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

Tree @0392724 (Download .tar.gz)

SIMachineFunctionInfo.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
//==- SIMachineFunctionInfo.h - SIMachineFunctionInfo interface --*- 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
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_AMDGPU_SIMACHINEFUNCTIONINFO_H
#define LLVM_LIB_TARGET_AMDGPU_SIMACHINEFUNCTIONINFO_H

#include "AMDGPUArgumentUsageInfo.h"
#include "AMDGPUMachineFunction.h"
#include "MCTargetDesc/AMDGPUMCTargetDesc.h"
#include "SIInstrInfo.h"
#include "SIRegisterInfo.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/SparseBitVector.h"
#include "llvm/CodeGen/MIRYamlMapping.h"
#include "llvm/CodeGen/PseudoSourceValue.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#include "llvm/MC/MCRegisterInfo.h"
#include "llvm/Support/ErrorHandling.h"
#include <array>
#include <cassert>
#include <utility>
#include <vector>

namespace llvm {

class MachineFrameInfo;
class MachineFunction;
class TargetRegisterClass;

class AMDGPUPseudoSourceValue : public PseudoSourceValue {
public:
  enum AMDGPUPSVKind : unsigned {
    PSVBuffer = PseudoSourceValue::TargetCustom,
    PSVImage,
    GWSResource
  };

protected:
  AMDGPUPseudoSourceValue(unsigned Kind, const TargetInstrInfo &TII)
      : PseudoSourceValue(Kind, TII) {}

public:
  bool isConstant(const MachineFrameInfo *) const override {
    // This should probably be true for most images, but we will start by being
    // conservative.
    return false;
  }

  bool isAliased(const MachineFrameInfo *) const override {
    return true;
  }

  bool mayAlias(const MachineFrameInfo *) const override {
    return true;
  }
};

class AMDGPUBufferPseudoSourceValue final : public AMDGPUPseudoSourceValue {
public:
  explicit AMDGPUBufferPseudoSourceValue(const TargetInstrInfo &TII)
      : AMDGPUPseudoSourceValue(PSVBuffer, TII) {}

  static bool classof(const PseudoSourceValue *V) {
    return V->kind() == PSVBuffer;
  }
};

class AMDGPUImagePseudoSourceValue final : public AMDGPUPseudoSourceValue {
public:
  // TODO: Is the img rsrc useful?
  explicit AMDGPUImagePseudoSourceValue(const TargetInstrInfo &TII)
      : AMDGPUPseudoSourceValue(PSVImage, TII) {}

  static bool classof(const PseudoSourceValue *V) {
    return V->kind() == PSVImage;
  }
};

class AMDGPUGWSResourcePseudoSourceValue final : public AMDGPUPseudoSourceValue {
public:
  explicit AMDGPUGWSResourcePseudoSourceValue(const TargetInstrInfo &TII)
      : AMDGPUPseudoSourceValue(GWSResource, TII) {}

  static bool classof(const PseudoSourceValue *V) {
    return V->kind() == GWSResource;
  }

  // These are inaccessible memory from IR.
  bool isAliased(const MachineFrameInfo *) const override {
    return false;
  }

  // These are inaccessible memory from IR.
  bool mayAlias(const MachineFrameInfo *) const override {
    return false;
  }

  void printCustom(raw_ostream &OS) const override {
    OS << "GWSResource";
  }
};

namespace yaml {

struct SIArgument {
  bool IsRegister;
  union {
    StringValue RegisterName;
    unsigned StackOffset;
  };
  Optional<unsigned> Mask;

  // Default constructor, which creates a stack argument.
  SIArgument() : IsRegister(false), StackOffset(0) {}
  SIArgument(const SIArgument &Other) {
    IsRegister = Other.IsRegister;
    if (IsRegister) {
      ::new ((void *)std::addressof(RegisterName))
          StringValue(Other.RegisterName);
    } else
      StackOffset = Other.StackOffset;
    Mask = Other.Mask;
  }
  SIArgument &operator=(const SIArgument &Other) {
    IsRegister = Other.IsRegister;
    if (IsRegister) {
      ::new ((void *)std::addressof(RegisterName))
          StringValue(Other.RegisterName);
    } else
      StackOffset = Other.StackOffset;
    Mask = Other.Mask;
    return *this;
  }
  ~SIArgument() {
    if (IsRegister)
      RegisterName.~StringValue();
  }

