aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm12/lib/Transforms/InstCombine/InstCombineInternal.h
blob: 79e9d5c46c70e7ea1a254fee6b5784ba2b3b2842 (plain) (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
//===- InstCombineInternal.h - InstCombine pass internals -------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
/// \file
///
/// This file provides internal interfaces used to implement the InstCombine.
//
//===----------------------------------------------------------------------===//

#ifndef LLVM_LIB_TRANSFORMS_INSTCOMBINE_INSTCOMBINEINTERNAL_H
#define LLVM_LIB_TRANSFORMS_INSTCOMBINE_INSTCOMBINEINTERNAL_H

#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/TargetFolder.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/KnownBits.h"
#include "llvm/Transforms/InstCombine/InstCombineWorklist.h"
#include "llvm/Transforms/InstCombine/InstCombiner.h"
#include "llvm/Transforms/Utils/Local.h"
#include <cassert>

#define DEBUG_TYPE "instcombine"

using namespace llvm::PatternMatch;

// As a default, let's assume that we want to be aggressive,
// and attempt to traverse with no limits in attempt to sink negation.
static constexpr unsigned NegatorDefaultMaxDepth = ~0U;

// Let's guesstimate that most often we will end up visiting/producing
// fairly small number of new instructions.
static constexpr unsigned NegatorMaxNodesSSO = 16;

namespace llvm {

class AAResults;
class APInt;
class AssumptionCache;
class BlockFrequencyInfo;
class DataLayout;
class DominatorTree;
class GEPOperator;
class GlobalVariable;
class LoopInfo;
class OptimizationRemarkEmitter;
class ProfileSummaryInfo;
class TargetLibraryInfo;
class User;

class LLVM_LIBRARY_VISIBILITY InstCombinerImpl final
    : public InstCombiner,
      public InstVisitor<InstCombinerImpl, Instruction *> {
public:
  InstCombinerImpl(InstCombineWorklist &Worklist, BuilderTy &Builder,
                   bool MinimizeSize, AAResults *AA, AssumptionCache &AC,
                   TargetLibraryInfo &TLI, TargetTransformInfo &TTI,
                   DominatorTree &DT, OptimizationRemarkEmitter &ORE,
                   BlockFrequencyInfo *BFI, ProfileSummaryInfo *PSI,
                   const DataLayout &DL, LoopInfo *LI)
      : InstCombiner(Worklist, Builder, MinimizeSize, AA, AC, TLI, TTI, DT, ORE,
                     BFI, PSI, DL, LI) {}

  virtual ~InstCombinerImpl() {}

  /// Run the combiner over the entire worklist until it is empty.
  ///
  /// \returns true if the IR is changed.
  bool run();

  // Visitation implementation - Implement instruction combining for different
  // instruction types.  The semantics are as follows:
  // Return Value:
  //    null        - No change was made
  //     I          - Change was made, I is still valid, I may be dead though
  //   otherwise    - Change was made, replace I with returned instruction
  //
  Instruction *visitFNeg(UnaryOperator &I);
  Instruction *visitAdd(BinaryOperator &I);
  Instruction *visitFAdd(BinaryOperator &I);
  Value *OptimizePointerDifference(
      Value *LHS, Value *RHS, Type *Ty, bool isNUW);
  Instruction *visitSub(BinaryOperator &I);
  Instruction *visitFSub(BinaryOperator &I);
  Instruction *visitMul(BinaryOperator &I);
  Instruction *visitFMul(BinaryOperator &I);
  Instruction *visitURem(BinaryOperator &I);
  Instruction *visitSRem(BinaryOperator &I);
  Instruction *visitFRem(BinaryOperator &I);
  bool simplifyDivRemOfSelectWithZeroOp(BinaryOperator &I);
  Instruction *commonIRemTransforms(BinaryOperator &I);
  Instruction *commonIDivTransforms(BinaryOperator &I);
  Instruction *visitUDiv(BinaryOperator &I);
  Instruction *visitSDiv(BinaryOperator &I);
  Instruction *visitFDiv(BinaryOperator &I);
  Value *simplifyRangeCheck(ICmpInst *Cmp0, ICmpInst *Cmp1, bool Inverted);
  Instruction *visitAnd(BinaryOperator &I);
  Instruction *visitOr(BinaryOperator &I);
  bool sinkNotIntoOtherHandOfAndOrOr(BinaryOperator &I);
  Instruction *visitXor(BinaryOperator &I);
  Instruction *visitShl(BinaryOperator &I);
  Value *reassociateShiftAmtsOfTwoSameDirectionShifts(
      BinaryOperator *Sh0, const SimplifyQuery &SQ,
      bool AnalyzeForSignBitExtraction = false);
  Instruction *canonicalizeCondSignextOfHighBitExtractToSignextHighBitExtract(
      BinaryOperator &I);
  Instruction *foldVariableSignZeroExtensionOfVariableHighBitExtract(
      BinaryOperator &OldAShr);
  Instruction *visitAShr(BinaryOperator &I);
  Instruction *visitLShr(BinaryOperator &I);
  Instruction *commonShiftTransforms(BinaryOperator &I);
  Instruction *visitFCmpInst(FCmpInst &I);
  CmpInst *canonicalizeICmpPredicate(CmpInst &I);
  Instruction *visitICmpInst(ICmpInst &I);
  Instruction *FoldShiftByConstant(Value *Op0, Constant *Op1,
                                   BinaryOperator &I);
  Instruction *commonCastTransforms(CastInst &CI);
  Instruction *commonPointerCastTransforms(CastInst &CI);
  Instruction *visitTrunc(TruncInst &CI);
  Instruction *visitZExt(ZExtInst &CI);
  Instruction *visitSExt(SExtInst &CI);
  Instruction *visitFPTrunc(FPTruncInst &CI);
  Instruction *visitFPExt(CastInst &CI);
  Instruction *visitFPToUI(FPToUIInst &FI);
  Instruction *visitFPToSI(FPToSIInst &FI);
  Instruction *visitUIToFP(CastInst &CI);
  Instruction *visitSIToFP(CastInst &CI);
  Instruction *visitPtrToInt(PtrToIntInst &CI);
  Instruction *visitIntToPtr(IntToPtrInst &CI);
  Instruction *visitBitCast(BitCastInst &CI);
  Instruction *visitAddrSpaceCast(AddrSpaceCastInst &CI);
  Instruction *foldItoFPtoI(CastInst &FI);
  Instruction *visitSelectInst(SelectInst &SI);
  Instruction *visitCallInst(CallInst &CI);
  Instruction *visitInvokeInst(InvokeInst &II);
  Instruction *visitCallBrInst(CallBrInst &CBI);

