llvm.org GIT mirror llvm / 15c435a lib / CodeGen / BasicTargetTransformInfo.cpp
15c435a

Tree @15c435a (Download .tar.gz)

BasicTargetTransformInfo.cpp @15c435araw · 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
//===- BasicTargetTransformInfo.cpp - Basic target-independent TTI impl ---===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
/// \file
/// This file provides the implementation of a basic TargetTransformInfo pass
/// predicated on the target abstractions present in the target independent
/// code generator. It uses these (primarily TargetLowering) to model as much
/// of the TTI query interface as possible. It is included by most targets so
/// that they can specialize only a small subset of the query space.
///
//===----------------------------------------------------------------------===//

#define DEBUG_TYPE "basictti"
#include "llvm/CodeGen/Passes.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Target/TargetLowering.h"
#include <utility>
using namespace llvm;

namespace {

class BasicTTI final : public ImmutablePass, public TargetTransformInfo {
  const TargetMachine *TM;

  /// Estimate the overhead of scalarizing an instruction. Insert and Extract
  /// are set if the result needs to be inserted and/or extracted from vectors.
  unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const;

  const TargetLoweringBase *getTLI() const { return TM->getTargetLowering(); }

public:
  BasicTTI() : ImmutablePass(ID), TM(0) {
    llvm_unreachable("This pass cannot be directly constructed");
  }

  BasicTTI(const TargetMachine *TM) : ImmutablePass(ID), TM(TM) {
    initializeBasicTTIPass(*PassRegistry::getPassRegistry());
  }

  void initializePass() override {
    pushTTIStack(this);
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    TargetTransformInfo::getAnalysisUsage(AU);
  }

  /// Pass identification.
  static char ID;

  /// Provide necessary pointer adjustments for the two base classes.
  void *getAdjustedAnalysisPointer(const void *ID) override {
    if (ID == &TargetTransformInfo::ID)
      return (TargetTransformInfo*)this;
    return this;
  }

  bool hasBranchDivergence() const override;

  /// \name Scalar TTI Implementations
  /// @{

  bool isLegalAddImmediate(int64_t imm) const override;
  bool isLegalICmpImmediate(int64_t imm) const override;
  bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV,
                             int64_t BaseOffset, bool HasBaseReg,
                             int64_t Scale) const override;
  int getScalingFactorCost(Type *Ty, GlobalValue *BaseGV,
                           int64_t BaseOffset, bool HasBaseReg,
                           int64_t Scale) const override;
  bool isTruncateFree(Type *Ty1, Type *Ty2) const override;
  bool isTypeLegal(Type *Ty) const override;
  unsigned getJumpBufAlignment() const override;
  unsigned getJumpBufSize() const override;
  bool shouldBuildLookupTables() const override;
  bool haveFastSqrt(Type *Ty) const override;
  void getUnrollingPreferences(Loop *L,
                               UnrollingPreferences &UP) const override;

  /// @}

  /// \name Vector TTI Implementations
  /// @{

  unsigned getNumberOfRegisters(bool Vector) const override;
  unsigned getMaximumUnrollFactor() const override;
  unsigned getRegisterBitWidth(bool Vector) const override;
  unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty, OperandValueKind,
                                  OperandValueKind) const override;
  unsigned getShuffleCost(ShuffleKind Kind, Type *Tp,
                          int Index, Type *SubTp) const override;
  unsigned getCastInstrCost(unsigned Opcode, Type *Dst,
                            Type *Src) const override;
  unsigned getCFInstrCost(unsigned Opcode) const override;
  unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
                              Type *CondTy) const override;
  unsigned getVectorInstrCost(unsigned Opcode, Type *Val,
                              unsigned Index) const override;
  unsigned getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
                           unsigned AddressSpace) const override;
  unsigned getIntrinsicInstrCost(Intrinsic::ID, Type *RetTy,
                                 ArrayRef<Type*> Tys) const override;
  unsigned getNumberOfParts(Type *Tp) const override;
  unsigned getAddressComputationCost( Type *Ty, bool IsComplex) const override;
  unsigned getReductionCost(unsigned Opcode, Type *Ty,
                            bool IsPairwise) const override;

  /// @}
};