  // Helper to create a register or stack argument.
  static inline SIArgument createArgument(bool IsReg) {
    if (IsReg)
      return SIArgument(IsReg);
    return SIArgument();
  }

private:
  // Construct a register argument.
  SIArgument(bool) : IsRegister(true), RegisterName() {}
};

template <> struct MappingTraits<SIArgument> {
  static void mapping(IO &YamlIO, SIArgument &A) {
    if (YamlIO.outputting()) {
      if (A.IsRegister)
        YamlIO.mapRequired("reg", A.RegisterName);
      else
        YamlIO.mapRequired("offset", A.StackOffset);
    } else {
      auto Keys = YamlIO.keys();
      if (is_contained(Keys, "reg")) {
        A = SIArgument::createArgument(true);
        YamlIO.mapRequired("reg", A.RegisterName);
      } else if (is_contained(Keys, "offset"))
        YamlIO.mapRequired("offset", A.StackOffset);
      else
        YamlIO.setError("missing required key 'reg' or 'offset'");
    }
    YamlIO.mapOptional("mask", A.Mask);
  }
  static const bool flow = true;
};

struct SIArgumentInfo {
  Optional<SIArgument> PrivateSegmentBuffer;
  Optional<SIArgument> DispatchPtr;
  Optional<SIArgument> QueuePtr;
  Optional<SIArgument> KernargSegmentPtr;
  Optional<SIArgument> DispatchID;
  Optional<SIArgument> FlatScratchInit;
  Optional<SIArgument> PrivateSegmentSize;

  Optional<SIArgument> WorkGroupIDX;
  Optional<SIArgument> WorkGroupIDY;
  Optional<SIArgument> WorkGroupIDZ;
  Optional<SIArgument> WorkGroupInfo;
  Optional<SIArgument> PrivateSegmentWaveByteOffset;

  Optional<SIArgument> ImplicitArgPtr;
  Optional<SIArgument> ImplicitBufferPtr;

  Optional<SIArgument> WorkItemIDX;
  Optional<SIArgument> WorkItemIDY;
  Optional<SIArgument> WorkItemIDZ;
};

template <> struct MappingTraits<SIArgumentInfo> {
  static void mapping(IO &YamlIO, SIArgumentInfo &AI) {
    YamlIO.mapOptional("privateSegmentBuffer", AI.PrivateSegmentBuffer);
    YamlIO.mapOptional("dispatchPtr", AI.DispatchPtr);
    YamlIO.mapOptional("queuePtr", AI.QueuePtr);
    YamlIO.mapOptional("kernargSegmentPtr", AI.KernargSegmentPtr);
    YamlIO.mapOptional("dispatchID", AI.DispatchID);
    YamlIO.mapOptional("flatScratchInit", AI.FlatScratchInit);
    YamlIO.mapOptional("privateSegmentSize", AI.PrivateSegmentSize);

    YamlIO.mapOptional("workGroupIDX", AI.WorkGroupIDX);
    YamlIO.mapOptional("workGroupIDY", AI.WorkGroupIDY);
    YamlIO.mapOptional("workGroupIDZ", AI.WorkGroupIDZ);
    YamlIO.mapOptional("workGroupInfo", AI.WorkGroupInfo);
    YamlIO.mapOptional("privateSegmentWaveByteOffset",
                       AI.PrivateSegmentWaveByteOffset);

    YamlIO.mapOptional("implicitArgPtr", AI.ImplicitArgPtr);
    YamlIO.mapOptional("implicitBufferPtr", AI.ImplicitBufferPtr);

    YamlIO.mapOptional("workItemIDX", AI.WorkItemIDX);
    YamlIO.mapOptional("workItemIDY", AI.WorkItemIDY);
    YamlIO.mapOptional("workItemIDZ", AI.WorkItemIDZ);
  }
};

struct SIMachineFunctionInfo final : public yaml::MachineFunctionInfo {
  uint64_t ExplicitKernArgSize = 0;
  unsigned MaxKernArgAlign = 0;
  unsigned LDSSize = 0;
  bool IsEntryFunction = false;
  bool NoSignedZerosFPMath = false;
  bool MemoryBound = false;
  bool WaveLimiter = false;

  StringValue ScratchRSrcReg = "$private_rsrc_reg";
  StringValue ScratchWaveOffsetReg = "$scratch_wave_offset_reg";
  StringValue FrameOffsetReg = "$fp_reg";
  StringValue StackPtrOffsetReg = "$sp_reg";

