C++ AllocaInst::eraseFromParent方法代码示例

void AMDGPUPromoteAlloca::handleAlloca(AllocaInst &I) {
  // Array allocations are probably not worth handling, since an allocation of
  // the array type is the canonical form.
  if (!I.isStaticAlloca() || I.isArrayAllocation())
    return;

  IRBuilder<> Builder(&I);

  // First try to replace the alloca with a vector
  Type *AllocaTy = I.getAllocatedType();

  DEBUG(dbgs() << "Trying to promote " << I << '\n');

  if (tryPromoteAllocaToVector(&I))
    return;

  DEBUG(dbgs() << " alloca is not a candidate for vectorization.\n");

  const Function &ContainingFunction = *I.getParent()->getParent();

  // FIXME: We should also try to get this value from the reqd_work_group_size
  // function attribute if it is available.
  unsigned WorkGroupSize = AMDGPU::getMaximumWorkGroupSize(ContainingFunction);

  int AllocaSize =
      WorkGroupSize * Mod->getDataLayout().getTypeAllocSize(AllocaTy);

  if (AllocaSize > LocalMemAvailable) {
    DEBUG(dbgs() << " Not enough local memory to promote alloca.\n");
    return;
  }

  std::vector<Value*> WorkList;

  if (!collectUsesWithPtrTypes(&I, WorkList)) {
    DEBUG(dbgs() << " Do not know how to convert all uses\n");
    return;
  }

  DEBUG(dbgs() << "Promoting alloca to local memory\n");
  LocalMemAvailable -= AllocaSize;

  Function *F = I.getParent()->getParent();

  Type *GVTy = ArrayType::get(I.getAllocatedType(), WorkGroupSize);
  GlobalVariable *GV = new GlobalVariable(
      *Mod, GVTy, false, GlobalValue::InternalLinkage,
      UndefValue::get(GVTy),
      Twine(F->getName()) + Twine('.') + I.getName(),
      nullptr,
      GlobalVariable::NotThreadLocal,
      AMDGPUAS::LOCAL_ADDRESS);
  GV->setUnnamedAddr(true);
  GV->setAlignment(I.getAlignment());

  Value *TCntY, *TCntZ;

  std::tie(TCntY, TCntZ) = getLocalSizeYZ(Builder);
  Value *TIdX = getWorkitemID(Builder, 0);
  Value *TIdY = getWorkitemID(Builder, 1);
  Value *TIdZ = getWorkitemID(Builder, 2);

  Value *Tmp0 = Builder.CreateMul(TCntY, TCntZ, "", true, true);
  Tmp0 = Builder.CreateMul(Tmp0, TIdX);
  Value *Tmp1 = Builder.CreateMul(TIdY, TCntZ, "", true, true);
  Value *TID = Builder.CreateAdd(Tmp0, Tmp1);
  TID = Builder.CreateAdd(TID, TIdZ);

  Value *Indices[] = {
    Constant::getNullValue(Type::getInt32Ty(Mod->getContext())),
    TID
  };

  Value *Offset = Builder.CreateInBoundsGEP(GVTy, GV, Indices);
  I.mutateType(Offset->getType());
  I.replaceAllUsesWith(Offset);
  I.eraseFromParent();

  for (Value *V : WorkList) {
    CallInst *Call = dyn_cast<CallInst>(V);
    if (!Call) {
      Type *EltTy = V->getType()->getPointerElementType();
      PointerType *NewTy = PointerType::get(EltTy, AMDGPUAS::LOCAL_ADDRESS);

      // The operand's value should be corrected on its own.
      if (isa<AddrSpaceCastInst>(V))
        continue;

      // FIXME: It doesn't really make sense to try to do this for all
      // instructions.
      V->mutateType(NewTy);
      continue;
    }

    IntrinsicInst *Intr = dyn_cast<IntrinsicInst>(Call);
    if (!Intr) {
      // FIXME: What is this for? It doesn't make sense to promote arbitrary
      // function calls. If the call is to a defined function that can also be
      // promoted, we should be able to do this once that function is also
      // rewritten.
//.........这里部分代码省略.........

void PromoteMem2Reg::run() {
  Function &F = *DF.getRoot()->getParent();

  if (AST) PointerAllocaValues.resize(Allocas.size());
  AllocaDbgDeclares.resize(Allocas.size());

  AllocaInfo Info;
  LargeBlockInfo LBI;

  for (unsigned AllocaNum = 0; AllocaNum != Allocas.size(); ++AllocaNum) {
    AllocaInst *AI = Allocas[AllocaNum];

    assert(isAllocaPromotable(AI) &&
           "Cannot promote non-promotable alloca!");
    assert(AI->getParent()->getParent() == &F &&
           "All allocas should be in the same function, which is same as DF!");

    if (AI->use_empty()) {
      // If there are no uses of the alloca, just delete it now.
      if (AST) AST->deleteValue(AI);
      AI->eraseFromParent();

      // Remove the alloca from the Allocas list, since it has been processed
      RemoveFromAllocasList(AllocaNum);
      ++NumDeadAlloca;
      continue;
    }
    
    // Calculate the set of read and write-locations for each alloca.  This is
    // analogous to finding the 'uses' and 'definitions' of each variable.
    Info.AnalyzeAlloca(AI);

    // If there is only a single store to this value, replace any loads of
    // it that are directly dominated by the definition with the value stored.
    if (Info.DefiningBlocks.size() == 1) {
      RewriteSingleStoreAlloca(AI, Info, LBI);

