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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=jump-threading -S | FileCheck %s
; RUN: opt < %s -aa-pipeline=basic-aa -passes=jump-threading -S | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i386-apple-darwin7"
; Test that we can thread through the block with the partially redundant load (%2).
; rdar://6402033
define i32 @test1(ptr %P) nounwind {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = tail call i32 (...) @f1() #[[ATTR0:[0-9]+]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[TMP1]], label [[BB1:%.*]], label [[BB1_THREAD:%.*]]
; CHECK: bb1.thread:
; CHECK-NEXT: store i32 42, ptr [[P:%.*]], align 4
; CHECK-NEXT: br label [[BB3:%.*]]
; CHECK: bb1:
; CHECK-NEXT: [[DOTPR:%.*]] = load i32, ptr [[P]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i32 [[DOTPR]], 36
; CHECK-NEXT: br i1 [[TMP2]], label [[BB3]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[TMP3:%.*]] = tail call i32 (...) @f2() #[[ATTR0]]
; CHECK-NEXT: ret i32 0
; CHECK: bb3:
; CHECK-NEXT: [[RES_02:%.*]] = phi i32 [ 1, [[BB1_THREAD]] ], [ 0, [[BB1]] ]
; CHECK-NEXT: ret i32 [[RES_02]]
;
entry:
%0 = tail call i32 (...) @f1() nounwind ; <i32> [#uses=1]
%1 = icmp eq i32 %0, 0 ; <i1> [#uses=1]
br i1 %1, label %bb1, label %bb
bb: ; preds = %entry
store i32 42, ptr %P, align 4
br label %bb1
bb1: ; preds = %entry, %bb
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ] ; <i32> [#uses=2]
%2 = load i32, ptr %P, align 4 ; <i32> [#uses=1]
%3 = icmp sgt i32 %2, 36 ; <i1> [#uses=1]
br i1 %3, label %bb3, label %bb2
bb2: ; preds = %bb1
%4 = tail call i32 (...) @f2() nounwind ; <i32> [#uses=0]
ret i32 %res.0
bb3: ; preds = %bb1
ret i32 %res.0
}
declare i32 @f1(...)
declare i32 @f2(...)
;; Check that we preserve TBAA information.
; rdar://11039258
define i32 @test2(ptr %P) nounwind {
; CHECK-LABEL: @test2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = tail call i32 (...) @f1() #[[ATTR0]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i32 [[TMP0]], 0
; CHECK-NEXT: br i1 [[TMP1]], label [[BB1:%.*]], label [[BB1_THREAD:%.*]]
; CHECK: bb1.thread:
; CHECK-NEXT: store i32 42, ptr [[P:%.*]], align 4, !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: br label [[BB3:%.*]]
; CHECK: bb1:
; CHECK-NEXT: [[DOTPR:%.*]] = load i32, ptr [[P]], align 4, !tbaa [[TBAA0]]
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i32 [[DOTPR]], 36
; CHECK-NEXT: br i1 [[TMP2]], label [[BB3]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[TMP3:%.*]] = tail call i32 (...) @f2() #[[ATTR0]]
; CHECK-NEXT: ret i32 0
; CHECK: bb3:
; CHECK-NEXT: [[RES_02:%.*]] = phi i32 [ 1, [[BB1_THREAD]] ], [ 0, [[BB1]] ]
; CHECK-NEXT: ret i32 [[RES_02]]
;
entry:
%0 = tail call i32 (...) @f1() nounwind ; <i32> [#uses=1]
%1 = icmp eq i32 %0, 0 ; <i1> [#uses=1]
br i1 %1, label %bb1, label %bb
bb: ; preds = %entry
store i32 42, ptr %P, align 4, !tbaa !0
br label %bb1
bb1: ; preds = %entry, %bb
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%2 = load i32, ptr %P, align 4, !tbaa !0
%3 = icmp sgt i32 %2, 36
br i1 %3, label %bb3, label %bb2
bb2: ; preds = %bb1
%4 = tail call i32 (...) @f2() nounwind
ret i32 %res.0
bb3: ; preds = %bb1
ret i32 %res.0
}
define i32 @test3(ptr %x, i1 %f) {
; Correctly thread loads of different (but compatible) types, placing bitcasts
; as necessary in the predecessors. This is especially tricky because the same
; predecessor ends up with two entries in the PHI node and they must share
; a single cast.
