llvm.org GIT mirror llvm / release_80 test / CodeGen / X86 / x86-shrink-wrapping.ll
release_80

Tree @release_80 (Download .tar.gz)

x86-shrink-wrapping.ll @release_80raw · history · blame

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
; RUN: llc %s -o - -enable-shrink-wrap=true -pass-remarks-output=%t | FileCheck %s --check-prefix=CHECK --check-prefix=ENABLE
; RUN: cat %t | FileCheck %s --check-prefix=REMARKS
; RUN: llc %s -o - -enable-shrink-wrap=false | FileCheck %s --check-prefix=CHECK --check-prefix=DISABLE
;
; Note: Lots of tests use inline asm instead of regular calls.
; This allows to have a better control on what the allocation will do.
; Otherwise, we may have spill right in the entry block, defeating
; shrink-wrapping. Moreover, some of the inline asm statement (nop)
; are here to ensure that the related paths do not end up as critical
; edges.
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "x86_64-apple-macosx"


; 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: movl %edi, [[ARG0CPY:%e[a-z]+]]
; ENABLE-NEXT: cmpl %esi, %edi
; ENABLE-NEXT: jge [[EXIT_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; (What we push does not matter. It should be some random sratch register.)
; CHECK: pushq
;
; Compare the arguments and jump to exit.
; After the prologue is set.
; DISABLE: movl %edi, [[ARG0CPY:%e[a-z]+]]
; DISABLE-NEXT: cmpl %esi, %edi
; DISABLE-NEXT: jge [[EXIT_LABEL:LBB[0-9_]+]]
;
; Store %a in the alloca.
; CHECK: movl [[ARG0CPY]], 4(%rsp)
; Set the alloca address in the second argument.
; CHECK-NEXT: leaq 4(%rsp), %rsi
; Set the first argument to zero.
; CHECK-NEXT: xorl %edi, %edi
; CHECK-NEXT: callq _doSomething
;
; With shrink-wrapping, epilogue is just after the call.
; ENABLE-NEXT: addq $8, %rsp
;
; CHECK: [[EXIT_LABEL]]:
;
; Without shrink-wrapping, epilogue is in the exit block.
; Epilogue code. (What we pop does not matter.)
; DISABLE-NEXT: popq
;
; CHECK-NEXT: retq
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: testl %edi, %edi  
; ENABLE: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; Make sure we save the CSR used in the inline asm: rbx.
; CHECK: pushq %rbx
;
; DISABLE: testl %edi, %edi
; DISABLE: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: xorl [[SUM:%eax]], [[SUM]]
; CHECK-NEXT: movl $10, [[IV:%e[a-z]+]]
;
; Next BB.
; CHECK: [[LOOP:LBB[0-9_]+]]: ## %for.body
; CHECK: movl $1, [[TMP:%e[a-z]+]]
; CHECK: addl [[TMP]], [[SUM]]
; CHECK-NEXT: decl [[IV]]
; CHECK-NEXT: jne [[LOOP]]
;
; Next BB.
; SUM << 3.
; CHECK: shll $3, [[SUM]]
;
; DISABLE: popq
; DISABLE: retq
;
; DISABLE: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one in returned register.
; DISABLE: movl %esi, %eax
; DISABLE: addl %esi, %eax
;
; Epilogue code.
; CHECK-DAG: popq %rbx
; CHECK: retq
;
; ENABLE: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one and store into returned register.
; ENABLE: movl %esi, %eax
; ENABLE: addl %esi, %eax
; ENABLE-NEXT: retq
define i32 @freqSaveAndRestoreOutsideLoop(i32 %cond, i32 %N) {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %for.preheader