      // Finally, after the scan, check to see if the store is all that is left.
      if (Info.UsingBlocks.empty()) {
        // Record debuginfo for the store and remove the declaration's debuginfo.
        if (DbgDeclareInst *DDI = Info.DbgDeclare) {
          ConvertDebugDeclareToDebugValue(DDI, Info.OnlyStore);
          DDI->eraseFromParent();
        }
        // Remove the (now dead) store and alloca.
        Info.OnlyStore->eraseFromParent();
        LBI.deleteValue(Info.OnlyStore);

        if (AST) AST->deleteValue(AI);
        AI->eraseFromParent();
        LBI.deleteValue(AI);
        
        // The alloca has been processed, move on.
        RemoveFromAllocasList(AllocaNum);
        
        ++NumSingleStore;
        continue;
      }
    }
    
    // If the alloca is only read and written in one basic block, just perform a
    // linear sweep over the block to eliminate it.
    if (Info.OnlyUsedInOneBlock) {
      PromoteSingleBlockAlloca(AI, Info, LBI);
      
      // Finally, after the scan, check to see if the stores are all that is
      // left.
      if (Info.UsingBlocks.empty()) {
        
        // Remove the (now dead) stores and alloca.
        while (!AI->use_empty()) {
          StoreInst *SI = cast<StoreInst>(AI->use_back());
          // Record debuginfo for the store before removing it.
          if (DbgDeclareInst *DDI = Info.DbgDeclare)
            ConvertDebugDeclareToDebugValue(DDI, SI);
          SI->eraseFromParent();
          LBI.deleteValue(SI);
        }
        
        if (AST) AST->deleteValue(AI);
        AI->eraseFromParent();
        LBI.deleteValue(AI);
        
        // The alloca has been processed, move on.
        RemoveFromAllocasList(AllocaNum);
        
        // The alloca's debuginfo can be removed as well.
        if (DbgDeclareInst *DDI = Info.DbgDeclare)
          DDI->eraseFromParent();

        ++NumLocalPromoted;
        continue;
      }
    }
    
    // If we haven't computed a numbering for the BB's in the function, do so
    // now.
    if (BBNumbers.empty()) {
      unsigned ID = 0;
      for (Function::iterator I = F.begin(), E = F.end(); I != E; ++I)
//.........这里部分代码省略.........

//.........这里部分代码省略.........

  Type *GVTy = ArrayType::get(I.getAllocatedType(), WorkGroupSize);
  GlobalVariable *GV = new GlobalVariable(
      *Mod, GVTy, false, GlobalValue::InternalLinkage,
      UndefValue::get(GVTy),
      Twine(F->getName()) + Twine('.') + I.getName(),
      nullptr,
      GlobalVariable::NotThreadLocal,
      AS.LOCAL_ADDRESS);
  GV->setUnnamedAddr(GlobalValue::UnnamedAddr::Global);
  GV->setAlignment(I.getAlignment());

  Value *TCntY, *TCntZ;

  std::tie(TCntY, TCntZ) = getLocalSizeYZ(Builder);
  Value *TIdX = getWorkitemID(Builder, 0);
  Value *TIdY = getWorkitemID(Builder, 1);
  Value *TIdZ = getWorkitemID(Builder, 2);

  Value *Tmp0 = Builder.CreateMul(TCntY, TCntZ, "", true, true);
  Tmp0 = Builder.CreateMul(Tmp0, TIdX);
  Value *Tmp1 = Builder.CreateMul(TIdY, TCntZ, "", true, true);
  Value *TID = Builder.CreateAdd(Tmp0, Tmp1);
  TID = Builder.CreateAdd(TID, TIdZ);

  Value *Indices[] = {
    Constant::getNullValue(Type::getInt32Ty(Mod->getContext())),
    TID
  };

  Value *Offset = Builder.CreateInBoundsGEP(GVTy, GV, Indices);
  I.mutateType(Offset->getType());
  I.replaceAllUsesWith(Offset);
  I.eraseFromParent();

  for (Value *V : WorkList) {
    CallInst *Call = dyn_cast<CallInst>(V);
    if (!Call) {
      if (ICmpInst *CI = dyn_cast<ICmpInst>(V)) {
        Value *Src0 = CI->getOperand(0);
        Type *EltTy = Src0->getType()->getPointerElementType();
        PointerType *NewTy = PointerType::get(EltTy, AS.LOCAL_ADDRESS);

        if (isa<ConstantPointerNull>(CI->getOperand(0)))
          CI->setOperand(0, ConstantPointerNull::get(NewTy));

        if (isa<ConstantPointerNull>(CI->getOperand(1)))
          CI->setOperand(1, ConstantPointerNull::get(NewTy));

        continue;
      }

      // The operand's value should be corrected on its own and we don't want to
      // touch the users.
      if (isa<AddrSpaceCastInst>(V))
        continue;

      Type *EltTy = V->getType()->getPointerElementType();
      PointerType *NewTy = PointerType::get(EltTy, AS.LOCAL_ADDRESS);

      // FIXME: It doesn't really make sense to try to do this for all
      // instructions.
      V->mutateType(NewTy);

      // Adjust the types of any constant operands.
      if (SelectInst *SI = dyn_cast<SelectInst>(V)) {

//.........这里部分代码省略.........
  //
  // Because we don't have this information, we do this simple and useful hack.
  //
  SmallPtrSet<AllocaInst*, 16> UsedAllocas;
  
