llvm.org GIT mirror llvm / release_40 lib / Target / AMDGPU / AMDGPUSubtarget.h
release_40

Tree @release_40 (Download .tar.gz)

AMDGPUSubtarget.h @release_40raw · 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
//=====-- AMDGPUSubtarget.h - Define Subtarget for AMDGPU ------*- C++ -*-====//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//==-----------------------------------------------------------------------===//
//
/// \file
/// \brief AMDGPU specific subclass of TargetSubtarget.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H

#include "AMDGPU.h"
#include "R600InstrInfo.h"
#include "R600ISelLowering.h"
#include "R600FrameLowering.h"
#include "SIInstrInfo.h"
#include "SIISelLowering.h"
#include "SIFrameLowering.h"
#include "Utils/AMDGPUBaseInfo.h"
#include "llvm/ADT/Triple.h"
#include "llvm/CodeGen/GlobalISel/GISelAccessor.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"

namespace llvm {

class StringRef;

class AMDGPUSubtarget : public AMDGPUGenSubtargetInfo {
public:
  enum Generation {
    R600 = 0,
    R700,
    EVERGREEN,
    NORTHERN_ISLANDS,
    SOUTHERN_ISLANDS,
    SEA_ISLANDS,
    VOLCANIC_ISLANDS,
  };

  enum {
    ISAVersion0_0_0,
    ISAVersion7_0_0,
    ISAVersion7_0_1,
    ISAVersion7_0_2,
    ISAVersion8_0_0,
    ISAVersion8_0_1,
    ISAVersion8_0_2,
    ISAVersion8_0_3,
    ISAVersion8_0_4,
    ISAVersion8_1_0,
  };

protected:
  // Basic subtarget description.
  Triple TargetTriple;
  Generation Gen;
  unsigned IsaVersion;
  unsigned WavefrontSize;
  int LocalMemorySize;
  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 FP16Denormals;
  bool FP32Denormals;
  bool FP64Denormals;
  bool FPExceptions;
  bool FlatForGlobal;
  bool UnalignedScratchAccess;
  bool UnalignedBufferAccess;
  bool EnableXNACK;
  bool DebuggerInsertNops;
  bool DebuggerReserveRegs;
  bool DebuggerEmitPrologue;

  // Used as options.
  bool EnableVGPRSpilling;
  bool EnablePromoteAlloca;
  bool EnableLoadStoreOpt;
  bool EnableUnsafeDSOffsetFolding;
  bool EnableSIScheduler;
  bool DumpCode;

  // Subtarget statically properties set by tablegen
  bool FP64;
  bool IsGCN;
  bool GCN1Encoding;
  bool GCN3Encoding;
  bool CIInsts;
  bool SGPRInitBug;
  bool HasSMemRealTime;
  bool Has16BitInsts;
  bool HasMovrel;
  bool HasVGPRIndexMode;
  bool HasScalarStores;
  bool HasInv2PiInlineImm;
  bool FlatAddressSpace;
  bool R600ALUInst;
  bool CaymanISA;
  bool CFALUBug;
  bool HasVertexCache;
  short TexVTXClauseSize;
  bool ScalarizeGlobal;

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

  InstrItineraryData InstrItins;
  SelectionDAGTargetInfo TSInfo;

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

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

  const AMDGPUInstrInfo *getInstrInfo() const override = 0;
  const AMDGPUFrameLowering *getFrameLowering() const override = 0;
  const AMDGPUTargetLowering *getTargetLowering() const override = 0;
  const AMDGPURegisterInfo *getRegisterInfo() const override = 0;

  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);

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

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

  bool isOpenCLEnv() const {
    return TargetTriple.getEnvironment() == Triple::OpenCL;
  }

