forked from llvm-mirror/llvm
-
Notifications
You must be signed in to change notification settings - Fork 0
/
TargetTransformInfo.cpp
1195 lines (1013 loc) · 42.2 KB
/
TargetTransformInfo.cpp
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
//===- llvm/Analysis/TargetTransformInfo.cpp ------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/TargetTransformInfoImpl.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ErrorHandling.h"
#include <utility>
using namespace llvm;
using namespace PatternMatch;
#define DEBUG_TYPE "tti"
static cl::opt<bool> UseWideMemcpyLoopLowering(
"use-wide-memcpy-loop-lowering", cl::init(false),
cl::desc("Enables the new wide memcpy loop lowering in Transforms/Utils."),
cl::Hidden);
static cl::opt<bool> EnableReduxCost("costmodel-reduxcost", cl::init(false),
cl::Hidden,
cl::desc("Recognize reduction patterns."));
namespace {
/// \brief No-op implementation of the TTI interface using the utility base
/// classes.
///
/// This is used when no target specific information is available.
struct NoTTIImpl : TargetTransformInfoImplCRTPBase<NoTTIImpl> {
explicit NoTTIImpl(const DataLayout &DL)
: TargetTransformInfoImplCRTPBase<NoTTIImpl>(DL) {}
};
}
TargetTransformInfo::TargetTransformInfo(const DataLayout &DL)
: TTIImpl(new Model<NoTTIImpl>(NoTTIImpl(DL))) {}
TargetTransformInfo::~TargetTransformInfo() {}
TargetTransformInfo::TargetTransformInfo(TargetTransformInfo &&Arg)
: TTIImpl(std::move(Arg.TTIImpl)) {}
TargetTransformInfo &TargetTransformInfo::operator=(TargetTransformInfo &&RHS) {
TTIImpl = std::move(RHS.TTIImpl);
return *this;
}
int TargetTransformInfo::getOperationCost(unsigned Opcode, Type *Ty,
Type *OpTy) const {
int Cost = TTIImpl->getOperationCost(Opcode, Ty, OpTy);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getCallCost(FunctionType *FTy, int NumArgs) const {
int Cost = TTIImpl->getCallCost(FTy, NumArgs);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getCallCost(const Function *F,
ArrayRef<const Value *> Arguments) const {
int Cost = TTIImpl->getCallCost(F, Arguments);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
unsigned TargetTransformInfo::getInliningThresholdMultiplier() const {
return TTIImpl->getInliningThresholdMultiplier();
}
int TargetTransformInfo::getGEPCost(Type *PointeeType, const Value *Ptr,
ArrayRef<const Value *> Operands) const {
return TTIImpl->getGEPCost(PointeeType, Ptr, Operands);
}
int TargetTransformInfo::getExtCost(const Instruction *I,
const Value *Src) const {
return TTIImpl->getExtCost(I, Src);
}
int TargetTransformInfo::getIntrinsicCost(
Intrinsic::ID IID, Type *RetTy, ArrayRef<const Value *> Arguments) const {
int Cost = TTIImpl->getIntrinsicCost(IID, RetTy, Arguments);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
unsigned
TargetTransformInfo::getEstimatedNumberOfCaseClusters(const SwitchInst &SI,
unsigned &JTSize) const {
return TTIImpl->getEstimatedNumberOfCaseClusters(SI, JTSize);
}
int TargetTransformInfo::getUserCost(const User *U,
ArrayRef<const Value *> Operands) const {
int Cost = TTIImpl->getUserCost(U, Operands);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
bool TargetTransformInfo::hasBranchDivergence() const {
return TTIImpl->hasBranchDivergence();
}
bool TargetTransformInfo::isSourceOfDivergence(const Value *V) const {
return TTIImpl->isSourceOfDivergence(V);
}
bool llvm::TargetTransformInfo::isAlwaysUniform(const Value *V) const {
return TTIImpl->isAlwaysUniform(V);
}
unsigned TargetTransformInfo::getFlatAddressSpace() const {
return TTIImpl->getFlatAddressSpace();
}
bool TargetTransformInfo::isLoweredToCall(const Function *F) const {
return TTIImpl->isLoweredToCall(F);
}
void TargetTransformInfo::getUnrollingPreferences(
Loop *L, ScalarEvolution &SE, UnrollingPreferences &UP) const {