  // When processing our SCC, check to see if CS was inlined from some other
  // call site.  For example, if we're processing "A" in this code:
  //   A() { B() }
  //   B() { x = alloca ... C() }
  //   C() { y = alloca ... }
  // Assume that C was not inlined into B initially, and so we're processing A
  // and decide to inline B into A.  Doing this makes an alloca available for
  // reuse and makes a callsite (C) available for inlining.  When we process
  // the C call site we don't want to do any alloca merging between X and Y
  // because their scopes are not disjoint.  We could make this smarter by
  // keeping track of the inline history for each alloca in the
  // InlinedArrayAllocas but this isn't likely to be a significant win.
  if (InlineHistory != -1)  // Only do merging for top-level call sites in SCC.
    return true;
  
  // Loop over all the allocas we have so far and see if they can be merged with
  // a previously inlined alloca.  If not, remember that we had it.
  for (unsigned AllocaNo = 0, e = IFI.StaticAllocas.size();
       AllocaNo != e; ++AllocaNo) {
    AllocaInst *AI = IFI.StaticAllocas[AllocaNo];
    
    // Don't bother trying to merge array allocations (they will usually be
    // canonicalized to be an allocation *of* an array), or allocations whose
    // type is not itself an array (because we're afraid of pessimizing SRoA).
    ArrayType *ATy = dyn_cast<ArrayType>(AI->getAllocatedType());
    if (!ATy || AI->isArrayAllocation())
      continue;
    
    // Get the list of all available allocas for this array type.
    std::vector<AllocaInst*> &AllocasForType = InlinedArrayAllocas[ATy];
    
    // Loop over the allocas in AllocasForType to see if we can reuse one.  Note
    // that we have to be careful not to reuse the same "available" alloca for
    // multiple different allocas that we just inlined, we use the 'UsedAllocas'
    // set to keep track of which "available" allocas are being used by this
    // function.  Also, AllocasForType can be empty of course!
    bool MergedAwayAlloca = false;
    for (unsigned i = 0, e = AllocasForType.size(); i != e; ++i) {
      AllocaInst *AvailableAlloca = AllocasForType[i];

      unsigned Align1 = AI->getAlignment(),
               Align2 = AvailableAlloca->getAlignment();
      
      // The available alloca has to be in the right function, not in some other
      // function in this SCC.
      if (AvailableAlloca->getParent() != AI->getParent())
        continue;
      
      // If the inlined function already uses this alloca then we can't reuse
      // it.
      if (!UsedAllocas.insert(AvailableAlloca).second)
        continue;
      
      // Otherwise, we *can* reuse it, RAUW AI into AvailableAlloca and declare
      // success!
      DEBUG(dbgs() << "    ***MERGED ALLOCA: " << *AI << "\n\t\tINTO: "
                   << *AvailableAlloca << '\n');
      
      AI->replaceAllUsesWith(AvailableAlloca);

      if (Align1 != Align2) {
        if (!Align1 || !Align2) {
          const DataLayout &DL = Caller->getParent()->getDataLayout();
          unsigned TypeAlign = DL.getABITypeAlignment(AI->getAllocatedType());

          Align1 = Align1 ? Align1 : TypeAlign;
          Align2 = Align2 ? Align2 : TypeAlign;
        }

        if (Align1 > Align2)
          AvailableAlloca->setAlignment(AI->getAlignment());
      }

      AI->eraseFromParent();
      MergedAwayAlloca = true;
      ++NumMergedAllocas;
      IFI.StaticAllocas[AllocaNo] = nullptr;
      break;
    }

    // If we already nuked the alloca, we're done with it.
    if (MergedAwayAlloca)
      continue;
    
    // If we were unable to merge away the alloca either because there are no
    // allocas of the right type available or because we reused them all
    // already, remember that this alloca came from an inlined function and mark
    // it used so we don't reuse it for other allocas from this inline
    // operation.
    AllocasForType.push_back(AI);
    UsedAllocas.insert(AI);
  }
  
  return true;
}

void AMDGPUPromoteAlloca::visitAlloca(AllocaInst &I) {
  IRBuilder<> Builder(&I);

  // First try to replace the alloca with a vector
  Type *AllocaTy = I.getAllocatedType();

  DEBUG(dbgs() << "Trying to promote " << I << '\n');

  if (tryPromoteAllocaToVector(&I))
    return;

  DEBUG(dbgs() << " alloca is not a candidate for vectorization.\n");

  // FIXME: This is the maximum work group size.  We should try to get
  // value from the reqd_work_group_size function attribute if it is
  // available.
  unsigned WorkGroupSize = 256;
  int AllocaSize = WorkGroupSize *
      Mod->getDataLayout()->getTypeAllocSize(AllocaTy);

  if (AllocaSize > LocalMemAvailable) {
    DEBUG(dbgs() << " Not enough local memory to promote alloca.\n");
    return;
  }

  std::vector<Value*> WorkList;

  if (!collectUsesWithPtrTypes(&I, WorkList)) {
    DEBUG(dbgs() << " Do not know how to convert all uses\n");
    return;
  }

  DEBUG(dbgs() << "Promoting alloca to local memory\n");
  LocalMemAvailable -= AllocaSize;

