llvm.org GIT mirror llvm / 0392724 lib / Target / AMDGPU / AMDGPUSubtarget.h
0392724

Tree @0392724 (Download .tar.gz)

AMDGPUSubtarget.h @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
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
//=====-- AMDGPUSubtarget.h - Define Subtarget for AMDGPU ------*- C++ -*-====//
//
// 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
/// AMDGPU specific subclass of TargetSubtarget.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H

#include "AMDGPU.h"
#include "AMDGPUCallLowering.h"
#include "R600FrameLowering.h"
#include "R600ISelLowering.h"
#include "R600InstrInfo.h"
#include "SIFrameLowering.h"
#include "SIISelLowering.h"
#include "SIInstrInfo.h"
#include "Utils/AMDGPUBaseInfo.h"
#include "llvm/ADT/Triple.h"
#include "llvm/CodeGen/GlobalISel/InstructionSelector.h"
#include "llvm/CodeGen/GlobalISel/LegalizerInfo.h"
#include "llvm/CodeGen/GlobalISel/RegisterBankInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/SelectionDAGTargetInfo.h"
#include "llvm/MC/MCInstrItineraries.h"
#include "llvm/Support/MathExtras.h"
#include <cassert>
#include <cstdint>
#include <memory>
#include <utility>

#define GET_SUBTARGETINFO_HEADER
#include "AMDGPUGenSubtargetInfo.inc"
#define GET_SUBTARGETINFO_HEADER
#include "R600GenSubtargetInfo.inc"

namespace llvm {

class StringRef;

class AMDGPUSubtarget {
public:
  enum Generation {
    R600 = 0,
    R700 = 1,
    EVERGREEN = 2,
    NORTHERN_ISLANDS = 3,
    SOUTHERN_ISLANDS = 4,
    SEA_ISLANDS = 5,
    VOLCANIC_ISLANDS = 6,
    GFX9 = 7,
    GFX10 = 8
  };

private:
  Triple TargetTriple;

protected:
  bool Has16BitInsts;
  bool HasMadMixInsts;
  bool FP32Denormals;
  bool FPExceptions;
  bool HasSDWA;
  bool HasVOP3PInsts;
  bool HasMulI24;
  bool HasMulU24;
  bool HasInv2PiInlineImm;
  bool HasFminFmaxLegacy;
  bool EnablePromoteAlloca;
  bool HasTrigReducedRange;
  int LocalMemorySize;
  unsigned WavefrontSize;

public:
  AMDGPUSubtarget(const Triple &TT);

  static const AMDGPUSubtarget &get(const MachineFunction &MF);
  static const AMDGPUSubtarget &get(const TargetMachine &TM,
                                    const Function &F);

  /// \returns Default range flat work group size for a calling convention.
  std::pair<unsigned, unsigned> getDefaultFlatWorkGroupSize(CallingConv::ID CC) const;

  /// \returns Subtarget's default pair of minimum/maximum flat work group sizes
  /// for function \p F, or minimum/maximum flat work group sizes explicitly
  /// requested using "amdgpu-flat-work-group-size" attribute attached to
  /// function \p F.
  ///
  /// \returns Subtarget's default values if explicitly requested values cannot
  /// be converted to integer, or violate subtarget's specifications.
  std::pair<unsigned, unsigned> getFlatWorkGroupSizes(const Function &F) const;

  /// \returns Subtarget's default pair of minimum/maximum number of waves per
  /// execution unit for function \p F, or minimum/maximum number of waves per
  /// execution unit explicitly requested using "amdgpu-waves-per-eu" attribute
  /// attached to function \p F.
  ///
  /// \returns Subtarget's default values if explicitly requested values cannot
  /// be converted to integer, violate subtarget's specifications, or are not
  /// compatible with minimum/maximum number of waves limited by flat work group
  /// size, register usage, and/or lds usage.
  std::pair<unsigned, unsigned> getWavesPerEU(const Function &F) const;

  /// Return the amount of LDS that can be used that will not restrict the
  /// occupancy lower than WaveCount.
  unsigned getMaxLocalMemSizeWithWaveCount(unsigned WaveCount,
                                           const Function &) const;

  /// Inverse of getMaxLocalMemWithWaveCount. Return the maximum wavecount if
  /// the given LDS memory size is the only constraint.
  unsigned getOccupancyWithLocalMemSize(uint32_t Bytes, const Function &) const;

  unsigned getOccupancyWithLocalMemSize(const MachineFunction &MF) const;

  bool isAmdHsaOS() const {
    return TargetTriple.getOS() == Triple::AMDHSA;
  }

  bool isAmdPalOS() const {
    return TargetTriple.getOS() == Triple::AMDPAL;
  }

  bool isMesa3DOS() const {
    return TargetTriple.getOS() == Triple::Mesa3D;
  }

  bool isMesaKernel(const Function &F) const {
    return isMesa3DOS() && !AMDGPU::isShader(F.getCallingConv());
  }

  bool isAmdHsaOrMesa(const Function &F) const {
    return isAmdHsaOS() || isMesaKernel(F);
  }