  Instruction *SliceUpIllegalIntegerPHI(PHINode &PN);
  Instruction *visitPHINode(PHINode &PN);
  Instruction *visitGetElementPtrInst(GetElementPtrInst &GEP);
  Instruction *visitAllocaInst(AllocaInst &AI);
  Instruction *visitAllocSite(Instruction &FI);
  Instruction *visitFree(CallInst &FI);
  Instruction *visitLoadInst(LoadInst &LI);
  Instruction *visitStoreInst(StoreInst &SI);
  Instruction *visitAtomicRMWInst(AtomicRMWInst &SI);
  Instruction *visitUnconditionalBranchInst(BranchInst &BI);
  Instruction *visitBranchInst(BranchInst &BI);
  Instruction *visitFenceInst(FenceInst &FI);
  Instruction *visitSwitchInst(SwitchInst &SI);
  Instruction *visitReturnInst(ReturnInst &RI);
  Instruction *visitUnreachableInst(UnreachableInst &I);
  Instruction *
  foldAggregateConstructionIntoAggregateReuse(InsertValueInst &OrigIVI);
  Instruction *visitInsertValueInst(InsertValueInst &IV);
  Instruction *visitInsertElementInst(InsertElementInst &IE);
  Instruction *visitExtractElementInst(ExtractElementInst &EI);
  Instruction *visitShuffleVectorInst(ShuffleVectorInst &SVI);
  Instruction *visitExtractValueInst(ExtractValueInst &EV);
  Instruction *visitLandingPadInst(LandingPadInst &LI);
  Instruction *visitVAEndInst(VAEndInst &I);
  Instruction *visitFreeze(FreezeInst &I);

  /// Specify what to return for unhandled instructions.
  Instruction *visitInstruction(Instruction &I) { return nullptr; }

  /// True when DB dominates all uses of DI except UI.
  /// UI must be in the same block as DI.
  /// The routine checks that the DI parent and DB are different.
  bool dominatesAllUses(const Instruction *DI, const Instruction *UI,
                        const BasicBlock *DB) const;

  /// Try to replace select with select operand SIOpd in SI-ICmp sequence.
  bool replacedSelectWithOperand(SelectInst *SI, const ICmpInst *Icmp,
                                 const unsigned SIOpd);

  LoadInst *combineLoadToNewType(LoadInst &LI, Type *NewTy,
                                 const Twine &Suffix = "");

private:
  bool shouldChangeType(unsigned FromBitWidth, unsigned ToBitWidth) const;
  bool shouldChangeType(Type *From, Type *To) const;
  Value *dyn_castNegVal(Value *V) const;
  Type *FindElementAtOffset(PointerType *PtrTy, int64_t Offset,
                            SmallVectorImpl<Value *> &NewIndices);

  /// Classify whether a cast is worth optimizing.
  ///
  /// This is a helper to decide whether the simplification of
  /// logic(cast(A), cast(B)) to cast(logic(A, B)) should be performed.
  ///
  /// \param CI The cast we are interested in.
  ///
  /// \return true if this cast actually results in any code being generated and
  /// if it cannot already be eliminated by some other transformation.
  bool shouldOptimizeCast(CastInst *CI);