; CHECK-LABEL: @test3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[X:%.*]], align 8
; CHECK-NEXT: br i1 [[F:%.*]], label [[IF_END57:%.*]], label [[IF_END57]]
; CHECK: if.end57:
; CHECK-NEXT: [[TMP3:%.*]] = phi ptr [ [[TMP1]], [[ENTRY:%.*]] ], [ [[TMP1]], [[ENTRY]] ]
; CHECK-NEXT: [[TOBOOL59:%.*]] = icmp eq ptr [[TMP3]], null
; CHECK-NEXT: br i1 [[TOBOOL59]], label [[RETURN:%.*]], label [[IF_THEN60:%.*]]
; CHECK: if.then60:
; CHECK-NEXT: ret i32 42
; CHECK: return:
; CHECK-NEXT: ret i32 13
;
entry:
%0 = load ptr, ptr %x, align 8
br i1 %f, label %if.end57, label %if.then56
if.then56:
br label %if.end57
if.end57:
%1 = load ptr, ptr %x, align 8
%tobool59 = icmp eq ptr %1, null
br i1 %tobool59, label %return, label %if.then60
if.then60:
ret i32 42
return:
ret i32 13
}
define i32 @test4(ptr %P) {
; CHECK-LABEL: @test4(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V0:%.*]] = tail call i32 (...) @f1()
; CHECK-NEXT: [[V1:%.*]] = icmp eq i32 [[V0]], 0
; CHECK-NEXT: br i1 [[V1]], label [[BB1:%.*]], label [[BB1_THREAD:%.*]]
; CHECK: bb1.thread:
; CHECK-NEXT: store atomic i32 42, ptr [[P:%.*]] unordered, align 4
; CHECK-NEXT: br label [[BB3:%.*]]
; CHECK: bb1:
; CHECK-NEXT: [[V2_PR:%.*]] = load atomic i32, ptr [[P]] unordered, align 4
; CHECK-NEXT: [[V3:%.*]] = icmp sgt i32 [[V2_PR]], 36
; CHECK-NEXT: br i1 [[V3]], label [[BB3]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[V4:%.*]] = tail call i32 (...) @f2()
; CHECK-NEXT: ret i32 0
; CHECK: bb3:
; CHECK-NEXT: [[RES_04:%.*]] = phi i32 [ 1, [[BB1_THREAD]] ], [ 0, [[BB1]] ]
; CHECK-NEXT: ret i32 [[RES_04]]
;
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
store atomic i32 42, ptr %P unordered, align 4
br label %bb1
bb1:
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, ptr %P unordered, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
define i32 @test5(ptr %P) {
; Negative test
; CHECK-LABEL: @test5(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V0:%.*]] = tail call i32 (...) @f1()
; CHECK-NEXT: [[V1:%.*]] = icmp eq i32 [[V0]], 0
; CHECK-NEXT: br i1 [[V1]], label [[BB1:%.*]], label [[BB:%.*]]
; CHECK: bb:
; CHECK-NEXT: store atomic i32 42, ptr [[P:%.*]] release, align 4
; CHECK-NEXT: br label [[BB1]]
; CHECK: bb1:
; CHECK-NEXT: [[RES_0:%.*]] = phi i32 [ 1, [[BB]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[V2:%.*]] = load atomic i32, ptr [[P]] acquire, align 4
; CHECK-NEXT: [[V3:%.*]] = icmp sgt i32 [[V2]], 36
; CHECK-NEXT: br i1 [[V3]], label [[BB3:%.*]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[V4:%.*]] = tail call i32 (...) @f2()
; CHECK-NEXT: ret i32 [[RES_0]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 [[RES_0]]
;
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
store atomic i32 42, ptr %P release, align 4
br label %bb1
bb1:
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, ptr %P acquire, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
define i32 @test6(ptr %P) {
; Negative test
; CHECK-LABEL: @test6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V0:%.*]] = tail call i32 (...) @f1()
