Transforms/Scalar/EarlyCSE.cpp

//===- 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/AssumptionCache.h"
#include "llvm/Analysis/GlobalsModRef.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 "llvm/Transforms/Utils/MemorySSA.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(NumCSECVP,   "Number of compare instructions CVP'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);

    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->isIdenticalToWhenDefined(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);

    // 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;
  MemorySSA *MSSA;
  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 {
    Instruction *DefInst;
    unsigned Generation;
    int MatchingId;
    bool IsAtomic;
    bool IsInvariant;
    LoadValue()
        : DefInst(nullptr), Generation(0), MatchingId(-1), IsAtomic(false),
          IsInvariant(false) {}
    LoadValue(Instruction *Inst, unsigned Generation, unsigned MatchingId,
              bool IsAtomic, bool IsInvariant)
        : DefInst(Inst), Generation(Generation), MatchingId(MatchingId),
          IsAtomic(IsAtomic), IsInvariant(IsInvariant) {}
  };
  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<Instruction *, 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, MemorySSA *MSSA)
      : TLI(TLI), TTI(TTI), DT(DT), AC(AC), MSSA(MSSA), 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 separately.
  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 isInvariantLoad() const {
      if (auto *LI = dyn_cast<LoadInst>(Inst))
        return LI->getMetadata(LLVMContext::MD_invariant_load) != nullptr;
      return false;
    }

    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 isSameMemGeneration(unsigned EarlierGeneration, unsigned LaterGeneration,
                           Instruction *EarlierInst, Instruction *LaterInst);

  void removeMSSA(Instruction *Inst) {
    if (!MSSA)
      return;
    // FIXME: Removing a store here can leave MemorySSA in an unoptimized state
    // by creating MemoryPhis that have identical arguments and by creating
    // MemoryUses whose defining access is not an actual clobber.
    if (MemoryAccess *MA = MSSA->getMemoryAccess(Inst))
      MSSA->removeMemoryAccess(MA);
  }
};
}

/// Determine if the memory referenced by LaterInst is from the same heap version
/// as EarlierInst.
/// This is currently called in two scenarios:
///
///   load p
///   ...
///   load p
///
/// and
///
///   x = load p
///   ...
///   store x, p
///
/// in both cases we want to verify that there are no possible writes to the
/// memory referenced by p between the earlier and later instruction.
bool EarlyCSE::isSameMemGeneration(unsigned EarlierGeneration,
                                   unsigned LaterGeneration,
                                   Instruction *EarlierInst,
                                   Instruction *LaterInst) {
  // Check the simple memory generation tracking first.
  if (EarlierGeneration == LaterGeneration)
    return true;

  if (!MSSA)
    return false;

  // Since we know LaterDef dominates LaterInst and EarlierInst dominates
  // LaterInst, if LaterDef dominates EarlierInst then it can't occur between
  // EarlierInst and LaterInst and neither can any other write that potentially
  // clobbers LaterInst.
  // FIXME: This is currently fairly expensive since it does an AA check even
  // for MemoryUses that were already optimized by MemorySSA construction.
  // Re-visit once MemorySSA optimized use tracking change has been committed.
  MemoryAccess *LaterDef =
      MSSA->getWalker()->getClobberingMemoryAccess(LaterInst);
  return MSSA->dominates(LaterDef, MSSA->getMemoryAccess(EarlierInst));
}

bool EarlyCSE::processNode(DomTreeNode *Node) {
  bool Changed = false;
  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 predecessor 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.
            if (unsigned Count =
                    replaceDominatedUsesWith(CondInst, ConditionalConstant, DT,
                                             BasicBlockEdge(Pred, BB))) {
              Changed = true;
              NumCSECVP = NumCSECVP + Count;
            }
          }

  /// 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;

  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');
      removeMSSA(Inst);
      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;
    }

    // Skip invariant.start intrinsics since they only read memory, and we can
    // forward values across it. Also, we dont need to consume the last store
    // since the semantics of invariant.start allow us to perform DSE of the
    // last store, if there was a store following invariant.start. Consider:
    //
    // store 30, i8* p
    // invariant.start(p)
    // store 40, i8* p
    // We can DSE the store to 30, since the store 40 to invariant location p
    // causes undefined behaviour.
    if (match(Inst, m_Intrinsic<Intrinsic::invariant_start>()))
      continue;

    if (match(Inst, m_Intrinsic<Intrinsic::experimental_guard>())) {
      if (auto *CondI =
              dyn_cast<Instruction>(cast<CallInst>(Inst)->getArgOperand(0))) {
        // The condition we're on guarding here is true for all dominated
        // locations.
        if (SimpleValue::canHandle(CondI))
          AvailableValues.insert(CondI, ConstantInt::getTrue(BB->getContext()));
      }