  /// Try to optimize a sequence of instructions checking if an operation
  /// on LHS and RHS overflows.
  ///
  /// If this overflow check is done via one of the overflow check intrinsics,
  /// then CtxI has to be the call instruction calling that intrinsic.  If this
  /// overflow check is done by arithmetic followed by a compare, then CtxI has
  /// to be the arithmetic instruction.
  ///
  /// If a simplification is possible, stores the simplified result of the
  /// operation in OperationResult and result of the overflow check in
  /// OverflowResult, and return true.  If no simplification is possible,
  /// returns false.
  bool OptimizeOverflowCheck(Instruction::BinaryOps BinaryOp, bool IsSigned,
                             Value *LHS, Value *RHS,
                             Instruction &CtxI, Value *&OperationResult,
                             Constant *&OverflowResult);

  Instruction *visitCallBase(CallBase &Call);
  Instruction *tryOptimizeCall(CallInst *CI);
  bool transformConstExprCastCall(CallBase &Call);
  Instruction *transformCallThroughTrampoline(CallBase &Call,
                                              IntrinsicInst &Tramp);

  Value *simplifyMaskedLoad(IntrinsicInst &II);
  Instruction *simplifyMaskedStore(IntrinsicInst &II);
  Instruction *simplifyMaskedGather(IntrinsicInst &II);
  Instruction *simplifyMaskedScatter(IntrinsicInst &II);

  /// Transform (zext icmp) to bitwise / integer operations in order to
  /// eliminate it.
  ///
  /// \param ICI The icmp of the (zext icmp) pair we are interested in.
  /// \parem CI The zext of the (zext icmp) pair we are interested in.
  /// \param DoTransform Pass false to just test whether the given (zext icmp)
  /// would be transformed. Pass true to actually perform the transformation.
  ///
  /// \return null if the transformation cannot be performed. If the
  /// transformation can be performed the new instruction that replaces the
  /// (zext icmp) pair will be returned (if \p DoTransform is false the
  /// unmodified \p ICI will be returned in this case).
  Instruction *transformZExtICmp(ICmpInst *ICI, ZExtInst &CI,
                                 bool DoTransform = true);

  Instruction *transformSExtICmp(ICmpInst *ICI, Instruction &CI);

  bool willNotOverflowSignedAdd(const Value *LHS, const Value *RHS,
                                const Instruction &CxtI) const {
    return computeOverflowForSignedAdd(LHS, RHS, &CxtI) ==
           OverflowResult::NeverOverflows;
  }

  bool willNotOverflowUnsignedAdd(const Value *LHS, const Value *RHS,
                                  const Instruction &CxtI) const {
    return computeOverflowForUnsignedAdd(LHS, RHS, &CxtI) ==
           OverflowResult::NeverOverflows;
  }

  bool willNotOverflowAdd(const Value *LHS, const Value *RHS,
                          const Instruction &CxtI, bool IsSigned) const {
    return IsSigned ? willNotOverflowSignedAdd(LHS, RHS, CxtI)
                    : willNotOverflowUnsignedAdd(LHS, RHS, CxtI);
  }

  bool willNotOverflowSignedSub(const Value *LHS, const Value *RHS,
                                const Instruction &CxtI) const {
    return computeOverflowForSignedSub(LHS, RHS, &CxtI) ==
           OverflowResult::NeverOverflows;
  }

  bool willNotOverflowUnsignedSub(const Value *LHS, const Value *RHS,
                                  const Instruction &CxtI) const {
    return computeOverflowForUnsignedSub(LHS, RHS, &CxtI) ==
           OverflowResult::NeverOverflows;
  }

  bool willNotOverflowSub(const Value *LHS, const Value *RHS,
                          const Instruction &CxtI, bool IsSigned) const {
    return IsSigned ? willNotOverflowSignedSub(LHS, RHS, CxtI)
                    : willNotOverflowUnsignedSub(LHS, RHS, CxtI);
  }

  bool willNotOverflowSignedMul(const Value *LHS, const Value *RHS,
                                const Instruction &CxtI) const {
    return computeOverflowForSignedMul(LHS, RHS, &CxtI) ==
           OverflowResult::NeverOverflows;
  }

  bool willNotOverflowUnsignedMul(const Value *LHS, const Value *RHS,
                                  const Instruction &CxtI) const {
    return computeOverflowForUnsignedMul(LHS, RHS, &CxtI) ==
           OverflowResult::NeverOverflows;
  }

  bool willNotOverflowMul(const Value *LHS, const Value *RHS,
                          const Instruction &CxtI, bool IsSigned) const {
    return IsSigned ? willNotOverflowSignedMul(LHS, RHS, CxtI)
                    : willNotOverflowUnsignedMul(LHS, RHS, CxtI);
  }

  bool willNotOverflow(BinaryOperator::BinaryOps Opcode, const Value *LHS,
                       const Value *RHS, const Instruction &CxtI,
                       bool IsSigned) const {
    switch (Opcode) {
    case Instruction::Add: return willNotOverflowAdd(LHS, RHS, CxtI, IsSigned);
    case Instruction::Sub: return willNotOverflowSub(LHS, RHS, CxtI, IsSigned);
    case Instruction::Mul: return willNotOverflowMul(LHS, RHS, CxtI, IsSigned);
    default: llvm_unreachable("Unexpected opcode for overflow query");
    }
  }