  bool has16BitInsts() const {
    return Has16BitInsts;
  }

  bool hasMadMixInsts() const {
    return HasMadMixInsts;
  }

  bool hasFP32Denormals() const {
    return FP32Denormals;
  }

  bool hasFPExceptions() const {
    return FPExceptions;
  }

  bool hasSDWA() const {
    return HasSDWA;
  }

  bool hasVOP3PInsts() const {
    return HasVOP3PInsts;
  }

  bool hasMulI24() const {
    return HasMulI24;
  }

  bool hasMulU24() const {
    return HasMulU24;
  }

  bool hasInv2PiInlineImm() const {
    return HasInv2PiInlineImm;
  }

  bool hasFminFmaxLegacy() const {
    return HasFminFmaxLegacy;
  }

  bool hasTrigReducedRange() const {
    return HasTrigReducedRange;
  }

  bool isPromoteAllocaEnabled() const {
    return EnablePromoteAlloca;
  }

  unsigned getWavefrontSize() const {
    return WavefrontSize;
  }

  int getLocalMemorySize() const {
    return LocalMemorySize;
  }

  unsigned getAlignmentForImplicitArgPtr() const {
    return isAmdHsaOS() ? 8 : 4;
  }

  /// Returns the offset in bytes from the start of the input buffer
  ///        of the first explicit kernel argument.
  unsigned getExplicitKernelArgOffset(const Function &F) const {
    return isAmdHsaOrMesa(F) ? 0 : 36;
  }

  /// \returns Maximum number of work groups per compute unit supported by the
  /// subtarget and limited by given \p FlatWorkGroupSize.
  virtual unsigned getMaxWorkGroupsPerCU(unsigned FlatWorkGroupSize) const = 0;

  /// \returns Minimum flat work group size supported by the subtarget.
  virtual unsigned getMinFlatWorkGroupSize() const = 0;

  /// \returns Maximum flat work group size supported by the subtarget.
  virtual unsigned getMaxFlatWorkGroupSize() const = 0;

  /// \returns Maximum number of waves per execution unit supported by the
  /// subtarget and limited by given \p FlatWorkGroupSize.
  virtual unsigned getMaxWavesPerEU(unsigned FlatWorkGroupSize) const  = 0;

  /// \returns Minimum number of waves per execution unit supported by the
  /// subtarget.
  virtual unsigned getMinWavesPerEU() const = 0;

  unsigned getMaxWavesPerEU() const { return 10; }

  /// Creates value range metadata on an workitemid.* inrinsic call or load.
  bool makeLIDRangeMetadata(Instruction *I) const;

  /// \returns Number of bytes of arguments that are passed to a shader or
  /// kernel in addition to the explicit ones declared for the function.
  unsigned getImplicitArgNumBytes(const Function &F) const {
    if (isMesaKernel(F))
      return 16;
    return AMDGPU::getIntegerAttribute(F, "amdgpu-implicitarg-num-bytes", 0);
  }
  uint64_t getExplicitKernArgSize(const Function &F,
                                  unsigned &MaxAlign) const;
  unsigned getKernArgSegmentSize(const Function &F,
                                 unsigned &MaxAlign) const;

  virtual ~AMDGPUSubtarget() {}
};

class GCNSubtarget : public AMDGPUGenSubtargetInfo,
                     public AMDGPUSubtarget {
public:
  enum TrapHandlerAbi {
    TrapHandlerAbiNone = 0,
    TrapHandlerAbiHsa = 1
  };

  enum TrapID {
    TrapIDHardwareReserved = 0,
    TrapIDHSADebugTrap = 1,
    TrapIDLLVMTrap = 2,
    TrapIDLLVMDebugTrap = 3,
    TrapIDDebugBreakpoint = 7,
    TrapIDDebugReserved8 = 8,
    TrapIDDebugReservedFE = 0xfe,
    TrapIDDebugReservedFF = 0xff
  };

  enum TrapRegValues {
    LLVMTrapHandlerRegValue = 1
  };

private:
  /// GlobalISel related APIs.
  std::unique_ptr<AMDGPUCallLowering> CallLoweringInfo;
  std::unique_ptr<InstructionSelector> InstSelector;
  std::unique_ptr<LegalizerInfo> Legalizer;
  std::unique_ptr<RegisterBankInfo> RegBankInfo;

protected:
  // Basic subtarget description.
  Triple TargetTriple;
  unsigned Gen;
  InstrItineraryData InstrItins;
  int LDSBankCount;
  unsigned MaxPrivateElementSize;

  // Possibly statically set by tablegen, but may want to be overridden.
  bool FastFMAF32;
  bool HalfRate64Ops;

  // Dynamially set bits that enable features.
  bool FP64FP16Denormals;
  bool FlatForGlobal;
  bool AutoWaitcntBeforeBarrier;
  bool CodeObjectV3;
  bool UnalignedScratchAccess;
  bool UnalignedBufferAccess;
  bool HasApertureRegs;
  bool EnableXNACK;
  bool DoesNotSupportXNACK;
  bool EnableCuMode;
  bool TrapHandler;

  // Used as options.
  bool EnableLoadStoreOpt;
  bool EnableUnsafeDSOffsetFolding;
  bool EnableSIScheduler;
  bool EnableDS128;
  bool EnablePRTStrictNull;
  bool DumpCode;

