llvm.org GIT mirror llvm / release_38 lib / Transforms / Scalar / EarlyCSE.cpp
release_38

Tree @release_38 (Download .tar.gz)

EarlyCSE.cpp @release_38raw · 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
//===- EarlyCSE.cpp - Simple and fast CSE pass ----------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass performs a simple dominator tree walk that eliminates trivially
// redundant instructions.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar/EarlyCSE.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/ScopedHashTable.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/Pass.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/RecyclingAllocator.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/Local.h"
#include <deque>
using namespace llvm;
using namespace llvm::PatternMatch;

#define DEBUG_TYPE "early-cse"

STATISTIC(NumSimplify, "Number of instructions simplified or DCE'd");
STATISTIC(NumCSE,      "Number of instructions CSE'd");
STATISTIC(NumCSELoad,  "Number of load instructions CSE'd");
STATISTIC(NumCSECall,  "Number of call instructions CSE'd");
STATISTIC(NumDSE,      "Number of trivial dead stores removed");

//===----------------------------------------------------------------------===//
// SimpleValue
//===----------------------------------------------------------------------===//

namespace {
/// \brief Struct representing the available values in the scoped hash table.
struct SimpleValue {
  Instruction *Inst;

  SimpleValue(Instruction *I) : Inst(I) {
    assert((isSentinel() || canHandle(I)) && "Inst can't be handled!");
  }

  bool isSentinel() const {
    return Inst == DenseMapInfo<Instruction *>::getEmptyKey() ||
           Inst == DenseMapInfo<Instruction *>::getTombstoneKey();
  }

  static bool canHandle(Instruction *Inst) {
    // This can only handle non-void readnone functions.
    if (CallInst *CI = dyn_cast<CallInst>(Inst))
      return CI->doesNotAccessMemory() && !CI->getType()->isVoidTy();
    return isa<CastInst>(Inst) || isa<BinaryOperator>(Inst) ||
           isa<GetElementPtrInst>(Inst) || isa<CmpInst>(Inst) ||
           isa<SelectInst>(Inst) || isa<ExtractElementInst>(Inst) ||
           isa<InsertElementInst>(Inst) || isa<ShuffleVectorInst>(Inst) ||
           isa<ExtractValueInst>(Inst) || isa<InsertValueInst>(Inst);
  }
};
}

namespace llvm {
template <> struct DenseMapInfo<SimpleValue> {
  static inline SimpleValue getEmptyKey() {
    return DenseMapInfo<Instruction *>::getEmptyKey();
  }
  static inline SimpleValue getTombstoneKey() {
    return DenseMapInfo<Instruction *>::getTombstoneKey();
  }
  static unsigned getHashValue(SimpleValue Val);
  static bool isEqual(SimpleValue LHS, SimpleValue RHS);
};
}

unsigned DenseMapInfo<SimpleValue>::getHashValue(SimpleValue Val) {
  Instruction *Inst = Val.Inst;
  // Hash in all of the operands as pointers.
  if (BinaryOperator *BinOp = dyn_cast<BinaryOperator>(Inst)) {
    Value *LHS = BinOp->getOperand(0);
    Value *RHS = BinOp->getOperand(1);
    if (BinOp->isCommutative() && BinOp->getOperand(0) > BinOp->getOperand(1))
      std::swap(LHS, RHS);

    if (isa<OverflowingBinaryOperator>(BinOp)) {
      // Hash the overflow behavior
      unsigned Overflow =
          BinOp->hasNoSignedWrap() * OverflowingBinaryOperator::NoSignedWrap |
          BinOp->hasNoUnsignedWrap() *
              OverflowingBinaryOperator::NoUnsignedWrap;
      return hash_combine(BinOp->getOpcode(), Overflow, LHS, RHS);
    }

    return hash_combine(BinOp->getOpcode(), LHS, RHS);
  }

  if (CmpInst *CI = dyn_cast<CmpInst>(Inst)) {
    Value *LHS = CI->getOperand(0);
    Value *RHS = CI->getOperand(1);
    CmpInst::Predicate Pred = CI->getPredicate();
    if (Inst->getOperand(0) > Inst->getOperand(1)) {
      std::swap(LHS, RHS);
      Pred = CI->getSwappedPredicate();
    }
    return hash_combine(Inst->getOpcode(), Pred, LHS, RHS);
  }