return TTIImpl->getUnrollingPreferences(L, SE, UP);
}
bool TargetTransformInfo::isLegalAddImmediate(int64_t Imm) const {
return TTIImpl->isLegalAddImmediate(Imm);
}
bool TargetTransformInfo::isLegalICmpImmediate(int64_t Imm) const {
return TTIImpl->isLegalICmpImmediate(Imm);
}
bool TargetTransformInfo::isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV,
int64_t BaseOffset,
bool HasBaseReg,
int64_t Scale,
unsigned AddrSpace,
Instruction *I) const {
return TTIImpl->isLegalAddressingMode(Ty, BaseGV, BaseOffset, HasBaseReg,
Scale, AddrSpace, I);
}
bool TargetTransformInfo::isLSRCostLess(LSRCost &C1, LSRCost &C2) const {
return TTIImpl->isLSRCostLess(C1, C2);
}
bool TargetTransformInfo::isLegalMaskedStore(Type *DataType) const {
return TTIImpl->isLegalMaskedStore(DataType);
}
bool TargetTransformInfo::isLegalMaskedLoad(Type *DataType) const {
return TTIImpl->isLegalMaskedLoad(DataType);
}
bool TargetTransformInfo::isLegalMaskedGather(Type *DataType) const {
return TTIImpl->isLegalMaskedGather(DataType);
}
bool TargetTransformInfo::isLegalMaskedScatter(Type *DataType) const {
return TTIImpl->isLegalMaskedScatter(DataType);
}
bool TargetTransformInfo::hasDivRemOp(Type *DataType, bool IsSigned) const {
return TTIImpl->hasDivRemOp(DataType, IsSigned);
}
bool TargetTransformInfo::prefersVectorizedAddressing() const {
return TTIImpl->prefersVectorizedAddressing();
}
int TargetTransformInfo::getScalingFactorCost(Type *Ty, GlobalValue *BaseGV,
int64_t BaseOffset,
bool HasBaseReg,
int64_t Scale,
unsigned AddrSpace) const {
int Cost = TTIImpl->getScalingFactorCost(Ty, BaseGV, BaseOffset, HasBaseReg,
Scale, AddrSpace);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
bool TargetTransformInfo::LSRWithInstrQueries() const {
return TTIImpl->LSRWithInstrQueries();
}
bool TargetTransformInfo::isTruncateFree(Type *Ty1, Type *Ty2) const {
return TTIImpl->isTruncateFree(Ty1, Ty2);
}
bool TargetTransformInfo::isProfitableToHoist(Instruction *I) const {
return TTIImpl->isProfitableToHoist(I);
}
bool TargetTransformInfo::isTypeLegal(Type *Ty) const {
return TTIImpl->isTypeLegal(Ty);
}
unsigned TargetTransformInfo::getJumpBufAlignment() const {
return TTIImpl->getJumpBufAlignment();
}
unsigned TargetTransformInfo::getJumpBufSize() const {
return TTIImpl->getJumpBufSize();
}
bool TargetTransformInfo::shouldBuildLookupTables() const {
return TTIImpl->shouldBuildLookupTables();
}
bool TargetTransformInfo::shouldBuildLookupTablesForConstant(Constant *C) const {
return TTIImpl->shouldBuildLookupTablesForConstant(C);
}
unsigned TargetTransformInfo::
getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const {
return TTIImpl->getScalarizationOverhead(Ty, Insert, Extract);
}
unsigned TargetTransformInfo::
getOperandsScalarizationOverhead(ArrayRef<const Value *> Args,
unsigned VF) const {
return TTIImpl->getOperandsScalarizationOverhead(Args, VF);
}
bool TargetTransformInfo::supportsEfficientVectorElementLoadStore() const {
return TTIImpl->supportsEfficientVectorElementLoadStore();
}
bool TargetTransformInfo::enableAggressiveInterleaving(bool LoopHasReductions) const {
return TTIImpl->enableAggressiveInterleaving(LoopHasReductions);
}
bool TargetTransformInfo::expandMemCmp(Instruction *I, unsigned &MaxLoadSize) const {
return TTIImpl->expandMemCmp(I, MaxLoadSize);
}
bool TargetTransformInfo::enableInterleavedAccessVectorization() const {
return TTIImpl->enableInterleavedAccessVectorization();
}
bool TargetTransformInfo::isFPVectorizationPotentiallyUnsafe() const {
return TTIImpl->isFPVectorizationPotentiallyUnsafe();
}
bool TargetTransformInfo::allowsMisalignedMemoryAccesses(LLVMContext &Context,
unsigned BitWidth,
unsigned AddressSpace,
unsigned Alignment,
bool *Fast) const {
