llvm.org GIT mirror llvm / release_39 include / llvm / CodeGen / BasicTTIImpl.h
release_39

Tree @release_39 (Download .tar.gz)

BasicTTIImpl.h @release_39raw · 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
//===- BasicTTIImpl.h -------------------------------------------*- C++ -*-===//
//
//                     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 a helper that implements much of the TTI interface in
/// terms of the target-independent code generator and TargetLowering
/// interfaces.
///
//===----------------------------------------------------------------------===//

#ifndef LLVM_CODEGEN_BASICTTIIMPL_H
#define LLVM_CODEGEN_BASICTTIIMPL_H

#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/TargetTransformInfoImpl.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include "llvm/Analysis/TargetLibraryInfo.h"

namespace llvm {

extern cl::opt<unsigned> PartialUnrollingThreshold;

/// \brief Base class which can be used to help build a TTI implementation.
///
/// This class provides as much implementation of the TTI interface as is
/// possible using the target independent parts of the code generator.
///
/// In order to subclass it, your class must implement a getST() method to
/// return the subtarget, and a getTLI() method to return the target lowering.
/// We need these methods implemented in the derived class so that this class
/// doesn't have to duplicate storage for them.
template <typename T>
class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
private:
  typedef TargetTransformInfoImplCRTPBase<T> BaseT;
  typedef TargetTransformInfo TTI;

  /// 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) {
    assert(Ty->isVectorTy() && "Can only scalarize vectors");
    unsigned Cost = 0;

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

    return Cost;
  }

  /// Estimate the cost overhead of SK_Alternate shuffle.
  unsigned getAltShuffleOverhead(Type *Ty) {
    assert(Ty->isVectorTy() && "Can only shuffle vectors");
    unsigned Cost = 0;
    // Shuffle cost is equal to the cost of extracting element from its argument
    // plus the cost of inserting them onto the result vector.

    // e.g. <4 x float> has a mask of <0,5,2,7> i.e we need to extract from
    // index 0 of first vector, index 1 of second vector,index 2 of first
    // vector and finally index 3 of second vector and insert them at index
    // <0,1,2,3> of result vector.
    for (int i = 0, e = Ty->getVectorNumElements(); i < e; ++i) {
      Cost += static_cast<T *>(this)
                  ->getVectorInstrCost(Instruction::InsertElement, Ty, i);
      Cost += static_cast<T *>(this)
                  ->getVectorInstrCost(Instruction::ExtractElement, Ty, i);
    }
    return Cost;
  }

  /// \brief Local query method delegates up to T which *must* implement this!
  const TargetSubtargetInfo *getST() const {
    return static_cast<const T *>(this)->getST();
  }

  /// \brief Local query method delegates up to T which *must* implement this!
  const TargetLoweringBase *getTLI() const {
    return static_cast<const T *>(this)->getTLI();
  }

protected:
  explicit BasicTTIImplBase(const TargetMachine *TM, const DataLayout &DL)
      : BaseT(DL) {}

  using TargetTransformInfoImplBase::DL;

public:
  // Provide value semantics. MSVC requires that we spell all of these out.
  BasicTTIImplBase(const BasicTTIImplBase &Arg)
      : BaseT(static_cast<const BaseT &>(Arg)) {}
  BasicTTIImplBase(BasicTTIImplBase &&Arg)
      : BaseT(std::move(static_cast<BaseT &>(Arg))) {}

  /// \name Scalar TTI Implementations
  /// @{
  bool allowsMisalignedMemoryAccesses(unsigned BitWidth, unsigned AddressSpace,
                                      unsigned Alignment, bool *Fast) const {
    MVT M = MVT::getIntegerVT(BitWidth);
    return getTLI()->allowsMisalignedMemoryAccesses(M, AddressSpace, Alignment, Fast);
  }

  bool hasBranchDivergence() { return false; }

  bool isSourceOfDivergence(const Value *V) { return false; }

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

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

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

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

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

  bool isProfitableToHoist(Instruction *I) {
    return getTLI()->isProfitableToHoist(I);
  }

  bool isTypeLegal(Type *Ty) {
    EVT VT = getTLI()->getValueType(DL, Ty);
    return getTLI()->isTypeLegal(VT);
  }