}

INITIALIZE_AG_PASS(BasicTTI, TargetTransformInfo, "basictti",
                   "Target independent code generator's TTI", true, true, false)
char BasicTTI::ID = 0;

ImmutablePass *
llvm::createBasicTargetTransformInfoPass(const TargetMachine *TM) {
  return new BasicTTI(TM);
}

bool BasicTTI::hasBranchDivergence() const { return false; }

bool BasicTTI::isLegalAddImmediate(int64_t imm) const {
  return getTLI()->isLegalAddImmediate(imm);
}

bool BasicTTI::isLegalICmpImmediate(int64_t imm) const {
  return getTLI()->isLegalICmpImmediate(imm);
}

bool BasicTTI::isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV,
                                     int64_t BaseOffset, bool HasBaseReg,
                                     int64_t Scale) const {
  TargetLoweringBase::AddrMode AM;
  AM.BaseGV = BaseGV;
  AM.BaseOffs = BaseOffset;
  AM.HasBaseReg = HasBaseReg;
  AM.Scale = Scale;
  return getTLI()->isLegalAddressingMode(AM, Ty);
}

int BasicTTI::getScalingFactorCost(Type *Ty, GlobalValue *BaseGV,
                                   int64_t BaseOffset, bool HasBaseReg,
                                   int64_t Scale) const {
  TargetLoweringBase::AddrMode AM;
  AM.BaseGV = BaseGV;
  AM.BaseOffs = BaseOffset;
  AM.HasBaseReg = HasBaseReg;
  AM.Scale = Scale;
  return getTLI()->getScalingFactorCost(AM, Ty);
}

bool BasicTTI::isTruncateFree(Type *Ty1, Type *Ty2) const {
  return getTLI()->isTruncateFree(Ty1, Ty2);
}

bool BasicTTI::isTypeLegal(Type *Ty) const {
  EVT T = getTLI()->getValueType(Ty);
  return getTLI()->isTypeLegal(T);
}

unsigned BasicTTI::getJumpBufAlignment() const {
  return getTLI()->getJumpBufAlignment();
}

unsigned BasicTTI::getJumpBufSize() const {
  return getTLI()->getJumpBufSize();
}

bool BasicTTI::shouldBuildLookupTables() const {
  const TargetLoweringBase *TLI = getTLI();
  return TLI->supportJumpTables() &&
      (TLI->isOperationLegalOrCustom(ISD::BR_JT, MVT::Other) ||
       TLI->isOperationLegalOrCustom(ISD::BRIND, MVT::Other));
}

bool BasicTTI::haveFastSqrt(Type *Ty) const {
  const TargetLoweringBase *TLI = getTLI();
  EVT VT = TLI->getValueType(Ty);
  return TLI->isTypeLegal(VT) && TLI->isOperationLegalOrCustom(ISD::FSQRT, VT);
}

void BasicTTI::getUnrollingPreferences(Loop *, UnrollingPreferences &) const { }

//===----------------------------------------------------------------------===//
//
// Calls used by the vectorizers.
//
//===----------------------------------------------------------------------===//

unsigned BasicTTI::getScalarizationOverhead(Type *Ty, bool Insert,
                                            bool Extract) const {
  assert (Ty->isVectorTy() && "Can only scalarize vectors");
  unsigned Cost = 0;

  for (int i = 0, e = Ty->getVectorNumElements(); i < e; ++i) {
    if (Insert)
      Cost += TopTTI->getVectorInstrCost(Instruction::InsertElement, Ty, i);
    if (Extract)
      Cost += TopTTI->getVectorInstrCost(Instruction::ExtractElement, Ty, i);
  }

  return Cost;
}

unsigned BasicTTI::getNumberOfRegisters(bool Vector) const {
  return 1;
}

unsigned BasicTTI::getRegisterBitWidth(bool Vector) const {
  return 32;
}

unsigned BasicTTI::getMaximumUnrollFactor() const {
  return 1;
}

unsigned BasicTTI::getArithmeticInstrCost(unsigned Opcode, Type *Ty,
                                          OperandValueKind,
                                          OperandValueKind) const {
  // Check if any of the operands are vector operands.
  const TargetLoweringBase *TLI = getTLI();
  int ISD = TLI->InstructionOpcodeToISD(Opcode);
  assert(ISD && "Invalid opcode");