; CHECK-NEXT: [[V1:%.*]] = icmp eq i32 [[V0]], 0
; CHECK-NEXT: br i1 [[V1]], label [[BB1:%.*]], label [[BB:%.*]]
; CHECK: bb:
; CHECK-NEXT: store i32 42, ptr [[P:%.*]], align 4
; CHECK-NEXT: br label [[BB1]]
; CHECK: bb1:
; CHECK-NEXT: [[RES_0:%.*]] = phi i32 [ 1, [[BB]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[V2:%.*]] = load atomic i32, ptr [[P]] acquire, align 4
; CHECK-NEXT: [[V3:%.*]] = icmp sgt i32 [[V2]], 36
; CHECK-NEXT: br i1 [[V3]], label [[BB3:%.*]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[V4:%.*]] = tail call i32 (...) @f2()
; CHECK-NEXT: ret i32 [[RES_0]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 [[RES_0]]
;
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
store i32 42, ptr %P
br label %bb1
bb1:
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, ptr %P acquire, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
define i32 @test7(ptr %P) {
; Negative test
; CHECK-LABEL: @test7(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V0:%.*]] = tail call i32 (...) @f1()
; CHECK-NEXT: [[V1:%.*]] = icmp eq i32 [[V0]], 0
; CHECK-NEXT: br i1 [[V1]], label [[BB1:%.*]], label [[BB:%.*]]
; CHECK: bb:
; CHECK-NEXT: [[VAL:%.*]] = load i32, ptr [[P:%.*]], align 4
; CHECK-NEXT: br label [[BB1]]
; CHECK: bb1:
; CHECK-NEXT: [[RES_0:%.*]] = phi i32 [ 1, [[BB]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[V2:%.*]] = load atomic i32, ptr [[P]] acquire, align 4
; CHECK-NEXT: [[V3:%.*]] = icmp sgt i32 [[V2]], 36
; CHECK-NEXT: br i1 [[V3]], label [[BB3:%.*]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: [[V4:%.*]] = tail call i32 (...) @f2()
; CHECK-NEXT: ret i32 [[RES_0]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 [[RES_0]]
;
entry:
%v0 = tail call i32 (...) @f1()
%v1 = icmp eq i32 %v0, 0
br i1 %v1, label %bb1, label %bb
bb:
%val = load i32, ptr %P
br label %bb1
bb1:
%res.0 = phi i32 [ 1, %bb ], [ 0, %entry ]
%v2 = load atomic i32, ptr %P acquire, align 4
%v3 = icmp sgt i32 %v2, 36
br i1 %v3, label %bb3, label %bb2
bb2:
%v4 = tail call i32 (...) @f2()
ret i32 %res.0
bb3:
ret i32 %res.0
}
; Make sure we merge the aliasing metadata. We keep the range metadata for the
; first load, as it dominates the second load. Hence we can eliminate the
; branch.
define void @test8(ptr, ptr, ptr) {
; CHECK-LABEL: @test8(
; CHECK-NEXT: ret2:
; CHECK-NEXT: [[A:%.*]] = load i32, ptr [[TMP0:%.*]], align 4, !range [[RNG4:![0-9]+]], !noundef !5
; CHECK-NEXT: store i32 [[A]], ptr [[TMP1:%.*]], align 4
; CHECK-NEXT: [[XXX:%.*]] = tail call i32 (...) @f1() #[[ATTR0]]
; CHECK-NEXT: ret void
;
%a = load i32, ptr %0, !tbaa !0, !range !4, !alias.scope !9, !noalias !10, !noundef !11
%b = load i32, ptr %0, !range !5
store i32 %a, ptr %1
%c = icmp eq i32 %b, 8
br i1 %c, label %ret1, label %ret2
ret1:
ret void
ret2:
%xxx = tail call i32 (...) @f1() nounwind
ret void
}
; Make sure we merge/PRE aliasing metadata correctly. That means that
; we need to remove metadata from the existing load, and add appropriate
; metadata to the newly inserted load.