  Generation getGeneration() const {
    return Gen;
  }

  unsigned getWavefrontSize() const {
    return WavefrontSize;
  }

  int getLocalMemorySize() const {
    return LocalMemorySize;
  }

  int getLDSBankCount() const {
    return LDSBankCount;
  }

  unsigned getMaxPrivateElementSize() const {
    return MaxPrivateElementSize;
  }

  bool has16BitInsts() const {
    return Has16BitInsts;
  }

  bool hasHWFP64() const {
    return FP64;
  }

  bool hasFastFMAF32() const {
    return FastFMAF32;
  }

  bool hasHalfRate64Ops() const {
    return HalfRate64Ops;
  }

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

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

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

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

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

    if (Size == 64)
      return (getGeneration() >= SOUTHERN_ISLANDS);

    return false;
  }

  bool hasMulU24() const {
    return (getGeneration() >= EVERGREEN);
  }

  bool hasMulI24() const {
    return (getGeneration() >= SOUTHERN_ISLANDS ||
            hasCaymanISA());
  }

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

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

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

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

  bool hasCaymanISA() const {
    return CaymanISA;
  }

  bool isPromoteAllocaEnabled() const {
    return EnablePromoteAlloca;
  }

  bool unsafeDSOffsetFoldingEnabled() const {
    return EnableUnsafeDSOffsetFolding;
  }

  bool dumpCode() const {
    return DumpCode;
  }

  bool enableIEEEBit(const MachineFunction &MF) const {
    return AMDGPU::isCompute(MF.getFunction()->getCallingConv());
  }

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

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

  bool hasFP16Denormals() const {
    return FP16Denormals;
  }

  bool hasFP32Denormals() const {
    return FP32Denormals;
  }

  bool hasFP64Denormals() const {
    return FP64Denormals;
  }

  bool hasFPExceptions() const {
    return FPExceptions;
  }

  bool useFlatForGlobal() const {
    return FlatForGlobal;
  }

  bool hasUnalignedBufferAccess() const {
    return UnalignedBufferAccess;
  }

  bool hasUnalignedScratchAccess() const {
    return UnalignedScratchAccess;
  }

  bool isXNACKEnabled() const {
    return EnableXNACK;
  }

  bool isMesaKernel(const MachineFunction &MF) const {
    return isMesa3DOS() && !AMDGPU::isShader(MF.getFunction()->getCallingConv());
  }

  // Covers VS/PS/CS graphics shaders
  bool isMesaGfxShader(const MachineFunction &MF) const {
    return isMesa3DOS() && AMDGPU::isShader(MF.getFunction()->getCallingConv());
  }

  bool isAmdCodeObjectV2(const MachineFunction &MF) const {
    return isAmdHsaOS() || isMesaKernel(MF);
  }

  /// \brief Returns the offset in bytes from the start of the input buffer
  ///        of the first explicit kernel argument.
  unsigned getExplicitKernelArgOffset(const MachineFunction &MF) const {
    return isAmdCodeObjectV2(MF) ? 0 : 36;
  }

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

  unsigned getImplicitArgNumBytes(const MachineFunction &MF) const {
    if (isMesaKernel(MF))
      return 16;
    if (isAmdHsaOS() && isOpenCLEnv())
      return 32;
    return 0;
  }

  unsigned getStackAlignment() const {
    // Scratch is allocated in 256 dword per wave blocks.
    return 4 * 256 / getWavefrontSize();
  }

  bool enableMachineScheduler() const override {
    return true;
  }

  bool enableSubRegLiveness() const override {
    return true;
  }

  /// \returns Number of execution units per compute unit supported by the
  /// subtarget.
  unsigned getEUsPerCU() const {
    return 4;
  }

  /// \returns Maximum number of work groups per compute unit supported by the
  /// subtarget and limited by given flat work group size.
  unsigned getMaxWorkGroupsPerCU(unsigned FlatWorkGroupSize) const {
    if (getGeneration() < AMDGPUSubtarget::SOUTHERN_ISLANDS)
      return 8;
    return getWavesPerWorkGroup(FlatWorkGroupSize) == 1 ? 40 : 16;
  }

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

  /// \returns Maximum number of waves per compute unit supported by the
  /// subtarget and limited by given flat work group size.
  unsigned getMaxWavesPerCU(unsigned FlatWorkGroupSize) const {
    return getWavesPerWorkGroup(FlatWorkGroupSize);
  }

  /// \returns Minimum number of waves per execution unit supported by the
  /// subtarget.
  unsigned getMinWavesPerEU() const {
    return 1;
  }