for.preheader:
  tail call void asm "nop", ""()
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.05 = phi i32 [ %inc, %for.body ], [ 0, %for.preheader ]
  %sum.04 = phi i32 [ %add, %for.body ], [ 0, %for.preheader ]
  %call = tail call i32 asm sideeffect "movl $$1, $0", "=r,~{ebx}"()
  %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.
; Make sure we save the CSR used in the inline asm: rbx.
; CHECK: pushq %rbx
; CHECK: nop
; CHECK: xorl [[SUM:%e[a-z]+]], [[SUM]]
; CHECK-NEXT: movl $10, [[IV:%e[a-z]+]]
; Next BB.
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ## %for.body
; CHECK: movl $1, [[TMP:%e[a-z]+]]
; CHECK: addl [[TMP]], [[SUM]]
; CHECK-NEXT: decl [[IV]]
; CHECK-NEXT: jne [[LOOP_LABEL]]
; Next BB.
; CHECK: ## %for.exit
; CHECK: nop
; CHECK: popq %rbx
; CHECK-NEXT: retq
define i32 @freqSaveAndRestoreOutsideLoop2(i32 %cond) {
entry:
  br label %for.preheader

for.preheader:
  tail call void asm "nop", ""()
  br label %for.body

for.body:                                         ; preds = %for.body, %entry
  %i.04 = phi i32 [ 0, %for.preheader ], [ %inc, %for.body ]
  %sum.03 = phi i32 [ 0, %for.preheader ], [ %add, %for.body ]
  %call = tail call i32 asm sideeffect "movl $$1, $0", "=r,~{ebx}"()
  %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.exit, label %for.body

for.exit:
  tail call void asm "nop", ""()
  br label %for.end

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: testl %edi, %edi
; ENABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; Make sure we save the CSR used in the inline asm: rbx.
; CHECK: pushq %rbx
;
; DISABLE: testl %edi, %edi
; DISABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: nop
; CHECK: xorl [[SUM:%eax]], [[SUM]]
; CHECK-NEXT: movl $10, [[IV:%e[a-z]+]]
;
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ## %for.body
; CHECK: movl $1, [[TMP:%e[a-z]+]]
; CHECK: addl [[TMP]], [[SUM]]
; CHECK-NEXT: decl [[IV]]
; CHECK-NEXT: jne [[LOOP_LABEL]]
; Next BB.
; CHECK: nop
; CHECK: shll $3, [[SUM]]
;
; DISABLE: popq
; DISABLE: retq
;
; DISABLE: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one in returned register.
; DISABLE: movl %esi, %eax
; DISABLE: addl %esi, %eax
;
; Epilogue code.
; CHECK-DAG: popq %rbx
; CHECK: retq
;
; ENABLE: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one and store into returned register.
; ENABLE: movl %esi, %eax
; ENABLE: addl %esi, %eax
; ENABLE-NEXT: retq
define i32 @loopInfoSaveOutsideLoop(i32 %cond, i32 %N) {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %for.preheader

for.preheader:
  tail call void asm "nop", ""()
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.05 = phi i32 [ %inc, %for.body ], [ 0, %for.preheader ]
  %sum.04 = phi i32 [ %add, %for.body ], [ 0, %for.preheader ]
  %call = tail call i32 asm sideeffect "movl $$1, $0", "=r,~{ebx}"()
  %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 asm "nop", "~{ebx}"()
  %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 with a more complex case that we do not have restore within the loop and
; save outside.
; CHECK-LABEL: loopInfoRestoreOutsideLoop:
;
; ENABLE: testl %edi, %edi
; ENABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; Make sure we save the CSR used in the inline asm: rbx.
; CHECK: pushq %rbx
;
; DISABLE: testl %edi, %edi
; DISABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: nop
; CHECK: xorl [[SUM:%eax]], [[SUM]]
; CHECK-NEXT: movl $10, [[IV:%e[a-z]+]]
;
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ## %for.body
; CHECK: movl $1, [[TMP:%e[a-z]+]]
; CHECK: addl [[TMP]], [[SUM]]
; CHECK-NEXT: decl [[IV]]
; CHECK-NEXT: jne [[LOOP_LABEL]]
; Next BB.
; CHECK: shll $3, [[SUM]]
;
; DISABLE: popq
; DISABLE: retq
;
; DISABLE: [[ELSE_LABEL]]: ## %if.else

