that we do not perform the shrink-wrapping inside the loop even
; though that would be legal. The cost model must prevent that.
; CHECK-LABEL: freqSaveAndRestoreOutsideLoop2:
; Prologue code.
; CHECK: stp [[CSR1:x[0-9]+]], [[CSR2:x[0-9]+]], [sp, #-32]!
; CHECK-NEXT: stp [[CSR3:x[0-9]+]], [[CSR4:x[0-9]+]], [sp, #16]
; CHECK-NEXT: add [[NEW_SP:x[0-9]+]], sp, #16
; CHECK: mov [[SUM:w[0-9]+]], wzr
; CHECK-NEXT: movz [[IV:w[0-9]+]], #0xa
; Next BB.
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ; %for.body
; CHECK: bl _something
; CHECK-NEXT: add [[SUM]], w0, [[SUM]]
; CHECK-NEXT: sub [[IV]], [[IV]], #1
; CHECK-NEXT: cbnz [[IV]], [[LOOP_LABEL]]
; Next BB.
; CHECK: ; %for.end
; CHECK: mov w0, [[SUM]]
; CHECK-NEXT: ldp [[CSR3]], [[CSR4]], [sp, #16]
; CHECK-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #32
; CHECK-NEXT: ret
define i32 @freqSaveAndRestoreOutsideLoop2(i32 %cond) {
entry:
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %i.04 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
  %sum.03 = phi i32 [ 0, %entry ], [ %add, %for.body ]
  %call = tail call i32 bitcast (i32 (...)* @something to i32 ()*)()
  %add = add nsw i32 %call, %sum.03
  %inc = add nuw nsw i32 %i.04, 1
  %exitcond = icmp eq i32 %inc, 10
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret i32 %add
}

; Check with a more complex case that we do not have save within the loop and
; restore outside.
; CHECK-LABEL: loopInfoSaveOutsideLoop:
;
; ENABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; CHECK: stp [[CSR1:x[0-9]+]], [[CSR2:x[0-9]+]], [sp, #-32]!
; CHECK-NEXT: stp [[CSR3:x[0-9]+]], [[CSR4:x[0-9]+]], [sp, #16]
; CHECK-NEXT: add [[NEW_SP:x[0-9]+]], sp, #16
;
; DISABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: mov [[SUM:w[0-9]+]], wzr
; CHECK-NEXT: movz [[IV:w[0-9]+]], #0xa
;
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ; %for.body
; CHECK: bl _something
; CHECK-NEXT: add [[SUM]], w0, [[SUM]]
; CHECK-NEXT: sub [[IV]], [[IV]], #1
; CHECK-NEXT: cbnz [[IV]], [[LOOP_LABEL]]
; Next BB.
; CHECK: bl _somethingElse
; CHECK-NEXT: lsl w0, [[SUM]], #3
;
; Jump to epilogue.
; DISABLE: b [[EPILOG_BB:LBB[0-9_]+]]
;
; DISABLE: [[ELSE_LABEL]]: ; %if.else
; Shift second argument by one and store into returned register.
; DISABLE: lsl w0, w1, #1
; DISABLE: [[EPILOG_BB]]: ; %if.end
; Epilogue code.
; CHECK-NEXT: ldp [[CSR3]], [[CSR4]], [sp, #16]
; CHECK-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #32
; CHECK-NEXT: ret
;
; ENABLE: [[ELSE_LABEL]]: ; %if.else
; Shift second argument by one and store into returned register.
; ENABLE: lsl w0, w1, #1
; ENABLE: ret
define i32 @loopInfoSaveOutsideLoop(i32 %cond, i32 %N) {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.05 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  %sum.04 = phi i32 [ %add, %for.body ], [ 0, %entry ]
  %call = tail call i32 bitcast (i32 (...)* @something to i32 ()*)()
  %add = add nsw i32 %call, %sum.04
  %inc = add nuw nsw i32 %i.05, 1
  %exitcond = icmp eq i32 %inc, 10
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  tail call void bitcast (void (...)* @somethingElse to void ()*)()
  %shl = shl i32 %add, 3
  br label %if.end

if.else:                                          ; preds = %entry
  %mul = shl nsw i32 %N, 1
  br label %if.end

if.end:                                           ; preds = %if.else, %for.end
  %sum.1 = phi i32 [ %shl, %for.end ], [ %mul, %if.else ]
  ret i32 %sum.1
}

declare void @somethingElse(...)