return TTIImpl->allowsMisalignedMemoryAccesses(Context, BitWidth, AddressSpace,
Alignment, Fast);
}
TargetTransformInfo::PopcntSupportKind
TargetTransformInfo::getPopcntSupport(unsigned IntTyWidthInBit) const {
return TTIImpl->getPopcntSupport(IntTyWidthInBit);
}
bool TargetTransformInfo::haveFastSqrt(Type *Ty) const {
return TTIImpl->haveFastSqrt(Ty);
}
int TargetTransformInfo::getFPOpCost(Type *Ty) const {
int Cost = TTIImpl->getFPOpCost(Ty);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getIntImmCodeSizeCost(unsigned Opcode, unsigned Idx,
const APInt &Imm,
Type *Ty) const {
int Cost = TTIImpl->getIntImmCodeSizeCost(Opcode, Idx, Imm, Ty);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getIntImmCost(const APInt &Imm, Type *Ty) const {
int Cost = TTIImpl->getIntImmCost(Imm, Ty);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getIntImmCost(unsigned Opcode, unsigned Idx,
const APInt &Imm, Type *Ty) const {
int Cost = TTIImpl->getIntImmCost(Opcode, Idx, Imm, Ty);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getIntImmCost(Intrinsic::ID IID, unsigned Idx,
const APInt &Imm, Type *Ty) const {
int Cost = TTIImpl->getIntImmCost(IID, Idx, Imm, Ty);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
unsigned TargetTransformInfo::getNumberOfRegisters(bool Vector) const {
return TTIImpl->getNumberOfRegisters(Vector);
}
unsigned TargetTransformInfo::getRegisterBitWidth(bool Vector) const {
return TTIImpl->getRegisterBitWidth(Vector);
}
unsigned TargetTransformInfo::getMinVectorRegisterBitWidth() const {
return TTIImpl->getMinVectorRegisterBitWidth();
}
bool TargetTransformInfo::shouldConsiderAddressTypePromotion(
const Instruction &I, bool &AllowPromotionWithoutCommonHeader) const {
return TTIImpl->shouldConsiderAddressTypePromotion(
I, AllowPromotionWithoutCommonHeader);
}
unsigned TargetTransformInfo::getCacheLineSize() const {
return TTIImpl->getCacheLineSize();
}
llvm::Optional<unsigned> TargetTransformInfo::getCacheSize(CacheLevel Level)
const {
return TTIImpl->getCacheSize(Level);
}
llvm::Optional<unsigned> TargetTransformInfo::getCacheAssociativity(
CacheLevel Level) const {
return TTIImpl->getCacheAssociativity(Level);
}
unsigned TargetTransformInfo::getPrefetchDistance() const {
return TTIImpl->getPrefetchDistance();
}
unsigned TargetTransformInfo::getMinPrefetchStride() const {
return TTIImpl->getMinPrefetchStride();
}
unsigned TargetTransformInfo::getMaxPrefetchIterationsAhead() const {
return TTIImpl->getMaxPrefetchIterationsAhead();
}
unsigned TargetTransformInfo::getMaxInterleaveFactor(unsigned VF) const {
return TTIImpl->getMaxInterleaveFactor(VF);
}
int TargetTransformInfo::getArithmeticInstrCost(
unsigned Opcode, Type *Ty, OperandValueKind Opd1Info,
OperandValueKind Opd2Info, OperandValueProperties Opd1PropInfo,
OperandValueProperties Opd2PropInfo,
ArrayRef<const Value *> Args) const {
int Cost = TTIImpl->getArithmeticInstrCost(Opcode, Ty, Opd1Info, Opd2Info,
Opd1PropInfo, Opd2PropInfo, Args);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getShuffleCost(ShuffleKind Kind, Type *Ty, int Index,
Type *SubTp) const {
int Cost = TTIImpl->getShuffleCost(Kind, Ty, Index, SubTp);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getCastInstrCost(unsigned Opcode, Type *Dst,
Type *Src, const Instruction *I) const {
assert ((I == nullptr || I->getOpcode() == Opcode) &&
"Opcode should reflect passed instruction.");
int Cost = TTIImpl->getCastInstrCost(Opcode, Dst, Src, I);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getExtractWithExtendCost(unsigned Opcode, Type *Dst,
VectorType *VecTy,
unsigned Index) const {
int Cost = TTIImpl->getExtractWithExtendCost(Opcode, Dst, VecTy, Index);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getCFInstrCost(unsigned Opcode) const {