  Value *EmitGEPOffset(User *GEP);
  Instruction *scalarizePHI(ExtractElementInst &EI, PHINode *PN);
  Instruction *foldCastedBitwiseLogic(BinaryOperator &I);
  Instruction *narrowBinOp(TruncInst &Trunc);
  Instruction *narrowMaskedBinOp(BinaryOperator &And);
  Instruction *narrowMathIfNoOverflow(BinaryOperator &I);
  Instruction *narrowFunnelShift(TruncInst &Trunc);
  Instruction *optimizeBitCastFromPhi(CastInst &CI, PHINode *PN);
  Instruction *matchSAddSubSat(SelectInst &MinMax1);

  void freelyInvertAllUsersOf(Value *V);

  /// Determine if a pair of casts can be replaced by a single cast.
  ///
  /// \param CI1 The first of a pair of casts.
  /// \param CI2 The second of a pair of casts.
  ///
  /// \return 0 if the cast pair cannot be eliminated, otherwise returns an
  /// Instruction::CastOps value for a cast that can replace the pair, casting
  /// CI1->getSrcTy() to CI2->getDstTy().
  ///
  /// \see CastInst::isEliminableCastPair
  Instruction::CastOps isEliminableCastPair(const CastInst *CI1,
                                            const CastInst *CI2);

  Value *foldAndOfICmps(ICmpInst *LHS, ICmpInst *RHS, BinaryOperator &And);
  Value *foldOrOfICmps(ICmpInst *LHS, ICmpInst *RHS, BinaryOperator &Or);
  Value *foldXorOfICmps(ICmpInst *LHS, ICmpInst *RHS, BinaryOperator &Xor);

  /// Optimize (fcmp)&(fcmp) or (fcmp)|(fcmp).
  /// NOTE: Unlike most of instcombine, this returns a Value which should
  /// already be inserted into the function.
  Value *foldLogicOfFCmps(FCmpInst *LHS, FCmpInst *RHS, bool IsAnd);

  Value *foldAndOrOfICmpsOfAndWithPow2(ICmpInst *LHS, ICmpInst *RHS,
                                       BinaryOperator &Logic);
  Value *matchSelectFromAndOr(Value *A, Value *B, Value *C, Value *D);
  Value *getSelectCondition(Value *A, Value *B);

  Instruction *foldIntrinsicWithOverflowCommon(IntrinsicInst *II);
  Instruction *foldFPSignBitOps(BinaryOperator &I);

public:
  /// Inserts an instruction \p New before instruction \p Old
  ///
  /// Also adds the new instruction to the worklist and returns \p New so that
  /// it is suitable for use as the return from the visitation patterns.
  Instruction *InsertNewInstBefore(Instruction *New, Instruction &Old) {
    assert(New && !New->getParent() &&
           "New instruction already inserted into a basic block!");
    BasicBlock *BB = Old.getParent();
    BB->getInstList().insert(Old.getIterator(), New); // Insert inst
    Worklist.add(New);
    return New;
  }

  /// Same as InsertNewInstBefore, but also sets the debug loc.
  Instruction *InsertNewInstWith(Instruction *New, Instruction &Old) {
    New->setDebugLoc(Old.getDebugLoc());
    return InsertNewInstBefore(New, Old);
  }

  /// A combiner-aware RAUW-like routine.
  ///
  /// This method is to be used when an instruction is found to be dead,
  /// replaceable with another preexisting expression. Here we add all uses of
  /// I to the worklist, replace all uses of I with the new value, then return
  /// I, so that the inst combiner will know that I was modified.
  Instruction *replaceInstUsesWith(Instruction &I, Value *V) {
    // If there are no uses to replace, then we return nullptr to indicate that
    // no changes were made to the program.
    if (I.use_empty()) return nullptr;

    Worklist.pushUsersToWorkList(I); // Add all modified instrs to worklist.