  /// \returns Maximum number of waves per execution unit supported by the
  /// subtarget without any kind of limitation.
  unsigned getMaxWavesPerEU() const {
    if (getGeneration() < AMDGPUSubtarget::SOUTHERN_ISLANDS)
      return 8;
    // FIXME: Need to take scratch memory into account.
    return 10;
  }

  /// \returns Maximum number of waves per execution unit supported by the
  /// subtarget and limited by given flat work group size.
  unsigned getMaxWavesPerEU(unsigned FlatWorkGroupSize) const {
    return alignTo(getMaxWavesPerCU(FlatWorkGroupSize), getEUsPerCU()) /
      getEUsPerCU();
  }

  /// \returns Minimum flat work group size supported by the subtarget.
  unsigned getMinFlatWorkGroupSize() const {
    return 1;
  }

  /// \returns Maximum flat work group size supported by the subtarget.
  unsigned getMaxFlatWorkGroupSize() const {
    return 2048;
  }

  /// \returns Number of waves per work group given the flat work group size.
  unsigned getWavesPerWorkGroup(unsigned FlatWorkGroupSize) const {
    return alignTo(FlatWorkGroupSize, getWavefrontSize()) / getWavefrontSize();
  }

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

  /// \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;
};

class R600Subtarget final : public AMDGPUSubtarget {
private:
  R600InstrInfo InstrInfo;
  R600FrameLowering FrameLowering;
  R600TargetLowering TLInfo;

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();
  }

  bool hasCFAluBug() const {
    return CFALUBug;
  }

  bool hasVertexCache() const {
    return HasVertexCache;
  }

  short getTexVTXClauseSize() const {
    return TexVTXClauseSize;
  }
};

class SISubtarget final : public AMDGPUSubtarget {
public:
  enum {
    // The closed Vulkan driver sets 96, which limits the wave count to 8 but
    // doesn't spill SGPRs as much as when 80 is set.
    FIXED_SGPR_COUNT_FOR_INIT_BUG = 96
  };

private:
  SIInstrInfo InstrInfo;
  SIFrameLowering FrameLowering;
  SITargetLowering TLInfo;
  std::unique_ptr<GISelAccessor> GISel;

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

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

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

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

  const CallLowering *getCallLowering() const override {
    assert(GISel && "Access to GlobalISel APIs not set");
    return GISel->getCallLowering();
  }

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

  void setGISelAccessor(GISelAccessor &GISel) {
    this->GISel.reset(&GISel);
  }

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

  bool isVGPRSpillingEnabled(const Function& F) const;

  unsigned getMaxNumUserSGPRs() const {
    return 16;
  }

  bool hasFlatAddressSpace() const {
    return FlatAddressSpace;
  }

  bool hasSMemRealTime() const {
    return HasSMemRealTime;
  }

  bool hasMovrel() const {
    return HasMovrel;
  }

  bool hasVGPRIndexMode() const {
    return HasVGPRIndexMode;
  }

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

  bool hasScalarStores() const {
    return HasScalarStores;
  }

  bool hasInv2PiInlineImm() const {
    return HasInv2PiInlineImm;
  }

  bool enableSIScheduler() const {
    return EnableSIScheduler;
  }

  bool debuggerSupported() const {
    return debuggerInsertNops() && debuggerReserveRegs() &&
      debuggerEmitPrologue();
  }

  bool debuggerInsertNops() const {
    return DebuggerInsertNops;
  }

  bool debuggerReserveRegs() const {
    return DebuggerReserveRegs;
  }

  bool debuggerEmitPrologue() const {
    return DebuggerEmitPrologue;
  }

  bool loadStoreOptEnabled() const {
    return EnableLoadStoreOpt;
  }

  bool hasSGPRInitBug() const {
    return SGPRInitBug;
  }

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

  unsigned getKernArgSegmentSize(const MachineFunction &MF, unsigned ExplictArgBytes) const;

  /// 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 waitcnt instruction is needed before barrier instruction,
  /// false otherwise.
  bool needWaitcntBeforeBarrier() const {
    return true;
  }

  unsigned getMaxNumSGPRs() const;
};

} // end namespace llvm

#endif // LLVM_LIB_TARGET_AMDGPU_AMDGPUSUBTARGET_H