; Check with a more complex case that we do not have restore within the loop and
; save outside.
; CHECK-LABEL: loopInfoRestoreOutsideLoop:
;
; ENABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: stp [[CSR1:x[0-9]+]], [[CSR2:x[0-9]+]], [sp, #-32]!
; CHECK-NEXT: stp [[CSR3:x[0-9]+]], [[CSR4:x[0-9]+]], [sp, #16]
; CHECK-NEXT: add [[NEW_SP:x[0-9]+]], sp, #16
;
; DISABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: bl _somethingElse
; CHECK-NEXT: mov [[SUM:w[0-9]+]], wzr
; CHECK-NEXT: movz [[IV:w[0-9]+]], #0xa
;
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ; %for.body
; CHECK: bl _something
; CHECK-NEXT: add [[SUM]], w0, [[SUM]]
; CHECK-NEXT: sub [[IV]], [[IV]], #1
; CHECK-NEXT: cbnz [[IV]], [[LOOP_LABEL]]
; Next BB.
; CHECK: lsl w0, [[SUM]], #3
;
; Jump to epilogue.
; DISABLE: b [[EPILOG_BB:LBB[0-9_]+]]
;
; DISABLE: [[ELSE_LABEL]]: ; %if.else
; Shift second argument by one and store into returned register.
; DISABLE: lsl w0, w1, #1
; DISABLE: [[EPILOG_BB]]: ; %if.end
; Epilogue code.
; CHECK: ldp [[CSR3]], [[CSR4]], [sp, #16]
; CHECK-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #32
; CHECK-NEXT: ret
;
; ENABLE: [[ELSE_LABEL]]: ; %if.else
; Shift second argument by one and store into returned register.
; ENABLE: lsl w0, w1, #1
; ENABLE: ret
define i32 @loopInfoRestoreOutsideLoop(i32 %cond, i32 %N) #0 {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %if.then

if.then:                                          ; preds = %entry
  tail call void bitcast (void (...)* @somethingElse to void ()*)()
  br label %for.body

for.body:                                         ; preds = %for.body, %if.then
  %i.05 = phi i32 [ 0, %if.then ], [ %inc, %for.body ]
  %sum.04 = phi i32 [ 0, %if.then ], [ %add, %for.body ]
  %call = tail call i32 bitcast (i32 (...)* @something to i32 ()*)()
  %add = add nsw i32 %call, %sum.04
  %inc = add nuw nsw i32 %i.05, 1
  %exitcond = icmp eq i32 %inc, 10
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  %shl = shl i32 %add, 3
  br label %if.end

if.else:                                          ; preds = %entry
  %mul = shl nsw i32 %N, 1
  br label %if.end

if.end:                                           ; preds = %if.else, %for.end
  %sum.1 = phi i32 [ %shl, %for.end ], [ %mul, %if.else ]
  ret i32 %sum.1
}

; Check that we handle function with no frame information correctly.
; CHECK-LABEL: emptyFrame:
; CHECK: ; %entry
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
define i32 @emptyFrame() {
entry:
  ret i32 0
}

; Check that we handle variadic function correctly.
; CHECK-LABEL: variadicFunc:
;
; ENABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; CHECK: sub sp, sp, #16
; DISABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; Sum is merged with the returned register.
; CHECK: mov [[SUM:w0]], wzr
; CHECK-NEXT: add [[VA_BASE:x[0-9]+]], sp, #16
; CHECK-NEXT: str [[VA_BASE]], [sp, #8]
; CHECK-NEXT: cmp w1, #1
; CHECK-NEXT: b.lt [[IFEND_LABEL:LBB[0-9_]+]]
;
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ; %for.body
; CHECK: ldr [[VA_ADDR:x[0-9]+]], [sp, #8]
; CHECK-NEXT: add [[NEXT_VA_ADDR:x[0-9]+]], [[VA_ADDR]], #8
; CHECK-NEXT: str [[NEXT_VA_ADDR]], [sp, #8]
; CHECK-NEXT: ldr [[VA_VAL:w[0-9]+]], {{\[}}[[VA_ADDR]]]
; CHECK-NEXT: add [[SUM]], [[SUM]], [[VA_VAL]]
; CHECK-NEXT: sub w1, w1, #1
; CHECK-NEXT: cbnz w1, [[LOOP_LABEL]]
;
; DISABLE-NEXT: b [[IFEND_LABEL]]
; DISABLE: [[ELSE_LABEL]]: ; %if.else
; DISABLE: lsl w0, w1, #1
;
; CHECK: [[IFEND_LABEL]]:
; Epilogue code.
; CHECK: add sp, sp, #16
; CHECK-NEXT: ret
;
; ENABLE: [[ELSE_LABEL]]: ; %if.else
; ENABLE: lsl w0, w1, #1
; ENABLE-NEXT: ret
define i32 @variadicFunc(i32 %cond, i32 %count, ...) #0 {
entry:
  %ap = alloca i8*, align 8
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %if.then