  GlobalVariable *GV = new GlobalVariable(
      *Mod, ArrayType::get(I.getAllocatedType(), 256), false,
      GlobalValue::ExternalLinkage, 0, I.getName(), 0,
      GlobalVariable::NotThreadLocal, AMDGPUAS::LOCAL_ADDRESS);

  FunctionType *FTy = FunctionType::get(
      Type::getInt32Ty(Mod->getContext()), false);
  AttributeSet AttrSet;
  AttrSet.addAttribute(Mod->getContext(), 0, Attribute::ReadNone);

  Value *ReadLocalSizeY = Mod->getOrInsertFunction(
      "llvm.r600.read.local.size.y", FTy, AttrSet);
  Value *ReadLocalSizeZ = Mod->getOrInsertFunction(
      "llvm.r600.read.local.size.z", FTy, AttrSet);
  Value *ReadTIDIGX = Mod->getOrInsertFunction(
      "llvm.r600.read.tidig.x", FTy, AttrSet);
  Value *ReadTIDIGY = Mod->getOrInsertFunction(
      "llvm.r600.read.tidig.y", FTy, AttrSet);
  Value *ReadTIDIGZ = Mod->getOrInsertFunction(
      "llvm.r600.read.tidig.z", FTy, AttrSet);


  Value *TCntY = Builder.CreateCall(ReadLocalSizeY);
  Value *TCntZ = Builder.CreateCall(ReadLocalSizeZ);
  Value *TIdX  = Builder.CreateCall(ReadTIDIGX);
  Value *TIdY  = Builder.CreateCall(ReadTIDIGY);
  Value *TIdZ  = Builder.CreateCall(ReadTIDIGZ);

  Value *Tmp0 = Builder.CreateMul(TCntY, TCntZ);
  Tmp0 = Builder.CreateMul(Tmp0, TIdX);
  Value *Tmp1 = Builder.CreateMul(TIdY, TCntZ);
  Value *TID = Builder.CreateAdd(Tmp0, Tmp1);
  TID = Builder.CreateAdd(TID, TIdZ);

  std::vector<Value*> Indices;
  Indices.push_back(Constant::getNullValue(Type::getInt32Ty(Mod->getContext())));
  Indices.push_back(TID);

  Value *Offset = Builder.CreateGEP(GV, Indices);
  I.mutateType(Offset->getType());
  I.replaceAllUsesWith(Offset);
  I.eraseFromParent();

  for (std::vector<Value*>::iterator i = WorkList.begin(),
                                     e = WorkList.end(); i != e; ++i) {
    Value *V = *i;
    CallInst *Call = dyn_cast<CallInst>(V);
    if (!Call) {
      Type *EltTy = V->getType()->getPointerElementType();
      PointerType *NewTy = PointerType::get(EltTy, AMDGPUAS::LOCAL_ADDRESS);

      // The operand's value should be corrected on its own.
      if (isa<AddrSpaceCastInst>(V))
        continue;

      // FIXME: It doesn't really make sense to try to do this for all
      // instructions.
      V->mutateType(NewTy);
      continue;
    }

    IntrinsicInst *Intr = dyn_cast<IntrinsicInst>(Call);
    if (!Intr) {
      std::vector<Type*> ArgTypes;
      for (unsigned ArgIdx = 0, ArgEnd = Call->getNumArgOperands();
//.........这里部分代码省略.........

/// InlineCallIfPossible - If it is possible to inline the specified call site,
/// do so and update the CallGraph for this operation.
///
/// This function also does some basic book-keeping to update the IR.  The
/// InlinedArrayAllocas map keeps track of any allocas that are already
/// available from other  functions inlined into the caller.  If we are able to
/// inline this call site we attempt to reuse already available allocas or add
/// any new allocas to the set if not possible.
static bool InlineCallIfPossible(CallSite CS, InlineFunctionInfo &IFI,
                                 InlinedArrayAllocasTy &InlinedArrayAllocas) {
  Function *Callee = CS.getCalledFunction();
  Function *Caller = CS.getCaller();

  // Try to inline the function.  Get the list of static allocas that were
  // inlined.
  if (!InlineFunction(CS, IFI))
    return false;

  // If the inlined function had a higher stack protection level than the
  // calling function, then bump up the caller's stack protection level.
  if (Callee->hasFnAttr(Attribute::StackProtectReq))
    Caller->addFnAttr(Attribute::StackProtectReq);
  else if (Callee->hasFnAttr(Attribute::StackProtect) &&
           !Caller->hasFnAttr(Attribute::StackProtectReq))
    Caller->addFnAttr(Attribute::StackProtect);

  
  // Look at all of the allocas that we inlined through this call site.  If we
  // have already inlined other allocas through other calls into this function,
  // then we know that they have disjoint lifetimes and that we can merge them.
  //
  // There are many heuristics possible for merging these allocas, and the
  // different options have different tradeoffs.  One thing that we *really*
  // don't want to hurt is SRoA: once inlining happens, often allocas are no
  // longer address taken and so they can be promoted.
  //
  // Our "solution" for that is to only merge allocas whose outermost type is an
  // array type.  These are usually not promoted because someone is using a
  // variable index into them.  These are also often the most important ones to
  // merge.
  //
  // A better solution would be to have real memory lifetime markers in the IR
  // and not have the inliner do any merging of allocas at all.  This would
  // allow the backend to do proper stack slot coloring of all allocas that
  // *actually make it to the backend*, which is really what we want.
  //
  // Because we don't have this information, we do this simple and useful hack.
  //
  SmallPtrSet<AllocaInst*, 16> UsedAllocas;
  
