/
basictest.ll
2262 lines (2018 loc) · 110 KB
/
basictest.ll
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
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=sroa -S | FileCheck %s
target datalayout = "e-p:64:64:64-p1:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64"
declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture)
declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture)
define i32 @test0() {
; CHECK-LABEL: @test0(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V2_INT:%.*]] = bitcast float 0.000000e+00 to i32
; CHECK-NEXT: [[SUM1:%.*]] = add i32 0, [[V2_INT]]
; CHECK-NEXT: ret i32 [[SUM1]]
;
entry:
%a1 = alloca i32
%a2 = alloca float
%a1.i8 = bitcast i32* %a1 to i8*
call void @llvm.lifetime.start.p0i8(i64 4, i8* %a1.i8)
store i32 0, i32* %a1
%v1 = load i32, i32* %a1
call void @llvm.lifetime.end.p0i8(i64 4, i8* %a1.i8)
%a2.i8 = bitcast float* %a2 to i8*
call void @llvm.lifetime.start.p0i8(i64 4, i8* %a2.i8)
store float 0.0, float* %a2
%v2 = load float , float * %a2
%v2.int = bitcast float %v2 to i32
%sum1 = add i32 %v1, %v2.int
call void @llvm.lifetime.end.p0i8(i64 4, i8* %a2.i8)
ret i32 %sum1
}
define i32 @test1() {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: ret i32 0
;
entry:
%X = alloca { i32, float }
%Y = getelementptr { i32, float }, { i32, float }* %X, i64 0, i32 0
store i32 0, i32* %Y
%Z = load i32, i32* %Y
ret i32 %Z
}
define i64 @test2(i64 %X) {
; CHECK-LABEL: @test2(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[L2:%.*]]
; CHECK: L2:
; CHECK-NEXT: ret i64 [[X:%.*]]
;
entry:
%A = alloca [8 x i8]
%B = bitcast [8 x i8]* %A to i64*
store i64 %X, i64* %B
br label %L2
L2:
%Z = load i64, i64* %B
ret i64 %Z
}
define i64 @test2_addrspacecast(i64 %X) {
; CHECK-LABEL: @test2_addrspacecast(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[L2:%.*]]
; CHECK: L2:
; CHECK-NEXT: ret i64 [[X:%.*]]
;
entry:
%A = alloca [8 x i8]
%B = addrspacecast [8 x i8]* %A to i64 addrspace(1)*
store i64 %X, i64 addrspace(1)* %B
br label %L2
L2:
%Z = load i64, i64 addrspace(1)* %B
ret i64 %Z
}
define i64 @test2_addrspacecast_gep(i64 %X, i16 %idx) {
; CHECK-LABEL: @test2_addrspacecast_gep(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[L2:%.*]]
; CHECK: L2:
; CHECK-NEXT: ret i64 [[X:%.*]]
;
entry:
%A = alloca [256 x i8]
%B = addrspacecast [256 x i8]* %A to i64 addrspace(1)*
%gepA = getelementptr [256 x i8], [256 x i8]* %A, i16 0, i16 32
%gepB = getelementptr i64, i64 addrspace(1)* %B, i16 4
store i64 %X, i64 addrspace(1)* %gepB, align 1
br label %L2
L2:
%gepA.bc = bitcast i8* %gepA to i64*
%Z = load i64, i64* %gepA.bc, align 1
ret i64 %Z
}
; Avoid crashing when load/storing at at different offsets.
define i64 @test2_addrspacecast_gep_offset(i64 %X) {
; CHECK-LABEL: @test2_addrspacecast_gep_offset(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_0:%.*]] = alloca [10 x i8], align 1
; CHECK-NEXT: [[A_SROA_0_2_GEPB_SROA_IDX:%.*]] = getelementptr inbounds [10 x i8], [10 x i8]* [[A_SROA_0]], i16 0, i16 2
; CHECK-NEXT: [[A_SROA_0_2_GEPB_SROA_CAST:%.*]] = addrspacecast i8* [[A_SROA_0_2_GEPB_SROA_IDX]] to i64 addrspace(1)*
; CHECK-NEXT: store i64 [[X:%.*]], i64 addrspace(1)* [[A_SROA_0_2_GEPB_SROA_CAST]], align 1
; CHECK-NEXT: br label [[L2:%.*]]
; CHECK: L2:
; CHECK-NEXT: [[A_SROA_0_0_GEPA_BC_SROA_CAST:%.*]] = bitcast [10 x i8]* [[A_SROA_0]] to i64*
; CHECK-NEXT: [[A_SROA_0_0_A_SROA_0_30_Z:%.*]] = load i64, i64* [[A_SROA_0_0_GEPA_BC_SROA_CAST]], align 1
; CHECK-NEXT: ret i64 [[A_SROA_0_0_A_SROA_0_30_Z]]
;
entry:
%A = alloca [256 x i8]
%B = addrspacecast [256 x i8]* %A to i64 addrspace(1)*
%gepA = getelementptr [256 x i8], [256 x i8]* %A, i16 0, i16 30
%gepB = getelementptr i64, i64 addrspace(1)* %B, i16 4
store i64 %X, i64 addrspace(1)* %gepB, align 1
br label %L2
L2:
%gepA.bc = bitcast i8* %gepA to i64*
%Z = load i64, i64* %gepA.bc, align 1
ret i64 %Z
}
define void @test3(i8* %dst, i8* align 8 %src) {
; CHECK-LABEL: @test3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_0:%.*]] = alloca [42 x i8], align 1
; CHECK-NEXT: [[A_SROA_3:%.*]] = alloca [99 x i8], align 1
; CHECK-NEXT: [[A_SROA_34:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[A_SROA_15:%.*]] = alloca [42 x i8], align 1
; CHECK-NEXT: [[A_SROA_16:%.*]] = alloca [7 x i8], align 1
; CHECK-NEXT: [[A_SROA_239:%.*]] = alloca [7 x i8], align 1
; CHECK-NEXT: [[A_SROA_31:%.*]] = alloca [85 x i8], align 1
; CHECK-NEXT: [[A_SROA_0_0_B_SROA_IDX:%.*]] = getelementptr inbounds [42 x i8], [42 x i8]* [[A_SROA_0]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_0_0_B_SROA_IDX]], i8* align 8 [[SRC:%.*]], i32 42, i1 false), !tbaa [[TBAA0:![0-9]+]]
; CHECK-NEXT: [[A_SROA_2_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 42
; CHECK-NEXT: [[A_SROA_2_0_COPYLOAD:%.*]] = load i8, i8* [[A_SROA_2_0_SRC_SROA_RAW_IDX]], align 2, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_3_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 43
; CHECK-NEXT: [[A_SROA_3_0_B_SROA_IDX:%.*]] = getelementptr inbounds [99 x i8], [99 x i8]* [[A_SROA_3]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_3_0_B_SROA_IDX]], i8* align 1 [[A_SROA_3_0_SRC_SROA_RAW_IDX]], i32 99, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_34_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 142
; CHECK-NEXT: [[A_SROA_34_0_B_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_34_0_B_SROA_IDX]], i8* align 2 [[A_SROA_34_0_SRC_SROA_RAW_IDX]], i32 16, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_15_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 158
; CHECK-NEXT: [[A_SROA_15_0_B_SROA_IDX:%.*]] = getelementptr inbounds [42 x i8], [42 x i8]* [[A_SROA_15]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_15_0_B_SROA_IDX]], i8* align 2 [[A_SROA_15_0_SRC_SROA_RAW_IDX]], i32 42, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_16_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 200
; CHECK-NEXT: [[A_SROA_16_0_B_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_16_0_B_SROA_IDX]], i8* align 8 [[A_SROA_16_0_SRC_SROA_RAW_IDX]], i32 7, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_23_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 207
; CHECK-NEXT: [[A_SROA_23_0_COPYLOAD:%.*]] = load i8, i8* [[A_SROA_23_0_SRC_SROA_RAW_IDX]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_239_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 208
; CHECK-NEXT: [[A_SROA_239_0_B_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_239_0_B_SROA_IDX]], i8* align 8 [[A_SROA_239_0_SRC_SROA_RAW_IDX]], i32 7, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_31_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 215
; CHECK-NEXT: [[A_SROA_31_0_B_SROA_IDX:%.*]] = getelementptr inbounds [85 x i8], [85 x i8]* [[A_SROA_31]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_31_0_B_SROA_IDX]], i8* align 1 [[A_SROA_31_0_SRC_SROA_RAW_IDX]], i32 85, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_34_0_OVERLAP_1_I8_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 0