; Shift second argument by one in returned register.
; DISABLE: movl %esi, %eax
; DISABLE: addl %esi, %eax
;
; Epilogue code.
; CHECK-DAG: popq %rbx
; CHECK: retq
;
; ENABLE: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one and store into returned register.
; ENABLE: movl %esi, %eax
; ENABLE: addl %esi, %eax
; ENABLE-NEXT: retq
define i32 @loopInfoRestoreOutsideLoop(i32 %cond, i32 %N) nounwind {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %if.then

if.then:                                          ; preds = %entry
  tail call void asm "nop", "~{ebx}"()
  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 asm sideeffect "movl $$1, $0", "=r,~{ebx}"()
  %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: xorl %eax, %eax
; CHECK-NEXT: retq
define i32 @emptyFrame() {
entry:
  ret i32 0
}

; Check that we handle inline asm correctly.
; CHECK-LABEL: inlineAsm:
;
; ENABLE: testl %edi, %edi
; ENABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; Make sure we save the CSR used in the inline asm: rbx.
; CHECK: pushq %rbx
;
; DISABLE: testl %edi, %edi
; DISABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; CHECK: nop
; CHECK: movl $10, [[IV:%e[a-z]+]]
;
; CHECK: [[LOOP_LABEL:LBB[0-9_]+]]: ## %for.body
; Inline asm statement.
; CHECK: addl $1, %ebx
; CHECK: decl [[IV]]
; CHECK-NEXT: jne [[LOOP_LABEL]]
; Next BB.
; CHECK: nop
; CHECK: xorl %eax, %eax
;
; DISABLE: popq
; DISABLE: retq
;
; DISABLE: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one in returned register.
; DISABLE: movl %esi, %eax
; DISABLE: addl %esi, %eax
;
; Epilogue code.
; CHECK-DAG: popq %rbx
; CHECK: retq
;
; ENABLE: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one and store into returned register.
; ENABLE: movl %esi, %eax
; ENABLE: addl %esi, %eax
; ENABLE-NEXT: retq
define i32 @inlineAsm(i32 %cond, i32 %N) {
entry:
  %tobool = icmp eq i32 %cond, 0
  br i1 %tobool, label %if.else, label %for.preheader

for.preheader:
  tail call void asm "nop", ""()
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %i.03 = phi i32 [ %inc, %for.body ], [ 0, %for.preheader ]
  tail call void asm "addl $$1, %ebx", "~{ebx}"()
  %inc = add nuw nsw i32 %i.03, 1
  %exitcond = icmp eq i32 %inc, 10
  br i1 %exitcond, label %for.exit, label %for.body

for.exit:
  tail call void asm "nop", ""()
  br label %if.end

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.exit ]
  ret i32 %sum.0
}

; Check that we handle calls to variadic functions correctly.
; CHECK-LABEL: callVariadicFunc:
;
; ENABLE: movl %esi, %eax
; ENABLE: testl %edi, %edi
; ENABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; CHECK: pushq
;
; DISABLE: movl %esi, %eax
; DISABLE: testl %edi, %edi
; DISABLE-NEXT: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; Setup of the varags.
; CHECK:       movl	%eax, (%rsp)
; CHECK-NEXT:  movl	%eax, %edi
; CHECK-NEXT:  movl	%eax, %esi
; CHECK-NEXT:  movl	%eax, %edx
; CHECK-NEXT:  movl	%eax, %ecx
; CHECK-NEXT:  movl	%eax, %r8d
; CHECK-NEXT:  movl	%eax, %r9d
; CHECK-NEXT:  xorl	%eax, %eax
; CHECK-NEXT: callq _someVariadicFunc
; CHECK-NEXT: shll $3, %eax
;
; ENABLE-NEXT: addq $8, %rsp
; ENABLE-NEXT: retq
;

; CHECK: [[ELSE_LABEL]]: ## %if.else
; Shift second argument by one and store into returned register.
; CHECK: addl %eax, %eax
;
; Epilogue code.
; DISABLE-NEXT: popq
; CHECK-NEXT: retq
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, ...)