  // Subtarget statically properties set by tablegen
  bool FP64;
  bool FMA;
  bool MIMG_R128;
  bool IsGCN;
  bool GCN3Encoding;
  bool CIInsts;
  bool GFX8Insts;
  bool GFX9Insts;
  bool GFX10Insts;
  bool GFX7GFX8GFX9Insts;
  bool SGPRInitBug;
  bool HasSMemRealTime;
  bool HasIntClamp;
  bool HasFmaMixInsts;
  bool HasMovrel;
  bool HasVGPRIndexMode;
  bool HasScalarStores;
  bool HasScalarAtomics;
  bool HasSDWAOmod;
  bool HasSDWAScalar;
  bool HasSDWASdst;
  bool HasSDWAMac;
  bool HasSDWAOutModsVOPC;
  bool HasDPP;
  bool HasDPP8;
  bool HasR128A16;
  bool HasNSAEncoding;
  bool HasDLInsts;
  bool HasDot1Insts;
  bool HasDot2Insts;
  bool HasDot3Insts;
  bool HasDot4Insts;
  bool HasDot5Insts;
  bool HasDot6Insts;
  bool HasMAIInsts;
  bool HasPkFmacF16Inst;
  bool HasAtomicFaddInsts;
  bool EnableSRAMECC;
  bool DoesNotSupportSRAMECC;
  bool HasNoSdstCMPX;
  bool HasVscnt;
  bool HasRegisterBanking;
  bool HasVOP3Literal;
  bool HasNoDataDepHazard;
  bool FlatAddressSpace;
  bool FlatInstOffsets;
  bool FlatGlobalInsts;
  bool FlatScratchInsts;
  bool ScalarFlatScratchInsts;
  bool AddNoCarryInsts;
  bool HasUnpackedD16VMem;
  bool R600ALUInst;
  bool CaymanISA;
  bool CFALUBug;
  bool LDSMisalignedBug;
  bool HasVertexCache;
  short TexVTXClauseSize;
  bool ScalarizeGlobal;

  bool HasVcmpxPermlaneHazard;
  bool HasVMEMtoScalarWriteHazard;
  bool HasSMEMtoVectorWriteHazard;
  bool HasInstFwdPrefetchBug;
  bool HasVcmpxExecWARHazard;
  bool HasLdsBranchVmemWARHazard;
  bool HasNSAtoVMEMBug;
  bool HasOffset3fBug;
  bool HasFlatSegmentOffsetBug;

  // Dummy feature to use for assembler in tablegen.
  bool FeatureDisable;

  SelectionDAGTargetInfo TSInfo;
private:
  SIInstrInfo InstrInfo;
  SITargetLowering TLInfo;
  SIFrameLowering FrameLowering;

  // See COMPUTE_TMPRING_SIZE.WAVESIZE, 13-bit field in units of 256-dword.
  static const unsigned MaxWaveScratchSize = (256 * 4) * ((1 << 13) - 1);

public:
  GCNSubtarget(const Triple &TT, StringRef GPU, StringRef FS,
               const GCNTargetMachine &TM);
  ~GCNSubtarget() override;

  GCNSubtarget &initializeSubtargetDependencies(const Triple &TT,
                                                   StringRef GPU, StringRef FS);

  const SIInstrInfo *getInstrInfo() const override {
    return &InstrInfo;
  }

  const SIFrameLowering *getFrameLowering() const override {
    return &FrameLowering;
  }

  const SITargetLowering *getTargetLowering() const override {
    return &TLInfo;
  }

  const SIRegisterInfo *getRegisterInfo() const override {
    return &InstrInfo.getRegisterInfo();
  }

  const CallLowering *getCallLowering() const override {
    return CallLoweringInfo.get();
  }

  const InstructionSelector *getInstructionSelector() const override {
    return InstSelector.get();
  }

  const LegalizerInfo *getLegalizerInfo() const override {
    return Legalizer.get();
  }

  const RegisterBankInfo *getRegBankInfo() const override {
    return RegBankInfo.get();
  }

  // Nothing implemented, just prevent crashes on use.
  const SelectionDAGTargetInfo *getSelectionDAGInfo() const override {
    return &TSInfo;
  }

  const InstrItineraryData *getInstrItineraryData() const override {
    return &InstrItins;
  }

  void ParseSubtargetFeatures(StringRef CPU, StringRef FS);

  Generation getGeneration() const {
    return (Generation)Gen;
  }

  unsigned getWavefrontSizeLog2() const {
    return Log2_32(WavefrontSize);
  }

  /// Return the number of high bits known to be zero fror a frame index.
  unsigned getKnownHighZeroBitsForFrameIndex() const {
    return countLeadingZeros(MaxWaveScratchSize) + getWavefrontSizeLog2();
  }

  int getLDSBankCount() const {
    return LDSBankCount;
  }

  unsigned getMaxPrivateElementSize() const {
    return MaxPrivateElementSize;
  }

  unsigned getConstantBusLimit(unsigned Opcode) const;

  bool hasIntClamp() const {
    return HasIntClamp;
  }

  bool hasFP64() const {
    return FP64;
  }

  bool hasMIMG_R128() const {
    return MIMG_R128;
  }

  bool hasHWFP64() const {
    return FP64;
  }

  bool hasFastFMAF32() const {
    return FastFMAF32;
  }

  bool hasHalfRate64Ops() const {
    return HalfRate64Ops;
  }

  bool hasAddr64() const {
    return (getGeneration() < AMDGPUSubtarget::VOLCANIC_ISLANDS);
  }