  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(Ty);

  bool IsFloat = Ty->getScalarType()->isFloatingPointTy();
  // Assume that floating point arithmetic operations cost twice as much as
  // integer operations.
  unsigned OpCost = (IsFloat ? 2 : 1);

  if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
    // The operation is legal. Assume it costs 1.
    // If the type is split to multiple registers, assume that there is some
    // overhead to this.
    // TODO: Once we have extract/insert subvector cost we need to use them.
    if (LT.first > 1)
      return LT.first * 2 * OpCost;
    return LT.first * 1 * OpCost;
  }

  if (!TLI->isOperationExpand(ISD, LT.second)) {
    // If the operation is custom lowered then assume
    // thare the code is twice as expensive.
    return LT.first * 2 * OpCost;
  }

  // Else, assume that we need to scalarize this op.
  if (Ty->isVectorTy()) {
    unsigned Num = Ty->getVectorNumElements();
    unsigned Cost = TopTTI->getArithmeticInstrCost(Opcode, Ty->getScalarType());
    // return the cost of multiple scalar invocation plus the cost of inserting
    // and extracting the values.
    return getScalarizationOverhead(Ty, true, true) + Num * Cost;
  }

  // We don't know anything about this scalar instruction.
  return OpCost;
}

unsigned BasicTTI::getShuffleCost(ShuffleKind Kind, Type *Tp, int Index,
                                  Type *SubTp) const {
  return 1;
}

unsigned BasicTTI::getCastInstrCost(unsigned Opcode, Type *Dst,
                                    Type *Src) const {
  const TargetLoweringBase *TLI = getTLI();
  int ISD = TLI->InstructionOpcodeToISD(Opcode);
  assert(ISD && "Invalid opcode");

  std::pair<unsigned, MVT> SrcLT = TLI->getTypeLegalizationCost(Src);
  std::pair<unsigned, MVT> DstLT = TLI->getTypeLegalizationCost(Dst);

  // Check for NOOP conversions.
  if (SrcLT.first == DstLT.first &&
      SrcLT.second.getSizeInBits() == DstLT.second.getSizeInBits()) {

      // Bitcast between types that are legalized to the same type are free.
      if (Opcode == Instruction::BitCast || Opcode == Instruction::Trunc)
        return 0;
  }

  if (Opcode == Instruction::Trunc &&
      TLI->isTruncateFree(SrcLT.second, DstLT.second))
    return 0;

  if (Opcode == Instruction::ZExt &&
      TLI->isZExtFree(SrcLT.second, DstLT.second))
    return 0;

  // If the cast is marked as legal (or promote) then assume low cost.
  if (SrcLT.first == DstLT.first &&
      TLI->isOperationLegalOrPromote(ISD, DstLT.second))
    return 1;

  // Handle scalar conversions.
  if (!Src->isVectorTy() && !Dst->isVectorTy()) {

    // Scalar bitcasts are usually free.
    if (Opcode == Instruction::BitCast)
      return 0;

    // Just check the op cost. If the operation is legal then assume it costs 1.
    if (!TLI->isOperationExpand(ISD, DstLT.second))
      return  1;

    // Assume that illegal scalar instruction are expensive.
    return 4;
  }

  // Check vector-to-vector casts.
  if (Dst->isVectorTy() && Src->isVectorTy()) {

    // If the cast is between same-sized registers, then the check is simple.
    if (SrcLT.first == DstLT.first &&
        SrcLT.second.getSizeInBits() == DstLT.second.getSizeInBits()) {

      // Assume that Zext is done using AND.
      if (Opcode == Instruction::ZExt)
        return 1;

      // Assume that sext is done using SHL and SRA.
      if (Opcode == Instruction::SExt)
        return 2;

      // Just check the op cost. If the operation is legal then assume it costs
      // 1 and multiply by the type-legalization overhead.
      if (!TLI->isOperationExpand(ISD, DstLT.second))
        return SrcLT.first * 1;
    }

    // If we are converting vectors and the operation is illegal, or
    // if the vectors are legalized to different types, estimate the
    // scalarization costs.
    unsigned Num = Dst->getVectorNumElements();
    unsigned Cost = TopTTI->getCastInstrCost(Opcode, Dst->getScalarType(),
                                             Src->getScalarType());