define void @test9(ptr, ptr, ptr, i1 %c) {
; CHECK-LABEL: @test9(
; CHECK-NEXT: br i1 [[C:%.*]], label [[D1:%.*]], label [[D2:%.*]]
; CHECK: d1:
; CHECK-NEXT: [[A:%.*]] = load i32, ptr [[TMP0:%.*]], align 4
; CHECK-NEXT: br label [[D3:%.*]]
; CHECK: d2:
; CHECK-NEXT: [[XXXX:%.*]] = tail call i32 (...) @f1() #[[ATTR0]]
; CHECK-NEXT: [[B_PR:%.*]] = load i32, ptr [[TMP0]], align 4, !tbaa [[TBAA0]]
; CHECK-NEXT: br label [[D3]]
; CHECK: d3:
; CHECK-NEXT: [[B:%.*]] = phi i32 [ [[B_PR]], [[D2]] ], [ [[A]], [[D1]] ]
; CHECK-NEXT: [[P:%.*]] = phi i32 [ 1, [[D2]] ], [ [[A]], [[D1]] ]
; CHECK-NEXT: store i32 [[P]], ptr [[TMP1:%.*]], align 4
; CHECK-NEXT: [[C2:%.*]] = icmp eq i32 [[B]], 8
; CHECK-NEXT: br i1 [[C2]], label [[RET1:%.*]], label [[RET2:%.*]]
; CHECK: ret1:
; CHECK-NEXT: ret void
; CHECK: ret2:
; CHECK-NEXT: [[XXX:%.*]] = tail call i32 (...) @f1() #[[ATTR0]]
; CHECK-NEXT: ret void
;
br i1 %c, label %d1, label %d2
d1:
%a = load i32, ptr %0, !range !4, !alias.scope !9, !noalias !10
br label %d3
d2:
%xxxx = tail call i32 (...) @f1() nounwind
br label %d3
d3:
%p = phi i32 [ 1, %d2 ], [ %a, %d1 ]
%b = load i32, ptr %0, !tbaa !0
store i32 %p, ptr %1
%c2 = icmp eq i32 %b, 8
br i1 %c2, label %ret1, label %ret2
ret1:
ret void
ret2:
%xxx = tail call i32 (...) @f1() nounwind
ret void
}
define i32 @fn_noalias(i1 %c2,ptr noalias %P, ptr noalias %P2) {
; CHECK-LABEL: @fn_noalias(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 [[C2:%.*]], label [[COND2:%.*]], label [[COND1:%.*]]
; CHECK: cond1:
; CHECK-NEXT: [[L1:%.*]] = load i64, ptr [[P:%.*]], align 4
; CHECK-NEXT: store i64 42, ptr [[P2:%.*]], align 4
; CHECK-NEXT: [[C:%.*]] = icmp eq i64 [[L1]], 0
; CHECK-NEXT: br i1 [[C]], label [[COND2_THREAD:%.*]], label [[END:%.*]]
; CHECK: cond2.thread:
; CHECK-NEXT: call void @fn2(i64 [[L1]])
; CHECK-NEXT: br label [[COND3:%.*]]
; CHECK: cond2:
; CHECK-NEXT: [[L2_PR:%.*]] = load i64, ptr [[P]], align 4
; CHECK-NEXT: call void @fn2(i64 [[L2_PR]])
; CHECK-NEXT: [[C3:%.*]] = icmp eq i64 [[L2_PR]], 0
; CHECK-NEXT: br i1 [[C3]], label [[COND3]], label [[END]]
; CHECK: cond3:
; CHECK-NEXT: [[L23:%.*]] = phi i64 [ [[L1]], [[COND2_THREAD]] ], [ [[L2_PR]], [[COND2]] ]
; CHECK-NEXT: call void @fn3(i64 [[L23]])
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret i32 0
;
entry:
br i1 %c2, label %cond2, label %cond1
cond1:
%l1 = load i64, ptr %P
store i64 42, ptr %P2
%c = icmp eq i64 %l1, 0
br i1 %c, label %cond2, label %end
cond2:
%l2 = load i64, ptr %P
call void @fn2(i64 %l2)
%c3 = icmp eq i64 %l2, 0
br i1 %c3, label %cond3, label %end
cond3:
call void @fn3(i64 %l2)
br label %end
end:
ret i32 0
}
; This tests if we can thread from %sw.bb.i to %do.body.preheader.i67 through
; %sw.bb21.i. To make this happen, %l2 should be detected as a partically
; redundant load with %l3 across the store to %phase in %sw.bb21.i.