int Cost = TTIImpl->getCFInstrCost(Opcode);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
Type *CondTy, const Instruction *I) const {
assert ((I == nullptr || I->getOpcode() == Opcode) &&
"Opcode should reflect passed instruction.");
int Cost = TTIImpl->getCmpSelInstrCost(Opcode, ValTy, CondTy, I);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getVectorInstrCost(unsigned Opcode, Type *Val,
unsigned Index) const {
int Cost = TTIImpl->getVectorInstrCost(Opcode, Val, Index);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getMemoryOpCost(unsigned Opcode, Type *Src,
unsigned Alignment,
unsigned AddressSpace,
const Instruction *I) const {
assert ((I == nullptr || I->getOpcode() == Opcode) &&
"Opcode should reflect passed instruction.");
int Cost = TTIImpl->getMemoryOpCost(Opcode, Src, Alignment, AddressSpace, I);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getMaskedMemoryOpCost(unsigned Opcode, Type *Src,
unsigned Alignment,
unsigned AddressSpace) const {
int Cost =
TTIImpl->getMaskedMemoryOpCost(Opcode, Src, Alignment, AddressSpace);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getGatherScatterOpCost(unsigned Opcode, Type *DataTy,
Value *Ptr, bool VariableMask,
unsigned Alignment) const {
int Cost = TTIImpl->getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
Alignment);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getInterleavedMemoryOpCost(
unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
unsigned Alignment, unsigned AddressSpace) const {
int Cost = TTIImpl->getInterleavedMemoryOpCost(Opcode, VecTy, Factor, Indices,
Alignment, AddressSpace);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
ArrayRef<Type *> Tys, FastMathFlags FMF,
unsigned ScalarizationCostPassed) const {
int Cost = TTIImpl->getIntrinsicInstrCost(ID, RetTy, Tys, FMF,
ScalarizationCostPassed);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy,
ArrayRef<Value *> Args, FastMathFlags FMF, unsigned VF) const {
int Cost = TTIImpl->getIntrinsicInstrCost(ID, RetTy, Args, FMF, VF);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getCallInstrCost(Function *F, Type *RetTy,
ArrayRef<Type *> Tys) const {
int Cost = TTIImpl->getCallInstrCost(F, RetTy, Tys);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
unsigned TargetTransformInfo::getNumberOfParts(Type *Tp) const {
return TTIImpl->getNumberOfParts(Tp);
}
int TargetTransformInfo::getAddressComputationCost(Type *Tp,
ScalarEvolution *SE,
const SCEV *Ptr) const {
int Cost = TTIImpl->getAddressComputationCost(Tp, SE, Ptr);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getArithmeticReductionCost(unsigned Opcode, Type *Ty,
bool IsPairwiseForm) const {
int Cost = TTIImpl->getArithmeticReductionCost(Opcode, Ty, IsPairwiseForm);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
int TargetTransformInfo::getMinMaxReductionCost(Type *Ty, Type *CondTy,
bool IsPairwiseForm,
bool IsUnsigned) const {
int Cost =
TTIImpl->getMinMaxReductionCost(Ty, CondTy, IsPairwiseForm, IsUnsigned);
assert(Cost >= 0 && "TTI should not produce negative costs!");
return Cost;
}
unsigned
TargetTransformInfo::getCostOfKeepingLiveOverCall(ArrayRef<Type *> Tys) const {
return TTIImpl->getCostOfKeepingLiveOverCall(Tys);
}
bool TargetTransformInfo::getTgtMemIntrinsic(IntrinsicInst *Inst,
MemIntrinsicInfo &Info) const {
return TTIImpl->getTgtMemIntrinsic(Inst, Info);
}
unsigned TargetTransformInfo::getAtomicMemIntrinsicMaxElementSize() const {
return TTIImpl->getAtomicMemIntrinsicMaxElementSize();
}
Value *TargetTransformInfo::getOrCreateResultFromMemIntrinsic(
IntrinsicInst *Inst, Type *ExpectedType) const {
return TTIImpl->getOrCreateResultFromMemIntrinsic(Inst, ExpectedType);
}
Type *TargetTransformInfo::getMemcpyLoopLoweringType(LLVMContext &Context,
Value *Length,