    // If we are replacing the instruction with itself, this must be in a
    // segment of unreachable code, so just clobber the instruction.
    if (&I == V)
      V = UndefValue::get(I.getType());

    LLVM_DEBUG(dbgs() << "IC: Replacing " << I << "\n"
                      << "    with " << *V << '\n');

    I.replaceAllUsesWith(V);
    MadeIRChange = true;
    return &I;
  }

  /// Replace operand of instruction and add old operand to the worklist.
  Instruction *replaceOperand(Instruction &I, unsigned OpNum, Value *V) {
    Worklist.addValue(I.getOperand(OpNum));
    I.setOperand(OpNum, V);
    return &I;
  }

  /// Replace use and add the previously used value to the worklist.
  void replaceUse(Use &U, Value *NewValue) {
    Worklist.addValue(U);
    U = NewValue;
  }

  /// Creates a result tuple for an overflow intrinsic \p II with a given
  /// \p Result and a constant \p Overflow value.
  Instruction *CreateOverflowTuple(IntrinsicInst *II, Value *Result,
                                   Constant *Overflow) {
    Constant *V[] = {UndefValue::get(Result->getType()), Overflow};
    StructType *ST = cast<StructType>(II->getType());
    Constant *Struct = ConstantStruct::get(ST, V);
    return InsertValueInst::Create(Struct, Result, 0);
  }

  /// Create and insert the idiom we use to indicate a block is unreachable
  /// without having to rewrite the CFG from within InstCombine.
  void CreateNonTerminatorUnreachable(Instruction *InsertAt) {
    auto &Ctx = InsertAt->getContext();
    new StoreInst(ConstantInt::getTrue(Ctx),
                  UndefValue::get(Type::getInt1PtrTy(Ctx)),
                  InsertAt);
  }


  /// Combiner aware instruction erasure.
  ///
  /// When dealing with an instruction that has side effects or produces a void
  /// value, we can't rely on DCE to delete the instruction. Instead, visit
  /// methods should return the value returned by this function.
  Instruction *eraseInstFromFunction(Instruction &I) override {
    LLVM_DEBUG(dbgs() << "IC: ERASE " << I << '\n');
    assert(I.use_empty() && "Cannot erase instruction that is used!");
    salvageDebugInfo(I);

    // Make sure that we reprocess all operands now that we reduced their
    // use counts.
    for (Use &Operand : I.operands())
      if (auto *Inst = dyn_cast<Instruction>(Operand))
        Worklist.add(Inst);

    Worklist.remove(&I);
    I.eraseFromParent();
    MadeIRChange = true;
    return nullptr; // Don't do anything with FI
  }

  void computeKnownBits(const Value *V, KnownBits &Known,
                        unsigned Depth, const Instruction *CxtI) const {
    llvm::computeKnownBits(V, Known, DL, Depth, &AC, CxtI, &DT);
  }

  KnownBits computeKnownBits(const Value *V, unsigned Depth,
                             const Instruction *CxtI) const {
    return llvm::computeKnownBits(V, DL, Depth, &AC, CxtI, &DT);
  }

  bool isKnownToBeAPowerOfTwo(const Value *V, bool OrZero = false,
                              unsigned Depth = 0,
                              const Instruction *CxtI = nullptr) {
    return llvm::isKnownToBeAPowerOfTwo(V, DL, OrZero, Depth, &AC, CxtI, &DT);
  }

  bool MaskedValueIsZero(const Value *V, const APInt &Mask, unsigned Depth = 0,
                         const Instruction *CxtI = nullptr) const {
    return llvm::MaskedValueIsZero(V, Mask, DL, Depth, &AC, CxtI, &DT);
  }

  unsigned ComputeNumSignBits(const Value *Op, unsigned Depth = 0,
                              const Instruction *CxtI = nullptr) const {
    return llvm::ComputeNumSignBits(Op, DL, Depth, &AC, CxtI, &DT);
  }

  OverflowResult computeOverflowForUnsignedMul(const Value *LHS,
                                               const Value *RHS,
                                               const Instruction *CxtI) const {
    return llvm::computeOverflowForUnsignedMul(LHS, RHS, DL, &AC, CxtI, &DT);
  }

  OverflowResult computeOverflowForSignedMul(const Value *LHS,
                                             const Value *RHS,
                                             const Instruction *CxtI) const {
    return llvm::computeOverflowForSignedMul(LHS, RHS, DL, &AC, CxtI, &DT);
  }

  OverflowResult computeOverflowForUnsignedAdd(const Value *LHS,
                                               const Value *RHS,
                                               const Instruction *CxtI) const {
    return llvm::computeOverflowForUnsignedAdd(LHS, RHS, DL, &AC, CxtI, &DT);
  }

  OverflowResult computeOverflowForSignedAdd(const Value *LHS,
                                             const Value *RHS,
                                             const Instruction *CxtI) const {
    return llvm::computeOverflowForSignedAdd(LHS, RHS, DL, &AC, CxtI, &DT);
  }

  OverflowResult computeOverflowForUnsignedSub(const Value *LHS,
                                               const Value *RHS,
                                               const Instruction *CxtI) const {
    return llvm::computeOverflowForUnsignedSub(LHS, RHS, DL, &AC, CxtI, &DT);
  }