; Check that we use LEA not to clobber EFLAGS.
%struct.temp_slot = type { %struct.temp_slot*, %struct.rtx_def*, %struct.rtx_def*, i32, i64, %union.tree_node*, %union.tree_node*, i8, i8, i32, i32, i64, i64 }
%union.tree_node = type { %struct.tree_decl }
%struct.tree_decl = type { %struct.tree_common, i8*, i32, i32, %union.tree_node*, i48, %union.anon, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %union.tree_node*, %struct.rtx_def*, %struct.rtx_def*, %union.anon.1, %union.tree_node*, %union.tree_node*, %union.tree_node*, i64, %struct.lang_decl* }
%struct.tree_common = type { %union.tree_node*, %union.tree_node*, i32 }
%union.anon = type { i64 }
%union.anon.1 = type { %struct.function* }
%struct.function = type { %struct.eh_status*, %struct.stmt_status*, %struct.expr_status*, %struct.emit_status*, %struct.varasm_status*, i8*, %union.tree_node*, %struct.function*, i32, i32, i32, i32, %struct.rtx_def*, %struct.ix86_args, %struct.rtx_def*, %struct.rtx_def*, i8*, %struct.initial_value_struct*, i32, %union.tree_node*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, %union.tree_node*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, i64, %union.tree_node*, %union.tree_node*, %struct.rtx_def*, %struct.rtx_def*, i32, %struct.rtx_def**, %struct.temp_slot*, i32, i32, i32, %struct.var_refs_queue*, i32, i32, i8*, %union.tree_node*, %struct.rtx_def*, i32, i32, %struct.machine_function*, i32, i32, %struct.language_function*, %struct.rtx_def*, i24 }
%struct.eh_status = type opaque
%struct.stmt_status = type opaque
%struct.expr_status = type { i32, i32, i32, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def*, %struct.rtx_def* }
%struct.emit_status = type { i32, i32, %struct.rtx_def*, %struct.rtx_def*, %union.tree_node*, %struct.sequence_stack*, i32, i32, i8*, i32, i8*, %union.tree_node**, %struct.rtx_def** }
%struct.sequence_stack = type { %struct.rtx_def*, %struct.rtx_def*, %union.tree_node*, %struct.sequence_stack* }
%struct.varasm_status = type opaque
%struct.ix86_args = type { i32, i32, i32, i32, i32, i32, i32 }
%struct.initial_value_struct = type opaque
%struct.var_refs_queue = type { %struct.rtx_def*, i32, i32, %struct.var_refs_queue* }
%struct.machine_function = type opaque
%struct.language_function = type opaque
%struct.lang_decl = type opaque
%struct.rtx_def = type { i32, [1 x %union.rtunion_def] }
%union.rtunion_def = type { i64 }

declare hidden fastcc %struct.temp_slot* @find_temp_slot_from_address(%struct.rtx_def* readonly)