unsigned SrcAlign,
unsigned DestAlign) const {
return TTIImpl->getMemcpyLoopLoweringType(Context, Length, SrcAlign,
DestAlign);
}
void TargetTransformInfo::getMemcpyLoopResidualLoweringType(
SmallVectorImpl<Type *> &OpsOut, LLVMContext &Context,
unsigned RemainingBytes, unsigned SrcAlign, unsigned DestAlign) const {
TTIImpl->getMemcpyLoopResidualLoweringType(OpsOut, Context, RemainingBytes,
SrcAlign, DestAlign);
}
bool TargetTransformInfo::useWideIRMemcpyLoopLowering() const {
return UseWideMemcpyLoopLowering;
}
bool TargetTransformInfo::areInlineCompatible(const Function *Caller,
const Function *Callee) const {
return TTIImpl->areInlineCompatible(Caller, Callee);
}
unsigned TargetTransformInfo::getLoadStoreVecRegBitWidth(unsigned AS) const {
return TTIImpl->getLoadStoreVecRegBitWidth(AS);
}
bool TargetTransformInfo::isLegalToVectorizeLoad(LoadInst *LI) const {
return TTIImpl->isLegalToVectorizeLoad(LI);
}
bool TargetTransformInfo::isLegalToVectorizeStore(StoreInst *SI) const {
return TTIImpl->isLegalToVectorizeStore(SI);
}
bool TargetTransformInfo::isLegalToVectorizeLoadChain(
unsigned ChainSizeInBytes, unsigned Alignment, unsigned AddrSpace) const {
return TTIImpl->isLegalToVectorizeLoadChain(ChainSizeInBytes, Alignment,
AddrSpace);
}
bool TargetTransformInfo::isLegalToVectorizeStoreChain(
unsigned ChainSizeInBytes, unsigned Alignment, unsigned AddrSpace) const {
return TTIImpl->isLegalToVectorizeStoreChain(ChainSizeInBytes, Alignment,
AddrSpace);
}
unsigned TargetTransformInfo::getLoadVectorFactor(unsigned VF,
unsigned LoadSize,
unsigned ChainSizeInBytes,
VectorType *VecTy) const {
return TTIImpl->getLoadVectorFactor(VF, LoadSize, ChainSizeInBytes, VecTy);
}
unsigned TargetTransformInfo::getStoreVectorFactor(unsigned VF,
unsigned StoreSize,
unsigned ChainSizeInBytes,
VectorType *VecTy) const {
return TTIImpl->getStoreVectorFactor(VF, StoreSize, ChainSizeInBytes, VecTy);
}
bool TargetTransformInfo::useReductionIntrinsic(unsigned Opcode,
Type *Ty, ReductionFlags Flags) const {
return TTIImpl->useReductionIntrinsic(Opcode, Ty, Flags);
}
bool TargetTransformInfo::shouldExpandReduction(const IntrinsicInst *II) const {
return TTIImpl->shouldExpandReduction(II);
}
int TargetTransformInfo::getInstructionLatency(const Instruction *I) const {
return TTIImpl->getInstructionLatency(I);
}
static bool isReverseVectorMask(ArrayRef<int> Mask) {
for (unsigned i = 0, MaskSize = Mask.size(); i < MaskSize; ++i)
if (Mask[i] >= 0 && Mask[i] != (int)(MaskSize - 1 - i))
return false;
return true;
}
static bool isSingleSourceVectorMask(ArrayRef<int> Mask) {
bool Vec0 = false;
bool Vec1 = false;
for (unsigned i = 0, NumVecElts = Mask.size(); i < NumVecElts; ++i) {
if (Mask[i] >= 0) {
if ((unsigned)Mask[i] >= NumVecElts)
Vec1 = true;
else
Vec0 = true;
}
}
return !(Vec0 && Vec1);
}
static bool isZeroEltBroadcastVectorMask(ArrayRef<int> Mask) {
for (unsigned i = 0; i < Mask.size(); ++i)
if (Mask[i] > 0)
return false;
return true;
}
static bool isAlternateVectorMask(ArrayRef<int> Mask) {
bool isAlternate = true;
unsigned MaskSize = Mask.size();
// Example: shufflevector A, B, <0,5,2,7>
for (unsigned i = 0; i < MaskSize && isAlternate; ++i) {
if (Mask[i] < 0)
continue;
isAlternate = Mask[i] == (int)((i & 1) ? MaskSize + i : i);
}
if (isAlternate)
return true;
isAlternate = true;
// Example: shufflevector A, B, <4,1,6,3>
for (unsigned i = 0; i < MaskSize && isAlternate; ++i) {
if (Mask[i] < 0)
continue;
isAlternate = Mask[i] == (int)((i & 1) ? i : MaskSize + i);
}
return isAlternate;
}
static TargetTransformInfo::OperandValueKind getOperandInfo(Value *V) {
TargetTransformInfo::OperandValueKind OpInfo =
TargetTransformInfo::OK_AnyValue;
// Check for a splat of a constant or for a non uniform vector of constants.