  Optional<SIArgumentInfo> ArgInfo;

  SIMachineFunctionInfo() = default;
  SIMachineFunctionInfo(const llvm::SIMachineFunctionInfo &,
                        const TargetRegisterInfo &TRI);

  void mappingImpl(yaml::IO &YamlIO) override;
  ~SIMachineFunctionInfo() = default;
};

template <> struct MappingTraits<SIMachineFunctionInfo> {
  static void mapping(IO &YamlIO, SIMachineFunctionInfo &MFI) {
    YamlIO.mapOptional("explicitKernArgSize", MFI.ExplicitKernArgSize,
                       UINT64_C(0));
    YamlIO.mapOptional("maxKernArgAlign", MFI.MaxKernArgAlign, 0u);
    YamlIO.mapOptional("ldsSize", MFI.LDSSize, 0u);
    YamlIO.mapOptional("isEntryFunction", MFI.IsEntryFunction, false);
    YamlIO.mapOptional("noSignedZerosFPMath", MFI.NoSignedZerosFPMath, false);
    YamlIO.mapOptional("memoryBound", MFI.MemoryBound, false);
    YamlIO.mapOptional("waveLimiter", MFI.WaveLimiter, false);
    YamlIO.mapOptional("scratchRSrcReg", MFI.ScratchRSrcReg,
                       StringValue("$private_rsrc_reg"));
    YamlIO.mapOptional("scratchWaveOffsetReg", MFI.ScratchWaveOffsetReg,
                       StringValue("$scratch_wave_offset_reg"));
    YamlIO.mapOptional("frameOffsetReg", MFI.FrameOffsetReg,
                       StringValue("$fp_reg"));
    YamlIO.mapOptional("stackPtrOffsetReg", MFI.StackPtrOffsetReg,
                       StringValue("$sp_reg"));
    YamlIO.mapOptional("argumentInfo", MFI.ArgInfo);
  }
};

} // end namespace yaml

/// This class keeps track of the SPI_SP_INPUT_ADDR config register, which
/// tells the hardware which interpolation parameters to load.
class SIMachineFunctionInfo final : public AMDGPUMachineFunction {
  friend class GCNTargetMachine;

  unsigned TIDReg = AMDGPU::NoRegister;

  // Registers that may be reserved for spilling purposes. These may be the same
  // as the input registers.
  unsigned ScratchRSrcReg = AMDGPU::PRIVATE_RSRC_REG;
  unsigned ScratchWaveOffsetReg = AMDGPU::SCRATCH_WAVE_OFFSET_REG;

  // This is the current function's incremented size from the kernel's scratch
  // wave offset register. For an entry function, this is exactly the same as
  // the ScratchWaveOffsetReg.
  unsigned FrameOffsetReg = AMDGPU::FP_REG;

  // Top of the stack SGPR offset derived from the ScratchWaveOffsetReg.
  unsigned StackPtrOffsetReg = AMDGPU::SP_REG;

  AMDGPUFunctionArgInfo ArgInfo;

  // State of MODE register, assumed FP mode.
  AMDGPU::SIModeRegisterDefaults Mode;

  // Graphics info.
  unsigned PSInputAddr = 0;
  unsigned PSInputEnable = 0;

  /// Number of bytes of arguments this function has on the stack. If the callee
  /// is expected to restore the argument stack this should be a multiple of 16,
  /// all usable during a tail call.
  ///
  /// The alternative would forbid tail call optimisation in some cases: if we
  /// want to transfer control from a function with 8-bytes of stack-argument
  /// space to a function with 16-bytes then misalignment of this value would
  /// make a stack adjustment necessary, which could not be undone by the
  /// callee.
  unsigned BytesInStackArgArea = 0;

  bool ReturnsVoid = true;

  // A pair of default/requested minimum/maximum flat work group sizes.
  // Minimum - first, maximum - second.
  std::pair<unsigned, unsigned> FlatWorkGroupSizes = {0, 0};

  // A pair of default/requested minimum/maximum number of waves per execution
  // unit. Minimum - first, maximum - second.
  std::pair<unsigned, unsigned> WavesPerEU = {0, 0};

