llvm.org GIT mirror llvm / 0392724 lib / Target / AMDGPU / AMDGPUTargetMachine.cpp
0392724

Tree @0392724 (Download .tar.gz)

AMDGPUTargetMachine.cpp @0392724raw · 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
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
//===-- AMDGPUTargetMachine.cpp - TargetMachine for hw codegen targets-----===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
/// \file
/// The AMDGPU target machine contains all of the hardware specific
/// information  needed to emit code for R600 and SI GPUs.
//
//===----------------------------------------------------------------------===//

#include "AMDGPUTargetMachine.h"
#include "AMDGPU.h"
#include "AMDGPUAliasAnalysis.h"
#include "AMDGPUCallLowering.h"
#include "AMDGPUInstructionSelector.h"
#include "AMDGPULegalizerInfo.h"
#include "AMDGPUMacroFusion.h"
#include "AMDGPUTargetObjectFile.h"
#include "AMDGPUTargetTransformInfo.h"
#include "GCNIterativeScheduler.h"
#include "GCNSchedStrategy.h"
#include "R600MachineScheduler.h"
#include "SIMachineFunctionInfo.h"
#include "SIMachineScheduler.h"
#include "TargetInfo/AMDGPUTargetInfo.h"
#include "llvm/CodeGen/GlobalISel/IRTranslator.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelect.h"
#include "llvm/CodeGen/GlobalISel/Legalizer.h"
#include "llvm/CodeGen/GlobalISel/RegBankSelect.h"
#include "llvm/CodeGen/MIRParser/MIParser.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/IPO/AlwaysInliner.h"
#include "llvm/Transforms/IPO/PassManagerBuilder.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Scalar/GVN.h"
#include "llvm/Transforms/Utils.h"
#include "llvm/Transforms/Vectorize.h"
#include <memory>

using namespace llvm;

static cl::opt<bool> EnableR600StructurizeCFG(
  "r600-ir-structurize",
  cl::desc("Use StructurizeCFG IR pass"),
  cl::init(true));

static cl::opt<bool> EnableSROA(
  "amdgpu-sroa",
  cl::desc("Run SROA after promote alloca pass"),
  cl::ReallyHidden,
  cl::init(true));

static cl::opt<bool>
EnableEarlyIfConversion("amdgpu-early-ifcvt", cl::Hidden,
                        cl::desc("Run early if-conversion"),
                        cl::init(false));

static cl::opt<bool>
OptExecMaskPreRA("amdgpu-opt-exec-mask-pre-ra", cl::Hidden,
            cl::desc("Run pre-RA exec mask optimizations"),
            cl::init(true));

static cl::opt<bool> EnableR600IfConvert(
  "r600-if-convert",
  cl::desc("Use if conversion pass"),
  cl::ReallyHidden,
  cl::init(true));

// Option to disable vectorizer for tests.
static cl::opt<bool> EnableLoadStoreVectorizer(
  "amdgpu-load-store-vectorizer",
  cl::desc("Enable load store vectorizer"),
  cl::init(true),
  cl::Hidden);

// Option to control global loads scalarization
static cl::opt<bool> ScalarizeGlobal(
  "amdgpu-scalarize-global-loads",
  cl::desc("Enable global load scalarization"),
  cl::init(true),
  cl::Hidden);

// Option to run internalize pass.
static cl::opt<bool> InternalizeSymbols(
  "amdgpu-internalize-symbols",
  cl::desc("Enable elimination of non-kernel functions and unused globals"),
  cl::init(false),
  cl::Hidden);

// Option to inline all early.
static cl::opt<bool> EarlyInlineAll(
  "amdgpu-early-inline-all",
  cl::desc("Inline all functions early"),
  cl::init(false),
  cl::Hidden);

static cl::opt<bool> EnableSDWAPeephole(
  "amdgpu-sdwa-peephole",
  cl::desc("Enable SDWA peepholer"),
  cl::init(true));

static cl::opt<bool> EnableDPPCombine(
  "amdgpu-dpp-combine",
  cl::desc("Enable DPP combiner"),
  cl::init(true));

// Enable address space based alias analysis
static cl::opt<bool> EnableAMDGPUAliasAnalysis("enable-amdgpu-aa", cl::Hidden,
  cl::desc("Enable AMDGPU Alias Analysis"),
  cl::init(true));

// Option to run late CFG structurizer
static cl::opt<bool, true> LateCFGStructurize(
  "amdgpu-late-structurize",
  cl::desc("Enable late CFG structurization"),
  cl::location(AMDGPUTargetMachine::EnableLateStructurizeCFG),
  cl::Hidden);

static cl::opt<bool, true> EnableAMDGPUFunctionCallsOpt(
  "amdgpu-function-calls",
  cl::desc("Enable AMDGPU function call support"),
  cl::location(AMDGPUTargetMachine::EnableFunctionCalls),
  cl::init(true),
  cl::Hidden);

// Enable lib calls simplifications
static cl::opt<bool> EnableLibCallSimplify(
  "amdgpu-simplify-libcall",
  cl::desc("Enable amdgpu library simplifications"),
  cl::init(true),
  cl::Hidden);

static cl::opt<bool> EnableLowerKernelArguments(
  "amdgpu-ir-lower-kernel-arguments",
  cl::desc("Lower kernel argument loads in IR pass"),
  cl::init(true),
  cl::Hidden);

static cl::opt<bool> EnableRegReassign(
  "amdgpu-reassign-regs",
  cl::desc("Enable register reassign optimizations on gfx10+"),
  cl::init(true),
  cl::Hidden);