; CHECK-NEXT: store i8 1, i8* [[A_SROA_34_0_OVERLAP_1_I8_SROA_IDX]], align 1, !tbaa [[TBAA3:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_0_OVERLAP_1_I16_SROA_CAST:%.*]] = bitcast [16 x i8]* [[A_SROA_34]] to i16*
; CHECK-NEXT: store i16 1, i16* [[A_SROA_34_0_OVERLAP_1_I16_SROA_CAST]], align 1, !tbaa [[TBAA5:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_0_OVERLAP_1_I32_SROA_CAST:%.*]] = bitcast [16 x i8]* [[A_SROA_34]] to i32*
; CHECK-NEXT: store i32 1, i32* [[A_SROA_34_0_OVERLAP_1_I32_SROA_CAST]], align 1, !tbaa [[TBAA7:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_0_OVERLAP_1_I64_SROA_CAST:%.*]] = bitcast [16 x i8]* [[A_SROA_34]] to i64*
; CHECK-NEXT: store i64 1, i64* [[A_SROA_34_0_OVERLAP_1_I64_SROA_CAST]], align 1, !tbaa [[TBAA9:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_1_OVERLAP_2_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 1
; CHECK-NEXT: [[A_SROA_34_1_OVERLAP_2_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_1_OVERLAP_2_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 2, i64* [[A_SROA_34_1_OVERLAP_2_I64_SROA_CAST]], align 1, !tbaa [[TBAA11:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_2_OVERLAP_3_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 2
; CHECK-NEXT: [[A_SROA_34_2_OVERLAP_3_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_2_OVERLAP_3_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 3, i64* [[A_SROA_34_2_OVERLAP_3_I64_SROA_CAST]], align 1, !tbaa [[TBAA13:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_3_OVERLAP_4_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 3
; CHECK-NEXT: [[A_SROA_34_3_OVERLAP_4_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_3_OVERLAP_4_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 4, i64* [[A_SROA_34_3_OVERLAP_4_I64_SROA_CAST]], align 1, !tbaa [[TBAA15:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_4_OVERLAP_5_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 4
; CHECK-NEXT: [[A_SROA_34_4_OVERLAP_5_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_4_OVERLAP_5_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 5, i64* [[A_SROA_34_4_OVERLAP_5_I64_SROA_CAST]], align 1, !tbaa [[TBAA17:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_5_OVERLAP_6_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 5
; CHECK-NEXT: [[A_SROA_34_5_OVERLAP_6_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_5_OVERLAP_6_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 6, i64* [[A_SROA_34_5_OVERLAP_6_I64_SROA_CAST]], align 1, !tbaa [[TBAA19:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_6_OVERLAP_7_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 6
; CHECK-NEXT: [[A_SROA_34_6_OVERLAP_7_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_6_OVERLAP_7_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 7, i64* [[A_SROA_34_6_OVERLAP_7_I64_SROA_CAST]], align 1, !tbaa [[TBAA21:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_7_OVERLAP_8_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 7
; CHECK-NEXT: [[A_SROA_34_7_OVERLAP_8_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_7_OVERLAP_8_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 8, i64* [[A_SROA_34_7_OVERLAP_8_I64_SROA_CAST]], align 1, !tbaa [[TBAA23:![0-9]+]]
; CHECK-NEXT: [[A_SROA_34_8_OVERLAP_9_I64_SROA_IDX:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 8
; CHECK-NEXT: [[A_SROA_34_8_OVERLAP_9_I64_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_8_OVERLAP_9_I64_SROA_IDX]] to i64*
; CHECK-NEXT: store i64 9, i64* [[A_SROA_34_8_OVERLAP_9_I64_SROA_CAST]], align 1, !tbaa [[TBAA25:![0-9]+]]
; CHECK-NEXT: [[A_SROA_16_0_OVERLAP2_1_0_I8_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 0
; CHECK-NEXT: store i8 1, i8* [[A_SROA_16_0_OVERLAP2_1_0_I8_SROA_IDX]], align 1, !tbaa [[TBAA27:![0-9]+]]
; CHECK-NEXT: [[A_SROA_16_0_OVERLAP2_1_0_I16_SROA_CAST:%.*]] = bitcast [7 x i8]* [[A_SROA_16]] to i16*
; CHECK-NEXT: store i16 1, i16* [[A_SROA_16_0_OVERLAP2_1_0_I16_SROA_CAST]], align 1, !tbaa [[TBAA29:![0-9]+]]
; CHECK-NEXT: [[A_SROA_16_0_OVERLAP2_1_0_I32_SROA_CAST:%.*]] = bitcast [7 x i8]* [[A_SROA_16]] to i32*
; CHECK-NEXT: store i32 1, i32* [[A_SROA_16_0_OVERLAP2_1_0_I32_SROA_CAST]], align 1, !tbaa [[TBAA31:![0-9]+]]
; CHECK-NEXT: [[A_SROA_16_1_OVERLAP2_1_1_I32_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 1
; CHECK-NEXT: [[A_SROA_16_1_OVERLAP2_1_1_I32_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_16_1_OVERLAP2_1_1_I32_SROA_IDX]] to i32*
; CHECK-NEXT: store i32 2, i32* [[A_SROA_16_1_OVERLAP2_1_1_I32_SROA_CAST]], align 1, !tbaa [[TBAA33:![0-9]+]]
; CHECK-NEXT: [[A_SROA_16_2_OVERLAP2_1_2_I32_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 2
; CHECK-NEXT: [[A_SROA_16_2_OVERLAP2_1_2_I32_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_16_2_OVERLAP2_1_2_I32_SROA_IDX]] to i32*
; CHECK-NEXT: store i32 3, i32* [[A_SROA_16_2_OVERLAP2_1_2_I32_SROA_CAST]], align 1, !tbaa [[TBAA35:![0-9]+]]
; CHECK-NEXT: [[A_SROA_16_3_OVERLAP2_1_3_I32_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 3
; CHECK-NEXT: [[A_SROA_16_3_OVERLAP2_1_3_I32_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_16_3_OVERLAP2_1_3_I32_SROA_IDX]] to i32*
; CHECK-NEXT: store i32 4, i32* [[A_SROA_16_3_OVERLAP2_1_3_I32_SROA_CAST]], align 1, !tbaa [[TBAA37:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_0_OVERLAP2_2_0_I32_SROA_CAST:%.*]] = bitcast [7 x i8]* [[A_SROA_239]] to i32*
; CHECK-NEXT: store i32 1, i32* [[A_SROA_239_0_OVERLAP2_2_0_I32_SROA_CAST]], align 1, !tbaa [[TBAA39:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_1_OVERLAP2_2_1_I8_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 1
; CHECK-NEXT: store i8 1, i8* [[A_SROA_239_1_OVERLAP2_2_1_I8_SROA_IDX]], align 1, !tbaa [[TBAA41:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_1_OVERLAP2_2_1_I16_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 1
; CHECK-NEXT: [[A_SROA_239_1_OVERLAP2_2_1_I16_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_239_1_OVERLAP2_2_1_I16_SROA_IDX]] to i16*
; CHECK-NEXT: store i16 1, i16* [[A_SROA_239_1_OVERLAP2_2_1_I16_SROA_CAST]], align 1, !tbaa [[TBAA43:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_1_OVERLAP2_2_1_I32_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 1
; CHECK-NEXT: [[A_SROA_239_1_OVERLAP2_2_1_I32_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_239_1_OVERLAP2_2_1_I32_SROA_IDX]] to i32*
; CHECK-NEXT: store i32 1, i32* [[A_SROA_239_1_OVERLAP2_2_1_I32_SROA_CAST]], align 1, !tbaa [[TBAA45:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_2_OVERLAP2_2_2_I32_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 2
; CHECK-NEXT: [[A_SROA_239_2_OVERLAP2_2_2_I32_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_239_2_OVERLAP2_2_2_I32_SROA_IDX]] to i32*
; CHECK-NEXT: store i32 3, i32* [[A_SROA_239_2_OVERLAP2_2_2_I32_SROA_CAST]], align 1, !tbaa [[TBAA47:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_3_OVERLAP2_2_3_I32_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 3
; CHECK-NEXT: [[A_SROA_239_3_OVERLAP2_2_3_I32_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_239_3_OVERLAP2_2_3_I32_SROA_IDX]] to i32*