  if (CastInst *CI = dyn_cast<CastInst>(Inst))
    return hash_combine(CI->getOpcode(), CI->getType(), CI->getOperand(0));

  if (const ExtractValueInst *EVI = dyn_cast<ExtractValueInst>(Inst))
    return hash_combine(EVI->getOpcode(), EVI->getOperand(0),
                        hash_combine_range(EVI->idx_begin(), EVI->idx_end()));

  if (const InsertValueInst *IVI = dyn_cast<InsertValueInst>(Inst))
    return hash_combine(IVI->getOpcode(), IVI->getOperand(0),
                        IVI->getOperand(1),
                        hash_combine_range(IVI->idx_begin(), IVI->idx_end()));

  assert((isa<CallInst>(Inst) || isa<BinaryOperator>(Inst) ||
          isa<GetElementPtrInst>(Inst) || isa<SelectInst>(Inst) ||
          isa<ExtractElementInst>(Inst) || isa<InsertElementInst>(Inst) ||
          isa<ShuffleVectorInst>(Inst)) &&
         "Invalid/unknown instruction");

  // Mix in the opcode.
  return hash_combine(
      Inst->getOpcode(),
      hash_combine_range(Inst->value_op_begin(), Inst->value_op_end()));
}

bool DenseMapInfo<SimpleValue>::isEqual(SimpleValue LHS, SimpleValue RHS) {
  Instruction *LHSI = LHS.Inst, *RHSI = RHS.Inst;

  if (LHS.isSentinel() || RHS.isSentinel())
    return LHSI == RHSI;

  if (LHSI->getOpcode() != RHSI->getOpcode())
    return false;
  if (LHSI->isIdenticalTo(RHSI))
    return true;

  // If we're not strictly identical, we still might be a commutable instruction
  if (BinaryOperator *LHSBinOp = dyn_cast<BinaryOperator>(LHSI)) {
    if (!LHSBinOp->isCommutative())
      return false;

    assert(isa<BinaryOperator>(RHSI) &&
           "same opcode, but different instruction type?");
    BinaryOperator *RHSBinOp = cast<BinaryOperator>(RHSI);

    // Check overflow attributes
    if (isa<OverflowingBinaryOperator>(LHSBinOp)) {
      assert(isa<OverflowingBinaryOperator>(RHSBinOp) &&
             "same opcode, but different operator type?");
      if (LHSBinOp->hasNoUnsignedWrap() != RHSBinOp->hasNoUnsignedWrap() ||
          LHSBinOp->hasNoSignedWrap() != RHSBinOp->hasNoSignedWrap())
        return false;
    }

    // Commuted equality
    return LHSBinOp->getOperand(0) == RHSBinOp->getOperand(1) &&
           LHSBinOp->getOperand(1) == RHSBinOp->getOperand(0);
  }
  if (CmpInst *LHSCmp = dyn_cast<CmpInst>(LHSI)) {
    assert(isa<CmpInst>(RHSI) &&
           "same opcode, but different instruction type?");
    CmpInst *RHSCmp = cast<CmpInst>(RHSI);
    // Commuted equality
    return LHSCmp->getOperand(0) == RHSCmp->getOperand(1) &&
           LHSCmp->getOperand(1) == RHSCmp->getOperand(0) &&
           LHSCmp->getSwappedPredicate() == RHSCmp->getPredicate();
  }

  return false;
}

//===----------------------------------------------------------------------===//
// CallValue
//===----------------------------------------------------------------------===//

namespace {
/// \brief Struct representing the available call values in the scoped hash
/// table.
struct CallValue {
  Instruction *Inst;

  CallValue(Instruction *I) : Inst(I) {
    assert((isSentinel() || canHandle(I)) && "Inst can't be handled!");
  }

  bool isSentinel() const {
    return Inst == DenseMapInfo<Instruction *>::getEmptyKey() ||
           Inst == DenseMapInfo<Instruction *>::getTombstoneKey();
  }

  static bool canHandle(Instruction *Inst) {
    // Don't value number anything that returns void.
    if (Inst->getType()->isVoidTy())
      return false;