// Enable atomic optimization
static cl::opt<bool> EnableAtomicOptimizations(
  "amdgpu-atomic-optimizations",
  cl::desc("Enable atomic optimizations"),
  cl::init(false),
  cl::Hidden);

// Enable Mode register optimization
static cl::opt<bool> EnableSIModeRegisterPass(
  "amdgpu-mode-register",
  cl::desc("Enable mode register pass"),
  cl::init(true),
  cl::Hidden);

// Option is used in lit tests to prevent deadcoding of patterns inspected.
static cl::opt<bool>
EnableDCEInRA("amdgpu-dce-in-ra",
    cl::init(true), cl::Hidden,
    cl::desc("Enable machine DCE inside regalloc"));

static cl::opt<bool> EnableScalarIRPasses(
  "amdgpu-scalar-ir-passes",
  cl::desc("Enable scalar IR passes"),
  cl::init(true),
  cl::Hidden);

extern "C" void LLVMInitializeAMDGPUTarget() {
  // Register the target
  RegisterTargetMachine<R600TargetMachine> X(getTheAMDGPUTarget());
  RegisterTargetMachine<GCNTargetMachine> Y(getTheGCNTarget());

  PassRegistry *PR = PassRegistry::getPassRegistry();
  initializeR600ClauseMergePassPass(*PR);
  initializeR600ControlFlowFinalizerPass(*PR);
  initializeR600PacketizerPass(*PR);
  initializeR600ExpandSpecialInstrsPassPass(*PR);
  initializeR600VectorRegMergerPass(*PR);
  initializeGlobalISel(*PR);
  initializeAMDGPUDAGToDAGISelPass(*PR);
  initializeGCNDPPCombinePass(*PR);
  initializeSILowerI1CopiesPass(*PR);
  initializeSILowerSGPRSpillsPass(*PR);
  initializeSIFixSGPRCopiesPass(*PR);
  initializeSIFixVGPRCopiesPass(*PR);
  initializeSIFixupVectorISelPass(*PR);
  initializeSIFoldOperandsPass(*PR);
  initializeSIPeepholeSDWAPass(*PR);
  initializeSIShrinkInstructionsPass(*PR);
  initializeSIOptimizeExecMaskingPreRAPass(*PR);
  initializeSILoadStoreOptimizerPass(*PR);
  initializeAMDGPUFixFunctionBitcastsPass(*PR);
  initializeAMDGPUAlwaysInlinePass(*PR);
  initializeAMDGPUAnnotateKernelFeaturesPass(*PR);
  initializeAMDGPUAnnotateUniformValuesPass(*PR);
  initializeAMDGPUArgumentUsageInfoPass(*PR);
  initializeAMDGPUAtomicOptimizerPass(*PR);
  initializeAMDGPULowerKernelArgumentsPass(*PR);
  initializeAMDGPULowerKernelAttributesPass(*PR);
  initializeAMDGPULowerIntrinsicsPass(*PR);
  initializeAMDGPUOpenCLEnqueuedBlockLoweringPass(*PR);
  initializeAMDGPUPromoteAllocaPass(*PR);
  initializeAMDGPUCodeGenPreparePass(*PR);
  initializeAMDGPUPropagateAttributesEarlyPass(*PR);
  initializeAMDGPUPropagateAttributesLatePass(*PR);
  initializeAMDGPURewriteOutArgumentsPass(*PR);
  initializeAMDGPUUnifyMetadataPass(*PR);
  initializeSIAnnotateControlFlowPass(*PR);
  initializeSIInsertWaitcntsPass(*PR);
  initializeSIModeRegisterPass(*PR);
  initializeSIWholeQuadModePass(*PR);
  initializeSILowerControlFlowPass(*PR);
  initializeSIInsertSkipsPass(*PR);
  initializeSIMemoryLegalizerPass(*PR);
  initializeSIOptimizeExecMaskingPass(*PR);
  initializeSIPreAllocateWWMRegsPass(*PR);
  initializeSIFormMemoryClausesPass(*PR);
  initializeAMDGPUUnifyDivergentExitNodesPass(*PR);
  initializeAMDGPUAAWrapperPassPass(*PR);
  initializeAMDGPUExternalAAWrapperPass(*PR);
  initializeAMDGPUUseNativeCallsPass(*PR);
  initializeAMDGPUSimplifyLibCallsPass(*PR);
  initializeAMDGPUInlinerPass(*PR);
  initializeGCNRegBankReassignPass(*PR);
  initializeGCNNSAReassignPass(*PR);
}

static std::unique_ptr<TargetLoweringObjectFile> createTLOF(const Triple &TT) {
  return llvm::make_unique<AMDGPUTargetObjectFile>();
}

static ScheduleDAGInstrs *createR600MachineScheduler(MachineSchedContext *C) {
  return new ScheduleDAGMILive(C, llvm::make_unique<R600SchedStrategy>());
}

static ScheduleDAGInstrs *createSIMachineScheduler(MachineSchedContext *C) {
  return new SIScheduleDAGMI(C);
}

static ScheduleDAGInstrs *
createGCNMaxOccupancyMachineScheduler(MachineSchedContext *C) {
  ScheduleDAGMILive *DAG =
    new GCNScheduleDAGMILive(C, make_unique<GCNMaxOccupancySchedStrategy>(C));
  DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
  DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
  DAG->addMutation(createAMDGPUMacroFusionDAGMutation());
  return DAG;
}

static ScheduleDAGInstrs *
createIterativeGCNMaxOccupancyMachineScheduler(MachineSchedContext *C) {
  auto DAG = new GCNIterativeScheduler(C,
    GCNIterativeScheduler::SCHEDULE_LEGACYMAXOCCUPANCY);
  DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
  DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
  return DAG;
}