; CHECK-NEXT: store i32 4, i32* [[A_SROA_239_3_OVERLAP2_2_3_I32_SROA_CAST]], align 1, !tbaa [[TBAA49:![0-9]+]]
; CHECK-NEXT: [[A_SROA_15_197_OVERLAP2_PREFIX_SROA_IDX:%.*]] = getelementptr inbounds [42 x i8], [42 x i8]* [[A_SROA_15]], i64 0, i64 39
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_15_197_OVERLAP2_PREFIX_SROA_IDX]], i8* align 1 [[SRC]], i32 3, i1 false), !tbaa [[TBAA51:![0-9]+]]
; CHECK-NEXT: [[A_SROA_16_197_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 3
; CHECK-NEXT: [[A_SROA_16_197_OVERLAP2_PREFIX_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_16_197_OVERLAP2_PREFIX_SROA_IDX]], i8* align 1 [[A_SROA_16_197_SRC_SROA_RAW_IDX]], i32 5, i1 false), !tbaa [[TBAA51]]
; CHECK-NEXT: [[A_SROA_16_2_OVERLAP2_1_2_I8_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 2
; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 [[A_SROA_16_2_OVERLAP2_1_2_I8_SROA_IDX]], i8 42, i32 5, i1 false), !tbaa [[TBAA53:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_0_OVERLAP2_1_2_I8_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 [[A_SROA_239_0_OVERLAP2_1_2_I8_SROA_IDX]], i8 42, i32 2, i1 false), !tbaa [[TBAA53]]
; CHECK-NEXT: [[A_SROA_239_209_OVERLAP2_2_1_I8_SROA_IDX11:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 1
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_239_209_OVERLAP2_2_1_I8_SROA_IDX11]], i8* align 1 [[SRC]], i32 5, i1 false), !tbaa [[TBAA55:![0-9]+]]
; CHECK-NEXT: [[A_SROA_239_210_OVERLAP2_2_2_I8_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 2
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_239_210_OVERLAP2_2_2_I8_SROA_IDX]], i8* align 1 [[SRC]], i32 5, i1 false), !tbaa [[TBAA57:![0-9]+]]
; CHECK-NEXT: [[A_SROA_31_210_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 5
; CHECK-NEXT: [[A_SROA_31_210_OVERLAP2_2_2_I8_SROA_IDX:%.*]] = getelementptr inbounds [85 x i8], [85 x i8]* [[A_SROA_31]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_31_210_OVERLAP2_2_2_I8_SROA_IDX]], i8* align 1 [[A_SROA_31_210_SRC_SROA_RAW_IDX]], i32 3, i1 false), !tbaa [[TBAA57]]
; CHECK-NEXT: [[A_SROA_0_0_B_SROA_IDX1:%.*]] = getelementptr inbounds [42 x i8], [42 x i8]* [[A_SROA_0]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[DST:%.*]], i8* align 1 [[A_SROA_0_0_B_SROA_IDX1]], i32 42, i1 false), !tbaa [[TBAA59:![0-9]+]]
; CHECK-NEXT: [[A_SROA_2_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 42
; CHECK-NEXT: store i8 0, i8* [[A_SROA_2_0_DST_SROA_RAW_IDX]], align 1, !tbaa [[TBAA59]]
; CHECK-NEXT: [[A_SROA_3_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 43
; CHECK-NEXT: [[A_SROA_3_0_B_SROA_IDX3:%.*]] = getelementptr inbounds [99 x i8], [99 x i8]* [[A_SROA_3]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_3_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_3_0_B_SROA_IDX3]], i32 99, i1 false), !tbaa [[TBAA59]]
; CHECK-NEXT: [[A_SROA_34_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 142
; CHECK-NEXT: [[A_SROA_34_0_B_SROA_IDX5:%.*]] = getelementptr inbounds [16 x i8], [16 x i8]* [[A_SROA_34]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_34_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_34_0_B_SROA_IDX5]], i32 16, i1 false), !tbaa [[TBAA59]]
; CHECK-NEXT: [[A_SROA_15_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 158
; CHECK-NEXT: [[A_SROA_15_0_B_SROA_IDX6:%.*]] = getelementptr inbounds [42 x i8], [42 x i8]* [[A_SROA_15]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_15_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_15_0_B_SROA_IDX6]], i32 42, i1 false), !tbaa [[TBAA59]]
; CHECK-NEXT: [[A_SROA_16_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 200
; CHECK-NEXT: [[A_SROA_16_0_B_SROA_IDX7:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_16]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_16_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_16_0_B_SROA_IDX7]], i32 7, i1 false), !tbaa [[TBAA59]]
; CHECK-NEXT: [[A_SROA_23_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 207
; CHECK-NEXT: store i8 42, i8* [[A_SROA_23_0_DST_SROA_RAW_IDX]], align 1, !tbaa [[TBAA59]]
; CHECK-NEXT: [[A_SROA_239_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 208
; CHECK-NEXT: [[A_SROA_239_0_B_SROA_IDX10:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_239]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_239_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_239_0_B_SROA_IDX10]], i32 7, i1 false), !tbaa [[TBAA59]]
; CHECK-NEXT: [[A_SROA_31_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 215
; CHECK-NEXT: [[A_SROA_31_0_B_SROA_IDX12:%.*]] = getelementptr inbounds [85 x i8], [85 x i8]* [[A_SROA_31]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_31_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_31_0_B_SROA_IDX12]], i32 85, i1 false), !tbaa [[TBAA59]]
; CHECK-NEXT: ret void
;
entry:
%a = alloca [300 x i8]
%b = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* align 8 %src, i32 300, i1 false), !tbaa !0
; Clobber a single element of the array, this should be promotable, and be deleted.
%c = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 42
store i8 0, i8* %c
; Make a sequence of overlapping stores to the array. These overlap both in
; forward strides and in shrinking accesses.
%overlap.1.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 142
%overlap.2.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 143
%overlap.3.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 144
%overlap.4.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 145
%overlap.5.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 146
%overlap.6.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 147
%overlap.7.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 148
%overlap.8.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 149
%overlap.9.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 150
%overlap.1.i16 = bitcast i8* %overlap.1.i8 to i16*
%overlap.1.i32 = bitcast i8* %overlap.1.i8 to i32*
%overlap.1.i64 = bitcast i8* %overlap.1.i8 to i64*
%overlap.2.i64 = bitcast i8* %overlap.2.i8 to i64*
%overlap.3.i64 = bitcast i8* %overlap.3.i8 to i64*
%overlap.4.i64 = bitcast i8* %overlap.4.i8 to i64*
%overlap.5.i64 = bitcast i8* %overlap.5.i8 to i64*
%overlap.6.i64 = bitcast i8* %overlap.6.i8 to i64*
%overlap.7.i64 = bitcast i8* %overlap.7.i8 to i64*
%overlap.8.i64 = bitcast i8* %overlap.8.i8 to i64*
%overlap.9.i64 = bitcast i8* %overlap.9.i8 to i64*
store i8 1, i8* %overlap.1.i8, !tbaa !3
store i16 1, i16* %overlap.1.i16, !tbaa !5
store i32 1, i32* %overlap.1.i32, !tbaa !7
store i64 1, i64* %overlap.1.i64, !tbaa !9
store i64 2, i64* %overlap.2.i64, !tbaa !11
store i64 3, i64* %overlap.3.i64, !tbaa !13
store i64 4, i64* %overlap.4.i64, !tbaa !15
store i64 5, i64* %overlap.5.i64, !tbaa !17
store i64 6, i64* %overlap.6.i64, !tbaa !19
store i64 7, i64* %overlap.7.i64, !tbaa !21
store i64 8, i64* %overlap.8.i64, !tbaa !23
store i64 9, i64* %overlap.9.i64, !tbaa !25
; Make two sequences of overlapping stores with more gaps and irregularities.