  int getGEPCost(Type *PointeeType, const Value *Ptr,
                 ArrayRef<const Value *> Operands) {
    return BaseT::getGEPCost(PointeeType, Ptr, Operands);
  }

  unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
                            ArrayRef<const Value *> Arguments) {
    return BaseT::getIntrinsicCost(IID, RetTy, Arguments);
  }

  unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy,
                            ArrayRef<Type *> ParamTys) {
    if (IID == Intrinsic::cttz) {
      if (getTLI()->isCheapToSpeculateCttz())
        return TargetTransformInfo::TCC_Basic;
      return TargetTransformInfo::TCC_Expensive;
    }

    if (IID == Intrinsic::ctlz) {
      if (getTLI()->isCheapToSpeculateCtlz())
        return TargetTransformInfo::TCC_Basic;
      return TargetTransformInfo::TCC_Expensive;
    }

    return BaseT::getIntrinsicCost(IID, RetTy, ParamTys);
  }

  unsigned getJumpBufAlignment() { return getTLI()->getJumpBufAlignment(); }

  unsigned getJumpBufSize() { return getTLI()->getJumpBufSize(); }

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

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

  unsigned getFPOpCost(Type *Ty) {
    // By default, FP instructions are no more expensive since they are
    // implemented in HW.  Target specific TTI can override this.
    return TargetTransformInfo::TCC_Basic;
  }

  unsigned getOperationCost(unsigned Opcode, Type *Ty, Type *OpTy) {
    const TargetLoweringBase *TLI = getTLI();
    switch (Opcode) {
    default: break;
    case Instruction::Trunc: {
      if (TLI->isTruncateFree(OpTy, Ty))
        return TargetTransformInfo::TCC_Free;
      return TargetTransformInfo::TCC_Basic;
    }
    case Instruction::ZExt: {
      if (TLI->isZExtFree(OpTy, Ty))
        return TargetTransformInfo::TCC_Free;
      return TargetTransformInfo::TCC_Basic;
    }
    }

    return BaseT::getOperationCost(Opcode, Ty, OpTy);
  }

  unsigned getInliningThresholdMultiplier() { return 1; }

  void getUnrollingPreferences(Loop *L, TTI::UnrollingPreferences &UP) {
    // This unrolling functionality is target independent, but to provide some
    // motivation for its intended use, for x86:

    // According to the Intel 64 and IA-32 Architectures Optimization Reference
    // Manual, Intel Core models and later have a loop stream detector (and
    // associated uop queue) that can benefit from partial unrolling.
    // The relevant requirements are:
    //  - The loop must have no more than 4 (8 for Nehalem and later) branches
    //    taken, and none of them may be calls.
    //  - The loop can have no more than 18 (28 for Nehalem and later) uops.

    // According to the Software Optimization Guide for AMD Family 15h
    // Processors, models 30h-4fh (Steamroller and later) have a loop predictor
    // and loop buffer which can benefit from partial unrolling.
    // The relevant requirements are:
    //  - The loop must have fewer than 16 branches
    //  - The loop must have less than 40 uops in all executed loop branches

    // The number of taken branches in a loop is hard to estimate here, and
    // benchmarking has revealed that it is better not to be conservative when
    // estimating the branch count. As a result, we'll ignore the branch limits
    // until someone finds a case where it matters in practice.

    unsigned MaxOps;
    const TargetSubtargetInfo *ST = getST();
    if (PartialUnrollingThreshold.getNumOccurrences() > 0)
      MaxOps = PartialUnrollingThreshold;
    else if (ST->getSchedModel().LoopMicroOpBufferSize > 0)
      MaxOps = ST->getSchedModel().LoopMicroOpBufferSize;
    else
      return;