      // Guard intrinsics read all memory, but don't write any memory.
      // Accordingly, don't update the generation but consume the last store (to
      // avoid an incorrect DSE).
      LastStore = nullptr;
      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');
      bool Killed = false;
      if (!Inst->use_empty()) {
        Inst->replaceAllUsesWith(V);
        Changed = true;
      }
      if (isInstructionTriviallyDead(Inst, &TLI)) {
        removeMSSA(Inst);
        Inst->eraseFromParent();
        Changed = true;
        Killed = true;
      }
      if (Changed)
        ++NumSimplify;
      if (Killed)
        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');
        if (auto *I = dyn_cast<Instruction>(V))
          I->andIRFlags(Inst);
        Inst->replaceAllUsesWith(V);
        removeMSSA(Inst);
        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 or the load is known to be from an invariant location,
      // replace this instruction.
      //
      // If either the dominating load or the current load are invariant, then
      // we can assume the current load loads the same value as the dominating
      // load.
      LoadValue InVal = AvailableLoads.lookup(MemInst.getPointerOperand());
      if (InVal.DefInst != nullptr &&
          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() &&
          (InVal.IsInvariant || MemInst.isInvariantLoad() ||
           isSameMemGeneration(InVal.Generation, CurrentGeneration,
                               InVal.DefInst, Inst))) {
        Value *Op = getOrCreateResult(InVal.DefInst, Inst->getType());
        if (Op != nullptr) {
          DEBUG(dbgs() << "EarlyCSE CSE LOAD: " << *Inst
                       << "  to: " << *InVal.DefInst << '\n');
          if (!Inst->use_empty())
            Inst->replaceAllUsesWith(Op);
          removeMSSA(Inst);
          Inst->eraseFromParent();
          Changed = true;
          ++NumCSELoad;
          continue;
        }
      }

      // Otherwise, remember that we have this instruction.
      AvailableLoads.insert(
          MemInst.getPointerOperand(),
          LoadValue(Inst, CurrentGeneration, MemInst.getMatchingId(),
                    MemInst.isAtomic(), MemInst.isInvariantLoad()));
      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<Instruction *, unsigned> InVal = AvailableCalls.lookup(Inst);
      if (InVal.first != nullptr &&
          isSameMemGeneration(InVal.second, CurrentGeneration, InVal.first,
                              Inst)) {
        DEBUG(dbgs() << "EarlyCSE CSE CALL: " << *Inst
                     << "  to: " << *InVal.first << '\n');
        if (!Inst->use_empty())
          Inst->replaceAllUsesWith(InVal.first);
        removeMSSA(Inst);
        Inst->eraseFromParent();
        Changed = true;
        ++NumCSECall;
        continue;
      }

      // Otherwise, remember that we have this instruction.
      AvailableCalls.insert(
          Inst, std::pair<Instruction *, 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() == AtomicOrdering::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.DefInst &&
          InVal.DefInst == getOrCreateResult(Inst, InVal.DefInst->getType()) &&
          InVal.MatchingId == MemInst.getMatchingId() &&
          // We don't yet handle removing stores with ordering of any kind.
          !MemInst.isVolatile() && MemInst.isUnordered() &&
          isSameMemGeneration(InVal.Generation, CurrentGeneration,
                              InVal.DefInst, Inst)) {
        // It is okay to have a LastStore to a different pointer here if MemorySSA
        // tells us that the load and store are from the same memory generation.
        // In that case, LastStore should keep its present value since we're
        // removing the current store.
        assert((!LastStore ||
                ParseMemoryInst(LastStore, TTI).getPointerOperand() ==
                    MemInst.getPointerOperand() ||
                MSSA) &&
               "can't have an intervening store if not using MemorySSA!");
        DEBUG(dbgs() << "EarlyCSE DSE (writeback): " << *Inst << '\n');
        removeMSSA(Inst);
        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');
            removeMSSA(LastStore);
            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(), /*IsInvariant=*/false));

        // 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,
                                    FunctionAnalysisManager &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);
  auto *MSSA =
      UseMemorySSA ? &AM.getResult<MemorySSAAnalysis>(F).getMSSA() : nullptr;

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

  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>();
  PA.preserve<GlobalsAA>();
  if (UseMemorySSA)
    PA.preserve<MemorySSAAnalysis>();
  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.
template<bool UseMemorySSA>
class EarlyCSELegacyCommonPass : public FunctionPass {
public:
  static char ID;

  EarlyCSELegacyCommonPass() : FunctionPass(ID) {
    if (UseMemorySSA)
      initializeEarlyCSEMemSSALegacyPassPass(*PassRegistry::getPassRegistry());
    else
      initializeEarlyCSELegacyPassPass(*PassRegistry::getPassRegistry());
  }

  bool runOnFunction(Function &F) override {
    if (skipFunction(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);
    auto *MSSA =
        UseMemorySSA ? &getAnalysis<MemorySSAWrapperPass>().getMSSA() : nullptr;

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

    return CSE.run();
  }

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

using EarlyCSELegacyPass = EarlyCSELegacyCommonPass</*UseMemorySSA=*/false>;

template<>
char EarlyCSELegacyPass::ID = 0;

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)

using EarlyCSEMemSSALegacyPass =
    EarlyCSELegacyCommonPass</*UseMemorySSA=*/true>;

template<>
char EarlyCSEMemSSALegacyPass::ID = 0;

FunctionPass *llvm::createEarlyCSEPass(bool UseMemorySSA) {
  if (UseMemorySSA)
    return new EarlyCSEMemSSALegacyPass();
  else
    return new EarlyCSELegacyPass();
}

INITIALIZE_PASS_BEGIN(EarlyCSEMemSSALegacyPass, "early-cse-memssa",
                      "Early CSE w/ MemorySSA", false, false)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
INITIALIZE_PASS_END(EarlyCSEMemSSALegacyPass, "early-cse-memssa",
                    "Early CSE w/ MemorySSA", false, false)