  OverflowResult computeOverflowForSignedSub(const Value *LHS, const Value *RHS,
                                             const Instruction *CxtI) const {
    return llvm::computeOverflowForSignedSub(LHS, RHS, DL, &AC, CxtI, &DT);
  }

  OverflowResult computeOverflow(
      Instruction::BinaryOps BinaryOp, bool IsSigned,
      Value *LHS, Value *RHS, Instruction *CxtI) const;

  /// Performs a few simplifications for operators which are associative
  /// or commutative.
  bool SimplifyAssociativeOrCommutative(BinaryOperator &I);

  /// Tries to simplify binary operations which some other binary
  /// operation distributes over.
  ///
  /// It does this by either by factorizing out common terms (eg "(A*B)+(A*C)"
  /// -> "A*(B+C)") or expanding out if this results in simplifications (eg: "A
  /// & (B | C) -> (A&B) | (A&C)" if this is a win).  Returns the simplified
  /// value, or null if it didn't simplify.
  Value *SimplifyUsingDistributiveLaws(BinaryOperator &I);

  /// Tries to simplify add operations using the definition of remainder.
  ///
  /// The definition of remainder is X % C = X - (X / C ) * C. The add
  /// expression X % C0 + (( X / C0 ) % C1) * C0 can be simplified to
  /// X % (C0 * C1)
  Value *SimplifyAddWithRemainder(BinaryOperator &I);

  // Binary Op helper for select operations where the expression can be
  // efficiently reorganized.
  Value *SimplifySelectsFeedingBinaryOp(BinaryOperator &I, Value *LHS,
                                        Value *RHS);

  /// This tries to simplify binary operations by factorizing out common terms
  /// (e. g. "(A*B)+(A*C)" -> "A*(B+C)").
  Value *tryFactorization(BinaryOperator &, Instruction::BinaryOps, Value *,
                          Value *, Value *, Value *);

  /// Match a select chain which produces one of three values based on whether
  /// the LHS is less than, equal to, or greater than RHS respectively.
  /// Return true if we matched a three way compare idiom. The LHS, RHS, Less,
  /// Equal and Greater values are saved in the matching process and returned to
  /// the caller.
  bool matchThreeWayIntCompare(SelectInst *SI, Value *&LHS, Value *&RHS,
                               ConstantInt *&Less, ConstantInt *&Equal,
                               ConstantInt *&Greater);

  /// Attempts to replace V with a simpler value based on the demanded
  /// bits.
  Value *SimplifyDemandedUseBits(Value *V, APInt DemandedMask, KnownBits &Known,
                                 unsigned Depth, Instruction *CxtI);
  bool SimplifyDemandedBits(Instruction *I, unsigned Op,
                            const APInt &DemandedMask, KnownBits &Known,
                            unsigned Depth = 0) override;

  /// Helper routine of SimplifyDemandedUseBits. It computes KnownZero/KnownOne
  /// bits. It also tries to handle simplifications that can be done based on
  /// DemandedMask, but without modifying the Instruction.
  Value *SimplifyMultipleUseDemandedBits(Instruction *I,
                                         const APInt &DemandedMask,
                                         KnownBits &Known,
                                         unsigned Depth, Instruction *CxtI);

  /// Helper routine of SimplifyDemandedUseBits. It tries to simplify demanded
  /// bit for "r1 = shr x, c1; r2 = shl r1, c2" instruction sequence.
  Value *simplifyShrShlDemandedBits(
      Instruction *Shr, const APInt &ShrOp1, Instruction *Shl,
      const APInt &ShlOp1, const APInt &DemandedMask, KnownBits &Known);

  /// Tries to simplify operands to an integer instruction based on its
  /// demanded bits.
  bool SimplifyDemandedInstructionBits(Instruction &Inst);

  virtual Value *
  SimplifyDemandedVectorElts(Value *V, APInt DemandedElts, APInt &UndefElts,
                             unsigned Depth = 0,
                             bool AllowMultipleUsers = false) override;

  /// Canonicalize the position of binops relative to shufflevector.
  Instruction *foldVectorBinop(BinaryOperator &Inst);
  Instruction *foldVectorSelect(SelectInst &Sel);

  /// Given a binary operator, cast instruction, or select which has a PHI node
  /// as operand #0, see if we can fold the instruction into the PHI (which is
  /// only possible if all operands to the PHI are constants).
  Instruction *foldOpIntoPhi(Instruction &I, PHINode *PN);

  /// Given an instruction with a select as one operand and a constant as the
  /// other operand, try to fold the binary operator into the select arguments.
  /// This also works for Cast instructions, which obviously do not have a
  /// second operand.
  Instruction *FoldOpIntoSelect(Instruction &Op, SelectInst *SI);