    // Scan the loop: don't unroll loops with calls.
    for (Loop::block_iterator I = L->block_begin(), E = L->block_end(); I != E;
         ++I) {
      BasicBlock *BB = *I;

      for (BasicBlock::iterator J = BB->begin(), JE = BB->end(); J != JE; ++J)
        if (isa<CallInst>(J) || isa<InvokeInst>(J)) {
          ImmutableCallSite CS(&*J);
          if (const Function *F = CS.getCalledFunction()) {
            if (!static_cast<T *>(this)->isLoweredToCall(F))
              continue;
          }

          return;
        }
    }

    // Enable runtime and partial unrolling up to the specified size.
    UP.Partial = UP.Runtime = true;
    UP.PartialThreshold = UP.PartialOptSizeThreshold = MaxOps;
  }

  /// @}

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

  unsigned getNumberOfRegisters(bool Vector) { return Vector ? 0 : 1; }

  unsigned getRegisterBitWidth(bool Vector) { return 32; }

  unsigned getMaxInterleaveFactor(unsigned VF) { return 1; }

  unsigned getArithmeticInstrCost(
      unsigned Opcode, Type *Ty,
      TTI::OperandValueKind Opd1Info = TTI::OK_AnyValue,
      TTI::OperandValueKind Opd2Info = TTI::OK_AnyValue,
      TTI::OperandValueProperties Opd1PropInfo = TTI::OP_None,
      TTI::OperandValueProperties Opd2PropInfo = TTI::OP_None) {
    // 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(DL, 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.
      // TODO: Once we have extract/insert subvector cost we need to use them.
      return LT.first * OpCost;
    }

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

    // Else, assume that we need to scalarize this op.
    // TODO: If one of the types get legalized by splitting, handle this
    // similarly to what getCastInstrCost() does.
    if (Ty->isVectorTy()) {
      unsigned Num = Ty->getVectorNumElements();
      unsigned Cost = static_cast<T *>(this)
                          ->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 getShuffleCost(TTI::ShuffleKind Kind, Type *Tp, int Index,
                          Type *SubTp) {
    if (Kind == TTI::SK_Alternate) {
      return getAltShuffleOverhead(Tp);
    }
    return 1;
  }

  unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) {
    const TargetLoweringBase *TLI = getTLI();
    int ISD = TLI->InstructionOpcodeToISD(Opcode);
    assert(ISD && "Invalid opcode");
    std::pair<unsigned, MVT> SrcLT = TLI->getTypeLegalizationCost(DL, Src);
    std::pair<unsigned, MVT> DstLT = TLI->getTypeLegalizationCost(DL, 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 (Opcode == Instruction::AddrSpaceCast &&
        TLI->isNoopAddrSpaceCast(Src->getPointerAddressSpace(),
                                 Dst->getPointerAddressSpace()))
      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 legalizing by splitting, query the concrete TTI for the cost
      // of casting the original vector twice. We also need to factor int the
      // cost of the split itself. Count that as 1, to be consistent with
      // TLI->getTypeLegalizationCost().
      if ((TLI->getTypeAction(Src->getContext(), TLI->getValueType(DL, Src)) ==
           TargetLowering::TypeSplitVector) ||
          (TLI->getTypeAction(Dst->getContext(), TLI->getValueType(DL, Dst)) ==
           TargetLowering::TypeSplitVector)) {
        Type *SplitDst = VectorType::get(Dst->getVectorElementType(),
                                         Dst->getVectorNumElements() / 2);
        Type *SplitSrc = VectorType::get(Src->getVectorElementType(),
                                         Src->getVectorNumElements() / 2);
        T *TTI = static_cast<T *>(this);
        return TTI->getVectorSplitCost() +
               (2 * TTI->getCastInstrCost(Opcode, SplitDst, SplitSrc));
      }

      // In other cases where the source or destination are illegal, assume
      // the operation will get scalarized.
      unsigned Num = Dst->getVectorNumElements();
      unsigned Cost = static_cast<T *>(this)->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 getExtractWithExtendCost(unsigned Opcode, Type *Dst,
                                    VectorType *VecTy, unsigned Index) {
    return static_cast<T *>(this)->getVectorInstrCost(
               Instruction::ExtractElement, VecTy, Index) +
           static_cast<T *>(this)->getCastInstrCost(Opcode, Dst,
                                                    VecTy->getElementType());
  }