  // Loop over all the allocas we have so far and see if they can be merged with
  // a previously inlined alloca.  If not, remember that we had it.
  for (unsigned AllocaNo = 0, e = IFI.StaticAllocas.size();
       AllocaNo != e; ++AllocaNo) {
    AllocaInst *AI = IFI.StaticAllocas[AllocaNo];
    
    // Don't bother trying to merge array allocations (they will usually be
    // canonicalized to be an allocation *of* an array), or allocations whose
    // type is not itself an array (because we're afraid of pessimizing SRoA).
    const ArrayType *ATy = dyn_cast<ArrayType>(AI->getAllocatedType());
    if (ATy == 0 || AI->isArrayAllocation())
      continue;
    
    // Get the list of all available allocas for this array type.
    std::vector<AllocaInst*> &AllocasForType = InlinedArrayAllocas[ATy];
    
    // Loop over the allocas in AllocasForType to see if we can reuse one.  Note
    // that we have to be careful not to reuse the same "available" alloca for
    // multiple different allocas that we just inlined, we use the 'UsedAllocas'
    // set to keep track of which "available" allocas are being used by this
    // function.  Also, AllocasForType can be empty of course!
    bool MergedAwayAlloca = false;
    for (unsigned i = 0, e = AllocasForType.size(); i != e; ++i) {
      AllocaInst *AvailableAlloca = AllocasForType[i];
      
      // The available alloca has to be in the right function, not in some other
      // function in this SCC.
      if (AvailableAlloca->getParent() != AI->getParent())
        continue;
      
      // If the inlined function already uses this alloca then we can't reuse
      // it.
      if (!UsedAllocas.insert(AvailableAlloca))
        continue;
      
      // Otherwise, we *can* reuse it, RAUW AI into AvailableAlloca and declare
      // success!
      DEBUG(dbgs() << "    ***MERGED ALLOCA: " << *AI);
      
      AI->replaceAllUsesWith(AvailableAlloca);
      AI->eraseFromParent();
      MergedAwayAlloca = true;
      ++NumMergedAllocas;
      break;
    }

    // If we already nuked the alloca, we're done with it.
    if (MergedAwayAlloca)
      continue;

//.........这里部分代码省略.........

//.........这里部分代码省略.........
    // We want the inliner to prune the code as it copies.  We would LOVE to
    // have no dead or constant instructions leftover after inlining occurs
    // (which can happen, e.g., because an argument was constant), but we'll be
    // happy with whatever the cloner can do.
    CloneAndPruneFunctionInto(Caller, CalledFunc, VMap, 
                              /*ModuleLevelChanges=*/false, Returns, ".i",
                              &InlinedFunctionInfo, IFI.TD, TheCall);

    // Remember the first block that is newly cloned over.
    FirstNewBlock = LastBlock; ++FirstNewBlock;

    // Update the callgraph if requested.
    if (IFI.CG)
      UpdateCallGraphAfterInlining(CS, FirstNewBlock, VMap, IFI);

    // Update inlined instructions' line number information.
    fixupLineNumbers(Caller, FirstNewBlock, TheCall);
  }

  // If there are any alloca instructions in the block that used to be the entry
  // block for the callee, move them to the entry block of the caller.  First
  // calculate which instruction they should be inserted before.  We insert the
  // instructions at the end of the current alloca list.
  {
    BasicBlock::iterator InsertPoint = Caller->begin()->begin();
    for (BasicBlock::iterator I = FirstNewBlock->begin(),
         E = FirstNewBlock->end(); I != E; ) {
      AllocaInst *AI = dyn_cast<AllocaInst>(I++);
      if (AI == 0) continue;
      
      // If the alloca is now dead, remove it.  This often occurs due to code
      // specialization.
      if (AI->use_empty()) {
        AI->eraseFromParent();
        continue;
      }

      if (!isa<Constant>(AI->getArraySize()))
        continue;
      
      // Keep track of the static allocas that we inline into the caller.
      IFI.StaticAllocas.push_back(AI);
      
      // Scan for the block of allocas that we can move over, and move them
      // all at once.
      while (isa<AllocaInst>(I) &&
             isa<Constant>(cast<AllocaInst>(I)->getArraySize())) {
        IFI.StaticAllocas.push_back(cast<AllocaInst>(I));
        ++I;
      }

      // Transfer all of the allocas over in a block.  Using splice means
      // that the instructions aren't removed from the symbol table, then
      // reinserted.
      Caller->getEntryBlock().getInstList().splice(InsertPoint,
                                                   FirstNewBlock->getInstList(),
                                                   AI, I);
    }
  }

  // Leave lifetime markers for the static alloca's, scoping them to the
  // function we just inlined.
  if (InsertLifetime && !IFI.StaticAllocas.empty()) {
    IRBuilder<> builder(FirstNewBlock->begin());
    for (unsigned ai = 0, ae = IFI.StaticAllocas.size(); ai != ae; ++ai) {
      AllocaInst *AI = IFI.StaticAllocas[ai];

void PromoteMem2Reg::run() {
  Function &F = *DT.getRoot()->getParent();

  AllocaDbgDeclares.resize(Allocas.size());