%struct.NEXT_MOVE = type { i32, i32, ptr }
@hash_move = unnamed_addr global [65 x i32] zeroinitializer, align 4
@current_move = internal global [65 x i32] zeroinitializer, align 4
@last = internal unnamed_addr global [65 x ptr] zeroinitializer, align 8
@next_status = internal unnamed_addr global [65 x %struct.NEXT_MOVE] zeroinitializer, align 8
define fastcc i32 @Search(i64 %idxprom.i, i64 %idxprom.i89, i32 %c) {
; CHECK-LABEL: @Search(
; CHECK-NEXT: cond.true282:
; CHECK-NEXT: [[ARRAYIDX185:%.*]] = getelementptr inbounds [65 x i32], ptr @hash_move, i64 0, i64 [[IDXPROM_I:%.*]]
; CHECK-NEXT: [[ARRAYIDX307:%.*]] = getelementptr inbounds [65 x i32], ptr @current_move, i64 0, i64 [[IDXPROM_I]]
; CHECK-NEXT: [[ARRAYIDX89:%.*]] = getelementptr inbounds [65 x ptr], ptr @last, i64 0, i64 [[IDXPROM_I]]
; CHECK-NEXT: [[PHASE:%.*]] = getelementptr inbounds [65 x %struct.NEXT_MOVE], ptr @next_status, i64 0, i64 [[IDXPROM_I]], i32 0
; CHECK-NEXT: switch i32 [[C:%.*]], label [[CLEANUP:%.*]] [
; CHECK-NEXT: i32 1, label [[SW_BB_I:%.*]]
; CHECK-NEXT: i32 0, label [[SW_BB21_I:%.*]]
; CHECK-NEXT: ]
; CHECK: sw.bb.i:
; CHECK-NEXT: [[CALL_I62:%.*]] = call fastcc ptr @GenerateCheckEvasions()
; CHECK-NEXT: store ptr [[CALL_I62]], ptr [[ARRAYIDX89]], align 8
; CHECK-NEXT: [[L2:%.*]] = load i32, ptr [[ARRAYIDX185]], align 4
; CHECK-NEXT: [[TOBOOL_I63:%.*]] = icmp eq i32 [[L2]], 0
; CHECK-NEXT: br i1 [[TOBOOL_I63]], label [[SW_BB21_I_THREAD:%.*]], label [[IF_THEN_I64:%.*]]
; CHECK: sw.bb21.i.thread:
; CHECK-NEXT: store i32 10, ptr [[PHASE]], align 8
; CHECK-NEXT: br label [[DO_BODY_PREHEADER_I67:%.*]]
; CHECK: if.then.i64:
; CHECK-NEXT: store i32 7, ptr [[PHASE]], align 8
; CHECK-NEXT: store i32 [[L2]], ptr [[ARRAYIDX307]], align 4
; CHECK-NEXT: [[CALL16_I:%.*]] = call fastcc i32 @ValidMove(i32 [[L2]])
; CHECK-NEXT: [[TOBOOL17_I:%.*]] = icmp eq i32 [[CALL16_I]], 0
; CHECK-NEXT: br i1 [[TOBOOL17_I]], label [[IF_ELSE_I65:%.*]], label [[CLEANUP]]
; CHECK: if.else.i65:
; CHECK-NEXT: call void @f65()
; CHECK-NEXT: br label [[SW_BB21_I]]
; CHECK: sw.bb21.i:
; CHECK-NEXT: [[L3_PR:%.*]] = load i32, ptr [[ARRAYIDX185]], align 4
; CHECK-NEXT: store i32 10, ptr [[PHASE]], align 8
; CHECK-NEXT: [[TOBOOL27_I:%.*]] = icmp eq i32 [[L3_PR]], 0
; CHECK-NEXT: br i1 [[TOBOOL27_I]], label [[DO_BODY_PREHEADER_I67]], label [[CLEANUP]]
; CHECK: do.body.preheader.i67:
; CHECK-NEXT: call void @f67()
; CHECK-NEXT: ret i32 67
; CHECK: cleanup:
; CHECK-NEXT: call void @Cleanup()
; CHECK-NEXT: ret i32 0
;
entry:
%arrayidx185 = getelementptr inbounds [65 x i32], ptr @hash_move, i64 0, i64 %idxprom.i
%arrayidx307 = getelementptr inbounds [65 x i32], ptr @current_move, i64 0, i64 %idxprom.i
%arrayidx89 = getelementptr inbounds [65 x ptr], ptr @last, i64 0, i64 %idxprom.i
%phase = getelementptr inbounds [65 x %struct.NEXT_MOVE], ptr @next_status, i64 0, i64 %idxprom.i, i32 0
br label %cond.true282
cond.true282:
switch i32 %c, label %sw.default.i [
i32 1, label %sw.bb.i
i32 0, label %sw.bb21.i
]
sw.default.i:
br label %cleanup
sw.bb.i:
%call.i62 = call fastcc ptr @GenerateCheckEvasions()
store ptr %call.i62, ptr %arrayidx89, align 8
%l2 = load i32, ptr %arrayidx185, align 4
%tobool.i63 = icmp eq i32 %l2, 0
br i1 %tobool.i63, label %sw.bb21.i, label %if.then.i64
if.then.i64: ; preds = %sw.bb.i
store i32 7, ptr %phase, align 8
store i32 %l2, ptr %arrayidx307, align 4
%call16.i = call fastcc i32 @ValidMove(i32 %l2)
%tobool17.i = icmp eq i32 %call16.i, 0
br i1 %tobool17.i, label %if.else.i65, label %cleanup
if.else.i65:
call void @f65()
br label %sw.bb21.i
sw.bb21.i:
store i32 10, ptr %phase, align 8
%l3= load i32, ptr %arrayidx185, align 4
%tobool27.i = icmp eq i32 %l3, 0
br i1 %tobool27.i, label %do.body.preheader.i67, label %cleanup
do.body.preheader.i67:
call void @f67()
ret i32 67
cleanup:
call void @Cleanup()
ret i32 0
}
declare fastcc ptr @GenerateCheckEvasions()
declare fastcc i32 @ValidMove(i32 %move)
declare void @f67()
declare void @Cleanup()
declare void @f65()
define i32 @fn_SinglePred(i1 %c2,ptr %P) {
; CHECK-LABEL: @fn_SinglePred(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[L1:%.*]] = load i64, ptr [[P:%.*]], align 4
; CHECK-NEXT: [[C:%.*]] = icmp eq i64 [[L1]], 0
; CHECK-NEXT: br i1 [[C]], label [[COND3:%.*]], label [[COND1:%.*]]
; CHECK: cond1:
; CHECK-NEXT: br i1 [[C2:%.*]], label [[COND2:%.*]], label [[END:%.*]]
; CHECK: cond2:
; CHECK-NEXT: [[L2:%.*]] = phi i64 [ [[L1]], [[COND1]] ]
; CHECK-NEXT: call void @fn2(i64 [[L2]])
; CHECK-NEXT: br label [[END]]
; CHECK: cond3:
; CHECK-NEXT: call void @fn2(i64 [[L1]])
; CHECK-NEXT: call void @fn3(i64 [[L1]])
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret i32 0
;
entry:
%l1 = load i64, ptr %P
%c = icmp eq i64 %l1, 0
br i1 %c, label %cond2, label %cond1
cond1:
br i1 %c2, label %cond2, label %end
cond2:
%l2 = load i64, ptr %P
call void @fn2(i64 %l2)
%c3 = icmp eq i64 %l2, 0
br i1 %c3, label %cond3, label %end
cond3:
call void @fn3(i64 %l2)
br label %end
end:
ret i32 0
}
define i32 @fn_SinglePredMultihop(i1 %c1, i1 %c2,ptr %P) {