if (isa<ConstantVector>(V) || isa<ConstantDataVector>(V)) {
OpInfo = TargetTransformInfo::OK_NonUniformConstantValue;
if (cast<Constant>(V)->getSplatValue() != nullptr)
OpInfo = TargetTransformInfo::OK_UniformConstantValue;
}
// Check for a splat of a uniform value. This is not loop aware, so return
// true only for the obviously uniform cases (argument, globalvalue)
const Value *Splat = getSplatValue(V);
if (Splat && (isa<Argument>(Splat) || isa<GlobalValue>(Splat)))
OpInfo = TargetTransformInfo::OK_UniformValue;
return OpInfo;
}
static bool matchPairwiseShuffleMask(ShuffleVectorInst *SI, bool IsLeft,
unsigned Level) {
// We don't need a shuffle if we just want to have element 0 in position 0 of
// the vector.
if (!SI && Level == 0 && IsLeft)
return true;
else if (!SI)
return false;
SmallVector<int, 32> Mask(SI->getType()->getVectorNumElements(), -1);
// Build a mask of 0, 2, ... (left) or 1, 3, ... (right) depending on whether
// we look at the left or right side.
for (unsigned i = 0, e = (1 << Level), val = !IsLeft; i != e; ++i, val += 2)
Mask[i] = val;
SmallVector<int, 16> ActualMask = SI->getShuffleMask();
return Mask == ActualMask;
}
namespace {
/// Kind of the reduction data.
enum ReductionKind {
RK_None, /// Not a reduction.
RK_Arithmetic, /// Binary reduction data.
RK_MinMax, /// Min/max reduction data.
RK_UnsignedMinMax, /// Unsigned min/max reduction data.
};
/// Contains opcode + LHS/RHS parts of the reduction operations.
struct ReductionData {
ReductionData() = delete;
ReductionData(ReductionKind Kind, unsigned Opcode, Value *LHS, Value *RHS)
: Opcode(Opcode), LHS(LHS), RHS(RHS), Kind(Kind) {
assert(Kind != RK_None && "expected binary or min/max reduction only.");
}
unsigned Opcode = 0;
Value *LHS = nullptr;
Value *RHS = nullptr;
ReductionKind Kind = RK_None;
bool hasSameData(ReductionData &RD) const {
return Kind == RD.Kind && Opcode == RD.Opcode;
}
};
} // namespace
static Optional<ReductionData> getReductionData(Instruction *I) {
Value *L, *R;
if (m_BinOp(m_Value(L), m_Value(R)).match(I))
return ReductionData(RK_Arithmetic, I->getOpcode(), L, R);
if (auto *SI = dyn_cast<SelectInst>(I)) {
if (m_SMin(m_Value(L), m_Value(R)).match(SI) ||
m_SMax(m_Value(L), m_Value(R)).match(SI) ||
m_OrdFMin(m_Value(L), m_Value(R)).match(SI) ||
m_OrdFMax(m_Value(L), m_Value(R)).match(SI) ||
m_UnordFMin(m_Value(L), m_Value(R)).match(SI) ||
m_UnordFMax(m_Value(L), m_Value(R)).match(SI)) {
auto *CI = cast<CmpInst>(SI->getCondition());
return ReductionData(RK_MinMax, CI->getOpcode(), L, R);
}
if (m_UMin(m_Value(L), m_Value(R)).match(SI) ||
m_UMax(m_Value(L), m_Value(R)).match(SI)) {
auto *CI = cast<CmpInst>(SI->getCondition());
return ReductionData(RK_UnsignedMinMax, CI->getOpcode(), L, R);
}
}
return llvm::None;
}
static ReductionKind matchPairwiseReductionAtLevel(Instruction *I,
unsigned Level,
unsigned NumLevels) {
// Match one level of pairwise operations.