  DenseMap<const Value *,
           std::unique_ptr<const AMDGPUBufferPseudoSourceValue>> BufferPSVs;
  DenseMap<const Value *,
           std::unique_ptr<const AMDGPUImagePseudoSourceValue>> ImagePSVs;
  std::unique_ptr<const AMDGPUGWSResourcePseudoSourceValue> GWSResourcePSV;

private:
  unsigned LDSWaveSpillSize = 0;
  unsigned NumUserSGPRs = 0;
  unsigned NumSystemSGPRs = 0;

  bool HasSpilledSGPRs = false;
  bool HasSpilledVGPRs = false;
  bool HasNonSpillStackObjects = false;
  bool IsStackRealigned = false;

  unsigned NumSpilledSGPRs = 0;
  unsigned NumSpilledVGPRs = 0;

  // Feature bits required for inputs passed in user SGPRs.
  bool PrivateSegmentBuffer : 1;
  bool DispatchPtr : 1;
  bool QueuePtr : 1;
  bool KernargSegmentPtr : 1;
  bool DispatchID : 1;
  bool FlatScratchInit : 1;

  // Feature bits required for inputs passed in system SGPRs.
  bool WorkGroupIDX : 1; // Always initialized.
  bool WorkGroupIDY : 1;
  bool WorkGroupIDZ : 1;
  bool WorkGroupInfo : 1;
  bool PrivateSegmentWaveByteOffset : 1;

  bool WorkItemIDX : 1; // Always initialized.
  bool WorkItemIDY : 1;
  bool WorkItemIDZ : 1;

  // Private memory buffer
  // Compute directly in sgpr[0:1]
  // Other shaders indirect 64-bits at sgpr[0:1]
  bool ImplicitBufferPtr : 1;

  // Pointer to where the ABI inserts special kernel arguments separate from the
  // user arguments. This is an offset from the KernargSegmentPtr.
  bool ImplicitArgPtr : 1;

  // The hard-wired high half of the address of the global information table
  // for AMDPAL OS type. 0xffffffff represents no hard-wired high half, since
  // current hardware only allows a 16 bit value.
  unsigned GITPtrHigh;

  unsigned HighBitsOf32BitAddress;
  unsigned GDSSize;

  // Current recorded maximum possible occupancy.
  unsigned Occupancy;

  MCPhysReg getNextUserSGPR() const;

  MCPhysReg getNextSystemSGPR() const;

public:
  struct SpilledReg {
    unsigned VGPR = 0;
    int Lane = -1;

    SpilledReg() = default;
    SpilledReg(unsigned R, int L) : VGPR (R), Lane (L) {}

    bool hasLane() { return Lane != -1;}
    bool hasReg() { return VGPR != 0;}
  };

  struct SGPRSpillVGPRCSR {
    // VGPR used for SGPR spills
    unsigned VGPR;

    // If the VGPR is a CSR, the stack slot used to save/restore it in the
    // prolog/epilog.
    Optional<int> FI;

    SGPRSpillVGPRCSR(unsigned V, Optional<int> F) : VGPR(V), FI(F) {}
  };

  SparseBitVector<> WWMReservedRegs;

  void ReserveWWMRegister(unsigned reg) { WWMReservedRegs.set(reg); }

private:
  // SGPR->VGPR spilling support.
  using SpillRegMask = std::pair<unsigned, unsigned>;

  // Track VGPR + wave index for each subregister of the SGPR spilled to
  // frameindex key.
  DenseMap<int, std::vector<SpilledReg>> SGPRToVGPRSpills;
  unsigned NumVGPRSpillLanes = 0;
  SmallVector<SGPRSpillVGPRCSR, 2> SpillVGPRs;

public: // FIXME
  /// If this is set, an SGPR used for save/restore of the register used for the
  /// frame pointer.
  unsigned SGPRForFPSaveRestoreCopy = 0;
  Optional<int> FramePointerSaveIndex;

public:
  SIMachineFunctionInfo(const MachineFunction &MF);

  bool initializeBaseYamlFields(const yaml::SIMachineFunctionInfo &YamlMFI);

  ArrayRef<SpilledReg> getSGPRToVGPRSpills(int FrameIndex) const {
    auto I = SGPRToVGPRSpills.find(FrameIndex);
    return (I == SGPRToVGPRSpills.end()) ?
      ArrayRef<SpilledReg>() : makeArrayRef(I->second);
  }

  ArrayRef<SGPRSpillVGPRCSR> getSGPRSpillVGPRs() const {
    return SpillVGPRs;
  }