  AllocaInfo Info;
  LargeBlockInfo LBI;
  ForwardIDFCalculator IDF(DT);

  for (unsigned AllocaNum = 0; AllocaNum != Allocas.size(); ++AllocaNum) {
    AllocaInst *AI = Allocas[AllocaNum];

    assert(isAllocaPromotable(AI) && "Cannot promote non-promotable alloca!");
    assert(AI->getParent()->getParent() == &F &&
           "All allocas should be in the same function, which is same as DF!");

    removeLifetimeIntrinsicUsers(AI);

    if (AI->use_empty()) {
      // If there are no uses of the alloca, just delete it now.
      AI->eraseFromParent();

      // Remove the alloca from the Allocas list, since it has been processed
      RemoveFromAllocasList(AllocaNum);
      ++NumDeadAlloca;
      continue;
    }

    // Calculate the set of read and write-locations for each alloca.  This is
    // analogous to finding the 'uses' and 'definitions' of each variable.
    Info.AnalyzeAlloca(AI);

    // If there is only a single store to this value, replace any loads of
    // it that are directly dominated by the definition with the value stored.
    if (Info.DefiningBlocks.size() == 1) {
      if (rewriteSingleStoreAlloca(AI, Info, LBI, SQ.DL, DT, AC)) {
        // The alloca has been processed, move on.
        RemoveFromAllocasList(AllocaNum);
        ++NumSingleStore;
        continue;
      }
    }

    // If the alloca is only read and written in one basic block, just perform a
    // linear sweep over the block to eliminate it.
    if (Info.OnlyUsedInOneBlock &&
        promoteSingleBlockAlloca(AI, Info, LBI, SQ.DL, DT, AC)) {
      // The alloca has been processed, move on.
      RemoveFromAllocasList(AllocaNum);
      continue;
    }

    // If we haven't computed a numbering for the BB's in the function, do so
    // now.
    if (BBNumbers.empty()) {
      unsigned ID = 0;
      for (auto &BB : F)
        BBNumbers[&BB] = ID++;
    }

    // Remember the dbg.declare intrinsic describing this alloca, if any.
    if (!Info.DbgDeclares.empty())
      AllocaDbgDeclares[AllocaNum] = Info.DbgDeclares;

    // Keep the reverse mapping of the 'Allocas' array for the rename pass.
    AllocaLookup[Allocas[AllocaNum]] = AllocaNum;

    // At this point, we're committed to promoting the alloca using IDF's, and
    // the standard SSA construction algorithm.  Determine which blocks need PHI
    // nodes and see if we can optimize out some work by avoiding insertion of
    // dead phi nodes.

    // Unique the set of defining blocks for efficient lookup.
    SmallPtrSet<BasicBlock *, 32> DefBlocks;
    DefBlocks.insert(Info.DefiningBlocks.begin(), Info.DefiningBlocks.end());

    // Determine which blocks the value is live in.  These are blocks which lead
    // to uses.
    SmallPtrSet<BasicBlock *, 32> LiveInBlocks;
    ComputeLiveInBlocks(AI, Info, DefBlocks, LiveInBlocks);

    // At this point, we're committed to promoting the alloca using IDF's, and
    // the standard SSA construction algorithm.  Determine which blocks need phi
    // nodes and see if we can optimize out some work by avoiding insertion of
    // dead phi nodes.
    IDF.setLiveInBlocks(LiveInBlocks);
    IDF.setDefiningBlocks(DefBlocks);
    SmallVector<BasicBlock *, 32> PHIBlocks;
    IDF.calculate(PHIBlocks);
    if (PHIBlocks.size() > 1)
      llvm::sort(PHIBlocks, [this](BasicBlock *A, BasicBlock *B) {
        return BBNumbers.lookup(A) < BBNumbers.lookup(B);
      });

    unsigned CurrentVersion = 0;
    for (BasicBlock *BB : PHIBlocks)
      QueuePhiNode(BB, AllocaNum, CurrentVersion);
  }

  if (Allocas.empty())
//.........这里部分代码省略.........

//.........这里部分代码省略.........

  // When processing our SCC, check to see if CS was inlined from some other
  // call site.  For example, if we're processing "A" in this code:
  //   A() { B() }
  //   B() { x = alloca ... C() }
  //   C() { y = alloca ... }
  // Assume that C was not inlined into B initially, and so we're processing A
  // and decide to inline B into A.  Doing this makes an alloca available for
  // reuse and makes a callsite (C) available for inlining.  When we process
  // the C call site we don't want to do any alloca merging between X and Y
  // because their scopes are not disjoint.  We could make this smarter by
  // keeping track of the inline history for each alloca in the
  // InlinedArrayAllocas but this isn't likely to be a significant win.
  if (InlineHistory != -1) // Only do merging for top-level call sites in SCC.
    return;

  // Loop over all the allocas we have so far and see if they can be merged with
  // a previously inlined alloca.  If not, remember that we had it.
  for (unsigned AllocaNo = 0, e = IFI.StaticAllocas.size(); AllocaNo != e;
       ++AllocaNo) {
    AllocaInst *AI = IFI.StaticAllocas[AllocaNo];

    // Don't bother trying to merge array allocations (they will usually be
    // canonicalized to be an allocation *of* an array), or allocations whose
    // type is not itself an array (because we're afraid of pessimizing SRoA).
    ArrayType *ATy = dyn_cast<ArrayType>(AI->getAllocatedType());
    if (!ATy || AI->isArrayAllocation())
      continue;

    // Get the list of all available allocas for this array type.
    std::vector<AllocaInst *> &AllocasForType = InlinedArrayAllocas[ATy];