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

  unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy) {
    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(DL, ValTy);

    if (!(ValTy->isVectorTy() && !LT.second.isVector()) &&
        !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.
    // TODO: If one of the types get legalized by splitting, handle this
    // similarly to what getCastInstrCost() does.
    if (ValTy->isVectorTy()) {
      unsigned Num = ValTy->getVectorNumElements();
      if (CondTy)
        CondTy = CondTy->getScalarType();
      unsigned Cost = static_cast<T *>(this)->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 getVectorInstrCost(unsigned Opcode, Type *Val, unsigned Index) {
    std::pair<unsigned, MVT> LT =
        getTLI()->getTypeLegalizationCost(DL, Val->getScalarType());

    return LT.first;
  }

  unsigned getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
                           unsigned AddressSpace) {
    assert(!Src->isVoidTy() && "Invalid type");
    std::pair<unsigned, MVT> LT = getTLI()->getTypeLegalizationCost(DL, 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 = TargetLowering::Expand;
      EVT MemVT = getTLI()->getValueType(DL, Src);
      if (Opcode == Instruction::Store)
        LA = getTLI()->getTruncStoreAction(LT.second, MemVT);
      else
        LA = getTLI()->getLoadExtAction(ISD::EXTLOAD, LT.second, 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 getInterleavedMemoryOpCost(unsigned Opcode, Type *VecTy,
                                      unsigned Factor,
                                      ArrayRef<unsigned> Indices,
                                      unsigned Alignment,
                                      unsigned AddressSpace) {
    VectorType *VT = dyn_cast<VectorType>(VecTy);
    assert(VT && "Expect a vector type for interleaved memory op");

    unsigned NumElts = VT->getNumElements();
    assert(Factor > 1 && NumElts % Factor == 0 && "Invalid interleave factor");

    unsigned NumSubElts = NumElts / Factor;
    VectorType *SubVT = VectorType::get(VT->getElementType(), NumSubElts);

    // Firstly, the cost of load/store operation.
    unsigned Cost = static_cast<T *>(this)->getMemoryOpCost(
        Opcode, VecTy, Alignment, AddressSpace);

    // Legalize the vector type, and get the legalized and unlegalized type
    // sizes.
    MVT VecTyLT = getTLI()->getTypeLegalizationCost(DL, VecTy).second;
    unsigned VecTySize =
        static_cast<T *>(this)->getDataLayout().getTypeStoreSize(VecTy);
    unsigned VecTyLTSize = VecTyLT.getStoreSize();

    // Return the ceiling of dividing A by B.
    auto ceil = [](unsigned A, unsigned B) { return (A + B - 1) / B; };

    // Scale the cost of the memory operation by the fraction of legalized
    // instructions that will actually be used. We shouldn't account for the
    // cost of dead instructions since they will be removed.
    //
    // E.g., An interleaved load of factor 8:
    //       %vec = load <16 x i64>, <16 x i64>* %ptr
    //       %v0 = shufflevector %vec, undef, <0, 8>
    //
    // If <16 x i64> is legalized to 8 v2i64 loads, only 2 of the loads will be
    // used (those corresponding to elements [0:1] and [8:9] of the unlegalized
    // type). The other loads are unused.
    //
    // We only scale the cost of loads since interleaved store groups aren't
    // allowed to have gaps.
    if (Opcode == Instruction::Load && VecTySize > VecTyLTSize) {

      // The number of loads of a legal type it will take to represent a load
      // of the unlegalized vector type.
      unsigned NumLegalInsts = ceil(VecTySize, VecTyLTSize);

      // The number of elements of the unlegalized type that correspond to a
      // single legal instruction.
      unsigned NumEltsPerLegalInst = ceil(NumElts, NumLegalInsts);

      // Determine which legal instructions will be used.
      BitVector UsedInsts(NumLegalInsts, false);
      for (unsigned Index : Indices)
        for (unsigned Elt = 0; Elt < NumSubElts; ++Elt)
          UsedInsts.set((Index + Elt * Factor) / NumEltsPerLegalInst);

      // Scale the cost of the load by the fraction of legal instructions that
      // will be used.
      Cost *= UsedInsts.count() / NumLegalInsts;
    }