    CallInst *CI = dyn_cast<CallInst>(Inst);
    if (!CI || !CI->onlyReadsMemory())
      return false;
    return true;
  }
};
}

namespace llvm {
template <> struct DenseMapInfo<CallValue> {
  static inline CallValue getEmptyKey() {
    return DenseMapInfo<Instruction *>::getEmptyKey();
  }
  static inline CallValue getTombstoneKey() {
    return DenseMapInfo<Instruction *>::getTombstoneKey();
  }
  static unsigned getHashValue(CallValue Val);
  static bool isEqual(CallValue LHS, CallValue RHS);
};
}

unsigned DenseMapInfo<CallValue>::getHashValue(CallValue Val) {
  Instruction *Inst = Val.Inst;
  // Hash all of the operands as pointers and mix in the opcode.
  return hash_combine(
      Inst->getOpcode(),
      hash_combine_range(Inst->value_op_begin(), Inst->value_op_end()));
}

bool DenseMapInfo<CallValue>::isEqual(CallValue LHS, CallValue RHS) {
  Instruction *LHSI = LHS.Inst, *RHSI = RHS.Inst;
  if (LHS.isSentinel() || RHS.isSentinel())
    return LHSI == RHSI;
  return LHSI->isIdenticalTo(RHSI);
}

//===----------------------------------------------------------------------===//
// EarlyCSE implementation
//===----------------------------------------------------------------------===//

namespace {
/// \brief A simple and fast domtree-based CSE pass.
///
/// This pass does a simple depth-first walk over the dominator tree,
/// eliminating trivially redundant instructions and using instsimplify to
/// canonicalize things as it goes. It is intended to be fast and catch obvious
/// cases so that instcombine and other passes are more effective. It is
/// expected that a later pass of GVN will catch the interesting/hard cases.
class EarlyCSE {
public:
  const TargetLibraryInfo &TLI;
  const TargetTransformInfo &TTI;
  DominatorTree &DT;
  AssumptionCache &AC;
  typedef RecyclingAllocator<
      BumpPtrAllocator, ScopedHashTableVal<SimpleValue, Value *>> AllocatorTy;
  typedef ScopedHashTable<SimpleValue, Value *, DenseMapInfo<SimpleValue>,
                          AllocatorTy> ScopedHTType;

  /// \brief A scoped hash table of the current values of all of our simple
  /// scalar expressions.
  ///
  /// As we walk down the domtree, we look to see if instructions are in this:
  /// if so, we replace them with what we find, otherwise we insert them so
  /// that dominated values can succeed in their lookup.
  ScopedHTType AvailableValues;

  /// A scoped hash table of the current values of previously encounted memory
  /// locations.
  ///
  /// This allows us to get efficient access to dominating loads or stores when
  /// we have a fully redundant load.  In addition to the most recent load, we
  /// keep track of a generation count of the read, which is compared against
  /// the current generation count.  The current generation count is incremented
  /// after every possibly writing memory operation, which ensures that we only
  /// CSE loads with other loads that have no intervening store.  Ordering
  /// events (such as fences or atomic instructions) increment the generation
  /// count as well; essentially, we model these as writes to all possible
  /// locations.  Note that atomic and/or volatile loads and stores can be
  /// present the table; it is the responsibility of the consumer to inspect
  /// the atomicity/volatility if needed.
  struct LoadValue {
    Value *Data;
    unsigned Generation;
    int MatchingId;
    bool IsAtomic;
    LoadValue()
      : Data(nullptr), Generation(0), MatchingId(-1), IsAtomic(false) {}
    LoadValue(Value *Data, unsigned Generation, unsigned MatchingId,
              bool IsAtomic)
      : Data(Data), Generation(Generation), MatchingId(MatchingId),
        IsAtomic(IsAtomic) {}
  };
  typedef RecyclingAllocator<BumpPtrAllocator,
                             ScopedHashTableVal<Value *, LoadValue>>
      LoadMapAllocator;
  typedef ScopedHashTable<Value *, LoadValue, DenseMapInfo<Value *>,
                          LoadMapAllocator> LoadHTType;
  LoadHTType AvailableLoads;

  /// \brief A scoped hash table of the current values of read-only call
  /// values.
  ///
  /// It uses the same generation count as loads.
  typedef ScopedHashTable<CallValue, std::pair<Value *, unsigned>> CallHTType;
  CallHTType AvailableCalls;

  /// \brief This is the current generation of the memory value.
  unsigned CurrentGeneration;