static ScheduleDAGInstrs *createMinRegScheduler(MachineSchedContext *C) {
  return new GCNIterativeScheduler(C,
    GCNIterativeScheduler::SCHEDULE_MINREGFORCED);
}

static ScheduleDAGInstrs *
createIterativeILPMachineScheduler(MachineSchedContext *C) {
  auto DAG = new GCNIterativeScheduler(C,
    GCNIterativeScheduler::SCHEDULE_ILP);
  DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
  DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
  DAG->addMutation(createAMDGPUMacroFusionDAGMutation());
  return DAG;
}

static MachineSchedRegistry
R600SchedRegistry("r600", "Run R600's custom scheduler",
                   createR600MachineScheduler);

static MachineSchedRegistry
SISchedRegistry("si", "Run SI's custom scheduler",
                createSIMachineScheduler);

static MachineSchedRegistry
GCNMaxOccupancySchedRegistry("gcn-max-occupancy",
                             "Run GCN scheduler to maximize occupancy",
                             createGCNMaxOccupancyMachineScheduler);

static MachineSchedRegistry
IterativeGCNMaxOccupancySchedRegistry("gcn-max-occupancy-experimental",
  "Run GCN scheduler to maximize occupancy (experimental)",
  createIterativeGCNMaxOccupancyMachineScheduler);

static MachineSchedRegistry
GCNMinRegSchedRegistry("gcn-minreg",
  "Run GCN iterative scheduler for minimal register usage (experimental)",
  createMinRegScheduler);

static MachineSchedRegistry
GCNILPSchedRegistry("gcn-ilp",
  "Run GCN iterative scheduler for ILP scheduling (experimental)",
  createIterativeILPMachineScheduler);

static StringRef computeDataLayout(const Triple &TT) {
  if (TT.getArch() == Triple::r600) {
    // 32-bit pointers.
      return "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
             "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5";
  }

  // 32-bit private, local, and region pointers. 64-bit global, constant and
  // flat, non-integral buffer fat pointers.
    return "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32"
         "-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
         "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"
         "-ni:7";
}

LLVM_READNONE
static StringRef getGPUOrDefault(const Triple &TT, StringRef GPU) {
  if (!GPU.empty())
    return GPU;

  // Need to default to a target with flat support for HSA.
  if (TT.getArch() == Triple::amdgcn)
    return TT.getOS() == Triple::AMDHSA ? "generic-hsa" : "generic";

  return "r600";
}

static Reloc::Model getEffectiveRelocModel(Optional<Reloc::Model> RM) {
  // The AMDGPU toolchain only supports generating shared objects, so we
  // must always use PIC.
  return Reloc::PIC_;
}

AMDGPUTargetMachine::AMDGPUTargetMachine(const Target &T, const Triple &TT,
                                         StringRef CPU, StringRef FS,
                                         TargetOptions Options,
                                         Optional<Reloc::Model> RM,
                                         Optional<CodeModel::Model> CM,
                                         CodeGenOpt::Level OptLevel)
    : LLVMTargetMachine(T, computeDataLayout(TT), TT, getGPUOrDefault(TT, CPU),
                        FS, Options, getEffectiveRelocModel(RM),
                        getEffectiveCodeModel(CM, CodeModel::Small), OptLevel),
      TLOF(createTLOF(getTargetTriple())) {
  initAsmInfo();
}

bool AMDGPUTargetMachine::EnableLateStructurizeCFG = false;
bool AMDGPUTargetMachine::EnableFunctionCalls = false;

AMDGPUTargetMachine::~AMDGPUTargetMachine() = default;

StringRef AMDGPUTargetMachine::getGPUName(const Function &F) const {
  Attribute GPUAttr = F.getFnAttribute("target-cpu");
  return GPUAttr.hasAttribute(Attribute::None) ?
    getTargetCPU() : GPUAttr.getValueAsString();
}

StringRef AMDGPUTargetMachine::getFeatureString(const Function &F) const {
  Attribute FSAttr = F.getFnAttribute("target-features");

  return FSAttr.hasAttribute(Attribute::None) ?
    getTargetFeatureString() :
    FSAttr.getValueAsString();
}

/// Predicate for Internalize pass.
static bool mustPreserveGV(const GlobalValue &GV) {
  if (const Function *F = dyn_cast<Function>(&GV))
    return F->isDeclaration() || AMDGPU::isEntryFunctionCC(F->getCallingConv());

  return !GV.use_empty();
}

void AMDGPUTargetMachine::adjustPassManager(PassManagerBuilder &Builder) {
  Builder.DivergentTarget = true;

  bool EnableOpt = getOptLevel() > CodeGenOpt::None;
  bool Internalize = InternalizeSymbols;
  bool EarlyInline = EarlyInlineAll && EnableOpt && !EnableFunctionCalls;
  bool AMDGPUAA = EnableAMDGPUAliasAnalysis && EnableOpt;
  bool LibCallSimplify = EnableLibCallSimplify && EnableOpt;

  if (EnableFunctionCalls) {
    delete Builder.Inliner;
    Builder.Inliner = createAMDGPUFunctionInliningPass();
  }