  AMDGPU::SIModeRegisterDefaults getMode() const {
    return Mode;
  }

  bool haveFreeLanesForSGPRSpill(const MachineFunction &MF,
                                 unsigned NumLane) const;
  bool allocateSGPRSpillToVGPR(MachineFunction &MF, int FI);
  void removeSGPRToVGPRFrameIndices(MachineFrameInfo &MFI);

  bool hasCalculatedTID() const { return TIDReg != 0; };
  unsigned getTIDReg() const { return TIDReg; };
  void setTIDReg(unsigned Reg) { TIDReg = Reg; }

  unsigned getBytesInStackArgArea() const {
    return BytesInStackArgArea;
  }

  void setBytesInStackArgArea(unsigned Bytes) {
    BytesInStackArgArea = Bytes;
  }

  // Add user SGPRs.
  unsigned addPrivateSegmentBuffer(const SIRegisterInfo &TRI);
  unsigned addDispatchPtr(const SIRegisterInfo &TRI);
  unsigned addQueuePtr(const SIRegisterInfo &TRI);
  unsigned addKernargSegmentPtr(const SIRegisterInfo &TRI);
  unsigned addDispatchID(const SIRegisterInfo &TRI);
  unsigned addFlatScratchInit(const SIRegisterInfo &TRI);
  unsigned addImplicitBufferPtr(const SIRegisterInfo &TRI);

  // Add system SGPRs.
  unsigned addWorkGroupIDX() {
    ArgInfo.WorkGroupIDX = ArgDescriptor::createRegister(getNextSystemSGPR());
    NumSystemSGPRs += 1;
    return ArgInfo.WorkGroupIDX.getRegister();
  }

  unsigned addWorkGroupIDY() {
    ArgInfo.WorkGroupIDY = ArgDescriptor::createRegister(getNextSystemSGPR());
    NumSystemSGPRs += 1;
    return ArgInfo.WorkGroupIDY.getRegister();
  }

  unsigned addWorkGroupIDZ() {
    ArgInfo.WorkGroupIDZ = ArgDescriptor::createRegister(getNextSystemSGPR());
    NumSystemSGPRs += 1;
    return ArgInfo.WorkGroupIDZ.getRegister();
  }

  unsigned addWorkGroupInfo() {
    ArgInfo.WorkGroupInfo = ArgDescriptor::createRegister(getNextSystemSGPR());
    NumSystemSGPRs += 1;
    return ArgInfo.WorkGroupInfo.getRegister();
  }

  // Add special VGPR inputs
  void setWorkItemIDX(ArgDescriptor Arg) {
    ArgInfo.WorkItemIDX = Arg;
  }

  void setWorkItemIDY(ArgDescriptor Arg) {
    ArgInfo.WorkItemIDY = Arg;
  }

  void setWorkItemIDZ(ArgDescriptor Arg) {
    ArgInfo.WorkItemIDZ = Arg;
  }

  unsigned addPrivateSegmentWaveByteOffset() {
    ArgInfo.PrivateSegmentWaveByteOffset
      = ArgDescriptor::createRegister(getNextSystemSGPR());
    NumSystemSGPRs += 1;
    return ArgInfo.PrivateSegmentWaveByteOffset.getRegister();
  }

  void setPrivateSegmentWaveByteOffset(unsigned Reg) {
    ArgInfo.PrivateSegmentWaveByteOffset = ArgDescriptor::createRegister(Reg);
  }

  bool hasPrivateSegmentBuffer() const {
    return PrivateSegmentBuffer;
  }

  bool hasDispatchPtr() const {
    return DispatchPtr;
  }

  bool hasQueuePtr() const {
    return QueuePtr;
  }

  bool hasKernargSegmentPtr() const {
    return KernargSegmentPtr;
  }

  bool hasDispatchID() const {
    return DispatchID;
  }

  bool hasFlatScratchInit() const {
    return FlatScratchInit;
  }

  bool hasWorkGroupIDX() const {
    return WorkGroupIDX;
  }

  bool hasWorkGroupIDY() const {
    return WorkGroupIDY;
  }

  bool hasWorkGroupIDZ() const {
    return WorkGroupIDZ;
  }

  bool hasWorkGroupInfo() const {
    return WorkGroupInfo;
  }

  bool hasPrivateSegmentWaveByteOffset() const {
    return PrivateSegmentWaveByteOffset;
  }