// %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef,
// <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef>
// %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef,
// <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
// %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
if (!I)
return RK_None;
assert(I->getType()->isVectorTy() && "Expecting a vector type");
Optional<ReductionData> RD = getReductionData(I);
if (!RD)
return RK_None;
ShuffleVectorInst *LS = dyn_cast<ShuffleVectorInst>(RD->LHS);
if (!LS && Level)
return RK_None;
ShuffleVectorInst *RS = dyn_cast<ShuffleVectorInst>(RD->RHS);
if (!RS && Level)
return RK_None;
// On level 0 we can omit one shufflevector instruction.
if (!Level && !RS && !LS)
return RK_None;
// Shuffle inputs must match.
Value *NextLevelOpL = LS ? LS->getOperand(0) : nullptr;
Value *NextLevelOpR = RS ? RS->getOperand(0) : nullptr;
Value *NextLevelOp = nullptr;
if (NextLevelOpR && NextLevelOpL) {
// If we have two shuffles their operands must match.
if (NextLevelOpL != NextLevelOpR)
return RK_None;
NextLevelOp = NextLevelOpL;
} else if (Level == 0 && (NextLevelOpR || NextLevelOpL)) {
// On the first level we can omit the shufflevector <0, undef,...>. So the
// input to the other shufflevector <1, undef> must match with one of the
// inputs to the current binary operation.
// Example:
// %NextLevelOpL = shufflevector %R, <1, undef ...>
// %BinOp = fadd %NextLevelOpL, %R
if (NextLevelOpL && NextLevelOpL != RD->RHS)
return RK_None;
else if (NextLevelOpR && NextLevelOpR != RD->LHS)
return RK_None;
NextLevelOp = NextLevelOpL ? RD->RHS : RD->LHS;
} else
return RK_None;
// Check that the next levels binary operation exists and matches with the
// current one.
if (Level + 1 != NumLevels) {
Optional<ReductionData> NextLevelRD =
getReductionData(cast<Instruction>(NextLevelOp));
if (!NextLevelRD || !RD->hasSameData(*NextLevelRD))
return RK_None;
}
// Shuffle mask for pairwise operation must match.
if (matchPairwiseShuffleMask(LS, /*IsLeft=*/true, Level)) {
if (!matchPairwiseShuffleMask(RS, /*IsLeft=*/false, Level))
return RK_None;
} else if (matchPairwiseShuffleMask(RS, /*IsLeft=*/true, Level)) {
if (!matchPairwiseShuffleMask(LS, /*IsLeft=*/false, Level))
return RK_None;
} else {
return RK_None;
}
if (++Level == NumLevels)
return RD->Kind;
// Match next level.
return matchPairwiseReductionAtLevel(cast<Instruction>(NextLevelOp), Level,
NumLevels);
}
static ReductionKind matchPairwiseReduction(const ExtractElementInst *ReduxRoot,
unsigned &Opcode, Type *&Ty) {
if (!EnableReduxCost)
return RK_None;
// Need to extract the first element.
ConstantInt *CI = dyn_cast<ConstantInt>(ReduxRoot->getOperand(1));
unsigned Idx = ~0u;
if (CI)
Idx = CI->getZExtValue();
if (Idx != 0)
return RK_None;
auto *RdxStart = dyn_cast<Instruction>(ReduxRoot->getOperand(0));
if (!RdxStart)
return RK_None;
Optional<ReductionData> RD = getReductionData(RdxStart);
if (!RD)
return RK_None;
Type *VecTy = RdxStart->getType();
unsigned NumVecElems = VecTy->getVectorNumElements();
if (!isPowerOf2_32(NumVecElems))
return RK_None;
// We look for a sequence of shuffle,shuffle,add triples like the following
// that builds a pairwise reduction tree.