if.then:                                          ; preds = %entry
  %ap1 = bitcast i8** %ap to i8*
  call void @llvm.va_start(i8* %ap1)
  %cmp6 = icmp sgt i32 %count, 0
  br i1 %cmp6, label %for.body, label %for.end

for.body:                                         ; preds = %if.then, %for.body
  %i.08 = phi i32 [ %inc, %for.body ], [ 0, %if.then ]
  %sum.07 = phi i32 [ %add, %for.body ], [ 0, %if.then ]
  %0 = va_arg i8** %ap, i32
  %add = add nsw i32 %sum.07, %0
  %inc = add nuw nsw i32 %i.08, 1
  %exitcond = icmp eq i32 %inc, %count
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %if.then
  %sum.0.lcssa = phi i32 [ 0, %if.then ], [ %add, %for.body ]
  call void @llvm.va_end(i8* %ap1)
  br label %if.end

if.else:                                          ; preds = %entry
  %mul = shl nsw i32 %count, 1
  br label %if.end

if.end:                                           ; preds = %if.else, %for.end
  %sum.1 = phi i32 [ %sum.0.lcssa, %for.end ], [ %mul, %if.else ]
  ret i32 %sum.1
}

declare void @llvm.va_start(i8*)

declare void @llvm.va_end(i8*)

; Check that we handle inline asm correctly.
; CHECK-LABEL: inlineAsm:
;
; ENABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; Make sure we save the CSR used in the inline asm: x19.
; CHECK: stp [[CSR1:x[0-9]+]], [[CSR2:x19]], [sp, #-16]!
;
; DISABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: movz [[IV:w[0-9]+]], #0xa
;
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ; %for.body
; Inline asm statement.
; CHECK: add x19, x19, #1
; CHECK: sub [[IV]], [[IV]], #1
; CHECK-NEXT: cbnz [[IV]], [[LOOP_LABEL]]
; Next BB.
; CHECK: mov w0, wzr
; Epilogue code.
; CHECK-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #16
; CHECK-NEXT: ret
; Next BB.
; CHECK: [[ELSE_LABEL]]: ; %if.else
; CHECK-NEXT: lsl w0, w1, #1
; Epilogue code.
; DISABLE-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #16
; CHECK-NEXT: ret
define i32 @inlineAsm(i32 %cond, i32 %N) {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.03 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
  tail call void asm sideeffect "add x19, x19, #1", "~{x19}"()
  %inc = add nuw nsw i32 %i.03, 1
  %exitcond = icmp eq i32 %inc, 10
  br i1 %exitcond, label %if.end, label %for.body

if.else:                                          ; preds = %entry
  %mul = shl nsw i32 %N, 1
  br label %if.end

if.end:                                           ; preds = %for.body, %if.else
  %sum.0 = phi i32 [ %mul, %if.else ], [ 0, %for.body ]
  ret i32 %sum.0
}

; Check that we handle calls to variadic functions correctly.
; CHECK-LABEL: callVariadicFunc:
;
; ENABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; CHECK: stp [[CSR1:x[0-9]+]], [[CSR2:x[0-9]+]], [sp, #-16]!
; CHECK-NEXT: mov [[NEW_SP:x[0-9]+]], sp
; CHECK-NEXT: sub sp, sp, #48
;
; DISABLE: cbz w0, [[ELSE_LABEL:LBB[0-9_]+]]
; Setup of the varags.
; CHECK: stp x1, x1, [sp, #32]
; CHECK-NEXT: stp x1, x1, [sp, #16]
; CHECK-NEXT: stp x1, x1, [sp]
; CHECK-NEXT: mov w0, w1
; CHECK-NEXT: bl _someVariadicFunc
; CHECK-NEXT: lsl w0, w0, #3
;
; DISABLE: b [[IFEND_LABEL:LBB[0-9_]+]]
; DISABLE: [[ELSE_LABEL]]: ; %if.else
; DISABLE-NEXT: lsl w0, w1, #1
; DISABLE: [[IFEND_LABEL]]: ; %if.end
;
; Epilogue code.
; CHECK: mov sp, [[NEW_SP]]
; CHECK-NEXT: ldp [[CSR1]], [[CSR2]], [sp], #16
; CHECK-NEXT: ret
;
; ENABLE: [[ELSE_LABEL]]: ; %if.else
; ENABLE-NEXT: lsl w0, w1, #1
; ENABLE-NEXT: ret
define i32 @callVariadicFunc(i32 %cond, i32 %N) {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %if.then