    // Loop over the allocas in AllocasForType to see if we can reuse one.  Note
    // that we have to be careful not to reuse the same "available" alloca for
    // multiple different allocas that we just inlined, we use the 'UsedAllocas'
    // set to keep track of which "available" allocas are being used by this
    // function.  Also, AllocasForType can be empty of course!
    bool MergedAwayAlloca = false;
    for (AllocaInst *AvailableAlloca : AllocasForType) {
      unsigned Align1 = AI->getAlignment(),
               Align2 = AvailableAlloca->getAlignment();

      // The available alloca has to be in the right function, not in some other
      // function in this SCC.
      if (AvailableAlloca->getParent() != AI->getParent())
        continue;

      // If the inlined function already uses this alloca then we can't reuse
      // it.
      if (!UsedAllocas.insert(AvailableAlloca).second)
        continue;

      // Otherwise, we *can* reuse it, RAUW AI into AvailableAlloca and declare
      // success!
      LLVM_DEBUG(dbgs() << "    ***MERGED ALLOCA: " << *AI
                        << "\n\t\tINTO: " << *AvailableAlloca << '\n');

      // Move affected dbg.declare calls immediately after the new alloca to
      // avoid the situation when a dbg.declare precedes its alloca.
      if (auto *L = LocalAsMetadata::getIfExists(AI))
        if (auto *MDV = MetadataAsValue::getIfExists(AI->getContext(), L))
          for (User *U : MDV->users())
            if (DbgDeclareInst *DDI = dyn_cast<DbgDeclareInst>(U))
              DDI->moveBefore(AvailableAlloca->getNextNode());

      AI->replaceAllUsesWith(AvailableAlloca);

      if (Align1 != Align2) {
        if (!Align1 || !Align2) {
          const DataLayout &DL = Caller->getParent()->getDataLayout();
          unsigned TypeAlign = DL.getABITypeAlignment(AI->getAllocatedType());

          Align1 = Align1 ? Align1 : TypeAlign;
          Align2 = Align2 ? Align2 : TypeAlign;
        }

        if (Align1 > Align2)
          AvailableAlloca->setAlignment(AI->getAlignment());
      }

      AI->eraseFromParent();
      MergedAwayAlloca = true;
      ++NumMergedAllocas;
      IFI.StaticAllocas[AllocaNo] = nullptr;
      break;
    }

    // If we already nuked the alloca, we're done with it.
    if (MergedAwayAlloca)
      continue;

    // If we were unable to merge away the alloca either because there are no
    // allocas of the right type available or because we reused them all
    // already, remember that this alloca came from an inlined function and mark
    // it used so we don't reuse it for other allocas from this inline
    // operation.
    AllocasForType.push_back(AI);
    UsedAllocas.insert(AI);
  }
}

bool AllocaMerging::runOnFunction(Function& F)
{
	cheerp::PointerAnalyzer & PA = getAnalysis<cheerp::PointerAnalyzer>();
	cheerp::Registerize & registerize = getAnalysis<cheerp::Registerize>();
	cheerp::TypeSupport types(*F.getParent());
	AllocaInfos allocaInfos;
	// Gather all the allocas
	for(BasicBlock& BB: F)
		analyzeBlock(registerize, BB, allocaInfos);
	if (allocaInfos.size() < 2)
		return false;
	bool Changed = false;
	BasicBlock& entryBlock=F.getEntryBlock();
	// Look if we can merge allocas of the same type
	for(auto targetCandidate=allocaInfos.begin();targetCandidate!=allocaInfos.end();++targetCandidate)
	{
		AllocaInst* targetAlloca = targetCandidate->first;
		Type* targetType = targetAlloca->getAllocatedType();
		// The range storing the sum of all ranges merged into target
		cheerp::Registerize::LiveRange targetRange(targetCandidate->second);
		// If the range is empty, we have an alloca that we can't analyze
		if (targetRange.empty())
			continue;
		std::vector<AllocaInfos::iterator> mergeSet;
		auto sourceCandidate=targetCandidate;
		++sourceCandidate;
		for(;sourceCandidate!=allocaInfos.end();++sourceCandidate)
		{
			AllocaInst* sourceAlloca = sourceCandidate->first;
			Type* sourceType = sourceAlloca->getAllocatedType();
			// Bail out for non compatible types
			if(!areTypesEquivalent(types, PA, targetType, sourceType))
				continue;
			const cheerp::Registerize::LiveRange& sourceRange = sourceCandidate->second;
			// Bail out if this source candidate is not analyzable
			if(sourceRange.empty())
				continue;
			// Bail out if the allocas interfere
			if(targetRange.doesInterfere(sourceRange))
				continue;
			// Add the range to the target range and the source alloca to the mergeSet
			mergeSet.push_back(sourceCandidate);
			PA.invalidate(sourceAlloca);
			targetRange.merge(sourceRange);
		}

		// If the merge set is empty try another target
		if(mergeSet.empty())
			continue;

		PA.invalidate(targetAlloca);

		if(!Changed)
			registerize.invalidateLiveRangeForAllocas(F);