//
// (X0, X1, X2, X3)
// (X0 + X1, X2 + X3, undef, undef)
// ((X0 + X1) + (X2 + X3), undef, undef, undef)
//
// %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef,
// <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef>
// %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef,
// <4 x i32> <i32 1, i32 3, i32 undef, i32 undef>
// %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1
// %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef,
// <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef>
// %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef,
// <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
// %bin.rdx8 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1
// %r = extractelement <4 x float> %bin.rdx8, i32 0
if (matchPairwiseReductionAtLevel(RdxStart, 0, Log2_32(NumVecElems)) ==
RK_None)
return RK_None;
Opcode = RD->Opcode;
Ty = VecTy;
return RD->Kind;
}
static std::pair<Value *, ShuffleVectorInst *>
getShuffleAndOtherOprd(Value *L, Value *R) {
ShuffleVectorInst *S = nullptr;
if ((S = dyn_cast<ShuffleVectorInst>(L)))
return std::make_pair(R, S);
S = dyn_cast<ShuffleVectorInst>(R);
return std::make_pair(L, S);
}
static ReductionKind
matchVectorSplittingReduction(const ExtractElementInst *ReduxRoot,
unsigned &Opcode, Type *&Ty) {
if (!EnableReduxCost)
return RK_None;
// Need to extract the first element.
ConstantInt *CI = dyn_cast<ConstantInt>(ReduxRoot->getOperand(1));
unsigned Idx = ~0u;
if (CI)
Idx = CI->getZExtValue();
if (Idx != 0)
return RK_None;
auto *RdxStart = dyn_cast<Instruction>(ReduxRoot->getOperand(0));
if (!RdxStart)
return RK_None;
Optional<ReductionData> RD = getReductionData(RdxStart);
if (!RD)
return RK_None;
Type *VecTy = ReduxRoot->getOperand(0)->getType();
unsigned NumVecElems = VecTy->getVectorNumElements();
if (!isPowerOf2_32(NumVecElems))
return RK_None;
// We look for a sequence of shuffles and adds like the following matching one
// fadd, shuffle vector pair at a time.
//
// %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef,
// <4 x i32> <i32 2, i32 3, i32 undef, i32 undef>
// %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf
// %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef,
// <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef>
// %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7
// %r = extractelement <4 x float> %bin.rdx8, i32 0
unsigned MaskStart = 1;
Instruction *RdxOp = RdxStart;
SmallVector<int, 32> ShuffleMask(NumVecElems, 0);
unsigned NumVecElemsRemain = NumVecElems;
while (NumVecElemsRemain - 1) {
// Check for the right reduction operation.
if (!RdxOp)
return RK_None;
Optional<ReductionData> RDLevel = getReductionData(RdxOp);
if (!RDLevel || !RDLevel->hasSameData(*RD))
return RK_None;
Value *NextRdxOp;
ShuffleVectorInst *Shuffle;
std::tie(NextRdxOp, Shuffle) =
getShuffleAndOtherOprd(RDLevel->LHS, RDLevel->RHS);
// Check the current reduction operation and the shuffle use the same value.
if (Shuffle == nullptr)
return RK_None;
if (Shuffle->getOperand(0) != NextRdxOp)
return RK_None;
// Check that shuffle masks matches.
for (unsigned j = 0; j != MaskStart; ++j)
ShuffleMask[j] = MaskStart + j;
// Fill the rest of the mask with -1 for undef.
std::fill(&ShuffleMask[MaskStart], ShuffleMask.end(), -1);
SmallVector<int, 16> Mask = Shuffle->getShuffleMask();
if (ShuffleMask != Mask)
return RK_None;
RdxOp = dyn_cast<Instruction>(NextRdxOp);
NumVecElemsRemain /= 2;
MaskStart *= 2;
}
Opcode = RD->Opcode;
Ty = VecTy;
return RD->Kind;
}
int TargetTransformInfo::getInstructionThroughput(const Instruction *I) const {
switch (I->getOpcode()) {
case Instruction::GetElementPtr:
return getUserCost(I);
case Instruction::Ret:
case Instruction::PHI:
case Instruction::Br: {
return getCFInstrCost(I->getOpcode());
}
case Instruction::Add:
case Instruction::FAdd:
case Instruction::Sub:
case Instruction::FSub:
case Instruction::Mul:
case Instruction::FMul:
case Instruction::UDiv:
case Instruction::SDiv:
case Instruction::FDiv:
case Instruction::URem:
case Instruction::SRem:
case Instruction::FRem:
case Instruction::Shl:
case Instruction::LShr:
case Instruction::AShr:
case Instruction::And:
case Instruction::Or:
case Instruction::Xor: {
TargetTransformInfo::OperandValueKind Op1VK =
getOperandInfo(I->getOperand(0));
TargetTransformInfo::OperandValueKind Op2VK =
getOperandInfo(I->getOperand(1));
SmallVector<const Value*, 2> Operands(I->operand_values());