if.then:                                          ; preds = %entry
  %call = tail call i32 (i32, ...) @someVariadicFunc(i32 %N, i32 %N, i32 %N, i32 %N, i32 %N, i32 %N, i32 %N)
  %shl = shl i32 %call, 3
  br label %if.end

if.else:                                          ; preds = %entry
  %mul = shl nsw i32 %N, 1
  br label %if.end

if.end:                                           ; preds = %if.else, %if.then
  %sum.0 = phi i32 [ %shl, %if.then ], [ %mul, %if.else ]
  ret i32 %sum.0
}

declare i32 @someVariadicFunc(i32, ...)

; Make sure we do not insert unreachable code after noreturn function.
; Although this is not incorrect to insert such code, it is useless
; and it hurts the binary size.
;
; CHECK-LABEL: noreturn:
; DISABLE: stp
;
; CHECK: and [[TEST:w[0-9]+]], w0, #0xff
; CHECK-NEXT: cbnz [[TEST]], [[ABORT:LBB[0-9_]+]]
;
; CHECK: movz w0, #0x2a
;
; DISABLE-NEXT: ldp
;
; CHECK-NEXT: ret
;
; CHECK: [[ABORT]]: ; %if.abort
;
; ENABLE: stp
;
; CHECK: bl _abort
; ENABLE-NOT: ldp
define i32 @noreturn(i8 signext %bad_thing) {
entry:
  %tobool = icmp eq i8 %bad_thing, 0
  br i1 %tobool, label %if.end, label %if.abort

if.abort:
  tail call void @abort() #0
  unreachable

if.end:
  ret i32 42
}

declare void @abort() #0

attributes #0 = { noreturn nounwind }

; Make sure that we handle infinite loops properly When checking that the Save
; and Restore blocks are control flow equivalent, the loop searches for the
; immediate (post) dominator for the (restore) save blocks. When either the Save
; or Restore block is located in an infinite loop the only immediate (post)
; dominator is itself. In this case, we cannot perform shrink wrapping, but we
; should return gracefully and continue compilation.
; The only condition for this test is the compilation finishes correctly.
;
; CHECK-LABEL: infiniteloop
; CHECK: ret
define void @infiniteloop() {
entry:
  br i1 undef, label %if.then, label %if.end

if.then:
  %ptr = alloca i32, i32 4
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %sum.03 = phi i32 [ 0, %if.then ], [ %add, %for.body ]
  %call = tail call i32 bitcast (i32 (...)* @something to i32 ()*)()
  %add = add nsw i32 %call, %sum.03
  store i32 %add, i32* %ptr
  br label %for.body

if.end:
  ret void
}

; Another infinite loop test this time with a body bigger than just one block.
; CHECK-LABEL: infiniteloop2
; CHECK: ret
define void @infiniteloop2() {
entry:
  br i1 undef, label %if.then, label %if.end

if.then:
  %ptr = alloca i32, i32 4
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %sum.03 = phi i32 [ 0, %if.then ], [ %add, %body1 ], [ 1, %body2]
  %call = tail call i32 asm "mov $0, #0", "=r,~{x19}"()
  %add = add nsw i32 %call, %sum.03
  store i32 %add, i32* %ptr
  br i1 undef, label %body1, label %body2

body1:
  tail call void asm sideeffect "nop", "~{x19}"()
  br label %for.body

body2:
  tail call void asm sideeffect "nop", "~{x19}"()
  br label %for.body

if.end:
  ret void
}

; Another infinite loop test this time with two nested infinite loop.
; CHECK-LABEL: infiniteloop3
; CHECK: ret
define void @infiniteloop3() {
entry:
  br i1 undef, label %loop2a, label %body

body:                                             ; preds = %entry
  br i1 undef, label %loop2a, label %end

loop1:                                            ; preds = %loop2a, %loop2b
  %var.phi = phi i32* [ %next.phi, %loop2b ], [ %var, %loop2a ]
  %next.phi = phi i32* [ %next.load, %loop2b ], [ %next.var, %loop2a ]
  %0 = icmp eq i32* %var, null
  %next.load = load i32*, i32** undef
  br i1 %0, label %loop2a, label %loop2b

loop2a:                                           ; preds = %loop1, %body, %entry
  %var = phi i32* [ null, %body ], [ null, %entry ], [ %next.phi, %loop1 ]
  %next.var = phi i32* [ undef, %body ], [ null, %entry ], [ %next.load, %loop1 ]
  br label %loop1