  Builder.addExtension(
    PassManagerBuilder::EP_ModuleOptimizerEarly,
    [Internalize, EarlyInline, AMDGPUAA, this](const PassManagerBuilder &,
                                               legacy::PassManagerBase &PM) {
      if (AMDGPUAA) {
        PM.add(createAMDGPUAAWrapperPass());
        PM.add(createAMDGPUExternalAAWrapperPass());
      }
      PM.add(createAMDGPUUnifyMetadataPass());
      PM.add(createAMDGPUPropagateAttributesLatePass(this));
      if (Internalize) {
        PM.add(createInternalizePass(mustPreserveGV));
        PM.add(createGlobalDCEPass());
      }
      if (EarlyInline)
        PM.add(createAMDGPUAlwaysInlinePass(false));
  });

  const auto &Opt = Options;
  Builder.addExtension(
    PassManagerBuilder::EP_EarlyAsPossible,
    [AMDGPUAA, LibCallSimplify, &Opt, this](const PassManagerBuilder &,
                                            legacy::PassManagerBase &PM) {
      if (AMDGPUAA) {
        PM.add(createAMDGPUAAWrapperPass());
        PM.add(createAMDGPUExternalAAWrapperPass());
      }
      PM.add(llvm::createAMDGPUPropagateAttributesEarlyPass(this));
      PM.add(llvm::createAMDGPUUseNativeCallsPass());
      if (LibCallSimplify)
        PM.add(llvm::createAMDGPUSimplifyLibCallsPass(Opt, this));
  });

  Builder.addExtension(
    PassManagerBuilder::EP_CGSCCOptimizerLate,
    [](const PassManagerBuilder &, legacy::PassManagerBase &PM) {
      // Add infer address spaces pass to the opt pipeline after inlining
      // but before SROA to increase SROA opportunities.
      PM.add(createInferAddressSpacesPass());

      // This should run after inlining to have any chance of doing anything,
      // and before other cleanup optimizations.
      PM.add(createAMDGPULowerKernelAttributesPass());
  });
}

//===----------------------------------------------------------------------===//
// R600 Target Machine (R600 -> Cayman)
//===----------------------------------------------------------------------===//

R600TargetMachine::R600TargetMachine(const Target &T, const Triple &TT,
                                     StringRef CPU, StringRef FS,
                                     TargetOptions Options,
                                     Optional<Reloc::Model> RM,
                                     Optional<CodeModel::Model> CM,
                                     CodeGenOpt::Level OL, bool JIT)
    : AMDGPUTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL) {
  setRequiresStructuredCFG(true);

  // Override the default since calls aren't supported for r600.
  if (EnableFunctionCalls &&
      EnableAMDGPUFunctionCallsOpt.getNumOccurrences() == 0)
    EnableFunctionCalls = false;
}

const R600Subtarget *R600TargetMachine::getSubtargetImpl(
  const Function &F) const {
  StringRef GPU = getGPUName(F);
  StringRef FS = getFeatureString(F);

  SmallString<128> SubtargetKey(GPU);
  SubtargetKey.append(FS);

  auto &I = SubtargetMap[SubtargetKey];
  if (!I) {
    // This needs to be done before we create a new subtarget since any
    // creation will depend on the TM and the code generation flags on the
    // function that reside in TargetOptions.
    resetTargetOptions(F);
    I = llvm::make_unique<R600Subtarget>(TargetTriple, GPU, FS, *this);
  }

  return I.get();
}

TargetTransformInfo
R600TargetMachine::getTargetTransformInfo(const Function &F) {
  return TargetTransformInfo(R600TTIImpl(this, F));
}

//===----------------------------------------------------------------------===//
// GCN Target Machine (SI+)
//===----------------------------------------------------------------------===//

GCNTargetMachine::GCNTargetMachine(const Target &T, const Triple &TT,
                                   StringRef CPU, StringRef FS,
                                   TargetOptions Options,
                                   Optional<Reloc::Model> RM,
                                   Optional<CodeModel::Model> CM,
                                   CodeGenOpt::Level OL, bool JIT)
    : AMDGPUTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL) {}

const GCNSubtarget *GCNTargetMachine::getSubtargetImpl(const Function &F) const {
  StringRef GPU = getGPUName(F);
  StringRef FS = getFeatureString(F);

  SmallString<128> SubtargetKey(GPU);
  SubtargetKey.append(FS);

  auto &I = SubtargetMap[SubtargetKey];
  if (!I) {
    // This needs to be done before we create a new subtarget since any
    // creation will depend on the TM and the code generation flags on the
    // function that reside in TargetOptions.
    resetTargetOptions(F);
    I = llvm::make_unique<GCNSubtarget>(TargetTriple, GPU, FS, *this);
  }

  I->setScalarizeGlobalBehavior(ScalarizeGlobal);

  return I.get();
}

TargetTransformInfo
GCNTargetMachine::getTargetTransformInfo(const Function &F) {
  return TargetTransformInfo(GCNTTIImpl(this, F));
}

//===----------------------------------------------------------------------===//
// AMDGPU Pass Setup
//===----------------------------------------------------------------------===//

namespace {

class AMDGPUPassConfig : public TargetPassConfig {
public:
  AMDGPUPassConfig(LLVMTargetMachine &TM, PassManagerBase &PM)
    : TargetPassConfig(TM, PM) {
    // Exceptions and StackMaps are not supported, so these passes will never do
    // anything.
    disablePass(&StackMapLivenessID);
    disablePass(&FuncletLayoutID);
  }

  AMDGPUTargetMachine &getAMDGPUTargetMachine() const {
    return getTM<AMDGPUTargetMachine>();
  }