  // Return true if the target only has the reverse operand versions of VALU
  // shift instructions (e.g. v_lshrrev_b32, and no v_lshr_b32).
  bool hasOnlyRevVALUShifts() const {
    return getGeneration() >= VOLCANIC_ISLANDS;
  }

  bool hasBFE() const {
    return true;
  }

  bool hasBFI() const {
    return true;
  }

  bool hasBFM() const {
    return hasBFE();
  }

  bool hasBCNT(unsigned Size) const {
    return true;
  }

  bool hasFFBL() const {
    return true;
  }

  bool hasFFBH() const {
    return true;
  }

  bool hasMed3_16() const {
    return getGeneration() >= AMDGPUSubtarget::GFX9;
  }

  bool hasMin3Max3_16() const {
    return getGeneration() >= AMDGPUSubtarget::GFX9;
  }

  bool hasFmaMixInsts() const {
    return HasFmaMixInsts;
  }

  bool hasCARRY() const {
    return true;
  }

  bool hasFMA() const {
    return FMA;
  }

  bool hasSwap() const {
    return GFX9Insts;
  }

  TrapHandlerAbi getTrapHandlerAbi() const {
    return isAmdHsaOS() ? TrapHandlerAbiHsa : TrapHandlerAbiNone;
  }

  /// True if the offset field of DS instructions works as expected. On SI, the
  /// offset uses a 16-bit adder and does not always wrap properly.
  bool hasUsableDSOffset() const {
    return getGeneration() >= SEA_ISLANDS;
  }

  bool unsafeDSOffsetFoldingEnabled() const {
    return EnableUnsafeDSOffsetFolding;
  }

  /// Condition output from div_scale is usable.
  bool hasUsableDivScaleConditionOutput() const {
    return getGeneration() != SOUTHERN_ISLANDS;
  }

  /// Extra wait hazard is needed in some cases before
  /// s_cbranch_vccnz/s_cbranch_vccz.
  bool hasReadVCCZBug() const {
    return getGeneration() <= SEA_ISLANDS;
  }

  /// A read of an SGPR by SMRD instruction requires 4 wait states when the SGPR
  /// was written by a VALU instruction.
  bool hasSMRDReadVALUDefHazard() const {
    return getGeneration() == SOUTHERN_ISLANDS;
  }

  /// A read of an SGPR by a VMEM instruction requires 5 wait states when the
  /// SGPR was written by a VALU Instruction.
  bool hasVMEMReadSGPRVALUDefHazard() const {
    return getGeneration() >= VOLCANIC_ISLANDS;
  }

  bool hasRFEHazards() const {
    return getGeneration() >= VOLCANIC_ISLANDS;
  }

  /// Number of hazard wait states for s_setreg_b32/s_setreg_imm32_b32.
  unsigned getSetRegWaitStates() const {
    return getGeneration() <= SEA_ISLANDS ? 1 : 2;
  }

  bool dumpCode() const {
    return DumpCode;
  }

  /// Return the amount of LDS that can be used that will not restrict the
  /// occupancy lower than WaveCount.
  unsigned getMaxLocalMemSizeWithWaveCount(unsigned WaveCount,
                                           const Function &) const;

  bool hasFP16Denormals() const {
    return FP64FP16Denormals;
  }

  bool hasFP64Denormals() const {
    return FP64FP16Denormals;
  }

  bool supportsMinMaxDenormModes() const {
    return getGeneration() >= AMDGPUSubtarget::GFX9;
  }

  bool useFlatForGlobal() const {
    return FlatForGlobal;
  }

  /// \returns If target supports ds_read/write_b128 and user enables generation
  /// of ds_read/write_b128.
  bool useDS128() const {
    return CIInsts && EnableDS128;
  }

  /// Have v_trunc_f64, v_ceil_f64, v_rndne_f64
  bool haveRoundOpsF64() const {
    return CIInsts;
  }

  /// \returns If MUBUF instructions always perform range checking, even for
  /// buffer resources used for private memory access.
  bool privateMemoryResourceIsRangeChecked() const {
    return getGeneration() < AMDGPUSubtarget::GFX9;
  }