; CHECK-LABEL: useLEA:
; DISABLE: pushq 
;
; CHECK: testq   %rdi, %rdi
; CHECK-NEXT: je      [[CLEANUP:LBB[0-9_]+]]
;
; CHECK: cmpw $66, (%rdi)
; CHECK-NEXT: jne [[CLEANUP]]
;
; CHECK: movq 8(%rdi), %rdi
; CHECK-NEXT: movzwl (%rdi), %e[[BF_LOAD2:[a-z]+]]
; CHECK-NEXT: leal -54(%r[[BF_LOAD2]]), [[TMP:%e[a-z]+]]
; CHECK-NEXT: cmpl $14, [[TMP]]
; CHECK-NEXT: ja [[LOR_LHS_FALSE:LBB[0-9_]+]]
;
; CHECK: movl $24599, [[TMP2:%e[a-z]+]]
; CHECK-NEXT: btl [[TMP]], [[TMP2]]
; CHECK-NEXT: jae [[LOR_LHS_FALSE:LBB[0-9_]+]]
;
; CHECK: [[CLEANUP]]: ## %cleanup
; DISABLE: popq
; CHECK-NEXT: retq
;
; CHECK: [[LOR_LHS_FALSE]]: ## %lor.lhs.false
; CHECK: cmpl $134, %e[[BF_LOAD2]]
; CHECK-NEXT: je [[CLEANUP]]
;
; CHECK: cmpl $140, %e[[BF_LOAD2]]
; CHECK-NEXT: je [[CLEANUP]]
;
; ENABLE: pushq
; CHECK: callq _find_temp_slot_from_address
; CHECK-NEXT: testq   %rax, %rax
;
; The adjustment must use LEA here (or be moved above the test).
; ENABLE-NEXT: leaq 8(%rsp), %rsp
;
; CHECK-NEXT: je [[CLEANUP]]
;
; CHECK: movb $1, 57(%rax)
define void @useLEA(%struct.rtx_def* readonly %x) {
entry:
  %cmp = icmp eq %struct.rtx_def* %x, null
  br i1 %cmp, label %cleanup, label %if.end

if.end:                                           ; preds = %entry
  %tmp = getelementptr inbounds %struct.rtx_def, %struct.rtx_def* %x, i64 0, i32 0
  %bf.load = load i32, i32* %tmp, align 8
  %bf.clear = and i32 %bf.load, 65535
  %cmp1 = icmp eq i32 %bf.clear, 66
  br i1 %cmp1, label %lor.lhs.false, label %cleanup

lor.lhs.false:                                    ; preds = %if.end
  %arrayidx = getelementptr inbounds %struct.rtx_def, %struct.rtx_def* %x, i64 0, i32 1, i64 0
  %rtx = bitcast %union.rtunion_def* %arrayidx to %struct.rtx_def**
  %tmp1 = load %struct.rtx_def*, %struct.rtx_def** %rtx, align 8
  %tmp2 = getelementptr inbounds %struct.rtx_def, %struct.rtx_def* %tmp1, i64 0, i32 0
  %bf.load2 = load i32, i32* %tmp2, align 8
  %bf.clear3 = and i32 %bf.load2, 65535
  switch i32 %bf.clear3, label %if.end.55 [
    i32 67, label %cleanup
    i32 68, label %cleanup
    i32 54, label %cleanup
    i32 55, label %cleanup
    i32 58, label %cleanup
    i32 134, label %cleanup
    i32 56, label %cleanup
    i32 140, label %cleanup
  ]

if.end.55:                                        ; preds = %lor.lhs.false
  %call = tail call fastcc %struct.temp_slot* @find_temp_slot_from_address(%struct.rtx_def* %tmp1) #2
  %cmp59 = icmp eq %struct.temp_slot* %call, null
  br i1 %cmp59, label %cleanup, label %if.then.60

if.then.60:                                       ; preds = %if.end.55
  %addr_taken = getelementptr inbounds %struct.temp_slot, %struct.temp_slot* %call, i64 0, i32 8
  store i8 1, i8* %addr_taken, align 1
  br label %cleanup

cleanup:                                          ; preds = %if.then.60, %if.end.55, %lor.lhs.false, %lor.lhs.false, %lor.lhs.false, %lor.lhs.false, %lor.lhs.false, %lor.lhs.false, %lor.lhs.false, %lor.lhs.false, %if.end, %entry
  ret void
}