; CHECK-LABEL: @fn_SinglePredMultihop(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[L1:%.*]] = load i64, ptr [[P:%.*]], align 4
; CHECK-NEXT: [[C0:%.*]] = icmp eq i64 [[L1]], 0
; CHECK-NEXT: br i1 [[C0]], label [[COND3:%.*]], label [[COND0:%.*]]
; CHECK: cond0:
; CHECK-NEXT: br i1 [[C1:%.*]], label [[COND1:%.*]], label [[END:%.*]]
; CHECK: cond1:
; CHECK-NEXT: br i1 [[C2:%.*]], label [[COND2:%.*]], label [[END]]
; CHECK: cond2:
; CHECK-NEXT: [[L2:%.*]] = phi i64 [ [[L1]], [[COND1]] ]
; CHECK-NEXT: call void @fn2(i64 [[L2]])
; CHECK-NEXT: br label [[END]]
; CHECK: cond3:
; CHECK-NEXT: call void @fn2(i64 [[L1]])
; CHECK-NEXT: call void @fn3(i64 [[L1]])
; CHECK-NEXT: br label [[END]]
; CHECK: end:
; CHECK-NEXT: ret i32 0
;
entry:
%l1 = load i64, ptr %P
%c0 = icmp eq i64 %l1, 0
br i1 %c0, label %cond2, label %cond0
cond0:
br i1 %c1, label %cond1, label %end
cond1:
br i1 %c2, label %cond2, label %end
cond2:
%l2 = load i64, ptr %P
call void @fn2(i64 %l2)
%c3 = icmp eq i64 %l2, 0
br i1 %c3, label %cond3, label %end
cond3:
call void @fn3(i64 %l2)
br label %end
end:
ret i32 0
}
declare void @fn2(i64)
declare void @fn3(i64)
; Make sure we phi-translate and make the partially redundant load in
; merge fully redudant and then we can jump-thread the block with the
; store.
;
define i32 @phi_translate_partial_redundant_loads(i32, ptr, ptr) {
; CHECK-LABEL: @phi_translate_partial_redundant_loads(
; CHECK-NEXT: [[CMP0:%.*]] = icmp ne i32 [[TMP0:%.*]], 0
; CHECK-NEXT: br i1 [[CMP0]], label [[MERGE_THREAD:%.*]], label [[MERGE:%.*]]
; CHECK: merge.thread:
; CHECK-NEXT: store i32 1, ptr [[TMP1:%.*]], align 4
; CHECK-NEXT: br label [[LEFT_X:%.*]]
; CHECK: merge:
; CHECK-NEXT: [[NEWLOAD_PR:%.*]] = load i32, ptr [[TMP2:%.*]], align 4
; CHECK-NEXT: [[CMP1:%.*]] = icmp slt i32 [[NEWLOAD_PR]], 5
; CHECK-NEXT: br i1 [[CMP1]], label [[LEFT_X]], label [[RIGHT_X:%.*]]
; CHECK: left_x:
; CHECK-NEXT: ret i32 20
; CHECK: right_x:
; CHECK-NEXT: ret i32 10
;
%cmp0 = icmp ne i32 %0, 0
br i1 %cmp0, label %left, label %right
left:
store i32 1, ptr %1, align 4
br label %merge
right:
br label %merge
merge:
%phiptr = phi ptr [ %1, %left ], [ %2, %right ]
%newload = load i32, ptr %phiptr, align 4
%cmp1 = icmp slt i32 %newload, 5
br i1 %cmp1, label %left_x, label %right_x
left_x:
ret i32 20
right_x:
ret i32 10
}
; CHECK: [[RNG4]] = !{i32 0, i32 1}
!0 = !{!3, !3, i64 0}
!1 = !{!"omnipotent char", !2}
!2 = !{!"Simple C/C++ TBAA"}
!3 = !{!"int", !1}
!4 = !{ i32 0, i32 1 }
!5 = !{ i32 8, i32 10 }
!6 = !{!6}
!7 = !{!7, !6}
!8 = !{!8, !6}
!9 = !{!7}
!10 = !{!8}
!11 = !{}
|