  /// \returns If target requires PRT Struct NULL support (zero result registers
  /// for sparse texture support).
  bool usePRTStrictNull() const {
    return EnablePRTStrictNull;
  }

  bool hasAutoWaitcntBeforeBarrier() const {
    return AutoWaitcntBeforeBarrier;
  }

  bool hasCodeObjectV3() const {
    // FIXME: Need to add code object v3 support for mesa and pal.
    return isAmdHsaOS() ? CodeObjectV3 : false;
  }

  bool hasUnalignedBufferAccess() const {
    return UnalignedBufferAccess;
  }

  bool hasUnalignedScratchAccess() const {
    return UnalignedScratchAccess;
  }

  bool hasApertureRegs() const {
    return HasApertureRegs;
  }

  bool isTrapHandlerEnabled() const {
    return TrapHandler;
  }

  bool isXNACKEnabled() const {
    return EnableXNACK;
  }

  bool isCuModeEnabled() const {
    return EnableCuMode;
  }

  bool hasFlatAddressSpace() const {
    return FlatAddressSpace;
  }

  bool hasFlatScrRegister() const {
    return hasFlatAddressSpace();
  }

  bool hasFlatInstOffsets() const {
    return FlatInstOffsets;
  }

  bool hasFlatGlobalInsts() const {
    return FlatGlobalInsts;
  }

  bool hasFlatScratchInsts() const {
    return FlatScratchInsts;
  }

  bool hasScalarFlatScratchInsts() const {
    return ScalarFlatScratchInsts;
  }

  bool hasFlatSegmentOffsetBug() const {
    return HasFlatSegmentOffsetBug;
  }

  bool hasFlatLgkmVMemCountInOrder() const {
    return getGeneration() > GFX9;
  }

  bool hasD16LoadStore() const {
    return getGeneration() >= GFX9;
  }

  bool d16PreservesUnusedBits() const {
    return hasD16LoadStore() && !isSRAMECCEnabled();
  }

  bool hasD16Images() const {
    return getGeneration() >= VOLCANIC_ISLANDS;
  }

  /// Return if most LDS instructions have an m0 use that require m0 to be
  /// iniitalized.
  bool ldsRequiresM0Init() const {
    return getGeneration() < GFX9;
  }

  // True if the hardware rewinds and replays GWS operations if a wave is
  // preempted.
  //
  // If this is false, a GWS operation requires testing if a nack set the
  // MEM_VIOL bit, and repeating if so.
  bool hasGWSAutoReplay() const {
    return getGeneration() >= GFX9;
  }

  /// \returns if target has ds_gws_sema_release_all instruction.
  bool hasGWSSemaReleaseAll() const {
    return CIInsts;
  }

  bool hasAddNoCarry() const {
    return AddNoCarryInsts;
  }

  bool hasUnpackedD16VMem() const {
    return HasUnpackedD16VMem;
  }

  // Covers VS/PS/CS graphics shaders
  bool isMesaGfxShader(const Function &F) const {
    return isMesa3DOS() && AMDGPU::isShader(F.getCallingConv());
  }

  bool hasMad64_32() const {
    return getGeneration() >= SEA_ISLANDS;
  }

  bool hasSDWAOmod() const {
    return HasSDWAOmod;
  }

  bool hasSDWAScalar() const {
    return HasSDWAScalar;
  }

  bool hasSDWASdst() const {
    return HasSDWASdst;
  }

  bool hasSDWAMac() const {
    return HasSDWAMac;
  }

  bool hasSDWAOutModsVOPC() const {
    return HasSDWAOutModsVOPC;
  }

  bool hasDLInsts() const {
    return HasDLInsts;
  }

  bool hasDot1Insts() const {
    return HasDot1Insts;
  }

  bool hasDot2Insts() const {
    return HasDot2Insts;
  }

  bool hasDot3Insts() const {
    return HasDot3Insts;
  }

  bool hasDot4Insts() const {
    return HasDot4Insts;
  }

  bool hasDot5Insts() const {
    return HasDot5Insts;
  }

  bool hasDot6Insts() const {
    return HasDot6Insts;
  }

  bool hasMAIInsts() const {
    return HasMAIInsts;
  }

  bool hasPkFmacF16Inst() const {
    return HasPkFmacF16Inst;
  }

  bool hasAtomicFaddInsts() const {
    return HasAtomicFaddInsts;
  }

  bool isSRAMECCEnabled() const {
    return EnableSRAMECC;
  }

  bool hasNoSdstCMPX() const {
    return HasNoSdstCMPX;
  }

  bool hasVscnt() const {
    return HasVscnt;
  }

  bool hasRegisterBanking() const {
    return HasRegisterBanking;
  }

  bool hasVOP3Literal() const {
    return HasVOP3Literal;
  }

  bool hasNoDataDepHazard() const {
    return HasNoDataDepHazard;
  }

  bool vmemWriteNeedsExpWaitcnt() const {
    return getGeneration() < SEA_ISLANDS;
  }

  // Scratch is allocated in 256 dword per wave blocks for the entire
  // wavefront. When viewed from the perspecive of an arbitrary workitem, this
  // is 4-byte aligned.
  //
  // Only 4-byte alignment is really needed to access anything. Transformations
  // on the pointer value itself may rely on the alignment / known low bits of
  // the pointer. Set this to something above the minimum to avoid needing
  // dynamic realignment in common cases.
  unsigned getStackAlignment() const {
    return 16;
  }

  bool enableMachineScheduler() const override {
    return true;
  }

  bool enableSubRegLiveness() const override {
    return true;
  }

  void setScalarizeGlobalBehavior(bool b) { ScalarizeGlobal = b; }
  bool getScalarizeGlobalBehavior() const { return ScalarizeGlobal; }