    // Return the cost of multiple scalar invocation plus the cost of
    // inserting and extracting the values.
    return getScalarizationOverhead(Dst, true, true) + Num * Cost;
  }

  // We already handled vector-to-vector and scalar-to-scalar conversions. This
  // is where we handle bitcast between vectors and scalars. We need to assume
  //  that the conversion is scalarized in one way or another.
  if (Opcode == Instruction::BitCast)
    // Illegal bitcasts are done by storing and loading from a stack slot.
    return (Src->isVectorTy()? getScalarizationOverhead(Src, false, true):0) +
           (Dst->isVectorTy()? getScalarizationOverhead(Dst, true, false):0);

  llvm_unreachable("Unhandled cast");
 }

unsigned BasicTTI::getCFInstrCost(unsigned Opcode) const {
  // Branches are assumed to be predicted.
  return 0;
}

unsigned BasicTTI::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
                                      Type *CondTy) const {
  const TargetLoweringBase *TLI = getTLI();
  int ISD = TLI->InstructionOpcodeToISD(Opcode);
  assert(ISD && "Invalid opcode");

  // Selects on vectors are actually vector selects.
  if (ISD == ISD::SELECT) {
    assert(CondTy && "CondTy must exist");
    if (CondTy->isVectorTy())
      ISD = ISD::VSELECT;
  }

  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(ValTy);

  if (!TLI->isOperationExpand(ISD, LT.second)) {
    // The operation is legal. Assume it costs 1. Multiply
    // by the type-legalization overhead.
    return LT.first * 1;
  }

  // Otherwise, assume that the cast is scalarized.
  if (ValTy->isVectorTy()) {
    unsigned Num = ValTy->getVectorNumElements();
    if (CondTy)
      CondTy = CondTy->getScalarType();
    unsigned Cost = TopTTI->getCmpSelInstrCost(Opcode, ValTy->getScalarType(),
                                               CondTy);

    // Return the cost of multiple scalar invocation plus the cost of inserting
    // and extracting the values.
    return getScalarizationOverhead(ValTy, true, false) + Num * Cost;
  }

  // Unknown scalar opcode.
  return 1;
}

unsigned BasicTTI::getVectorInstrCost(unsigned Opcode, Type *Val,
                                      unsigned Index) const {
  std::pair<unsigned, MVT> LT =  getTLI()->getTypeLegalizationCost(Val->getScalarType());

  return LT.first;
}

unsigned BasicTTI::getMemoryOpCost(unsigned Opcode, Type *Src,
                                   unsigned Alignment,
                                   unsigned AddressSpace) const {
  assert(!Src->isVoidTy() && "Invalid type");
  std::pair<unsigned, MVT> LT = getTLI()->getTypeLegalizationCost(Src);

  // Assuming that all loads of legal types cost 1.
  unsigned Cost = LT.first;

  if (Src->isVectorTy() &&
      Src->getPrimitiveSizeInBits() < LT.second.getSizeInBits()) {
    // This is a vector load that legalizes to a larger type than the vector
    // itself. Unless the corresponding extending load or truncating store is
    // legal, then this will scalarize.
    TargetLowering::LegalizeAction LA;
    MVT MemVT = getTLI()->getSimpleValueType(Src, true);
    if (Opcode == Instruction::Store)
      LA = getTLI()->getTruncStoreAction(LT.second, MemVT);
    else
      LA = getTLI()->getLoadExtAction(ISD::EXTLOAD, MemVT);

    if (LA != TargetLowering::Legal && LA != TargetLowering::Custom) {
      // This is a vector load/store for some illegal type that is scalarized.
      // We must account for the cost of building or decomposing the vector.
      Cost += getScalarizationOverhead(Src, Opcode != Instruction::Store,
                                            Opcode == Instruction::Store);
    }
  }

  return Cost;
}

unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
                                         ArrayRef<Type *> Tys) const {
  unsigned ISD = 0;
  switch (IID) {
  default: {
    // Assume that we need to scalarize this intrinsic.
    unsigned ScalarizationCost = 0;
    unsigned ScalarCalls = 1;
    if (RetTy->isVectorTy()) {
      ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
      ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
    }
    for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
      if (Tys[i]->isVectorTy()) {
        ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
        ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
      }
    }