  bool hasWorkItemIDX() const {
    return WorkItemIDX;
  }

  bool hasWorkItemIDY() const {
    return WorkItemIDY;
  }

  bool hasWorkItemIDZ() const {
    return WorkItemIDZ;
  }

  bool hasImplicitArgPtr() const {
    return ImplicitArgPtr;
  }

  bool hasImplicitBufferPtr() const {
    return ImplicitBufferPtr;
  }

  AMDGPUFunctionArgInfo &getArgInfo() {
    return ArgInfo;
  }

  const AMDGPUFunctionArgInfo &getArgInfo() const {
    return ArgInfo;
  }

  std::pair<const ArgDescriptor *, const TargetRegisterClass *>
  getPreloadedValue(AMDGPUFunctionArgInfo::PreloadedValue Value) const {
    return ArgInfo.getPreloadedValue(Value);
  }

  Register getPreloadedReg(AMDGPUFunctionArgInfo::PreloadedValue Value) const {
    auto Arg = ArgInfo.getPreloadedValue(Value).first;
    return Arg ? Arg->getRegister() : Register();
  }

  unsigned getGITPtrHigh() const {
    return GITPtrHigh;
  }

  unsigned get32BitAddressHighBits() const {
    return HighBitsOf32BitAddress;
  }

  unsigned getGDSSize() const {
    return GDSSize;
  }

  unsigned getNumUserSGPRs() const {
    return NumUserSGPRs;
  }

  unsigned getNumPreloadedSGPRs() const {
    return NumUserSGPRs + NumSystemSGPRs;
  }

  unsigned getPrivateSegmentWaveByteOffsetSystemSGPR() const {
    return ArgInfo.PrivateSegmentWaveByteOffset.getRegister();
  }

  /// Returns the physical register reserved for use as the resource
  /// descriptor for scratch accesses.
  unsigned getScratchRSrcReg() const {
    return ScratchRSrcReg;
  }

  void setScratchRSrcReg(unsigned Reg) {
    assert(Reg != 0 && "Should never be unset");
    ScratchRSrcReg = Reg;
  }

  unsigned getScratchWaveOffsetReg() const {
    return ScratchWaveOffsetReg;
  }

  unsigned getFrameOffsetReg() const {
    return FrameOffsetReg;
  }

  void setFrameOffsetReg(unsigned Reg) {
    assert(Reg != 0 && "Should never be unset");
    FrameOffsetReg = Reg;
  }

  void setStackPtrOffsetReg(unsigned Reg) {
    assert(Reg != 0 && "Should never be unset");
    StackPtrOffsetReg = Reg;
  }

  // Note the unset value for this is AMDGPU::SP_REG rather than
  // NoRegister. This is mostly a workaround for MIR tests where state that
  // can't be directly computed from the function is not preserved in serialized
  // MIR.
  unsigned getStackPtrOffsetReg() const {
    return StackPtrOffsetReg;
  }

  void setScratchWaveOffsetReg(unsigned Reg) {
    assert(Reg != 0 && "Should never be unset");
    ScratchWaveOffsetReg = Reg;
  }

  unsigned getQueuePtrUserSGPR() const {
    return ArgInfo.QueuePtr.getRegister();
  }

  unsigned getImplicitBufferPtrUserSGPR() const {
    return ArgInfo.ImplicitBufferPtr.getRegister();
  }

  bool hasSpilledSGPRs() const {
    return HasSpilledSGPRs;
  }

  void setHasSpilledSGPRs(bool Spill = true) {
    HasSpilledSGPRs = Spill;
  }

  bool hasSpilledVGPRs() const {
    return HasSpilledVGPRs;
  }

  void setHasSpilledVGPRs(bool Spill = true) {
    HasSpilledVGPRs = Spill;
  }

  bool hasNonSpillStackObjects() const {
    return HasNonSpillStackObjects;
  }

  void setHasNonSpillStackObjects(bool StackObject = true) {
    HasNonSpillStackObjects = StackObject;
  }

  bool isStackRealigned() const {
    return IsStackRealigned;
  }

  void setIsStackRealigned(bool Realigned = true) {
    IsStackRealigned = Realigned;
  }