; 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: pushq
;
; CHECK: testb   %dil, %dil
; CHECK-NEXT: jne      [[ABORT:LBB[0-9_]+]]
;
; CHECK: movl $42, %eax
;
; DISABLE-NEXT: popq
;
; CHECK-NEXT: retq
;
; CHECK: [[ABORT]]: ## %if.abort
;
; ENABLE: pushq
;
; CHECK: callq _abort
; ENABLE-NOT: popq
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: retq
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 asm "movl $$1, $0", "=r,~{ebx}"()
  %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: retq
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 "movl $$1, $0", "=r,~{ebx}"()
  %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", "~{ebx}"()
  br label %for.body

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

if.end:
  ret void
}

; Another infinite loop test this time with two nested infinite loop.
; CHECK-LABEL: infiniteloop3
; CHECK: retq
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
}

; Check that we just don't bail out on RegMask.
; In this case, the RegMask does not touch a CSR so we are good to go!
; CHECK-LABEL: regmask:
;
; Compare the arguments and jump to exit.
; No prologue needed.
; ENABLE: cmpl %esi, %edi
; ENABLE-NEXT: jge [[EXIT_LABEL:LBB[0-9_]+]]
;
; Prologue code.
; (What we push does not matter. It should be some random sratch register.)
; CHECK: pushq
;
; Compare the arguments and jump to exit.
; After the prologue is set.
; DISABLE: cmpl %esi, %edi
; DISABLE-NEXT: jge [[EXIT_LABEL:LBB[0-9_]+]]
;
; CHECK: nop
; Set the first argument to zero.
; CHECK: xorl %edi, %edi
; Set the second argument to addr.
; CHECK-NEXT: movq %rdx, %rsi
; CHECK-NEXT: callq _doSomething
; CHECK-NEXT: popq
; CHECK-NEXT: retq
;
; CHECK: [[EXIT_LABEL]]:
; Set the first argument to 6.
; CHECK-NEXT: movl $6, %edi
; Set the second argument to addr.
; CHECK-NEXT: movq %rdx, %rsi
;
; Without shrink-wrapping, we need to restore the stack before
; making the tail call.
; Epilogue code.
; DISABLE-NEXT: popq
;
; CHECK-NEXT: jmp _doSomething
define i32 @regmask(i32 %a, i32 %b, i32* %addr) {
  %tmp2 = icmp slt i32 %a, %b
  br i1 %tmp2, label %true, label %false

true:
  ; Clobber a CSR so that we check something on the regmask
  ; of the tail call.
  tail call void asm sideeffect "nop", "~{ebx}"()
  %tmp4 = call i32 @doSomething(i32 0, i32* %addr)
  br label %end

false:
  %tmp5 = tail call i32 @doSomething(i32 6, i32* %addr)
  br label %end

end:
  %tmp.0 = phi i32 [ %tmp4, %true ], [ %tmp5, %false ]
  ret i32 %tmp.0
}

@b = internal unnamed_addr global i1 false
@c = internal unnamed_addr global i8 0, align 1
@a = common global i32 0, align 4