  /// \brief Set up the EarlyCSE runner for a particular function.
  EarlyCSE(const TargetLibraryInfo &TLI, const TargetTransformInfo &TTI,
           DominatorTree &DT, AssumptionCache &AC)
      : TLI(TLI), TTI(TTI), DT(DT), AC(AC), CurrentGeneration(0) {}

  bool run();

private:
  // Almost a POD, but needs to call the constructors for the scoped hash
  // tables so that a new scope gets pushed on. These are RAII so that the
  // scope gets popped when the NodeScope is destroyed.
  class NodeScope {
  public:
    NodeScope(ScopedHTType &AvailableValues, LoadHTType &AvailableLoads,
              CallHTType &AvailableCalls)
        : Scope(AvailableValues), LoadScope(AvailableLoads),
          CallScope(AvailableCalls) {}

  private:
    NodeScope(const NodeScope &) = delete;
    void operator=(const NodeScope &) = delete;

    ScopedHTType::ScopeTy Scope;
    LoadHTType::ScopeTy LoadScope;
    CallHTType::ScopeTy CallScope;
  };

  // Contains all the needed information to create a stack for doing a depth
  // first tranversal of the tree. This includes scopes for values, loads, and
  // calls as well as the generation. There is a child iterator so that the
  // children do not need to be store spearately.
  class StackNode {
  public:
    StackNode(ScopedHTType &AvailableValues, LoadHTType &AvailableLoads,
              CallHTType &AvailableCalls, unsigned cg, DomTreeNode *n,
              DomTreeNode::iterator child, DomTreeNode::iterator end)
        : CurrentGeneration(cg), ChildGeneration(cg), Node(n), ChildIter(child),
          EndIter(end), Scopes(AvailableValues, AvailableLoads, AvailableCalls),
          Processed(false) {}

    // Accessors.
    unsigned currentGeneration() { return CurrentGeneration; }
    unsigned childGeneration() { return ChildGeneration; }
    void childGeneration(unsigned generation) { ChildGeneration = generation; }
    DomTreeNode *node() { return Node; }
    DomTreeNode::iterator childIter() { return ChildIter; }
    DomTreeNode *nextChild() {
      DomTreeNode *child = *ChildIter;
      ++ChildIter;
      return child;
    }
    DomTreeNode::iterator end() { return EndIter; }
    bool isProcessed() { return Processed; }
    void process() { Processed = true; }

  private:
    StackNode(const StackNode &) = delete;
    void operator=(const StackNode &) = delete;

    // Members.
    unsigned CurrentGeneration;
    unsigned ChildGeneration;
    DomTreeNode *Node;
    DomTreeNode::iterator ChildIter;
    DomTreeNode::iterator EndIter;
    NodeScope Scopes;
    bool Processed;
  };

  /// \brief Wrapper class to handle memory instructions, including loads,
  /// stores and intrinsic loads and stores defined by the target.
  class ParseMemoryInst {
  public:
    ParseMemoryInst(Instruction *Inst, const TargetTransformInfo &TTI)
      : IsTargetMemInst(false), Inst(Inst) {
      if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(Inst))
        if (TTI.getTgtMemIntrinsic(II, Info) && Info.NumMemRefs == 1)
          IsTargetMemInst = true;
    }
    bool isLoad() const {
      if (IsTargetMemInst) return Info.ReadMem;
      return isa<LoadInst>(Inst);
    }
    bool isStore() const {
      if (IsTargetMemInst) return Info.WriteMem;
      return isa<StoreInst>(Inst);
    }
    bool isAtomic() const {
      if (IsTargetMemInst) {
        assert(Info.IsSimple && "need to refine IsSimple in TTI");
        return false;
      }
      return Inst->isAtomic();
    }
    bool isUnordered() const {
      if (IsTargetMemInst) {
        assert(Info.IsSimple && "need to refine IsSimple in TTI");
        return true;
      }
      if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
        return LI->isUnordered();
      } else if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
        return SI->isUnordered();
      }
      // Conservative answer
      return !Inst->isAtomic();
    }

    bool isVolatile() const {
      if (IsTargetMemInst) {
        assert(Info.IsSimple && "need to refine IsSimple in TTI");
        return false;
      }
      if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
        return LI->isVolatile();
      } else if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
        return SI->isVolatile();
      }
      // Conservative answer
      return true;
    }

    
    bool isMatchingMemLoc(const ParseMemoryInst &Inst) const {
      return (getPointerOperand() == Inst.getPointerOperand() &&
              getMatchingId() == Inst.getMatchingId());
    }
    bool isValid() const { return getPointerOperand() != nullptr; }