  /// This is a convenience wrapper function for the above two functions.
  Instruction *foldBinOpIntoSelectOrPhi(BinaryOperator &I);

  Instruction *foldAddWithConstant(BinaryOperator &Add);

  /// Try to rotate an operation below a PHI node, using PHI nodes for
  /// its operands.
  Instruction *foldPHIArgOpIntoPHI(PHINode &PN);
  Instruction *foldPHIArgBinOpIntoPHI(PHINode &PN);
  Instruction *foldPHIArgInsertValueInstructionIntoPHI(PHINode &PN);
  Instruction *foldPHIArgExtractValueInstructionIntoPHI(PHINode &PN);
  Instruction *foldPHIArgGEPIntoPHI(PHINode &PN);
  Instruction *foldPHIArgLoadIntoPHI(PHINode &PN);
  Instruction *foldPHIArgZextsIntoPHI(PHINode &PN);

  /// If an integer typed PHI has only one use which is an IntToPtr operation,
  /// replace the PHI with an existing pointer typed PHI if it exists. Otherwise
  /// insert a new pointer typed PHI and replace the original one.
  Instruction *foldIntegerTypedPHI(PHINode &PN);

  /// Helper function for FoldPHIArgXIntoPHI() to set debug location for the
  /// folded operation.
  void PHIArgMergedDebugLoc(Instruction *Inst, PHINode &PN);

  Instruction *foldGEPICmp(GEPOperator *GEPLHS, Value *RHS,
                           ICmpInst::Predicate Cond, Instruction &I);
  Instruction *foldAllocaCmp(ICmpInst &ICI, const AllocaInst *Alloca,
                             const Value *Other);
  Instruction *foldCmpLoadFromIndexedGlobal(GetElementPtrInst *GEP,
                                            GlobalVariable *GV, CmpInst &ICI,
                                            ConstantInt *AndCst = nullptr);
  Instruction *foldFCmpIntToFPConst(FCmpInst &I, Instruction *LHSI,
                                    Constant *RHSC);
  Instruction *foldICmpAddOpConst(Value *X, const APInt &C,
                                  ICmpInst::Predicate Pred);
  Instruction *foldICmpWithCastOp(ICmpInst &ICI);

  Instruction *foldICmpUsingKnownBits(ICmpInst &Cmp);
  Instruction *foldICmpWithDominatingICmp(ICmpInst &Cmp);
  Instruction *foldICmpWithConstant(ICmpInst &Cmp);
  Instruction *foldICmpInstWithConstant(ICmpInst &Cmp);
  Instruction *foldICmpInstWithConstantNotInt(ICmpInst &Cmp);
  Instruction *foldICmpBinOp(ICmpInst &Cmp, const SimplifyQuery &SQ);
  Instruction *foldICmpEquality(ICmpInst &Cmp);
  Instruction *foldIRemByPowerOfTwoToBitTest(ICmpInst &I);
  Instruction *foldSignBitTest(ICmpInst &I);
  Instruction *foldICmpWithZero(ICmpInst &Cmp);

  Value *foldUnsignedMultiplicationOverflowCheck(ICmpInst &Cmp);

  Instruction *foldICmpSelectConstant(ICmpInst &Cmp, SelectInst *Select,
                                      ConstantInt *C);
  Instruction *foldICmpTruncConstant(ICmpInst &Cmp, TruncInst *Trunc,
                                     const APInt &C);
  Instruction *foldICmpAndConstant(ICmpInst &Cmp, BinaryOperator *And,
                                   const APInt &C);
  Instruction *foldICmpXorConstant(ICmpInst &Cmp, BinaryOperator *Xor,
                                   const APInt &C);
  Instruction *foldICmpOrConstant(ICmpInst &Cmp, BinaryOperator *Or,
                                  const APInt &C);
  Instruction *foldICmpMulConstant(ICmpInst &Cmp, BinaryOperator *Mul,
                                   const APInt &C);
  Instruction *foldICmpShlConstant(ICmpInst &Cmp, BinaryOperator *Shl,
                                   const APInt &C);
  Instruction *foldICmpShrConstant(ICmpInst &Cmp, BinaryOperator *Shr,
                                   const APInt &C);
  Instruction *foldICmpSRemConstant(ICmpInst &Cmp, BinaryOperator *UDiv,
                                    const APInt &C);
  Instruction *foldICmpUDivConstant(ICmpInst &Cmp, BinaryOperator *UDiv,
                                    const APInt &C);
  Instruction *foldICmpDivConstant(ICmpInst &Cmp, BinaryOperator *Div,
                                   const APInt &C);
  Instruction *foldICmpSubConstant(ICmpInst &Cmp, BinaryOperator *Sub,
                                   const APInt &C);
  Instruction *foldICmpAddConstant(ICmpInst &Cmp, BinaryOperator *Add,
                                   const APInt &C);
  Instruction *foldICmpAndConstConst(ICmpInst &Cmp, BinaryOperator *And,
                                     const APInt &C1);
  Instruction *foldICmpAndShift(ICmpInst &Cmp, BinaryOperator *And,
                                const APInt &C1, const APInt &C2);
  Instruction *foldICmpShrConstConst(ICmpInst &I, Value *ShAmt, const APInt &C1,
                                     const APInt &C2);
  Instruction *foldICmpShlConstConst(ICmpInst &I, Value *ShAmt, const APInt &C1,
                                     const APInt &C2);