    return ScalarCalls + ScalarizationCost;
  }
  // Look for intrinsics that can be lowered directly or turned into a scalar
  // intrinsic call.
  case Intrinsic::sqrt:    ISD = ISD::FSQRT;  break;
  case Intrinsic::sin:     ISD = ISD::FSIN;   break;
  case Intrinsic::cos:     ISD = ISD::FCOS;   break;
  case Intrinsic::exp:     ISD = ISD::FEXP;   break;
  case Intrinsic::exp2:    ISD = ISD::FEXP2;  break;
  case Intrinsic::log:     ISD = ISD::FLOG;   break;
  case Intrinsic::log10:   ISD = ISD::FLOG10; break;
  case Intrinsic::log2:    ISD = ISD::FLOG2;  break;
  case Intrinsic::fabs:    ISD = ISD::FABS;   break;
  case Intrinsic::copysign: ISD = ISD::FCOPYSIGN; break;
  case Intrinsic::floor:   ISD = ISD::FFLOOR; break;
  case Intrinsic::ceil:    ISD = ISD::FCEIL;  break;
  case Intrinsic::trunc:   ISD = ISD::FTRUNC; break;
  case Intrinsic::nearbyint:
                           ISD = ISD::FNEARBYINT; break;
  case Intrinsic::rint:    ISD = ISD::FRINT;  break;
  case Intrinsic::round:   ISD = ISD::FROUND; break;
  case Intrinsic::pow:     ISD = ISD::FPOW;   break;
  case Intrinsic::fma:     ISD = ISD::FMA;    break;
  case Intrinsic::fmuladd: ISD = ISD::FMA;    break; // FIXME: mul + add?
  case Intrinsic::lifetime_start:
  case Intrinsic::lifetime_end:
    return 0;
  }

  const TargetLoweringBase *TLI = getTLI();
  std::pair<unsigned, MVT> LT = TLI->getTypeLegalizationCost(RetTy);

  if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
    // The operation is legal. Assume it costs 1.
    // If the type is split to multiple registers, assume that thre is some
    // overhead to this.
    // TODO: Once we have extract/insert subvector cost we need to use them.
    if (LT.first > 1)
      return LT.first * 2;
    return LT.first * 1;
  }

  if (!TLI->isOperationExpand(ISD, LT.second)) {
    // If the operation is custom lowered then assume
    // thare the code is twice as expensive.
    return LT.first * 2;
  }

  // Else, assume that we need to scalarize this intrinsic. For math builtins
  // this will emit a costly libcall, adding call overhead and spills. Make it
  // very expensive.
  if (RetTy->isVectorTy()) {
    unsigned Num = RetTy->getVectorNumElements();
    unsigned Cost = TopTTI->getIntrinsicInstrCost(IID, RetTy->getScalarType(),
                                                  Tys);
    return 10 * Cost * Num;
  }

  // This is going to be turned into a library call, make it expensive.
  return 10;
}

unsigned BasicTTI::getNumberOfParts(Type *Tp) const {
  std::pair<unsigned, MVT> LT = getTLI()->getTypeLegalizationCost(Tp);
  return LT.first;
}

unsigned BasicTTI::getAddressComputationCost(Type *Ty, bool IsComplex) const {
  return 0;
}

unsigned BasicTTI::getReductionCost(unsigned Opcode, Type *Ty,
                                    bool IsPairwise) const {
  assert(Ty->isVectorTy() && "Expect a vector type");
  unsigned NumVecElts = Ty->getVectorNumElements();
  unsigned NumReduxLevels = Log2_32(NumVecElts);
  unsigned ArithCost = NumReduxLevels *
    TopTTI->getArithmeticInstrCost(Opcode, Ty);
  // Assume the pairwise shuffles add a cost.
  unsigned ShuffleCost =
      NumReduxLevels * (IsPairwise + 1) *
      TopTTI->getShuffleCost(SK_ExtractSubvector, Ty, NumVecElts / 2, Ty);
  return ShuffleCost + ArithCost + getScalarizationOverhead(Ty, false, true);
}