    // For regular (non-intrinsic) loads/stores, this is set to -1. For
    // intrinsic loads/stores, the id is retrieved from the corresponding
    // field in the MemIntrinsicInfo structure.  That field contains
    // non-negative values only.
    int getMatchingId() const {
      if (IsTargetMemInst) return Info.MatchingId;
      return -1;
    }
    Value *getPointerOperand() const {
      if (IsTargetMemInst) return Info.PtrVal;
      if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
        return LI->getPointerOperand();
      } else if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
        return SI->getPointerOperand();
      }
      return nullptr;
    }
    bool mayReadFromMemory() const {
      if (IsTargetMemInst) return Info.ReadMem;
      return Inst->mayReadFromMemory();
    }
    bool mayWriteToMemory() const {
      if (IsTargetMemInst) return Info.WriteMem;
      return Inst->mayWriteToMemory();
    }

  private:
    bool IsTargetMemInst;
    MemIntrinsicInfo Info;
    Instruction *Inst;
  };

  bool processNode(DomTreeNode *Node);

  Value *getOrCreateResult(Value *Inst, Type *ExpectedType) const {
    if (LoadInst *LI = dyn_cast<LoadInst>(Inst))
      return LI;
    else if (StoreInst *SI = dyn_cast<StoreInst>(Inst))
      return SI->getValueOperand();
    assert(isa<IntrinsicInst>(Inst) && "Instruction not supported");
    return TTI.getOrCreateResultFromMemIntrinsic(cast<IntrinsicInst>(Inst),
                                                 ExpectedType);
  }
};
}

bool EarlyCSE::processNode(DomTreeNode *Node) {
  BasicBlock *BB = Node->getBlock();

  // If this block has a single predecessor, then the predecessor is the parent
  // of the domtree node and all of the live out memory values are still current
  // in this block.  If this block has multiple predecessors, then they could
  // have invalidated the live-out memory values of our parent value.  For now,
  // just be conservative and invalidate memory if this block has multiple
  // predecessors.
  if (!BB->getSinglePredecessor())
    ++CurrentGeneration;

  // If this node has a single predecessor which ends in a conditional branch,
  // we can infer the value of the branch condition given that we took this
  // path.  We need the single predeccesor to ensure there's not another path
  // which reaches this block where the condition might hold a different
  // value.  Since we're adding this to the scoped hash table (like any other
  // def), it will have been popped if we encounter a future merge block.
  if (BasicBlock *Pred = BB->getSinglePredecessor())
    if (auto *BI = dyn_cast<BranchInst>(Pred->getTerminator()))
      if (BI->isConditional())
        if (auto *CondInst = dyn_cast<Instruction>(BI->getCondition()))
          if (SimpleValue::canHandle(CondInst)) {
            assert(BI->getSuccessor(0) == BB || BI->getSuccessor(1) == BB);
            auto *ConditionalConstant = (BI->getSuccessor(0) == BB) ?
              ConstantInt::getTrue(BB->getContext()) :
              ConstantInt::getFalse(BB->getContext());
            AvailableValues.insert(CondInst, ConditionalConstant);
            DEBUG(dbgs() << "EarlyCSE CVP: Add conditional value for '"
                  << CondInst->getName() << "' as " << *ConditionalConstant
                  << " in " << BB->getName() << "\n");
            // Replace all dominated uses with the known value
            replaceDominatedUsesWith(CondInst, ConditionalConstant, DT,
                                     BasicBlockEdge(Pred, BB));
          }

  /// LastStore - Keep track of the last non-volatile store that we saw... for
  /// as long as there in no instruction that reads memory.  If we see a store
  /// to the same location, we delete the dead store.  This zaps trivial dead
  /// stores which can occur in bitfield code among other things.
  Instruction *LastStore = nullptr;

  bool Changed = false;
  const DataLayout &DL = BB->getModule()->getDataLayout();

  // See if any instructions in the block can be eliminated.  If so, do it.  If
  // not, add them to AvailableValues.
  for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E;) {
    Instruction *Inst = &*I++;

    // Dead instructions should just be removed.
    if (isInstructionTriviallyDead(Inst, &TLI)) {
      DEBUG(dbgs() << "EarlyCSE DCE: " << *Inst << '\n');
      Inst->eraseFromParent();
      Changed = true;
      ++NumSimplify;
      continue;
    }