  ScheduleDAGInstrs *
  createMachineScheduler(MachineSchedContext *C) const override {
    ScheduleDAGMILive *DAG = createGenericSchedLive(C);
    DAG->addMutation(createLoadClusterDAGMutation(DAG->TII, DAG->TRI));
    DAG->addMutation(createStoreClusterDAGMutation(DAG->TII, DAG->TRI));
    return DAG;
  }

  void addEarlyCSEOrGVNPass();
  void addStraightLineScalarOptimizationPasses();
  void addIRPasses() override;
  void addCodeGenPrepare() override;
  bool addPreISel() override;
  bool addInstSelector() override;
  bool addGCPasses() override;

  std::unique_ptr<CSEConfigBase> getCSEConfig() const override;
};

std::unique_ptr<CSEConfigBase> AMDGPUPassConfig::getCSEConfig() const {
  return getStandardCSEConfigForOpt(TM->getOptLevel());
}

class R600PassConfig final : public AMDGPUPassConfig {
public:
  R600PassConfig(LLVMTargetMachine &TM, PassManagerBase &PM)
    : AMDGPUPassConfig(TM, PM) {}

  ScheduleDAGInstrs *createMachineScheduler(
    MachineSchedContext *C) const override {
    return createR600MachineScheduler(C);
  }

  bool addPreISel() override;
  bool addInstSelector() override;
  void addPreRegAlloc() override;
  void addPreSched2() override;
  void addPreEmitPass() override;
};

class GCNPassConfig final : public AMDGPUPassConfig {
public:
  GCNPassConfig(LLVMTargetMachine &TM, PassManagerBase &PM)
    : AMDGPUPassConfig(TM, PM) {
    // It is necessary to know the register usage of the entire call graph.  We
    // allow calls without EnableAMDGPUFunctionCalls if they are marked
    // noinline, so this is always required.
    setRequiresCodeGenSCCOrder(true);
  }

  GCNTargetMachine &getGCNTargetMachine() const {
    return getTM<GCNTargetMachine>();
  }

  ScheduleDAGInstrs *
  createMachineScheduler(MachineSchedContext *C) const override;

  bool addPreISel() override;
  void addMachineSSAOptimization() override;
  bool addILPOpts() override;
  bool addInstSelector() override;
  bool addIRTranslator() override;
  bool addLegalizeMachineIR() override;
  bool addRegBankSelect() override;
  bool addGlobalInstructionSelect() override;
  void addFastRegAlloc() override;
  void addOptimizedRegAlloc() override;
  void addPreRegAlloc() override;
  bool addPreRewrite() override;
  void addPostRegAlloc() override;
  void addPreSched2() override;
  void addPreEmitPass() override;
};

} // end anonymous namespace

void AMDGPUPassConfig::addEarlyCSEOrGVNPass() {
  if (getOptLevel() == CodeGenOpt::Aggressive)
    addPass(createGVNPass());
  else
    addPass(createEarlyCSEPass());
}

void AMDGPUPassConfig::addStraightLineScalarOptimizationPasses() {
  addPass(createLICMPass());
  addPass(createSeparateConstOffsetFromGEPPass());
  addPass(createSpeculativeExecutionPass());
  // ReassociateGEPs exposes more opportunites for SLSR. See
  // the example in reassociate-geps-and-slsr.ll.
  addPass(createStraightLineStrengthReducePass());
  // SeparateConstOffsetFromGEP and SLSR creates common expressions which GVN or
  // EarlyCSE can reuse.
  addEarlyCSEOrGVNPass();
  // Run NaryReassociate after EarlyCSE/GVN to be more effective.
  addPass(createNaryReassociatePass());
  // NaryReassociate on GEPs creates redundant common expressions, so run
  // EarlyCSE after it.
  addPass(createEarlyCSEPass());
}

void AMDGPUPassConfig::addIRPasses() {
  const AMDGPUTargetMachine &TM = getAMDGPUTargetMachine();

  // There is no reason to run these.
  disablePass(&StackMapLivenessID);
  disablePass(&FuncletLayoutID);
  disablePass(&PatchableFunctionID);

  // This must occur before inlining, as the inliner will not look through
  // bitcast calls.
  addPass(createAMDGPUFixFunctionBitcastsPass());

  // A call to propagate attributes pass in the backend in case opt was not run.
  addPass(createAMDGPUPropagateAttributesEarlyPass(&TM));

  addPass(createAtomicExpandPass());


  addPass(createAMDGPULowerIntrinsicsPass());

  // Function calls are not supported, so make sure we inline everything.
  addPass(createAMDGPUAlwaysInlinePass());
  addPass(createAlwaysInlinerLegacyPass());
  // We need to add the barrier noop pass, otherwise adding the function
  // inlining pass will cause all of the PassConfigs passes to be run
  // one function at a time, which means if we have a nodule with two
  // functions, then we will generate code for the first function
  // without ever running any passes on the second.
  addPass(createBarrierNoopPass());

  if (TM.getTargetTriple().getArch() == Triple::amdgcn) {
    // TODO: May want to move later or split into an early and late one.

    addPass(createAMDGPUCodeGenPreparePass());
  }

  // Handle uses of OpenCL image2d_t, image3d_t and sampler_t arguments.
  if (TM.getTargetTriple().getArch() == Triple::r600)
    addPass(createR600OpenCLImageTypeLoweringPass());

  // Replace OpenCL enqueued block function pointers with global variables.
  addPass(createAMDGPUOpenCLEnqueuedBlockLoweringPass());

  if (TM.getOptLevel() > CodeGenOpt::None) {
    addPass(createInferAddressSpacesPass());
    addPass(createAMDGPUPromoteAlloca());

    if (EnableSROA)
      addPass(createSROAPass());

    if (EnableScalarIRPasses)
      addStraightLineScalarOptimizationPasses();

    if (EnableAMDGPUAliasAnalysis) {
      addPass(createAMDGPUAAWrapperPass());
      addPass(createExternalAAWrapperPass([](Pass &P, Function &,
                                             AAResults &AAR) {
        if (auto *WrapperPass = P.getAnalysisIfAvailable<AMDGPUAAWrapperPass>())
          AAR.addAAResult(WrapperPass->getResult());
        }));
    }
  }