%overlap2.1.0.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 200
%overlap2.1.1.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 201
%overlap2.1.2.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 202
%overlap2.1.3.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 203
%overlap2.2.0.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 208
%overlap2.2.1.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 209
%overlap2.2.2.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 210
%overlap2.2.3.i8 = getelementptr [300 x i8], [300 x i8]* %a, i64 0, i64 211
%overlap2.1.0.i16 = bitcast i8* %overlap2.1.0.i8 to i16*
%overlap2.1.0.i32 = bitcast i8* %overlap2.1.0.i8 to i32*
%overlap2.1.1.i32 = bitcast i8* %overlap2.1.1.i8 to i32*
%overlap2.1.2.i32 = bitcast i8* %overlap2.1.2.i8 to i32*
%overlap2.1.3.i32 = bitcast i8* %overlap2.1.3.i8 to i32*
store i8 1, i8* %overlap2.1.0.i8, !tbaa !27
store i16 1, i16* %overlap2.1.0.i16, !tbaa !29
store i32 1, i32* %overlap2.1.0.i32, !tbaa !31
store i32 2, i32* %overlap2.1.1.i32, !tbaa !33
store i32 3, i32* %overlap2.1.2.i32, !tbaa !35
store i32 4, i32* %overlap2.1.3.i32, !tbaa !37
%overlap2.2.0.i32 = bitcast i8* %overlap2.2.0.i8 to i32*
%overlap2.2.1.i16 = bitcast i8* %overlap2.2.1.i8 to i16*
%overlap2.2.1.i32 = bitcast i8* %overlap2.2.1.i8 to i32*
%overlap2.2.2.i32 = bitcast i8* %overlap2.2.2.i8 to i32*
%overlap2.2.3.i32 = bitcast i8* %overlap2.2.3.i8 to i32*
store i32 1, i32* %overlap2.2.0.i32, !tbaa !39
store i8 1, i8* %overlap2.2.1.i8, !tbaa !41
store i16 1, i16* %overlap2.2.1.i16, !tbaa !43
store i32 1, i32* %overlap2.2.1.i32, !tbaa !45
store i32 3, i32* %overlap2.2.2.i32, !tbaa !47
store i32 4, i32* %overlap2.2.3.i32, !tbaa !49
%overlap2.prefix = getelementptr i8, i8* %overlap2.1.1.i8, i64 -4
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.prefix, i8* %src, i32 8, i1 false), !tbaa !51
; Bridge between the overlapping areas
call void @llvm.memset.p0i8.i32(i8* %overlap2.1.2.i8, i8 42, i32 8, i1 false), !tbaa !53
; ...promoted i8 store...
; Entirely within the second overlap.
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.1.i8, i8* %src, i32 5, i1 false), !tbaa !55
; Trailing past the second overlap.
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %overlap2.2.2.i8, i8* %src, i32 8, i1 false), !tbaa !57
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 300, i1 false), !tbaa !59
ret void
}
define void @test4(i8* %dst, i8* %src) {
; CHECK-LABEL: @test4(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_0:%.*]] = alloca [20 x i8], align 1
; CHECK-NEXT: [[A_SROA_2_SROA_4:%.*]] = alloca [7 x i8], align 1
; CHECK-NEXT: [[A_SROA_3:%.*]] = alloca [10 x i8], align 1
; CHECK-NEXT: [[A_SROA_34_SROA_5:%.*]] = alloca [7 x i8], align 1
; CHECK-NEXT: [[A_SROA_6_SROA_4:%.*]] = alloca [7 x i8], align 1
; CHECK-NEXT: [[A_SROA_7:%.*]] = alloca [40 x i8], align 1
; CHECK-NEXT: [[A_SROA_0_0_B_SROA_IDX:%.*]] = getelementptr inbounds [20 x i8], [20 x i8]* [[A_SROA_0]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_0_0_B_SROA_IDX]], i8* align 1 [[SRC:%.*]], i32 20, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_2_SROA_0_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 20
; CHECK-NEXT: [[A_SROA_2_SROA_0_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_2_SROA_0_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_IDX]] to i16*
; CHECK-NEXT: [[A_SROA_2_SROA_0_0_COPYLOAD:%.*]] = load i16, i16* [[A_SROA_2_SROA_0_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_CAST]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_2_SROA_3_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 22
; CHECK-NEXT: [[A_SROA_2_SROA_3_0_COPYLOAD:%.*]] = load i8, i8* [[A_SROA_2_SROA_3_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_2_SROA_4_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 23
; CHECK-NEXT: [[A_SROA_2_SROA_4_0_B_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_2_SROA_4]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_2_SROA_4_0_B_SROA_IDX]], i8* align 1 [[A_SROA_2_SROA_4_0_A_SROA_2_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX]], i32 7, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_3_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 30
; CHECK-NEXT: [[A_SROA_3_0_B_SROA_IDX:%.*]] = getelementptr inbounds [10 x i8], [10 x i8]* [[A_SROA_3]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_3_0_B_SROA_IDX]], i8* align 1 [[A_SROA_3_0_SRC_SROA_RAW_IDX]], i32 10, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_34_SROA_0_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 40
; CHECK-NEXT: [[A_SROA_34_SROA_0_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_SROA_0_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_IDX]] to i16*
; CHECK-NEXT: [[A_SROA_34_SROA_0_0_COPYLOAD:%.*]] = load i16, i16* [[A_SROA_34_SROA_0_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_CAST]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_34_SROA_4_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 42
; CHECK-NEXT: [[A_SROA_34_SROA_4_0_COPYLOAD:%.*]] = load i8, i8* [[A_SROA_34_SROA_4_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_34_SROA_5_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 43
; CHECK-NEXT: [[A_SROA_34_SROA_5_0_B_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_34_SROA_5]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_34_SROA_5_0_B_SROA_IDX]], i8* align 1 [[A_SROA_34_SROA_5_0_A_SROA_34_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX]], i32 7, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_6_SROA_0_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 50
; CHECK-NEXT: [[A_SROA_6_SROA_0_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_6_SROA_0_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_IDX]] to i16*
; CHECK-NEXT: [[A_SROA_6_SROA_0_0_COPYLOAD:%.*]] = load i16, i16* [[A_SROA_6_SROA_0_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_CAST]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_6_SROA_3_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 52
; CHECK-NEXT: [[A_SROA_6_SROA_3_0_COPYLOAD:%.*]] = load i8, i8* [[A_SROA_6_SROA_3_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_6_SROA_4_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 53
; CHECK-NEXT: [[A_SROA_6_SROA_4_0_B_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_6_SROA_4]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_6_SROA_4_0_B_SROA_IDX]], i8* align 1 [[A_SROA_6_SROA_4_0_A_SROA_6_0_SRC_SROA_RAW_IDX_SROA_RAW_IDX]], i32 7, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_7_0_SRC_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 60
; CHECK-NEXT: [[A_SROA_7_0_B_SROA_IDX:%.*]] = getelementptr inbounds [40 x i8], [40 x i8]* [[A_SROA_7]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_7_0_B_SROA_IDX]], i8* align 1 [[A_SROA_7_0_SRC_SROA_RAW_IDX]], i32 40, i1 false), !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_2_SROA_4_3_A_SROA_34_SROA_5_0_A_DST_1_SROA_IDX_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_34_SROA_5]], i64 0, i64 0
; CHECK-NEXT: [[A_SROA_2_SROA_4_3_A_SRC_1_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_2_SROA_4]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_2_SROA_4_3_A_SROA_34_SROA_5_0_A_DST_1_SROA_IDX_SROA_IDX]], i8* align 1 [[A_SROA_2_SROA_4_3_A_SRC_1_SROA_IDX]], i32 7, i1 false), !tbaa [[TBAA3]]
; CHECK-NEXT: [[A_SROA_6_SROA_4_3_A_SROA_34_SROA_5_0_A_DST_1_SROA_IDX16_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_34_SROA_5]], i64 0, i64 0
; CHECK-NEXT: [[A_SROA_6_SROA_4_3_A_SRC_2_SROA_IDX:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_6_SROA_4]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_6_SROA_4_3_A_SROA_34_SROA_5_0_A_DST_1_SROA_IDX16_SROA_IDX]], i8* align 1 [[A_SROA_6_SROA_4_3_A_SRC_2_SROA_IDX]], i32 7, i1 false), !tbaa [[TBAA5]]
; CHECK-NEXT: [[A_SROA_0_0_B_SROA_IDX1:%.*]] = getelementptr inbounds [20 x i8], [20 x i8]* [[A_SROA_0]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[DST:%.*]], i8* align 1 [[A_SROA_0_0_B_SROA_IDX1]], i32 20, i1 false), !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_2_SROA_0_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 20
; CHECK-NEXT: [[A_SROA_2_SROA_0_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_2_SROA_0_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_IDX]] to i16*
; CHECK-NEXT: store i16 [[A_SROA_2_SROA_0_0_COPYLOAD]], i16* [[A_SROA_2_SROA_0_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_CAST]], align 1, !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_2_SROA_3_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 22
; CHECK-NEXT: store i8 [[A_SROA_2_SROA_3_0_COPYLOAD]], i8* [[A_SROA_2_SROA_3_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_RAW_IDX]], align 1, !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_2_SROA_4_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 23