    // Then plus the cost of interleave operation.
    if (Opcode == Instruction::Load) {
      // The interleave cost is similar to extract sub vectors' elements
      // from the wide vector, and insert them into sub vectors.
      //
      // E.g. An interleaved load of factor 2 (with one member of index 0):
      //      %vec = load <8 x i32>, <8 x i32>* %ptr
      //      %v0 = shuffle %vec, undef, <0, 2, 4, 6>         ; Index 0
      // The cost is estimated as extract elements at 0, 2, 4, 6 from the
      // <8 x i32> vector and insert them into a <4 x i32> vector.

      assert(Indices.size() <= Factor &&
             "Interleaved memory op has too many members");

      for (unsigned Index : Indices) {
        assert(Index < Factor && "Invalid index for interleaved memory op");

        // Extract elements from loaded vector for each sub vector.
        for (unsigned i = 0; i < NumSubElts; i++)
          Cost += static_cast<T *>(this)->getVectorInstrCost(
              Instruction::ExtractElement, VT, Index + i * Factor);
      }

      unsigned InsSubCost = 0;
      for (unsigned i = 0; i < NumSubElts; i++)
        InsSubCost += static_cast<T *>(this)->getVectorInstrCost(
            Instruction::InsertElement, SubVT, i);

      Cost += Indices.size() * InsSubCost;
    } else {
      // The interleave cost is extract all elements from sub vectors, and
      // insert them into the wide vector.
      //
      // E.g. An interleaved store of factor 2:
      //      %v0_v1 = shuffle %v0, %v1, <0, 4, 1, 5, 2, 6, 3, 7>
      //      store <8 x i32> %interleaved.vec, <8 x i32>* %ptr
      // The cost is estimated as extract all elements from both <4 x i32>
      // vectors and insert into the <8 x i32> vector.

      unsigned ExtSubCost = 0;
      for (unsigned i = 0; i < NumSubElts; i++)
        ExtSubCost += static_cast<T *>(this)->getVectorInstrCost(
            Instruction::ExtractElement, SubVT, i);
      Cost += ExtSubCost * Factor;

      for (unsigned i = 0; i < NumElts; i++)
        Cost += static_cast<T *>(this)
                    ->getVectorInstrCost(Instruction::InsertElement, VT, i);
    }

    return Cost;
  }

  /// Get intrinsic cost based on arguments  
  unsigned getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
                                 ArrayRef<Value *> Args, FastMathFlags FMF) {
    switch (IID) {
    default: {
      SmallVector<Type *, 4> Types;
      for (Value *Op : Args)
        Types.push_back(Op->getType());
      return static_cast<T *>(this)->getIntrinsicInstrCost(IID, RetTy, Types,
                                                           FMF);
    }
    case Intrinsic::masked_scatter: {
      Value *Mask = Args[3];
      bool VarMask = !isa<Constant>(Mask);
      unsigned Alignment = cast<ConstantInt>(Args[2])->getZExtValue();
      return
        static_cast<T *>(this)->getGatherScatterOpCost(Instruction::Store,
                                                       Args[0]->getType(),
                                                       Args[1], VarMask,
                                                       Alignment);
    }
    case Intrinsic::masked_gather: {
      Value *Mask = Args[2];
      bool VarMask = !isa<Constant>(Mask);
      unsigned Alignment = cast<ConstantInt>(Args[1])->getZExtValue();
      return
        static_cast<T *>(this)->getGatherScatterOpCost(Instruction::Load,
                                                       RetTy, Args[0], VarMask,
                                                       Alignment);
    }
    }
  }
  
  /// Get intrinsic cost based on argument types
  unsigned getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
                                 ArrayRef<Type *> Tys, FastMathFlags FMF) {
    SmallVector<unsigned, 2> ISDs;
    unsigned SingleCallCost = 10; // Library call cost. Make it expensive.
    switch (IID) {
    default: {
      // Assume that we need to scalarize this intrinsic.
      unsigned ScalarizationCost = 0;
      unsigned ScalarCalls = 1;
      Type *ScalarRetTy = RetTy;
      if (RetTy->isVectorTy()) {
        ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
        ScalarCalls = std::max(ScalarCalls, RetTy->getVectorNumElements());
        ScalarRetTy = RetTy->getScalarType();
      }
      SmallVector<Type *, 4> ScalarTys;
      for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
        Type *Ty = Tys[i];
        if (Ty->isVectorTy()) {
          ScalarizationCost += getScalarizationOverhead(Ty, false, true);
          ScalarCalls = std::max(ScalarCalls, Ty->getVectorNumElements());
          Ty = Ty->getScalarType();
        }
        ScalarTys.push_back(Ty);
      }
      if (ScalarCalls == 1)
        return 1; // Return cost of a scalar intrinsic. Assume it to be cheap.