  TargetPassConfig::addIRPasses();

  // EarlyCSE is not always strong enough to clean up what LSR produces. For
  // example, GVN can combine
  //
  //   %0 = add %a, %b
  //   %1 = add %b, %a
  //
  // and
  //
  //   %0 = shl nsw %a, 2
  //   %1 = shl %a, 2
  //
  // but EarlyCSE can do neither of them.
  if (getOptLevel() != CodeGenOpt::None && EnableScalarIRPasses)
    addEarlyCSEOrGVNPass();
}

void AMDGPUPassConfig::addCodeGenPrepare() {
  if (TM->getTargetTriple().getArch() == Triple::amdgcn)
    addPass(createAMDGPUAnnotateKernelFeaturesPass());

  if (TM->getTargetTriple().getArch() == Triple::amdgcn &&
      EnableLowerKernelArguments)
    addPass(createAMDGPULowerKernelArgumentsPass());

  addPass(&AMDGPUPerfHintAnalysisID);

  TargetPassConfig::addCodeGenPrepare();

  if (EnableLoadStoreVectorizer)
    addPass(createLoadStoreVectorizerPass());
}

bool AMDGPUPassConfig::addPreISel() {
  addPass(createLowerSwitchPass());
  addPass(createFlattenCFGPass());
  return false;
}

bool AMDGPUPassConfig::addInstSelector() {
  // Defer the verifier until FinalizeISel.
  addPass(createAMDGPUISelDag(&getAMDGPUTargetMachine(), getOptLevel()), false);
  return false;
}

bool AMDGPUPassConfig::addGCPasses() {
  // Do nothing. GC is not supported.
  return false;
}

//===----------------------------------------------------------------------===//
// R600 Pass Setup
//===----------------------------------------------------------------------===//

bool R600PassConfig::addPreISel() {
  AMDGPUPassConfig::addPreISel();

  if (EnableR600StructurizeCFG)
    addPass(createStructurizeCFGPass());
  return false;
}

bool R600PassConfig::addInstSelector() {
  addPass(createR600ISelDag(&getAMDGPUTargetMachine(), getOptLevel()));
  return false;
}

void R600PassConfig::addPreRegAlloc() {
  addPass(createR600VectorRegMerger());
}

void R600PassConfig::addPreSched2() {
  addPass(createR600EmitClauseMarkers(), false);
  if (EnableR600IfConvert)
    addPass(&IfConverterID, false);
  addPass(createR600ClauseMergePass(), false);
}

void R600PassConfig::addPreEmitPass() {
  addPass(createAMDGPUCFGStructurizerPass(), false);
  addPass(createR600ExpandSpecialInstrsPass(), false);
  addPass(&FinalizeMachineBundlesID, false);
  addPass(createR600Packetizer(), false);
  addPass(createR600ControlFlowFinalizer(), false);
}

TargetPassConfig *R600TargetMachine::createPassConfig(PassManagerBase &PM) {
  return new R600PassConfig(*this, PM);
}

//===----------------------------------------------------------------------===//
// GCN Pass Setup
//===----------------------------------------------------------------------===//

ScheduleDAGInstrs *GCNPassConfig::createMachineScheduler(
  MachineSchedContext *C) const {
  const GCNSubtarget &ST = C->MF->getSubtarget<GCNSubtarget>();
  if (ST.enableSIScheduler())
    return createSIMachineScheduler(C);
  return createGCNMaxOccupancyMachineScheduler(C);
}

bool GCNPassConfig::addPreISel() {
  AMDGPUPassConfig::addPreISel();

  if (EnableAtomicOptimizations) {
    addPass(createAMDGPUAtomicOptimizerPass());
  }

  // FIXME: We need to run a pass to propagate the attributes when calls are
  // supported.

  // Merge divergent exit nodes. StructurizeCFG won't recognize the multi-exit
  // regions formed by them.
  addPass(&AMDGPUUnifyDivergentExitNodesID);
  if (!LateCFGStructurize) {
    addPass(createStructurizeCFGPass(true)); // true -> SkipUniformRegions
  }
  addPass(createSinkingPass());
  addPass(createAMDGPUAnnotateUniformValues());
  if (!LateCFGStructurize) {
    addPass(createSIAnnotateControlFlowPass());
  }
  addPass(createLCSSAPass());

  return false;
}

void GCNPassConfig::addMachineSSAOptimization() {
  TargetPassConfig::addMachineSSAOptimization();

  // We want to fold operands after PeepholeOptimizer has run (or as part of
  // it), because it will eliminate extra copies making it easier to fold the
  // real source operand. We want to eliminate dead instructions after, so that
  // we see fewer uses of the copies. We then need to clean up the dead
  // instructions leftover after the operands are folded as well.
  //
  // XXX - Can we get away without running DeadMachineInstructionElim again?
  addPass(&SIFoldOperandsID);
  if (EnableDPPCombine)
    addPass(&GCNDPPCombineID);
  addPass(&DeadMachineInstructionElimID);
  addPass(&SILoadStoreOptimizerID);
  if (EnableSDWAPeephole) {
    addPass(&SIPeepholeSDWAID);
    addPass(&EarlyMachineLICMID);
    addPass(&MachineCSEID);
    addPass(&SIFoldOperandsID);
    addPass(&DeadMachineInstructionElimID);
  }
  addPass(createSIShrinkInstructionsPass());
}

bool GCNPassConfig::addILPOpts() {
  if (EnableEarlyIfConversion)
    addPass(&EarlyIfConverterID);