; CHECK-NEXT: [[A_SROA_2_SROA_4_0_B_SROA_IDX22:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_2_SROA_4]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_2_SROA_4_0_A_SROA_2_0_DST_SROA_RAW_IDX_SROA_RAW_IDX]], i8* align 1 [[A_SROA_2_SROA_4_0_B_SROA_IDX22]], i32 7, i1 false), !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_3_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 30
; CHECK-NEXT: [[A_SROA_3_0_B_SROA_IDX3:%.*]] = getelementptr inbounds [10 x i8], [10 x i8]* [[A_SROA_3]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_3_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_3_0_B_SROA_IDX3]], i32 10, i1 false), !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_34_SROA_0_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 40
; CHECK-NEXT: [[A_SROA_34_SROA_0_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_34_SROA_0_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_IDX]] to i16*
; CHECK-NEXT: store i16 [[A_SROA_6_SROA_0_0_COPYLOAD]], i16* [[A_SROA_34_SROA_0_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_CAST]], align 1, !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_34_SROA_4_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 42
; CHECK-NEXT: store i8 [[A_SROA_6_SROA_3_0_COPYLOAD]], i8* [[A_SROA_34_SROA_4_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_RAW_IDX]], align 1, !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_34_SROA_5_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 43
; CHECK-NEXT: [[A_SROA_34_SROA_5_0_B_SROA_IDX15:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_34_SROA_5]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_34_SROA_5_0_A_SROA_34_0_DST_SROA_RAW_IDX_SROA_RAW_IDX]], i8* align 1 [[A_SROA_34_SROA_5_0_B_SROA_IDX15]], i32 7, i1 false), !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_6_SROA_0_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 50
; CHECK-NEXT: [[A_SROA_6_SROA_0_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_6_SROA_0_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_IDX]] to i16*
; CHECK-NEXT: store i16 [[A_SROA_6_SROA_0_0_COPYLOAD]], i16* [[A_SROA_6_SROA_0_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_CAST]], align 1, !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_6_SROA_3_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 52
; CHECK-NEXT: store i8 [[A_SROA_6_SROA_3_0_COPYLOAD]], i8* [[A_SROA_6_SROA_3_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_RAW_IDX]], align 1, !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_6_SROA_4_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 53
; CHECK-NEXT: [[A_SROA_6_SROA_4_0_B_SROA_IDX19:%.*]] = getelementptr inbounds [7 x i8], [7 x i8]* [[A_SROA_6_SROA_4]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_6_SROA_4_0_A_SROA_6_0_DST_SROA_RAW_IDX_SROA_RAW_IDX]], i8* align 1 [[A_SROA_6_SROA_4_0_B_SROA_IDX19]], i32 7, i1 false), !tbaa [[TBAA7]]
; CHECK-NEXT: [[A_SROA_7_0_DST_SROA_RAW_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 60
; CHECK-NEXT: [[A_SROA_7_0_B_SROA_IDX8:%.*]] = getelementptr inbounds [40 x i8], [40 x i8]* [[A_SROA_7]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_7_0_DST_SROA_RAW_IDX]], i8* align 1 [[A_SROA_7_0_B_SROA_IDX8]], i32 40, i1 false), !tbaa [[TBAA7]]
; CHECK-NEXT: ret void
;
entry:
%a = alloca [100 x i8]
%b = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %b, i8* %src, i32 100, i1 false), !tbaa !0
%a.src.1 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 20
%a.dst.1 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 40
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.1, i32 10, i1 false), !tbaa !3
; Clobber a single element of the array, this should be promotable, and be deleted.
%c = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 42
store i8 0, i8* %c
%a.src.2 = getelementptr [100 x i8], [100 x i8]* %a, i64 0, i64 50
call void @llvm.memmove.p0i8.p0i8.i32(i8* %a.dst.1, i8* %a.src.2, i32 10, i1 false), !tbaa !5
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %b, i32 100, i1 false), !tbaa !7
ret void
}
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
declare void @llvm.memcpy.p1i8.p0i8.i32(i8 addrspace(1)* nocapture, i8* nocapture, i32, i1) nounwind
declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind
define i16 @test5() {
; CHECK-LABEL: @test5(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float 0.000000e+00 to i32
; CHECK-NEXT: [[A_SROA_0_2_EXTRACT_SHIFT:%.*]] = lshr i32 [[TMP0]], 16
; CHECK-NEXT: [[A_SROA_0_2_EXTRACT_TRUNC:%.*]] = trunc i32 [[A_SROA_0_2_EXTRACT_SHIFT]] to i16
; CHECK-NEXT: ret i16 [[A_SROA_0_2_EXTRACT_TRUNC]]
;
entry:
%a = alloca [4 x i8]
%fptr = bitcast [4 x i8]* %a to float*
store float 0.0, float* %fptr
%ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 2
%iptr = bitcast i8* %ptr to i16*
%val = load i16, i16* %iptr
ret i16 %val
}
define i16 @test5_multi_addrspace_access() {
; CHECK-LABEL: @test5_multi_addrspace_access(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float 0.000000e+00 to i32
; CHECK-NEXT: [[A_SROA_0_2_EXTRACT_SHIFT:%.*]] = lshr i32 [[TMP0]], 16
; CHECK-NEXT: [[A_SROA_0_2_EXTRACT_TRUNC:%.*]] = trunc i32 [[A_SROA_0_2_EXTRACT_SHIFT]] to i16
; CHECK-NEXT: ret i16 [[A_SROA_0_2_EXTRACT_TRUNC]]
;
entry:
%a = alloca [4 x i8]
%fptr = bitcast [4 x i8]* %a to float*
%fptr.as1 = addrspacecast float* %fptr to float addrspace(1)*
store float 0.0, float addrspace(1)* %fptr.as1
%ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 2
%iptr = bitcast i8* %ptr to i16*
%val = load i16, i16* %iptr
ret i16 %val
}
define i32 @test6() {
; CHECK-LABEL: @test6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_0:%.*]] = alloca i32, align 4
; CHECK-NEXT: store volatile i32 707406378, i32* [[A_SROA_0]], align 4
; CHECK-NEXT: [[A_SROA_0_0_A_SROA_0_0_VAL:%.*]] = load i32, i32* [[A_SROA_0]], align 4
; CHECK-NEXT: ret i32 [[A_SROA_0_0_A_SROA_0_0_VAL]]
;
entry:
%a = alloca [4 x i8]
%ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 0
call void @llvm.memset.p0i8.i32(i8* %ptr, i8 42, i32 4, i1 true)
%iptr = bitcast i8* %ptr to i32*
%val = load i32, i32* %iptr
ret i32 %val
}
define void @test7(i8* %src, i8* %dst) {
; CHECK-LABEL: @test7(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_0:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[A_SROA_0_0_SRC_SROA_CAST:%.*]] = bitcast i8* [[SRC:%.*]] to i32*
; CHECK-NEXT: [[A_SROA_0_0_COPYLOAD:%.*]] = load volatile i32, i32* [[A_SROA_0_0_SRC_SROA_CAST]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: store volatile i32 [[A_SROA_0_0_COPYLOAD]], i32* [[A_SROA_0]], align 4, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_0_0_DST_SROA_CAST:%.*]] = bitcast i8* [[DST:%.*]] to i32*
; CHECK-NEXT: [[A_SROA_0_0_A_SROA_0_0_COPYLOAD1:%.*]] = load volatile i32, i32* [[A_SROA_0]], align 4, !tbaa [[TBAA3]]
; CHECK-NEXT: store volatile i32 [[A_SROA_0_0_A_SROA_0_0_COPYLOAD1]], i32* [[A_SROA_0_0_DST_SROA_CAST]], align 1, !tbaa [[TBAA3]]
; CHECK-NEXT: ret void
;
entry:
%a = alloca [4 x i8]
%ptr = getelementptr [4 x i8], [4 x i8]* %a, i32 0, i32 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 true), !tbaa !0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 true), !tbaa !3
ret void
}
%S1 = type { i32, i32, [16 x i8] }
%S2 = type { %S1*, %S2* }
define %S2 @test8(%S2* %arg) {
; CHECK-LABEL: @test8(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[S2_NEXT_PTR:%.*]] = getelementptr [[S2:%.*]], %S2* [[ARG:%.*]], i64 0, i32 1
; CHECK-NEXT: [[S2_NEXT:%.*]] = load %S2*, %S2** [[S2_NEXT_PTR]], align 8, !tbaa [[TBAA0]]
; CHECK-NEXT: [[S2_NEXT_S1_PTR:%.*]] = getelementptr [[S2]], %S2* [[S2_NEXT]], i64 0, i32 0
; CHECK-NEXT: [[S2_NEXT_S1:%.*]] = load %S1*, %S1** [[S2_NEXT_S1_PTR]], align 8, !tbaa [[TBAA3]]
; CHECK-NEXT: [[S2_NEXT_NEXT_PTR:%.*]] = getelementptr [[S2]], %S2* [[S2_NEXT]], i64 0, i32 1
; CHECK-NEXT: [[S2_NEXT_NEXT:%.*]] = load %S2*, %S2** [[S2_NEXT_NEXT_PTR]], align 8, !tbaa [[TBAA7]]
; CHECK-NEXT: [[RESULT1:%.*]] = insertvalue [[S2]] undef, %S1* [[S2_NEXT_S1]], 0
; CHECK-NEXT: [[RESULT2:%.*]] = insertvalue [[S2]] [[RESULT1]], %S2* [[S2_NEXT_NEXT]], 1
; CHECK-NEXT: ret [[S2]] [[RESULT2]]
;
entry:
%new = alloca %S2
%s2.next.ptr = getelementptr %S2, %S2* %arg, i64 0, i32 1
%s2.next = load %S2*, %S2** %s2.next.ptr, !tbaa !0
%s2.next.s1.ptr = getelementptr %S2, %S2* %s2.next, i64 0, i32 0
%s2.next.s1 = load %S1*, %S1** %s2.next.s1.ptr, !tbaa !3
%new.s1.ptr = getelementptr %S2, %S2* %new, i64 0, i32 0
store %S1* %s2.next.s1, %S1** %new.s1.ptr, !tbaa !5
%s2.next.next.ptr = getelementptr %S2, %S2* %s2.next, i64 0, i32 1
%s2.next.next = load %S2*, %S2** %s2.next.next.ptr, !tbaa !7
%new.next.ptr = getelementptr %S2, %S2* %new, i64 0, i32 1
store %S2* %s2.next.next, %S2** %new.next.ptr, !tbaa !9
%new.s1 = load %S1*, %S1** %new.s1.ptr
%result1 = insertvalue %S2 undef, %S1* %new.s1, 0
%new.next = load %S2*, %S2** %new.next.ptr
%result2 = insertvalue %S2 %result1, %S2* %new.next, 1
ret %S2 %result2
}
define i64 @test9() {
; Ensure we can handle loads off the end of an alloca even when wrapped in
; weird bit casts and types. This is valid IR due to the alignment and masking
; off the bits past the end of the alloca.