    // Skip assume intrinsics, they don't really have side effects (although
    // they're marked as such to ensure preservation of control dependencies),
    // and this pass will not disturb any of the assumption's control
    // dependencies.
    if (match(Inst, m_Intrinsic<Intrinsic::assume>())) {
      DEBUG(dbgs() << "EarlyCSE skipping assumption: " << *Inst << '\n');
      continue;
    }

    // If the instruction can be simplified (e.g. X+0 = X) then replace it with
    // its simpler value.
    if (Value *V = SimplifyInstruction(Inst, DL, &TLI, &DT, &AC)) {
      DEBUG(dbgs() << "EarlyCSE Simplify: " << *Inst << "  to: " << *V << '\n');
      Inst->replaceAllUsesWith(V);
      Inst->eraseFromParent();
      Changed = true;
      ++NumSimplify;
      continue;
    }

    // If this is a simple instruction that we can value number, process it.
    if (SimpleValue::canHandle(Inst)) {
      // See if the instruction has an available value.  If so, use it.
      if (Value *V = AvailableValues.lookup(Inst)) {
        DEBUG(dbgs() << "EarlyCSE CSE: " << *Inst << "  to: " << *V << '\n');
        Inst->replaceAllUsesWith(V);
        Inst->eraseFromParent();
        Changed = true;
        ++NumCSE;
        continue;
      }

      // Otherwise, just remember that this value is available.
      AvailableValues.insert(Inst, Inst);
      continue;
    }

    ParseMemoryInst MemInst(Inst, TTI);
    // If this is a non-volatile load, process it.
    if (MemInst.isValid() && MemInst.isLoad()) {
      // (conservatively) we can't peak past the ordering implied by this
      // operation, but we can add this load to our set of available values
      if (MemInst.isVolatile() || !MemInst.isUnordered()) {
        LastStore = nullptr;
        ++CurrentGeneration;
      }

      // If we have an available version of this load, and if it is the right
      // generation, replace this instruction.
      LoadValue InVal = AvailableLoads.lookup(MemInst.getPointerOperand());
      if (InVal.Data != nullptr && InVal.Generation == CurrentGeneration &&
          InVal.MatchingId == MemInst.getMatchingId() &&
          // We don't yet handle removing loads with ordering of any kind.
          !MemInst.isVolatile() && MemInst.isUnordered() &&
          // We can't replace an atomic load with one which isn't also atomic.
          InVal.IsAtomic >= MemInst.isAtomic()) {
        Value *Op = getOrCreateResult(InVal.Data, Inst->getType());
        if (Op != nullptr) {
          DEBUG(dbgs() << "EarlyCSE CSE LOAD: " << *Inst
                       << "  to: " << *InVal.Data << '\n');
          if (!Inst->use_empty())
            Inst->replaceAllUsesWith(Op);
          Inst->eraseFromParent();
          Changed = true;
          ++NumCSELoad;
          continue;
        }
      }

      // Otherwise, remember that we have this instruction.
      AvailableLoads.insert(
          MemInst.getPointerOperand(),
          LoadValue(Inst, CurrentGeneration, MemInst.getMatchingId(),
                    MemInst.isAtomic()));
      LastStore = nullptr;
      continue;
    }

    // If this instruction may read from memory, forget LastStore.
    // Load/store intrinsics will indicate both a read and a write to
    // memory.  The target may override this (e.g. so that a store intrinsic
    // does not read  from memory, and thus will be treated the same as a
    // regular store for commoning purposes).
    if (Inst->mayReadFromMemory() &&
        !(MemInst.isValid() && !MemInst.mayReadFromMemory()))
      LastStore = nullptr;

    // If this is a read-only call, process it.
    if (CallValue::canHandle(Inst)) {
      // If we have an available version of this call, and if it is the right
      // generation, replace this instruction.
      std::pair<Value *, unsigned> InVal = AvailableCalls.lookup(Inst);
      if (InVal.first != nullptr && InVal.second == CurrentGeneration) {
        DEBUG(dbgs() << "EarlyCSE CSE CALL: " << *Inst
                     << "  to: " << *InVal.first << '\n');
        if (!Inst->use_empty())
          Inst->replaceAllUsesWith(InVal.first);
        Inst->eraseFromParent();
        Changed = true;
        ++NumCSECall;
        continue;
      }