  TargetPassConfig::addILPOpts();
  return false;
}

bool GCNPassConfig::addInstSelector() {
  AMDGPUPassConfig::addInstSelector();
  addPass(&SIFixSGPRCopiesID);
  addPass(createSILowerI1CopiesPass());
  addPass(createSIFixupVectorISelPass());
  addPass(createSIAddIMGInitPass());
  return false;
}

bool GCNPassConfig::addIRTranslator() {
  addPass(new IRTranslator());
  return false;
}

bool GCNPassConfig::addLegalizeMachineIR() {
  addPass(new Legalizer());
  return false;
}

bool GCNPassConfig::addRegBankSelect() {
  addPass(new RegBankSelect());
  return false;
}

bool GCNPassConfig::addGlobalInstructionSelect() {
  addPass(new InstructionSelect());
  return false;
}

void GCNPassConfig::addPreRegAlloc() {
  if (LateCFGStructurize) {
    addPass(createAMDGPUMachineCFGStructurizerPass());
  }
  addPass(createSIWholeQuadModePass());
}

void GCNPassConfig::addFastRegAlloc() {
  // FIXME: We have to disable the verifier here because of PHIElimination +
  // TwoAddressInstructions disabling it.

  // This must be run immediately after phi elimination and before
  // TwoAddressInstructions, otherwise the processing of the tied operand of
  // SI_ELSE will introduce a copy of the tied operand source after the else.
  insertPass(&PHIEliminationID, &SILowerControlFlowID, false);

  // This must be run just after RegisterCoalescing.
  insertPass(&RegisterCoalescerID, &SIPreAllocateWWMRegsID, false);

  TargetPassConfig::addFastRegAlloc();
}

void GCNPassConfig::addOptimizedRegAlloc() {
  if (OptExecMaskPreRA) {
    insertPass(&MachineSchedulerID, &SIOptimizeExecMaskingPreRAID);
    insertPass(&SIOptimizeExecMaskingPreRAID, &SIFormMemoryClausesID);
  } else {
    insertPass(&MachineSchedulerID, &SIFormMemoryClausesID);
  }

  // This must be run immediately after phi elimination and before
  // TwoAddressInstructions, otherwise the processing of the tied operand of
  // SI_ELSE will introduce a copy of the tied operand source after the else.
  insertPass(&PHIEliminationID, &SILowerControlFlowID, false);

  // This must be run just after RegisterCoalescing.
  insertPass(&RegisterCoalescerID, &SIPreAllocateWWMRegsID, false);

  if (EnableDCEInRA)
    insertPass(&RenameIndependentSubregsID, &DeadMachineInstructionElimID);

  TargetPassConfig::addOptimizedRegAlloc();
}

bool GCNPassConfig::addPreRewrite() {
  if (EnableRegReassign) {
    addPass(&GCNNSAReassignID);
    addPass(&GCNRegBankReassignID);
  }
  return true;
}

void GCNPassConfig::addPostRegAlloc() {
  addPass(&SIFixVGPRCopiesID);
  if (getOptLevel() > CodeGenOpt::None)
    addPass(&SIOptimizeExecMaskingID);
  TargetPassConfig::addPostRegAlloc();

  // Equivalent of PEI for SGPRs.
  addPass(&SILowerSGPRSpillsID);
}

void GCNPassConfig::addPreSched2() {
}

void GCNPassConfig::addPreEmitPass() {
  addPass(createSIMemoryLegalizerPass());
  addPass(createSIInsertWaitcntsPass());
  addPass(createSIShrinkInstructionsPass());
  addPass(createSIModeRegisterPass());

  // The hazard recognizer that runs as part of the post-ra scheduler does not
  // guarantee to be able handle all hazards correctly. This is because if there
  // are multiple scheduling regions in a basic block, the regions are scheduled
  // bottom up, so when we begin to schedule a region we don't know what
  // instructions were emitted directly before it.
  //
  // Here we add a stand-alone hazard recognizer pass which can handle all
  // cases.
  //
  // FIXME: This stand-alone pass will emit indiv. S_NOP 0, as needed. It would
  // be better for it to emit S_NOP <N> when possible.
  addPass(&PostRAHazardRecognizerID);

  addPass(&SIInsertSkipsPassID);
  addPass(&BranchRelaxationPassID);
}

TargetPassConfig *GCNTargetMachine::createPassConfig(PassManagerBase &PM) {
  return new GCNPassConfig(*this, PM);
}

yaml::MachineFunctionInfo *GCNTargetMachine::createDefaultFuncInfoYAML() const {
  return new yaml::SIMachineFunctionInfo();
}

yaml::MachineFunctionInfo *
GCNTargetMachine::convertFuncInfoToYAML(const MachineFunction &MF) const {
  const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
  return new yaml::SIMachineFunctionInfo(*MFI,
                                         *MF.getSubtarget().getRegisterInfo());
}

bool GCNTargetMachine::parseMachineFunctionInfo(
    const yaml::MachineFunctionInfo &MFI_, PerFunctionMIParsingState &PFS,
    SMDiagnostic &Error, SMRange &SourceRange) const {
  const yaml::SIMachineFunctionInfo &YamlMFI =
      reinterpret_cast<const yaml::SIMachineFunctionInfo &>(MFI_);
  MachineFunction &MF = PFS.MF;
  SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();