; Make sure the prologue does not clobber the EFLAGS when
; it is live accross.
; PR25629.
; Note: The registers may change in the following patterns, but
; because they imply register hierarchy (e.g., eax, al) this is
; tricky to write robust patterns.
;
; CHECK-LABEL: useLEAForPrologue:
;
; Prologue is at the beginning of the function when shrink-wrapping
; is disabled.
; DISABLE: pushq
; The stack adjustment can use SUB instr because we do not need to
; preserve the EFLAGS at this point.
; DISABLE-NEXT: subq $16, %rsp
;
; Load the value of b.
; Create the zero value for the select assignment.
; CHECK: xorl [[CMOVE_VAL:%eax]], [[CMOVE_VAL]]
; CHECK-NEXT: cmpb $0, _b(%rip)
; CHECK-NEXT: jne [[STOREC_LABEL:LBB[0-9_]+]]
;
; CHECK: movb $48, [[CMOVE_VAL:%al]]
;
; CHECK: [[STOREC_LABEL]]:
;
; ENABLE-NEXT: pushq
; For the stack adjustment, we need to preserve the EFLAGS.
; ENABLE-NEXT: leaq -16(%rsp), %rsp
;
; Technically, we should use CMOVE_VAL here or its subregister.
; CHECK-NEXT: movb %al, _c(%rip)
; testb set the EFLAGS read here.
; CHECK-NEXT: je [[VARFUNC_CALL:LBB[0-9_]+]]
;
; The code of the loop is not interesting.
; [...]
;
; CHECK: [[VARFUNC_CALL]]:
; Set the null parameter.
; CHECK-NEXT: xorl %edi, %edi
; CHECK-NEXT: callq _varfunc
;
; Set the return value.
; CHECK-NEXT: xorl %eax, %eax
;
; Epilogue code.
; CHECK-NEXT: addq $16, %rsp
; CHECK-NEXT: popq
; CHECK-NEXT: retq
define i32 @useLEAForPrologue(i32 %d, i32 %a, i8 %c) #3 {
entry:
  %tmp = alloca i3
  %.b = load i1, i1* @b, align 1
  %bool = select i1 %.b, i8 0, i8 48
  store i8 %bool, i8* @c, align 1
  br i1 %.b, label %for.body.lr.ph, label %for.end

for.body.lr.ph:                                   ; preds = %entry
  tail call void asm sideeffect "nop", "~{ebx}"()
  br label %for.body

for.body:                                         ; preds = %for.body.lr.ph, %for.body
  %inc6 = phi i8 [ %c, %for.body.lr.ph ], [ %inc, %for.body ]
  %cond5 = phi i32 [ %a, %for.body.lr.ph ], [ %conv3, %for.body ]
  %cmp2 = icmp slt i32 %d, %cond5
  %conv3 = zext i1 %cmp2 to i32
  %inc = add i8 %inc6, 1
  %cmp = icmp slt i8 %inc, 45
  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge

for.cond.for.end_crit_edge:                       ; preds = %for.body
  store i32 %conv3, i32* @a, align 4
  br label %for.end

for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
  %call = tail call i32 (i8*) @varfunc(i8* null)
  ret i32 0
}

declare i32 @varfunc(i8* nocapture readonly)

@sum1 = external hidden thread_local global i32, align 4


; Function Attrs: nounwind
; Make sure the TLS call used to access @sum1 happens after the prologue
; and before the epilogue.
; TLS calls used to be wrongly model and shrink-wrapping would have inserted
; the prologue and epilogue just around the call to doSomething.
; PR25820.
;
; CHECK-LABEL: tlsCall:
; CHECK: pushq
; CHECK: testb $1, %dil
; CHECK: je [[ELSE_LABEL:LBB[0-9_]+]]
;
; master bb
; CHECK: movq _sum1@TLVP(%rip), %rdi
; CHECK-NEXT: callq *(%rdi)
; CHECK: jmp [[EXIT_LABEL:LBB[0-9_]+]]
;
; [[ELSE_LABEL]]:
; CHECK: callq _doSomething
;
; [[EXIT_LABEL]]:
; CHECK: popq
; CHECK-NEXT: retq
define i32 @tlsCall(i1 %bool1, i32 %arg, i32* readonly dereferenceable(4) %sum1) #3 {
entry:
  br i1 %bool1, label %master, label %else

master:
  %tmp1 = load i32, i32* %sum1, align 4
  store i32 %tmp1, i32* @sum1, align 4
  br label %exit

else:
  %call = call i32 @doSomething(i32 0, i32* null)
  br label %exit

exit:
  %res = phi i32 [ %arg, %master], [ %call, %else ]
  ret i32 %res
}

attributes #3 = { nounwind }

@irreducibleCFGa = common global i32 0, align 4
@irreducibleCFGf = common global i8 0, align 1
@irreducibleCFGb = common global i32 0, align 4