  unsigned getNumSpilledSGPRs() const {
    return NumSpilledSGPRs;
  }

  unsigned getNumSpilledVGPRs() const {
    return NumSpilledVGPRs;
  }

  void addToSpilledSGPRs(unsigned num) {
    NumSpilledSGPRs += num;
  }

  void addToSpilledVGPRs(unsigned num) {
    NumSpilledVGPRs += num;
  }

  unsigned getPSInputAddr() const {
    return PSInputAddr;
  }

  unsigned getPSInputEnable() const {
    return PSInputEnable;
  }

  bool isPSInputAllocated(unsigned Index) const {
    return PSInputAddr & (1 << Index);
  }

  void markPSInputAllocated(unsigned Index) {
    PSInputAddr |= 1 << Index;
  }

  void markPSInputEnabled(unsigned Index) {
    PSInputEnable |= 1 << Index;
  }

  bool returnsVoid() const {
    return ReturnsVoid;
  }

  void setIfReturnsVoid(bool Value) {
    ReturnsVoid = Value;
  }

  /// \returns A pair of default/requested minimum/maximum flat work group sizes
  /// for this function.
  std::pair<unsigned, unsigned> getFlatWorkGroupSizes() const {
    return FlatWorkGroupSizes;
  }

  /// \returns Default/requested minimum flat work group size for this function.
  unsigned getMinFlatWorkGroupSize() const {
    return FlatWorkGroupSizes.first;
  }

  /// \returns Default/requested maximum flat work group size for this function.
  unsigned getMaxFlatWorkGroupSize() const {
    return FlatWorkGroupSizes.second;
  }

  /// \returns A pair of default/requested minimum/maximum number of waves per
  /// execution unit.
  std::pair<unsigned, unsigned> getWavesPerEU() const {
    return WavesPerEU;
  }

  /// \returns Default/requested minimum number of waves per execution unit.
  unsigned getMinWavesPerEU() const {
    return WavesPerEU.first;
  }

  /// \returns Default/requested maximum number of waves per execution unit.
  unsigned getMaxWavesPerEU() const {
    return WavesPerEU.second;
  }

  /// \returns SGPR used for \p Dim's work group ID.
  unsigned getWorkGroupIDSGPR(unsigned Dim) const {
    switch (Dim) {
    case 0:
      assert(hasWorkGroupIDX());
      return ArgInfo.WorkGroupIDX.getRegister();
    case 1:
      assert(hasWorkGroupIDY());
      return ArgInfo.WorkGroupIDY.getRegister();
    case 2:
      assert(hasWorkGroupIDZ());
      return ArgInfo.WorkGroupIDZ.getRegister();
    }
    llvm_unreachable("unexpected dimension");
  }

  unsigned getLDSWaveSpillSize() const {
    return LDSWaveSpillSize;
  }

  const AMDGPUBufferPseudoSourceValue *getBufferPSV(const SIInstrInfo &TII,
                                                    const Value *BufferRsrc) {
    assert(BufferRsrc);
    auto PSV = BufferPSVs.try_emplace(
      BufferRsrc,
      llvm::make_unique<AMDGPUBufferPseudoSourceValue>(TII));
    return PSV.first->second.get();
  }

  const AMDGPUImagePseudoSourceValue *getImagePSV(const SIInstrInfo &TII,
                                                  const Value *ImgRsrc) {
    assert(ImgRsrc);
    auto PSV = ImagePSVs.try_emplace(
      ImgRsrc,
      llvm::make_unique<AMDGPUImagePseudoSourceValue>(TII));
    return PSV.first->second.get();
  }

  const AMDGPUGWSResourcePseudoSourceValue *getGWSPSV(const SIInstrInfo &TII) {
    if (!GWSResourcePSV) {
      GWSResourcePSV =
          llvm::make_unique<AMDGPUGWSResourcePseudoSourceValue>(TII);
    }

    return GWSResourcePSV.get();
  }

  unsigned getOccupancy() const {
    return Occupancy;
  }

  unsigned getMinAllowedOccupancy() const {
    if (!isMemoryBound() && !needsWaveLimiter())
      return Occupancy;
    return (Occupancy < 4) ? Occupancy : 4;
  }

  void limitOccupancy(const MachineFunction &MF);

  void limitOccupancy(unsigned Limit) {
    if (Occupancy > Limit)
      Occupancy = Limit;
  }

  void increaseOccupancy(const MachineFunction &MF, unsigned Limit) {
    if (Occupancy < Limit)
      Occupancy = Limit;
    limitOccupancy(MF);
  }
};

} // end namespace llvm

#endif // LLVM_LIB_TARGET_AMDGPU_SIMACHINEFUNCTIONINFO_H