  /// \returns Number of execution units per compute unit supported by the
  /// subtarget.
  unsigned getEUsPerCU() const {
    return AMDGPU::IsaInfo::getEUsPerCU(this);
  }

  /// \returns Maximum number of waves per compute unit supported by the
  /// subtarget without any kind of limitation.
  unsigned getMaxWavesPerCU() const {
    return AMDGPU::IsaInfo::getMaxWavesPerCU(this);
  }

  /// \returns Maximum number of waves per compute unit supported by the
  /// subtarget and limited by given \p FlatWorkGroupSize.
  unsigned getMaxWavesPerCU(unsigned FlatWorkGroupSize) const {
    return AMDGPU::IsaInfo::getMaxWavesPerCU(this, FlatWorkGroupSize);
  }

  /// \returns Maximum number of waves per execution unit supported by the
  /// subtarget without any kind of limitation.
  unsigned getMaxWavesPerEU() const {
    return AMDGPU::IsaInfo::getMaxWavesPerEU();
  }

  /// \returns Number of waves per work group supported by the subtarget and
  /// limited by given \p FlatWorkGroupSize.
  unsigned getWavesPerWorkGroup(unsigned FlatWorkGroupSize) const {
    return AMDGPU::IsaInfo::getWavesPerWorkGroup(this, FlatWorkGroupSize);
  }

  // static wrappers
  static bool hasHalfRate64Ops(const TargetSubtargetInfo &STI);

  // XXX - Why is this here if it isn't in the default pass set?
  bool enableEarlyIfConversion() const override {
    return true;
  }

  void overrideSchedPolicy(MachineSchedPolicy &Policy,
                           unsigned NumRegionInstrs) const override;

  unsigned getMaxNumUserSGPRs() const {
    return 16;
  }

  bool hasSMemRealTime() const {
    return HasSMemRealTime;
  }

  bool hasMovrel() const {
    return HasMovrel;
  }

  bool hasVGPRIndexMode() const {
    return HasVGPRIndexMode;
  }

  bool useVGPRIndexMode(bool UserEnable) const {
    return !hasMovrel() || (UserEnable && hasVGPRIndexMode());
  }

  bool hasScalarCompareEq64() const {
    return getGeneration() >= VOLCANIC_ISLANDS;
  }

  bool hasScalarStores() const {
    return HasScalarStores;
  }

  bool hasScalarAtomics() const {
    return HasScalarAtomics;
  }

  bool hasLDSFPAtomics() const {
    return GFX8Insts;
  }

  bool hasDPP() const {
    return HasDPP;
  }

  bool hasDPP8() const {
    return HasDPP8;
  }

  bool hasR128A16() const {
    return HasR128A16;
  }

  bool hasOffset3fBug() const {
    return HasOffset3fBug;
  }

  bool hasNSAEncoding() const {
    return HasNSAEncoding;
  }

  bool hasMadF16() const;

  bool enableSIScheduler() const {
    return EnableSIScheduler;
  }

  bool loadStoreOptEnabled() const {
    return EnableLoadStoreOpt;
  }

  bool hasSGPRInitBug() const {
    return SGPRInitBug;
  }

  bool has12DWordStoreHazard() const {
    return getGeneration() != AMDGPUSubtarget::SOUTHERN_ISLANDS;
  }

  // \returns true if the subtarget supports DWORDX3 load/store instructions.
  bool hasDwordx3LoadStores() const {
    return CIInsts;
  }

  bool hasSMovFedHazard() const {
    return getGeneration() == AMDGPUSubtarget::GFX9;
  }

  bool hasReadM0MovRelInterpHazard() const {
    return getGeneration() == AMDGPUSubtarget::GFX9;
  }

  bool hasReadM0SendMsgHazard() const {
    return getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS &&
           getGeneration() <= AMDGPUSubtarget::GFX9;
  }

  bool hasVcmpxPermlaneHazard() const {
    return HasVcmpxPermlaneHazard;
  }

  bool hasVMEMtoScalarWriteHazard() const {
    return HasVMEMtoScalarWriteHazard;
  }

  bool hasSMEMtoVectorWriteHazard() const {
    return HasSMEMtoVectorWriteHazard;
  }

  bool hasLDSMisalignedBug() const {
    return LDSMisalignedBug && !EnableCuMode;
  }

  bool hasInstFwdPrefetchBug() const {
    return HasInstFwdPrefetchBug;
  }

  bool hasVcmpxExecWARHazard() const {
    return HasVcmpxExecWARHazard;
  }

  bool hasLdsBranchVmemWARHazard() const {
    return HasLdsBranchVmemWARHazard;
  }

  bool hasNSAtoVMEMBug() const {
    return HasNSAtoVMEMBug;
  }

  /// Return the maximum number of waves per SIMD for kernels using \p SGPRs
  /// SGPRs
  unsigned getOccupancyWithNumSGPRs(unsigned SGPRs) const;

  /// Return the maximum number of waves per SIMD for kernels using \p VGPRs
  /// VGPRs
  unsigned getOccupancyWithNumVGPRs(unsigned VGPRs) const;