; Check that we do not run shrink-wrapping on irreducible CFGs until
; it is actually supported.
; At the moment, on those CFGs the loop information may be incorrect
; and since we use that information to do the placement, we may end up
; inserting the prologue/epilogue at incorrect places.
; PR25988.
;
; CHECK-LABEL: irreducibleCFG:
; CHECK: %entry
; Make sure the prologue happens in the entry block.
; CHECK-NEXT: pushq
; ...
; Make sure the epilogue happens in the exit block.
; CHECK-NOT: popq
; CHECK: popq
; CHECK-NEXT: popq
; CHECK-NEXT: retq
; Make sure we emit missed optimization remarks for this.
; REMARKS: Pass:            shrink-wrap
; REMARKS-NEXT: Name:            UnsupportedIrreducibleCFG
; REMARKS-NEXT: Function:        irreducibleCFG
; REMARKS-NEXT: Args:
; REMARKS-NEXT:   - String:          Irreducible CFGs are not supported yet

define i32 @irreducibleCFG() #4 {
entry:
  %i0 = load i32, i32* @irreducibleCFGa, align 4
  %.pr = load i8, i8* @irreducibleCFGf, align 1
  %bool = icmp eq i8 %.pr, 0
  br i1 %bool, label %split, label %preheader

preheader:
  br label %preheader

split:
  %i1 = load i32, i32* @irreducibleCFGb, align 4
  %tobool1.i = icmp ne i32 %i1, 0
  br i1 %tobool1.i, label %for.body4.i, label %for.cond8.i.preheader

for.body4.i:
  %call.i = tail call i32 (...) @something(i32 %i0)
  br label %for.cond8

for.cond8:
  %p1 = phi i32 [ %inc18.i, %for.inc ], [ 0, %for.body4.i ]
  %.pr1.pr = load i32, i32* @irreducibleCFGb, align 4
  br label %for.cond8.i.preheader

for.cond8.i.preheader:
  %.pr1 = phi i32 [ %.pr1.pr, %for.cond8 ], [ %i1, %split ]
  %p13 = phi i32 [ %p1, %for.cond8 ], [ 0, %split ]
  br label %for.inc

fn1.exit:
  ret i32 0

for.inc:
  %inc18.i = add nuw nsw i32 %p13, 1
  %cmp = icmp slt i32 %inc18.i, 7
  br i1 %cmp, label %for.cond8, label %fn1.exit
}

attributes #4 = { "no-frame-pointer-elim"="true" }

@x = external global i32, align 4
@y = external global i32, align 4

; The post-dominator tree does not include the branch containing the infinite
; loop, which can occur into a misplacement of the restore block, if we're
; looking for the nearest common post-dominator of an "unreachable" block.

; CHECK-LABEL: infiniteLoopNoSuccessor:
; CHECK: ## %bb.0:
; Make sure the prologue happens in the entry block.
; CHECK-NEXT: pushq %rbp
; ...
; Make sure we don't shrink-wrap.
; CHECK: ## %bb.1
; CHECK-NOT: pushq %rbp
; ...
; Make sure the epilogue happens in the exit block.
; CHECK: ## %bb.5
; CHECK: popq %rbp
; CHECK-NEXT: retq
define void @infiniteLoopNoSuccessor() #5 {
  %1 = load i32, i32* @x, align 4
  %2 = icmp ne i32 %1, 0
  br i1 %2, label %3, label %4

; <label>:3:
  store i32 0, i32* @x, align 4
  br label %4

; <label>:4:
  call void (...) @somethingElse()
  %5 = load i32, i32* @y, align 4
  %6 = icmp ne i32 %5, 0
  br i1 %6, label %10, label %7

; <label>:7:
  %8 = call i32 (...) @something()
  br label %9

; <label>:9:
  call void (...) @somethingElse()
  br label %9

; <label>:10:
  ret void
}

declare void @somethingElse(...)

attributes #5 = { nounwind  "no-frame-pointer-elim-non-leaf" }