      // Otherwise, remember that we have this instruction.
      AvailableCalls.insert(
          Inst, std::pair<Value *, unsigned>(Inst, CurrentGeneration));
      continue;
    }

    // A release fence requires that all stores complete before it, but does
    // not prevent the reordering of following loads 'before' the fence.  As a
    // result, we don't need to consider it as writing to memory and don't need
    // to advance the generation.  We do need to prevent DSE across the fence,
    // but that's handled above.
    if (FenceInst *FI = dyn_cast<FenceInst>(Inst))
      if (FI->getOrdering() == Release) {
        assert(Inst->mayReadFromMemory() && "relied on to prevent DSE above");
        continue;
      }

    // write back DSE - If we write back the same value we just loaded from
    // the same location and haven't passed any intervening writes or ordering
    // operations, we can remove the write.  The primary benefit is in allowing
    // the available load table to remain valid and value forward past where
    // the store originally was.
    if (MemInst.isValid() && MemInst.isStore()) {
      LoadValue InVal = AvailableLoads.lookup(MemInst.getPointerOperand());
      if (InVal.Data &&
          InVal.Data == getOrCreateResult(Inst, InVal.Data->getType()) &&
          InVal.Generation == CurrentGeneration &&
          InVal.MatchingId == MemInst.getMatchingId() &&
          // We don't yet handle removing stores with ordering of any kind.
          !MemInst.isVolatile() && MemInst.isUnordered()) {
        assert((!LastStore ||
                ParseMemoryInst(LastStore, TTI).getPointerOperand() ==
                MemInst.getPointerOperand()) &&
               "can't have an intervening store!");
        DEBUG(dbgs() << "EarlyCSE DSE (writeback): " << *Inst << '\n');
        Inst->eraseFromParent();
        Changed = true;
        ++NumDSE;
        // We can avoid incrementing the generation count since we were able
        // to eliminate this store.
        continue;
      }
    }

    // Okay, this isn't something we can CSE at all.  Check to see if it is
    // something that could modify memory.  If so, our available memory values
    // cannot be used so bump the generation count.
    if (Inst->mayWriteToMemory()) {
      ++CurrentGeneration;

      if (MemInst.isValid() && MemInst.isStore()) {
        // We do a trivial form of DSE if there are two stores to the same
        // location with no intervening loads.  Delete the earlier store.
        // At the moment, we don't remove ordered stores, but do remove
        // unordered atomic stores.  There's no special requirement (for
        // unordered atomics) about removing atomic stores only in favor of
        // other atomic stores since we we're going to execute the non-atomic
        // one anyway and the atomic one might never have become visible.
        if (LastStore) {
          ParseMemoryInst LastStoreMemInst(LastStore, TTI);
          assert(LastStoreMemInst.isUnordered() &&
                 !LastStoreMemInst.isVolatile() &&
                 "Violated invariant");
          if (LastStoreMemInst.isMatchingMemLoc(MemInst)) {
            DEBUG(dbgs() << "EarlyCSE DEAD STORE: " << *LastStore
                         << "  due to: " << *Inst << '\n');
            LastStore->eraseFromParent();
            Changed = true;
            ++NumDSE;
            LastStore = nullptr;
          }
          // fallthrough - we can exploit information about this store
        }

        // Okay, we just invalidated anything we knew about loaded values.  Try
        // to salvage *something* by remembering that the stored value is a live
        // version of the pointer.  It is safe to forward from volatile stores
        // to non-volatile loads, so we don't have to check for volatility of
        // the store.
        AvailableLoads.insert(
            MemInst.getPointerOperand(),
            LoadValue(Inst, CurrentGeneration, MemInst.getMatchingId(),
                      MemInst.isAtomic()));

        // Remember that this was the last unordered store we saw for DSE. We
        // don't yet handle DSE on ordered or volatile stores since we don't
        // have a good way to model the ordering requirement for following
        // passes  once the store is removed.  We could insert a fence, but
        // since fences are slightly stronger than stores in their ordering,
        // it's not clear this is a profitable transform. Another option would
        // be to merge the ordering with that of the post dominating store.
        if (MemInst.isUnordered() && !MemInst.isVolatile())
          LastStore = Inst;
        else
          LastStore = nullptr;
      }
    }
  }

  return Changed;
}

bool EarlyCSE::run() {
  // Note, deque is being used here because there is significant performance
  // gains over vector when the container becomes very large due to the
  // specific access patterns. For more information see the mailing list
  // discussion on this:
  // http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20120116/135228.html
  std::deque<StackNode *> nodesToProcess;

  bool Changed = false;