;
; CHECK-LABEL: @test9(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_3_0_INSERT_EXT:%.*]] = zext i8 26 to i64
; CHECK-NEXT: [[A_SROA_3_0_INSERT_SHIFT:%.*]] = shl i64 [[A_SROA_3_0_INSERT_EXT]], 16
; CHECK-NEXT: [[A_SROA_3_0_INSERT_MASK:%.*]] = and i64 undef, -16711681
; CHECK-NEXT: [[A_SROA_3_0_INSERT_INSERT:%.*]] = or i64 [[A_SROA_3_0_INSERT_MASK]], [[A_SROA_3_0_INSERT_SHIFT]]
; CHECK-NEXT: [[A_SROA_2_0_INSERT_EXT:%.*]] = zext i8 0 to i64
; CHECK-NEXT: [[A_SROA_2_0_INSERT_SHIFT:%.*]] = shl i64 [[A_SROA_2_0_INSERT_EXT]], 8
; CHECK-NEXT: [[A_SROA_2_0_INSERT_MASK:%.*]] = and i64 [[A_SROA_3_0_INSERT_INSERT]], -65281
; CHECK-NEXT: [[A_SROA_2_0_INSERT_INSERT:%.*]] = or i64 [[A_SROA_2_0_INSERT_MASK]], [[A_SROA_2_0_INSERT_SHIFT]]
; CHECK-NEXT: [[A_SROA_0_0_INSERT_EXT:%.*]] = zext i8 0 to i64
; CHECK-NEXT: [[A_SROA_0_0_INSERT_MASK:%.*]] = and i64 [[A_SROA_2_0_INSERT_INSERT]], -256
; CHECK-NEXT: [[A_SROA_0_0_INSERT_INSERT:%.*]] = or i64 [[A_SROA_0_0_INSERT_MASK]], [[A_SROA_0_0_INSERT_EXT]]
; CHECK-NEXT: [[RESULT:%.*]] = and i64 [[A_SROA_0_0_INSERT_INSERT]], 16777215
; CHECK-NEXT: ret i64 [[RESULT]]
;
entry:
%a = alloca { [3 x i8] }, align 8
%gep1 = getelementptr inbounds { [3 x i8] }, { [3 x i8] }* %a, i32 0, i32 0, i32 0
store i8 0, i8* %gep1, align 1
%gep2 = getelementptr inbounds { [3 x i8] }, { [3 x i8] }* %a, i32 0, i32 0, i32 1
store i8 0, i8* %gep2, align 1
%gep3 = getelementptr inbounds { [3 x i8] }, { [3 x i8] }* %a, i32 0, i32 0, i32 2
store i8 26, i8* %gep3, align 1
%cast = bitcast { [3 x i8] }* %a to { i64 }*
%elt = getelementptr inbounds { i64 }, { i64 }* %cast, i32 0, i32 0
%load = load i64, i64* %elt
%result = and i64 %load, 16777215
ret i64 %result
}
define %S2* @test10() {
; CHECK-LABEL: @test10(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = ptrtoint %S2* null to i64
; CHECK-NEXT: ret %S2* null
;
entry:
%a = alloca [8 x i8]
%ptr = getelementptr [8 x i8], [8 x i8]* %a, i32 0, i32 0
call void @llvm.memset.p0i8.i32(i8* %ptr, i8 0, i32 8, i1 false)
%s2ptrptr = bitcast i8* %ptr to %S2**
%s2ptr = load %S2*, %S2** %s2ptrptr
ret %S2* %s2ptr
}
define i32 @test11() {
; CHECK-LABEL: @test11(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 undef, label [[GOOD:%.*]], label [[BAD:%.*]]
; CHECK: good:
; CHECK-NEXT: ret i32 0
; CHECK: bad:
; CHECK-NEXT: ret i32 poison
;
entry:
%X = alloca i32
br i1 undef, label %good, label %bad
good:
%Y = getelementptr i32, i32* %X, i64 0
store i32 0, i32* %Y
%Z = load i32, i32* %Y
ret i32 %Z
bad:
%Y2 = getelementptr i32, i32* %X, i64 1
store i32 0, i32* %Y2
%Z2 = load i32, i32* %Y2
ret i32 %Z2
}
define i8 @test12() {
; We fully promote these to the i24 load or store size, resulting in just masks
; and other operations that instcombine will fold, but no alloca.