      unsigned ScalarCost = static_cast<T *>(this)->getIntrinsicInstrCost(
          IID, ScalarRetTy, ScalarTys, FMF);

      return ScalarCalls * ScalarCost + ScalarizationCost;
    }
    // Look for intrinsics that can be lowered directly or turned into a scalar
    // intrinsic call.
    case Intrinsic::sqrt:
      ISDs.push_back(ISD::FSQRT);
      break;
    case Intrinsic::sin:
      ISDs.push_back(ISD::FSIN);
      break;
    case Intrinsic::cos:
      ISDs.push_back(ISD::FCOS);
      break;
    case Intrinsic::exp:
      ISDs.push_back(ISD::FEXP);
      break;
    case Intrinsic::exp2:
      ISDs.push_back(ISD::FEXP2);
      break;
    case Intrinsic::log:
      ISDs.push_back(ISD::FLOG);
      break;
    case Intrinsic::log10:
      ISDs.push_back(ISD::FLOG10);
      break;
    case Intrinsic::log2:
      ISDs.push_back(ISD::FLOG2);
      break;
    case Intrinsic::fabs:
      ISDs.push_back(ISD::FABS);
      break;
    case Intrinsic::minnum:
      ISDs.push_back(ISD::FMINNUM);
      if (FMF.noNaNs())
        ISDs.push_back(ISD::FMINNAN);
      break;
    case Intrinsic::maxnum:
      ISDs.push_back(ISD::FMAXNUM);
      if (FMF.noNaNs())
        ISDs.push_back(ISD::FMAXNAN);
      break;
    case Intrinsic::copysign:
      ISDs.push_back(ISD::FCOPYSIGN);
      break;
    case Intrinsic::floor:
      ISDs.push_back(ISD::FFLOOR);
      break;
    case Intrinsic::ceil:
      ISDs.push_back(ISD::FCEIL);
      break;
    case Intrinsic::trunc:
      ISDs.push_back(ISD::FTRUNC);
      break;
    case Intrinsic::nearbyint:
      ISDs.push_back(ISD::FNEARBYINT);
      break;
    case Intrinsic::rint:
      ISDs.push_back(ISD::FRINT);
      break;
    case Intrinsic::round:
      ISDs.push_back(ISD::FROUND);
      break;
    case Intrinsic::pow:
      ISDs.push_back(ISD::FPOW);
      break;
    case Intrinsic::fma:
      ISDs.push_back(ISD::FMA);
      break;
    case Intrinsic::fmuladd:
      ISDs.push_back(ISD::FMA);
      break;
    // FIXME: We should return 0 whenever getIntrinsicCost == TCC_Free.
    case Intrinsic::lifetime_start:
    case Intrinsic::lifetime_end:
      return 0;
    case Intrinsic::masked_store:
      return static_cast<T *>(this)
          ->getMaskedMemoryOpCost(Instruction::Store, Tys[0], 0, 0);
    case Intrinsic::masked_load:
      return static_cast<T *>(this)
          ->getMaskedMemoryOpCost(Instruction::Load, RetTy, 0, 0);
    case Intrinsic::ctpop:
      ISDs.push_back(ISD::CTPOP);
      // In case of legalization use TCC_Expensive. This is cheaper than a
      // library call but still not a cheap instruction.
      SingleCallCost = TargetTransformInfo::TCC_Expensive;
      break;
    // FIXME: ctlz, cttz, ...
    }