  MFI->initializeBaseYamlFields(YamlMFI);

  auto parseRegister = [&](const yaml::StringValue &RegName, unsigned &RegVal) {
    if (parseNamedRegisterReference(PFS, RegVal, RegName.Value, Error)) {
      SourceRange = RegName.SourceRange;
      return true;
    }

    return false;
  };

  auto diagnoseRegisterClass = [&](const yaml::StringValue &RegName) {
    // Create a diagnostic for a the register string literal.
    const MemoryBuffer &Buffer =
        *PFS.SM->getMemoryBuffer(PFS.SM->getMainFileID());
    Error = SMDiagnostic(*PFS.SM, SMLoc(), Buffer.getBufferIdentifier(), 1,
                         RegName.Value.size(), SourceMgr::DK_Error,
                         "incorrect register class for field", RegName.Value,
                         None, None);
    SourceRange = RegName.SourceRange;
    return true;
  };

  if (parseRegister(YamlMFI.ScratchRSrcReg, MFI->ScratchRSrcReg) ||
      parseRegister(YamlMFI.ScratchWaveOffsetReg, MFI->ScratchWaveOffsetReg) ||
      parseRegister(YamlMFI.FrameOffsetReg, MFI->FrameOffsetReg) ||
      parseRegister(YamlMFI.StackPtrOffsetReg, MFI->StackPtrOffsetReg))
    return true;

  if (MFI->ScratchRSrcReg != AMDGPU::PRIVATE_RSRC_REG &&
      !AMDGPU::SReg_128RegClass.contains(MFI->ScratchRSrcReg)) {
    return diagnoseRegisterClass(YamlMFI.ScratchRSrcReg);
  }

  if (MFI->ScratchWaveOffsetReg != AMDGPU::SCRATCH_WAVE_OFFSET_REG &&
      !AMDGPU::SGPR_32RegClass.contains(MFI->ScratchWaveOffsetReg)) {
    return diagnoseRegisterClass(YamlMFI.ScratchWaveOffsetReg);
  }

  if (MFI->FrameOffsetReg != AMDGPU::FP_REG &&
      !AMDGPU::SGPR_32RegClass.contains(MFI->FrameOffsetReg)) {
    return diagnoseRegisterClass(YamlMFI.FrameOffsetReg);
  }

  if (MFI->StackPtrOffsetReg != AMDGPU::SP_REG &&
      !AMDGPU::SGPR_32RegClass.contains(MFI->StackPtrOffsetReg)) {
    return diagnoseRegisterClass(YamlMFI.StackPtrOffsetReg);
  }

  auto parseAndCheckArgument = [&](const Optional<yaml::SIArgument> &A,
                                   const TargetRegisterClass &RC,
                                   ArgDescriptor &Arg) {
    // Skip parsing if it's not present.
    if (!A)
      return false;

    if (A->IsRegister) {
      unsigned Reg;
      if (parseNamedRegisterReference(PFS, Reg, A->RegisterName.Value,
                                      Error)) {
        SourceRange = A->RegisterName.SourceRange;
        return true;
      }
      if (!RC.contains(Reg))
        return diagnoseRegisterClass(A->RegisterName);
      Arg = ArgDescriptor::createRegister(Reg);
    } else
      Arg = ArgDescriptor::createStack(A->StackOffset);
    // Check and apply the optional mask.
    if (A->Mask)
      Arg = ArgDescriptor::createArg(Arg, A->Mask.getValue());

    return false;
  };

  if (YamlMFI.ArgInfo &&
      (parseAndCheckArgument(YamlMFI.ArgInfo->PrivateSegmentBuffer,
                             AMDGPU::SReg_128RegClass,
                             MFI->ArgInfo.PrivateSegmentBuffer) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->DispatchPtr,
                             AMDGPU::SReg_64RegClass,
                             MFI->ArgInfo.DispatchPtr) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->QueuePtr, AMDGPU::SReg_64RegClass,
                             MFI->ArgInfo.QueuePtr) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->KernargSegmentPtr,
                             AMDGPU::SReg_64RegClass,
                             MFI->ArgInfo.KernargSegmentPtr) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->DispatchID,
                             AMDGPU::SReg_64RegClass,
                             MFI->ArgInfo.DispatchID) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->FlatScratchInit,
                             AMDGPU::SReg_64RegClass,
                             MFI->ArgInfo.FlatScratchInit) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->PrivateSegmentSize,
                             AMDGPU::SGPR_32RegClass,
                             MFI->ArgInfo.PrivateSegmentSize) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->WorkGroupIDX,
                             AMDGPU::SGPR_32RegClass,
                             MFI->ArgInfo.WorkGroupIDX) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->WorkGroupIDY,
                             AMDGPU::SGPR_32RegClass,
                             MFI->ArgInfo.WorkGroupIDY) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->WorkGroupIDZ,
                             AMDGPU::SGPR_32RegClass,
                             MFI->ArgInfo.WorkGroupIDZ) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->WorkGroupInfo,
                             AMDGPU::SGPR_32RegClass,
                             MFI->ArgInfo.WorkGroupInfo) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->PrivateSegmentWaveByteOffset,
                             AMDGPU::SGPR_32RegClass,
                             MFI->ArgInfo.PrivateSegmentWaveByteOffset) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->ImplicitArgPtr,
                             AMDGPU::SReg_64RegClass,
                             MFI->ArgInfo.ImplicitArgPtr) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->ImplicitBufferPtr,
                             AMDGPU::SReg_64RegClass,
                             MFI->ArgInfo.ImplicitBufferPtr) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->WorkItemIDX,
                             AMDGPU::VGPR_32RegClass,
                             MFI->ArgInfo.WorkItemIDX) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->WorkItemIDY,
                             AMDGPU::VGPR_32RegClass,
                             MFI->ArgInfo.WorkItemIDY) ||
       parseAndCheckArgument(YamlMFI.ArgInfo->WorkItemIDZ,
                             AMDGPU::VGPR_32RegClass,
                             MFI->ArgInfo.WorkItemIDZ)))
    return true;

  return false;
}