  /// \returns true if the flat_scratch register should be initialized with the
  /// pointer to the wave's scratch memory rather than a size and offset.
  bool flatScratchIsPointer() const {
    return getGeneration() >= AMDGPUSubtarget::GFX9;
  }

  /// \returns true if the machine has merged shaders in which s0-s7 are
  /// reserved by the hardware and user SGPRs start at s8
  bool hasMergedShaders() const {
    return getGeneration() >= GFX9;
  }

  /// \returns SGPR allocation granularity supported by the subtarget.
  unsigned getSGPRAllocGranule() const {
    return AMDGPU::IsaInfo::getSGPRAllocGranule(this);
  }

  /// \returns SGPR encoding granularity supported by the subtarget.
  unsigned getSGPREncodingGranule() const {
    return AMDGPU::IsaInfo::getSGPREncodingGranule(this);
  }

  /// \returns Total number of SGPRs supported by the subtarget.
  unsigned getTotalNumSGPRs() const {
    return AMDGPU::IsaInfo::getTotalNumSGPRs(this);
  }

  /// \returns Addressable number of SGPRs supported by the subtarget.
  unsigned getAddressableNumSGPRs() const {
    return AMDGPU::IsaInfo::getAddressableNumSGPRs(this);
  }

  /// \returns Minimum number of SGPRs that meets the given number of waves per
  /// execution unit requirement supported by the subtarget.
  unsigned getMinNumSGPRs(unsigned WavesPerEU) const {
    return AMDGPU::IsaInfo::getMinNumSGPRs(this, WavesPerEU);
  }

  /// \returns Maximum number of SGPRs that meets the given number of waves per
  /// execution unit requirement supported by the subtarget.
  unsigned getMaxNumSGPRs(unsigned WavesPerEU, bool Addressable) const {
    return AMDGPU::IsaInfo::getMaxNumSGPRs(this, WavesPerEU, Addressable);
  }

  /// \returns Reserved number of SGPRs for given function \p MF.
  unsigned getReservedNumSGPRs(const MachineFunction &MF) const;

  /// \returns Maximum number of SGPRs that meets number of waves per execution
  /// unit requirement for function \p MF, or number of SGPRs explicitly
  /// requested using "amdgpu-num-sgpr" attribute attached to function \p MF.
  ///
  /// \returns Value that meets number of waves per execution unit requirement
  /// if explicitly requested value cannot be converted to integer, violates
  /// subtarget's specifications, or does not meet number of waves per execution
  /// unit requirement.
  unsigned getMaxNumSGPRs(const MachineFunction &MF) const;

  /// \returns VGPR allocation granularity supported by the subtarget.
  unsigned getVGPRAllocGranule() const {
    return AMDGPU::IsaInfo::getVGPRAllocGranule(this);
  }

  /// \returns VGPR encoding granularity supported by the subtarget.
  unsigned getVGPREncodingGranule() const {
    return AMDGPU::IsaInfo::getVGPREncodingGranule(this);
  }

  /// \returns Total number of VGPRs supported by the subtarget.
  unsigned getTotalNumVGPRs() const {
    return AMDGPU::IsaInfo::getTotalNumVGPRs(this);
  }

  /// \returns Addressable number of VGPRs supported by the subtarget.
  unsigned getAddressableNumVGPRs() const {
    return AMDGPU::IsaInfo::getAddressableNumVGPRs(this);
  }

  /// \returns Minimum number of VGPRs that meets given number of waves per
  /// execution unit requirement supported by the subtarget.
  unsigned getMinNumVGPRs(unsigned WavesPerEU) const {
    return AMDGPU::IsaInfo::getMinNumVGPRs(this, WavesPerEU);
  }

  /// \returns Maximum number of VGPRs that meets given number of waves per
  /// execution unit requirement supported by the subtarget.
  unsigned getMaxNumVGPRs(unsigned WavesPerEU) const {
    return AMDGPU::IsaInfo::getMaxNumVGPRs(this, WavesPerEU);
  }

  /// \returns Maximum number of VGPRs that meets number of waves per execution
  /// unit requirement for function \p MF, or number of VGPRs explicitly
  /// requested using "amdgpu-num-vgpr" attribute attached to function \p MF.
  ///
  /// \returns Value that meets number of waves per execution unit requirement
  /// if explicitly requested value cannot be converted to integer, violates
  /// subtarget's specifications, or does not meet number of waves per execution
  /// unit requirement.
  unsigned getMaxNumVGPRs(const MachineFunction &MF) const;

  void getPostRAMutations(
      std::vector<std::unique_ptr<ScheduleDAGMutation>> &Mutations)
      const override;

  bool isWave32() const {
    return WavefrontSize == 32;
  }

  const TargetRegisterClass *getBoolRC() const {
    return getRegisterInfo()->getBoolRC();
  }

  /// \returns Maximum number of work groups per compute unit supported by the
  /// subtarget and limited by given \p FlatWorkGroupSize.
  unsigned getMaxWorkGroupsPerCU(unsigned FlatWorkGroupSize) const override {
    return AMDGPU::IsaInfo::getMaxWorkGroupsPerCU(this, FlatWorkGroupSize);
  }