  // Process the root node.
  nodesToProcess.push_back(new StackNode(
      AvailableValues, AvailableLoads, AvailableCalls, CurrentGeneration,
      DT.getRootNode(), DT.getRootNode()->begin(), DT.getRootNode()->end()));

  // Save the current generation.
  unsigned LiveOutGeneration = CurrentGeneration;

  // Process the stack.
  while (!nodesToProcess.empty()) {
    // Grab the first item off the stack. Set the current generation, remove
    // the node from the stack, and process it.
    StackNode *NodeToProcess = nodesToProcess.back();

    // Initialize class members.
    CurrentGeneration = NodeToProcess->currentGeneration();

    // Check if the node needs to be processed.
    if (!NodeToProcess->isProcessed()) {
      // Process the node.
      Changed |= processNode(NodeToProcess->node());
      NodeToProcess->childGeneration(CurrentGeneration);
      NodeToProcess->process();
    } else if (NodeToProcess->childIter() != NodeToProcess->end()) {
      // Push the next child onto the stack.
      DomTreeNode *child = NodeToProcess->nextChild();
      nodesToProcess.push_back(
          new StackNode(AvailableValues, AvailableLoads, AvailableCalls,
                        NodeToProcess->childGeneration(), child, child->begin(),
                        child->end()));
    } else {
      // It has been processed, and there are no more children to process,
      // so delete it and pop it off the stack.
      delete NodeToProcess;
      nodesToProcess.pop_back();
    }
  } // while (!nodes...)

  // Reset the current generation.
  CurrentGeneration = LiveOutGeneration;

  return Changed;
}

PreservedAnalyses EarlyCSEPass::run(Function &F,
                                    AnalysisManager<Function> *AM) {
  auto &TLI = AM->getResult<TargetLibraryAnalysis>(F);
  auto &TTI = AM->getResult<TargetIRAnalysis>(F);
  auto &DT = AM->getResult<DominatorTreeAnalysis>(F);
  auto &AC = AM->getResult<AssumptionAnalysis>(F);

  EarlyCSE CSE(TLI, TTI, DT, AC);

  if (!CSE.run())
    return PreservedAnalyses::all();

  // CSE preserves the dominator tree because it doesn't mutate the CFG.
  // FIXME: Bundle this with other CFG-preservation.
  PreservedAnalyses PA;
  PA.preserve<DominatorTreeAnalysis>();
  return PA;
}

namespace {
/// \brief A simple and fast domtree-based CSE pass.
///
/// This pass does a simple depth-first walk over the dominator tree,
/// eliminating trivially redundant instructions and using instsimplify to
/// canonicalize things as it goes. It is intended to be fast and catch obvious
/// cases so that instcombine and other passes are more effective. It is
/// expected that a later pass of GVN will catch the interesting/hard cases.
class EarlyCSELegacyPass : public FunctionPass {
public:
  static char ID;

  EarlyCSELegacyPass() : FunctionPass(ID) {
    initializeEarlyCSELegacyPassPass(*PassRegistry::getPassRegistry());
  }

  bool runOnFunction(Function &F) override {
    if (skipOptnoneFunction(F))
      return false;

    auto &TLI = getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
    auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
    auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
    auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);

    EarlyCSE CSE(TLI, TTI, DT, AC);

    return CSE.run();
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<AssumptionCacheTracker>();
    AU.addRequired<DominatorTreeWrapperPass>();
    AU.addRequired<TargetLibraryInfoWrapperPass>();
    AU.addRequired<TargetTransformInfoWrapperPass>();
    AU.addPreserved<GlobalsAAWrapperPass>();
    AU.setPreservesCFG();
  }
};
}

char EarlyCSELegacyPass::ID = 0;

FunctionPass *llvm::createEarlyCSEPass() { return new EarlyCSELegacyPass(); }

INITIALIZE_PASS_BEGIN(EarlyCSELegacyPass, "early-cse", "Early CSE", false,
                      false)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(EarlyCSELegacyPass, "early-cse", "Early CSE", false, false)