;
; CHECK-LABEL: @test12(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_3_0_INSERT_EXT:%.*]] = zext i8 0 to i24
; CHECK-NEXT: [[A_SROA_3_0_INSERT_SHIFT:%.*]] = shl i24 [[A_SROA_3_0_INSERT_EXT]], 16
; CHECK-NEXT: [[A_SROA_3_0_INSERT_MASK:%.*]] = and i24 undef, 65535
; CHECK-NEXT: [[A_SROA_3_0_INSERT_INSERT:%.*]] = or i24 [[A_SROA_3_0_INSERT_MASK]], [[A_SROA_3_0_INSERT_SHIFT]]
; CHECK-NEXT: [[A_SROA_2_0_INSERT_EXT:%.*]] = zext i8 0 to i24
; CHECK-NEXT: [[A_SROA_2_0_INSERT_SHIFT:%.*]] = shl i24 [[A_SROA_2_0_INSERT_EXT]], 8
; CHECK-NEXT: [[A_SROA_2_0_INSERT_MASK:%.*]] = and i24 [[A_SROA_3_0_INSERT_INSERT]], -65281
; CHECK-NEXT: [[A_SROA_2_0_INSERT_INSERT:%.*]] = or i24 [[A_SROA_2_0_INSERT_MASK]], [[A_SROA_2_0_INSERT_SHIFT]]
; CHECK-NEXT: [[A_SROA_0_0_INSERT_EXT:%.*]] = zext i8 0 to i24
; CHECK-NEXT: [[A_SROA_0_0_INSERT_MASK:%.*]] = and i24 [[A_SROA_2_0_INSERT_INSERT]], -256
; CHECK-NEXT: [[A_SROA_0_0_INSERT_INSERT:%.*]] = or i24 [[A_SROA_0_0_INSERT_MASK]], [[A_SROA_0_0_INSERT_EXT]]
; CHECK-NEXT: [[B_SROA_0_0_EXTRACT_TRUNC:%.*]] = trunc i24 [[A_SROA_0_0_INSERT_INSERT]] to i8
; CHECK-NEXT: [[B_SROA_2_0_EXTRACT_SHIFT:%.*]] = lshr i24 [[A_SROA_0_0_INSERT_INSERT]], 8
; CHECK-NEXT: [[B_SROA_2_0_EXTRACT_TRUNC:%.*]] = trunc i24 [[B_SROA_2_0_EXTRACT_SHIFT]] to i8
; CHECK-NEXT: [[B_SROA_3_0_EXTRACT_SHIFT:%.*]] = lshr i24 [[A_SROA_0_0_INSERT_INSERT]], 16
; CHECK-NEXT: [[B_SROA_3_0_EXTRACT_TRUNC:%.*]] = trunc i24 [[B_SROA_3_0_EXTRACT_SHIFT]] to i8
; CHECK-NEXT: [[BSUM0:%.*]] = add i8 [[B_SROA_0_0_EXTRACT_TRUNC]], [[B_SROA_2_0_EXTRACT_TRUNC]]
; CHECK-NEXT: [[BSUM1:%.*]] = add i8 [[BSUM0]], [[B_SROA_3_0_EXTRACT_TRUNC]]
; CHECK-NEXT: ret i8 [[BSUM1]]
;
entry:
%a = alloca [3 x i8]
%b = alloca [3 x i8]
%a0ptr = getelementptr [3 x i8], [3 x i8]* %a, i64 0, i32 0
store i8 0, i8* %a0ptr
%a1ptr = getelementptr [3 x i8], [3 x i8]* %a, i64 0, i32 1
store i8 0, i8* %a1ptr
%a2ptr = getelementptr [3 x i8], [3 x i8]* %a, i64 0, i32 2
store i8 0, i8* %a2ptr
%aiptr = bitcast [3 x i8]* %a to i24*
%ai = load i24, i24* %aiptr
%biptr = bitcast [3 x i8]* %b to i24*
store i24 %ai, i24* %biptr
%b0ptr = getelementptr [3 x i8], [3 x i8]* %b, i64 0, i32 0
%b0 = load i8, i8* %b0ptr
%b1ptr = getelementptr [3 x i8], [3 x i8]* %b, i64 0, i32 1
%b1 = load i8, i8* %b1ptr
%b2ptr = getelementptr [3 x i8], [3 x i8]* %b, i64 0, i32 2
%b2 = load i8, i8* %b2ptr
%bsum0 = add i8 %b0, %b1
%bsum1 = add i8 %bsum0, %b2
ret i8 %bsum1
}
define i32 @test13() {
; Ensure we don't crash and handle undefined loads that straddle the end of the
; allocation.
; CHECK-LABEL: @test13(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_2_2_LOAD_EXT:%.*]] = zext i8 0 to i16
; CHECK-NEXT: [[RET:%.*]] = zext i16 [[A_SROA_2_2_LOAD_EXT]] to i32
; CHECK-NEXT: ret i32 [[RET]]
;
entry:
%a = alloca [3 x i8], align 2
%b0ptr = getelementptr [3 x i8], [3 x i8]* %a, i64 0, i32 0
store i8 0, i8* %b0ptr
%b1ptr = getelementptr [3 x i8], [3 x i8]* %a, i64 0, i32 1
store i8 0, i8* %b1ptr
%b2ptr = getelementptr [3 x i8], [3 x i8]* %a, i64 0, i32 2
store i8 0, i8* %b2ptr
%iptrcast = bitcast [3 x i8]* %a to i16*
%iptrgep = getelementptr i16, i16* %iptrcast, i64 1
%i = load i16, i16* %iptrgep
%ret = zext i16 %i to i32
ret i32 %ret
}
%test14.struct = type { [3 x i32] }
define void @test14(...) nounwind uwtable {
; This is a strange case where we split allocas into promotable partitions, but
; also gain enough data to prove they must be dead allocas due to GEPs that walk
; across two adjacent allocas. Test that we don't try to promote or otherwise
; do bad things to these dead allocas, they should just be removed.
; CHECK-LABEL: @test14(
; CHECK-NEXT: entry:
; CHECK-NEXT: ret void
;
entry:
%a = alloca %test14.struct
%p = alloca %test14.struct*
%0 = bitcast %test14.struct* %a to i8*
%1 = getelementptr i8, i8* %0, i64 12
%2 = bitcast i8* %1 to %test14.struct*
%3 = getelementptr inbounds %test14.struct, %test14.struct* %2, i32 0, i32 0
%4 = getelementptr inbounds %test14.struct, %test14.struct* %a, i32 0, i32 0
%5 = bitcast [3 x i32]* %3 to i32*
%6 = bitcast [3 x i32]* %4 to i32*
%7 = load i32, i32* %6, align 4
store i32 %7, i32* %5, align 4
%8 = getelementptr inbounds i32, i32* %5, i32 1
%9 = getelementptr inbounds i32, i32* %6, i32 1
%10 = load i32, i32* %9, align 4
store i32 %10, i32* %8, align 4
%11 = getelementptr inbounds i32, i32* %5, i32 2
%12 = getelementptr inbounds i32, i32* %6, i32 2
%13 = load i32, i32* %12, align 4
store i32 %13, i32* %11, align 4
ret void
}
define i32 @test15(i1 %flag) nounwind uwtable {
; Ensure that when there are dead instructions using an alloca that are not
; loads or stores we still delete them during partitioning and rewriting.
; Otherwise we'll go to promote them while thy still have unpromotable uses.
; CHECK-LABEL: @test15(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: br label [[LOOP]]
;
entry:
%l0 = alloca i64
%l1 = alloca i64
%l2 = alloca i64
%l3 = alloca i64
br label %loop
loop:
%dead3 = phi i8* [ %gep3, %loop ], [ null, %entry ]
store i64 1879048192, i64* %l0, align 8
%bc0 = bitcast i64* %l0 to i8*
%gep0 = getelementptr i8, i8* %bc0, i64 3
%dead0 = bitcast i8* %gep0 to i64*
store i64 1879048192, i64* %l1, align 8
%bc1 = bitcast i64* %l1 to i8*
%gep1 = getelementptr i8, i8* %bc1, i64 3
%dead1 = getelementptr i8, i8* %gep1, i64 1
store i64 1879048192, i64* %l2, align 8
%bc2 = bitcast i64* %l2 to i8*
%gep2.1 = getelementptr i8, i8* %bc2, i64 1
%gep2.2 = getelementptr i8, i8* %bc2, i64 3
; Note that this select should get visited multiple times due to using two
; different GEPs off the same alloca. We should only delete it once.
%dead2 = select i1 %flag, i8* %gep2.1, i8* %gep2.2
store i64 1879048192, i64* %l3, align 8
%bc3 = bitcast i64* %l3 to i8*
%gep3 = getelementptr i8, i8* %bc3, i64 3
br label %loop
}
define void @test16(i8* %src, i8* %dst) {
; Ensure that we can promote an alloca of [3 x i8] to an i24 SSA value.
; CHECK-LABEL: @test16(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_0_0_SRC_SROA_CAST:%.*]] = bitcast i8* [[SRC:%.*]] to i24*
; CHECK-NEXT: [[A_SROA_0_0_COPYLOAD:%.*]] = load i24, i24* [[A_SROA_0_0_SRC_SROA_CAST]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_0_0_DST_SROA_CAST:%.*]] = bitcast i8* [[DST:%.*]] to i24*
; CHECK-NEXT: store i24 0, i24* [[A_SROA_0_0_DST_SROA_CAST]], align 1, !tbaa [[TBAA5]]
; CHECK-NEXT: ret void
;
entry:
%a = alloca [3 x i8]
%ptr = getelementptr [3 x i8], [3 x i8]* %a, i32 0, i32 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 false), !tbaa !0
%cast = bitcast i8* %ptr to i24*
store i24 0, i24* %cast, !tbaa !3
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 false), !tbaa !5
ret void
}
define void @test17(i8* %src, i8* %dst) {
; Ensure that we can rewrite unpromotable memcpys which extend past the end of
; the alloca.