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

    SmallVector<unsigned, 2> LegalCost;
    SmallVector<unsigned, 2> CustomCost;
    for (unsigned ISD : ISDs) {
      if (TLI->isOperationLegalOrPromote(ISD, LT.second)) {
        if (IID == Intrinsic::fabs && TLI->isFAbsFree(LT.second)) {
          return 0;
        }

        // 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)
          LegalCost.push_back(LT.first * 2);
        else
          LegalCost.push_back(LT.first * 1);
      } else if (!TLI->isOperationExpand(ISD, LT.second)) {
        // If the operation is custom lowered then assume
        // that the code is twice as expensive.
        CustomCost.push_back(LT.first * 2);
      }
    }

    auto MinLegalCostI = std::min_element(LegalCost.begin(), LegalCost.end());
    if (MinLegalCostI != LegalCost.end())
      return *MinLegalCostI;

    auto MinCustomCostI = std::min_element(CustomCost.begin(), CustomCost.end());
    if (MinCustomCostI != CustomCost.end())
      return *MinCustomCostI;

    // If we can't lower fmuladd into an FMA estimate the cost as a floating
    // point mul followed by an add.
    if (IID == Intrinsic::fmuladd)
      return static_cast<T *>(this)
                 ->getArithmeticInstrCost(BinaryOperator::FMul, RetTy) +
             static_cast<T *>(this)
                 ->getArithmeticInstrCost(BinaryOperator::FAdd, RetTy);

    // 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 ScalarizationCost = getScalarizationOverhead(RetTy, true, false);
      unsigned ScalarCalls = RetTy->getVectorNumElements();
      SmallVector<Type *, 4> ScalarTys;
      for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
        Type *Ty = Tys[i];
        if (Ty->isVectorTy())
          Ty = Ty->getScalarType();
        ScalarTys.push_back(Ty);
      }
      unsigned ScalarCost = static_cast<T *>(this)->getIntrinsicInstrCost(
          IID, RetTy->getScalarType(), ScalarTys, FMF);
      for (unsigned i = 0, ie = Tys.size(); i != ie; ++i) {
        if (Tys[i]->isVectorTy()) {
          ScalarizationCost += getScalarizationOverhead(Tys[i], false, true);
          ScalarCalls = std::max(ScalarCalls, Tys[i]->getVectorNumElements());
        }
      }

      return ScalarCalls * ScalarCost + ScalarizationCost;
    }

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

  /// \brief Compute a cost of the given call instruction.
  ///
  /// Compute the cost of calling function F with return type RetTy and
  /// argument types Tys. F might be nullptr, in this case the cost of an
  /// arbitrary call with the specified signature will be returned.
  /// This is used, for instance,  when we estimate call of a vector
  /// counterpart of the given function.
  /// \param F Called function, might be nullptr.
  /// \param RetTy Return value types.
  /// \param Tys Argument types.
  /// \returns The cost of Call instruction.
  unsigned getCallInstrCost(Function *F, Type *RetTy, ArrayRef<Type *> Tys) {
    return 10;
  }

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

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

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

  unsigned getVectorSplitCost() { return 1; }

  /// @}
};

/// \brief Concrete BasicTTIImpl that can be used if no further customization
/// is needed.
class BasicTTIImpl : public BasicTTIImplBase<BasicTTIImpl> {
  typedef BasicTTIImplBase<BasicTTIImpl> BaseT;
  friend class BasicTTIImplBase<BasicTTIImpl>;

  const TargetSubtargetInfo *ST;
  const TargetLoweringBase *TLI;

  const TargetSubtargetInfo *getST() const { return ST; }
  const TargetLoweringBase *getTLI() const { return TLI; }

public:
  explicit BasicTTIImpl(const TargetMachine *ST, const Function &F);

  // Provide value semantics. MSVC requires that we spell all of these out.
  BasicTTIImpl(const BasicTTIImpl &Arg)
      : BaseT(static_cast<const BaseT &>(Arg)), ST(Arg.ST), TLI(Arg.TLI) {}
  BasicTTIImpl(BasicTTIImpl &&Arg)
      : BaseT(std::move(static_cast<BaseT &>(Arg))), ST(std::move(Arg.ST)),
        TLI(std::move(Arg.TLI)) {}
};

}

#endif