loop2b:                                           ; preds = %loop1
  %gep1 = bitcast i32* %var.phi to i32*
  %next.ptr = bitcast i32* %gep1 to i32**
  store i32* %next.phi, i32** %next.ptr
  br label %loop1

end:
  ret void
}

; Don't do shrink-wrapping when we need to re-align the stack pointer.
; See bug 26642.
; CHECK-LABEL: stack_realign:
; CHECK-NOT: lsl w[[LSL1:[0-9]+]], w0, w1
; CHECK-NOT: lsl w[[LSL2:[0-9]+]], w1, w0
; CHECK: stp x29, x30, [sp, #-16]!
; CHECK: mov x29, sp
; CHECK: sub x{{[0-9]+}}, sp, #16
; CHECK-DAG: lsl w[[LSL1:[0-9]+]], w0, w1
; CHECK-DAG: lsl w[[LSL2:[0-9]+]], w1, w0
; CHECK-DAG: str w[[LSL1]],
; CHECK-DAG: str w[[LSL2]],

define i32 @stack_realign(i32 %a, i32 %b, i32* %ptr1, i32* %ptr2) {
  %tmp = alloca i32, align 32
  %shl1 = shl i32 %a, %b
  %shl2 = shl i32 %b, %a
  %tmp2 = icmp slt i32 %a, %b
  br i1 %tmp2, label %true, label %false

true:
  store i32 %a, i32* %tmp, align 4
  %tmp4 = load i32, i32* %tmp
  br label %false

false:
  %tmp.0 = phi i32 [ %tmp4, %true ], [ %a, %0 ]
  store i32 %shl1, i32* %ptr1
  store i32 %shl2, i32* %ptr2
  ret i32 %tmp.0
}

; Re-aligned stack pointer with all caller-save regs live.  See bug
; 26642.  In this case we currently avoid shrink wrapping because
; ensuring we have a scratch register to re-align the stack pointer is
; too complicated.  Output should be the same for both enabled and
; disabled shrink wrapping.
; CHECK-LABEL: stack_realign2:
; CHECK: stp {{x[0-9]+}}, {{x[0-9]+}}, [sp, #-{{[0-9]+}}]!
; CHECK: add x29, sp, #{{[0-9]+}}
; CHECK: lsl {{w[0-9]+}}, w0, w1

define void @stack_realign2(i32 %a, i32 %b, i32* %ptr1, i32* %ptr2, i32* %ptr3, i32* %ptr4, i32* %ptr5, i32* %ptr6) {
  %tmp = alloca i32, align 32
  %tmp1 = shl i32 %a, %b
  %tmp2 = shl i32 %b, %a
  %tmp3 = lshr i32 %a, %b
  %tmp4 = lshr i32 %b, %a
  %tmp5 = add i32 %b, %a
  %tmp6 = sub i32 %b, %a
  %tmp7 = add i32 %tmp1, %tmp2
  %tmp8 = sub i32 %tmp2, %tmp3
  %tmp9 = add i32 %tmp3, %tmp4
  %tmp10 = add i32 %tmp4, %tmp5
  %cmp = icmp slt i32 %a, %b
  br i1 %cmp, label %true, label %false

true:
  store i32 %a, i32* %tmp, align 4
  call void asm sideeffect "nop", "~{x19},~{x20},~{x21},~{x22},~{x23},~{x24},~{x25},~{x26},~{x27},~{x28}"() nounwind
  br label %false

false:
  store i32 %tmp1, i32* %ptr1, align 4
  store i32 %tmp2, i32* %ptr2, align 4
  store i32 %tmp3, i32* %ptr3, align 4
  store i32 %tmp4, i32* %ptr4, align 4
  store i32 %tmp5, i32* %ptr5, align 4
  store i32 %tmp6, i32* %ptr6, align 4
  %idx1 = getelementptr inbounds i32, i32* %ptr1, i64 1
  store i32 %a, i32* %idx1, align 4
  %idx2 = getelementptr inbounds i32, i32* %ptr1, i64 2
  store i32 %b, i32* %idx2, align 4
  %idx3 = getelementptr inbounds i32, i32* %ptr1, i64 3
  store i32 %tmp7, i32* %idx3, align 4
  %idx4 = getelementptr inbounds i32, i32* %ptr1, i64 4
  store i32 %tmp8, i32* %idx4, align 4
  %idx5 = getelementptr inbounds i32, i32* %ptr1, i64 5
  store i32 %tmp9, i32* %idx5, align 4
  %idx6 = getelementptr inbounds i32, i32* %ptr1, i64 6
  store i32 %tmp10, i32* %idx6, align 4

  ret void
}