; CHECK-LABEL: @test17(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A:%.*]] = alloca [3 x i8], align 1
; CHECK-NEXT: [[PTR:%.*]] = getelementptr [3 x i8], [3 x i8]* [[A]], i32 0, i32 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[PTR]], i8* [[SRC:%.*]], i32 4, i1 true), !tbaa [[TBAA0]]
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[DST:%.*]], i8* [[PTR]], i32 4, i1 true), !tbaa [[TBAA3]]
; CHECK-NEXT: ret void
;
entry:
%a = alloca [3 x i8]
%ptr = getelementptr [3 x i8], [3 x i8]* %a, i32 0, i32 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 4, i1 true), !tbaa !0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 4, i1 true), !tbaa !3
ret void
}
define void @test18(i8* %src, i8* %dst, i32 %size) {
; Preserve transfer intrinsics with a variable size, even if they overlap with
; fixed size operations. Further, continue to split and promote allocas preceding
; the variable sized intrinsic.
; CHECK-LABEL: @test18(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A_SROA_33:%.*]] = alloca [34 x i8], align 1
; CHECK-NEXT: [[A_SROA_0_0_SRC_SROA_CAST:%.*]] = bitcast i8* [[SRC:%.*]] to i32*
; CHECK-NEXT: [[A_SROA_0_0_COPYLOAD:%.*]] = load i32, i32* [[A_SROA_0_0_SRC_SROA_CAST]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_3_0_SRC_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 4
; CHECK-NEXT: [[A_SROA_3_0_SRC_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_3_0_SRC_SROA_IDX]] to i32*
; CHECK-NEXT: [[A_SROA_3_0_COPYLOAD:%.*]] = load i32, i32* [[A_SROA_3_0_SRC_SROA_CAST]], align 1, !tbaa [[TBAA0]]
; CHECK-NEXT: [[A_SROA_33_0_PTR2_SROA_IDX:%.*]] = getelementptr inbounds [34 x i8], [34 x i8]* [[A_SROA_33]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 1 [[A_SROA_33_0_PTR2_SROA_IDX]], i8* [[SRC]], i32 [[SIZE:%.*]], i1 false), !tbaa [[TBAA3]]
; CHECK-NEXT: [[A_SROA_33_0_PTR2_SROA_IDX6:%.*]] = getelementptr inbounds [34 x i8], [34 x i8]* [[A_SROA_33]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memset.p0i8.i32(i8* align 1 [[A_SROA_33_0_PTR2_SROA_IDX6]], i8 42, i32 [[SIZE]], i1 false), !tbaa [[TBAA5]]
; CHECK-NEXT: [[A_SROA_0_0_DST_SROA_CAST:%.*]] = bitcast i8* [[DST:%.*]] to i32*
; CHECK-NEXT: store i32 42, i32* [[A_SROA_0_0_DST_SROA_CAST]], align 1, !tbaa [[TBAA9]]
; CHECK-NEXT: [[A_SROA_3_0_DST_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 4
; CHECK-NEXT: [[A_SROA_3_0_DST_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_3_0_DST_SROA_IDX]] to i32*
; CHECK-NEXT: store i32 [[A_SROA_3_0_COPYLOAD]], i32* [[A_SROA_3_0_DST_SROA_CAST]], align 1, !tbaa [[TBAA9]]
; CHECK-NEXT: [[A_SROA_33_0_PTR2_SROA_IDX7:%.*]] = getelementptr inbounds [34 x i8], [34 x i8]* [[A_SROA_33]], i64 0, i64 0
; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* [[DST]], i8* align 1 [[A_SROA_33_0_PTR2_SROA_IDX7]], i32 [[SIZE]], i1 false), !tbaa [[TBAA11]]
; CHECK-NEXT: ret void
;
entry:
%a = alloca [42 x i8]
%ptr = getelementptr [42 x i8], [42 x i8]* %a, i32 0, i32 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr, i8* %src, i32 8, i1 false), !tbaa !0
%ptr2 = getelementptr [42 x i8], [42 x i8]* %a, i32 0, i32 8
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %ptr2, i8* %src, i32 %size, i1 false), !tbaa !3
call void @llvm.memset.p0i8.i32(i8* %ptr2, i8 42, i32 %size, i1 false), !tbaa !5
%cast = bitcast i8* %ptr to i32*
store i32 42, i32* %cast, !tbaa !7
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr, i32 8, i1 false), !tbaa !9
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dst, i8* %ptr2, i32 %size, i1 false), !tbaa !11
ret void
}
%opaque = type opaque
define i32 @test19(%opaque* %x) {
; This input will cause us to try to compute a natural GEP when rewriting
; pointers in such a way that we try to GEP through the opaque type. Previously,
; a check for an unsized type was missing and this crashed. Ensure it behaves
; reasonably now.
; CHECK-LABEL: @test19(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CAST1:%.*]] = bitcast %opaque* [[X:%.*]] to i8*
; CHECK-NEXT: [[A_SROA_0_0_CAST1_SROA_CAST:%.*]] = bitcast i8* [[CAST1]] to i64*
; CHECK-NEXT: [[A_SROA_0_0_COPYLOAD:%.*]] = load i64, i64* [[A_SROA_0_0_CAST1_SROA_CAST]], align 1
; CHECK-NEXT: [[A_SROA_2_0_CAST1_SROA_IDX:%.*]] = getelementptr inbounds i8, i8* [[CAST1]], i64 8
; CHECK-NEXT: [[A_SROA_2_0_CAST1_SROA_CAST:%.*]] = bitcast i8* [[A_SROA_2_0_CAST1_SROA_IDX]] to i8**
; CHECK-NEXT: [[A_SROA_2_0_COPYLOAD:%.*]] = load i8*, i8** [[A_SROA_2_0_CAST1_SROA_CAST]], align 1
; CHECK-NEXT: ret i32 undef
;
entry:
%a = alloca { i64, i8* }
%cast1 = bitcast %opaque* %x to i8*
%cast2 = bitcast { i64, i8* }* %a to i8*
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %cast2, i8* %cast1, i32 16, i1 false)
%gep = getelementptr inbounds { i64, i8* }, { i64, i8* }* %a, i32 0, i32 0
%val = load i64, i64* %gep
ret i32 undef
}
declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture, i32, i32, i1) nounwind
define i32 @test19_addrspacecast(%opaque* %x) {
; This input will cause us to try to compute a natural GEP when rewriting
; pointers in such a way that we try to GEP through the opaque type. Previously,
; a check for an unsized type was missing and this crashed. Ensure it behaves
; reasonably now.
; CHECK-LABEL: @test19_addrspacecast(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CAST1:%.*]] = addrspacecast %opaque* [[X:%.*]] to i8 addrspace(1)*
; CHECK-NEXT: [[A_SROA_0_0_CAST1_SROA_CAST:%.*]] = bitcast i8 addrspace(1)* [[CAST1]] to i64 addrspace(1)*
; CHECK-NEXT: [[A_SROA_0_0_COPYLOAD:%.*]] = load i64, i64 addrspace(1)* [[A_SROA_0_0_CAST1_SROA_CAST]], align 1
; CHECK-NEXT: [[A_SROA_2_0_CAST1_SROA_IDX:%.*]] = getelementptr inbounds i8, i8 addrspace(1)* [[CAST1]], i16 8
; CHECK-NEXT: [[A_SROA_2_0_CAST1_SROA_CAST:%.*]] = bitcast i8 addrspace(1)* [[A_SROA_2_0_CAST1_SROA_IDX]] to i8* addrspace(1)*
; CHECK-NEXT: [[A_SROA_2_0_COPYLOAD:%.*]] = load i8*, i8* addrspace(1)* [[A_SROA_2_0_CAST1_SROA_CAST]], align 1
; CHECK-NEXT: ret i32 undef
;
entry:
%a = alloca { i64, i8* }
%cast1 = addrspacecast %opaque* %x to i8 addrspace(1)*
%cast2 = bitcast { i64, i8* }* %a to i8*
call void @llvm.memcpy.p0i8.p1i8.i32(i8* %cast2, i8 addrspace(1)* %cast1, i32 16, i32 1, i1 false)
%gep = getelementptr inbounds { i64, i8* }, { i64, i8* }* %a, i32 0, i32 0
%val = load i64, i64* %gep
ret i32 undef
}
define i32 @test20() {
; Ensure we can track negative offsets (before the beginning of the alloca) and
; negative relative offsets from offsets starting past the end of the alloca.
; CHECK-LABEL: @test20(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[SUM1:%.*]] = add i32 1, 2
; CHECK-NEXT: [[SUM2:%.*]] = add i32 [[SUM1]], 3
; CHECK-NEXT: ret i32 [[SUM2]]
;
entry:
%a = alloca [3 x i32]
%gep1 = getelementptr [3 x i32], [3 x i32]* %a, i32 0, i32 0
store i32 1, i32* %gep1
%gep2.1 = getelementptr [3 x i32], [3 x i32]* %a, i32 0, i32 -2