  /// \returns Minimum flat work group size supported by the subtarget.
  unsigned getMinFlatWorkGroupSize() const override {
    return AMDGPU::IsaInfo::getMinFlatWorkGroupSize(this);
  }

  /// \returns Maximum flat work group size supported by the subtarget.
  unsigned getMaxFlatWorkGroupSize() const override {
    return AMDGPU::IsaInfo::getMaxFlatWorkGroupSize(this);
  }

  /// \returns Maximum number of waves per execution unit supported by the
  /// subtarget and limited by given \p FlatWorkGroupSize.
  unsigned getMaxWavesPerEU(unsigned FlatWorkGroupSize) const override {
    return AMDGPU::IsaInfo::getMaxWavesPerEU(this, FlatWorkGroupSize);
  }

  /// \returns Minimum number of waves per execution unit supported by the
  /// subtarget.
  unsigned getMinWavesPerEU() const override {
    return AMDGPU::IsaInfo::getMinWavesPerEU(this);
  }
};

class R600Subtarget final : public R600GenSubtargetInfo,
                            public AMDGPUSubtarget {
private:
  R600InstrInfo InstrInfo;
  R600FrameLowering FrameLowering;
  bool FMA;
  bool CaymanISA;
  bool CFALUBug;
  bool HasVertexCache;
  bool R600ALUInst;
  bool FP64;
  short TexVTXClauseSize;
  Generation Gen;
  R600TargetLowering TLInfo;
  InstrItineraryData InstrItins;
  SelectionDAGTargetInfo TSInfo;

public:
  R600Subtarget(const Triple &TT, StringRef CPU, StringRef FS,
                const TargetMachine &TM);

  const R600InstrInfo *getInstrInfo() const override { return &InstrInfo; }

  const R600FrameLowering *getFrameLowering() const override {
    return &FrameLowering;
  }

  const R600TargetLowering *getTargetLowering() const override {
    return &TLInfo;
  }

  const R600RegisterInfo *getRegisterInfo() const override {
    return &InstrInfo.getRegisterInfo();
  }

  const InstrItineraryData *getInstrItineraryData() const override {
    return &InstrItins;
  }

  // Nothing implemented, just prevent crashes on use.
  const SelectionDAGTargetInfo *getSelectionDAGInfo() const override {
    return &TSInfo;
  }

  void ParseSubtargetFeatures(StringRef CPU, StringRef FS);

  Generation getGeneration() const {
    return Gen;
  }

  unsigned getStackAlignment() const {
    return 4;
  }

  R600Subtarget &initializeSubtargetDependencies(const Triple &TT,
                                                 StringRef GPU, StringRef FS);

  bool hasBFE() const {
    return (getGeneration() >= EVERGREEN);
  }

  bool hasBFI() const {
    return (getGeneration() >= EVERGREEN);
  }

  bool hasBCNT(unsigned Size) const {
    if (Size == 32)
      return (getGeneration() >= EVERGREEN);

    return false;
  }

  bool hasBORROW() const {
    return (getGeneration() >= EVERGREEN);
  }

  bool hasCARRY() const {
    return (getGeneration() >= EVERGREEN);
  }

  bool hasCaymanISA() const {
    return CaymanISA;
  }

  bool hasFFBL() const {
    return (getGeneration() >= EVERGREEN);
  }

  bool hasFFBH() const {
    return (getGeneration() >= EVERGREEN);
  }

  bool hasFMA() const { return FMA; }

  bool hasCFAluBug() const { return CFALUBug; }

  bool hasVertexCache() const { return HasVertexCache; }

  short getTexVTXClauseSize() const { return TexVTXClauseSize; }

  bool enableMachineScheduler() const override {
    return true;
  }

  bool enableSubRegLiveness() const override {
    return true;
  }

  /// \returns Maximum number of work groups per compute unit supported by the
  /// subtarget and limited by given \p FlatWorkGroupSize.
  unsigned getMaxWorkGroupsPerCU(unsigned FlatWorkGroupSize) const override {
    return AMDGPU::IsaInfo::getMaxWorkGroupsPerCU(this, FlatWorkGroupSize);
  }

  /// \returns Minimum flat work group size supported by the subtarget.
  unsigned getMinFlatWorkGroupSize() const override {
    return AMDGPU::IsaInfo::getMinFlatWorkGroupSize(this);
  }

  /// \returns Maximum flat work group size supported by the subtarget.
  unsigned getMaxFlatWorkGroupSize() const override {
    return AMDGPU::IsaInfo::getMaxFlatWorkGroupSize(this);
  }

  /// \returns Maximum number of waves per execution unit supported by the
  /// subtarget and limited by given \p FlatWorkGroupSize.
  unsigned getMaxWavesPerEU(unsigned FlatWorkGroupSize) const override {
    return AMDGPU::IsaInfo::getMaxWavesPerEU(this, FlatWorkGroupSize);
  }

  /// \returns Minimum number of waves per execution unit supported by the
  /// subtarget.
  unsigned getMinWavesPerEU() const override {
    return AMDGPU::IsaInfo::getMinWavesPerEU(this);
  }
};

} // end namespace llvm

#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H