  Instruction *foldICmpBinOpEqualityWithConstant(ICmpInst &Cmp,
                                                 BinaryOperator *BO,
                                                 const APInt &C);
  Instruction *foldICmpIntrinsicWithConstant(ICmpInst &ICI, IntrinsicInst *II,
                                             const APInt &C);
  Instruction *foldICmpEqIntrinsicWithConstant(ICmpInst &ICI, IntrinsicInst *II,
                                               const APInt &C);

  // Helpers of visitSelectInst().
  Instruction *foldSelectExtConst(SelectInst &Sel);
  Instruction *foldSelectOpOp(SelectInst &SI, Instruction *TI, Instruction *FI);
  Instruction *foldSelectIntoOp(SelectInst &SI, Value *, Value *);
  Instruction *foldSPFofSPF(Instruction *Inner, SelectPatternFlavor SPF1,
                            Value *A, Value *B, Instruction &Outer,
                            SelectPatternFlavor SPF2, Value *C);
  Instruction *foldSelectInstWithICmp(SelectInst &SI, ICmpInst *ICI);
  Instruction *foldSelectValueEquivalence(SelectInst &SI, ICmpInst &ICI);

  Value *insertRangeTest(Value *V, const APInt &Lo, const APInt &Hi,
                         bool isSigned, bool Inside);
  Instruction *PromoteCastOfAllocation(BitCastInst &CI, AllocaInst &AI);
  bool mergeStoreIntoSuccessor(StoreInst &SI);

  /// Given an 'or' instruction, check to see if it is part of a
  /// bswap/bitreverse idiom. If so, return the equivalent bswap/bitreverse
  /// intrinsic.
  Instruction *matchBSwapOrBitReverse(BinaryOperator &Or, bool MatchBSwaps,
                                      bool MatchBitReversals);

  Instruction *SimplifyAnyMemTransfer(AnyMemTransferInst *MI);
  Instruction *SimplifyAnyMemSet(AnyMemSetInst *MI);

  Value *EvaluateInDifferentType(Value *V, Type *Ty, bool isSigned);

  /// Returns a value X such that Val = X * Scale, or null if none.
  ///
  /// If the multiplication is known not to overflow then NoSignedWrap is set.
  Value *Descale(Value *Val, APInt Scale, bool &NoSignedWrap);
};

class Negator final {
  /// Top-to-bottom, def-to-use negated instruction tree we produced.
  SmallVector<Instruction *, NegatorMaxNodesSSO> NewInstructions;

  using BuilderTy = IRBuilder<TargetFolder, IRBuilderCallbackInserter>;
  BuilderTy Builder;

  const DataLayout &DL;
  AssumptionCache &AC;
  const DominatorTree &DT;

  const bool IsTrulyNegation;

  SmallDenseMap<Value *, Value *> NegationsCache;

  Negator(LLVMContext &C, const DataLayout &DL, AssumptionCache &AC,
          const DominatorTree &DT, bool IsTrulyNegation);

#if LLVM_ENABLE_STATS
  unsigned NumValuesVisitedInThisNegator = 0;
  ~Negator();
#endif

  using Result = std::pair<ArrayRef<Instruction *> /*NewInstructions*/,
                           Value * /*NegatedRoot*/>;

  std::array<Value *, 2> getSortedOperandsOfBinOp(Instruction *I);

  LLVM_NODISCARD Value *visitImpl(Value *V, unsigned Depth);

  LLVM_NODISCARD Value *negate(Value *V, unsigned Depth);

  /// Recurse depth-first and attempt to sink the negation.
  /// FIXME: use worklist?
  LLVM_NODISCARD Optional<Result> run(Value *Root);

  Negator(const Negator &) = delete;
  Negator(Negator &&) = delete;
  Negator &operator=(const Negator &) = delete;
  Negator &operator=(Negator &&) = delete;

public:
  /// Attempt to negate \p Root. Retuns nullptr if negation can't be performed,
  /// otherwise returns negated value.
  LLVM_NODISCARD static Value *Negate(bool LHSIsZero, Value *Root,
                                      InstCombinerImpl &IC);
};

} // end namespace llvm

#undef DEBUG_TYPE

#endif // LLVM_LIB_TRANSFORMS_INSTCOMBINE_INSTCOMBINEINTERNAL_H