		// Make sure that this alloca is in the entry block
		if(targetAlloca->getParent()!=&entryBlock)
			targetAlloca->moveBefore(entryBlock.begin());
		// We can merge the allocas
		for(const AllocaInfos::iterator& it: mergeSet)
		{
			AllocaInst* allocaToMerge = it->first;
			Instruction* targetVal=targetAlloca;
			if(targetVal->getType()!=allocaToMerge->getType())
			{
				targetVal=new BitCastInst(targetVal, allocaToMerge->getType());
				targetVal->insertAfter(targetAlloca);
			}
			allocaToMerge->replaceAllUsesWith(targetVal);
			allocaToMerge->eraseFromParent();
			if(targetVal != targetAlloca)
				PA.getPointerKind(targetVal);
			allocaInfos.erase(it);
			NumAllocaMerged++;
		}
		PA.getPointerKind(targetAlloca);
		Changed = true;
	}
	if(Changed)
		registerize.computeLiveRangeForAllocas(F);
	return Changed;
}

//
// Method: insertBadAllocationSizes()
//
// Description:
//  This method will look for allocations and change their size to be
//  incorrect.  It does the following:
//    o) Changes the number of array elements allocated by alloca and malloc.
//
// Return value:
//  true  - The module was modified.
//  false - The module was left unmodified.
//
bool
FaultInjector::insertBadAllocationSizes  (Function & F) {
  // Worklist of allocation sites to rewrite
  std::vector<AllocaInst * > WorkList;

  for (Function::iterator fI = F.begin(), fE = F.end(); fI != fE; ++fI) {
    BasicBlock & BB = *fI;
    for (BasicBlock::iterator I = BB.begin(), bE = BB.end(); I != bE; ++I) {
      if (AllocaInst * AI = dyn_cast<AllocaInst>(I)) {
        if (AI->isArrayAllocation()) {
          // Skip if we should not insert a fault.
          if (!doFault()) continue;

          WorkList.push_back(AI);
        }
      }
    }
  }

  while (WorkList.size()) {
    AllocaInst * AI = WorkList.back();
    WorkList.pop_back();

    //
    // Print information about where the fault is being inserted.
    //
    printSourceInfo ("Bad allocation size", AI);

    Instruction * NewAlloc = 0;
    NewAlloc =  new AllocaInst (AI->getAllocatedType(),
                                ConstantInt::get(Int32Type,0),
                                AI->getAlignment(),
                                AI->getName(),
                                AI);
    AI->replaceAllUsesWith (NewAlloc);
    AI->eraseFromParent();
    ++BadSizes;
  }

  //
  // Try harder to make bad allocation sizes.
  //
  WorkList.clear();
  for (Function::iterator fI = F.begin(), fE = F.end(); fI != fE; ++fI) {
    BasicBlock & BB = *fI;
    for (BasicBlock::iterator I = BB.begin(), bE = BB.end(); I != bE; ++I) {
      if (AllocaInst * AI = dyn_cast<AllocaInst>(I)) {
        //
        // Determine if this is a data type that we can make smaller.
        //
        if (((TD->getTypeAllocSize(AI->getAllocatedType())) > 4) && doFault()) {
          WorkList.push_back(AI);
        }
      }
    }
  }

  //
  // Replace these allocations with an allocation of an integer and cast the
  // result back into the appropriate type.
  //
  while (WorkList.size()) {
    AllocaInst * AI = WorkList.back();
    WorkList.pop_back();

    Instruction * NewAlloc = 0;
    NewAlloc =  new AllocaInst (Int32Type,
                                AI->getArraySize(),
                                AI->getAlignment(),
                                AI->getName(),
                                AI);
    NewAlloc = castTo (NewAlloc, AI->getType(), "", AI);
    AI->replaceAllUsesWith (NewAlloc);
    AI->eraseFromParent();
    ++BadSizes;
  }

  return (BadSizes > 0);
}

//.........这里部分代码省略.........
      VMap[I] = ActualArg;
    }

    // We want the inliner to prune the code as it copies.  We would LOVE to
    // have no dead or constant instructions leftover after inlining occurs
    // (which can happen, e.g., because an argument was constant), but we'll be
    // happy with whatever the cloner can do.
    CloneAndPruneFunctionInto(Caller, CalledFunc, VMap, Returns, ".i",
                              &InlinedFunctionInfo, IFI.TD, TheCall);

    // Remember the first block that is newly cloned over.
    FirstNewBlock = LastBlock; ++FirstNewBlock;

    // Update the callgraph if requested.
    if (IFI.CG)
      UpdateCallGraphAfterInlining(CS, FirstNewBlock, VMap, IFI);
  }

  // If there are any alloca instructions in the block that used to be the entry
  // block for the callee, move them to the entry block of the caller.  First
  // calculate which instruction they should be inserted before.  We insert the
  // instructions at the end of the current alloca list.
  //
  {
    BasicBlock::iterator InsertPoint = Caller->begin()->begin();
    for (BasicBlock::iterator I = FirstNewBlock->begin(),
         E = FirstNewBlock->end(); I != E; ) {
      AllocaInst *AI = dyn_cast<AllocaInst>(I++);
      if (AI == 0) continue;
      
      // If the alloca is now dead, remove it.  This often occurs due to code
      // specialization.
      if (AI->use_empty()) {
        AI->eraseFromParent();
        continue;
      }

      if (!isa<Constant>(AI->getArraySize()))
        continue;
      
      // Keep track of the static allocas that we inline into the caller if the
      // StaticAllocas pointer is non-null.
      IFI.StaticAllocas.push_back(AI);
      
      // Scan for the block of allocas that we can move over, and move them
      // all at once.
      while (isa<AllocaInst>(I) &&
             isa<Constant>(cast<AllocaInst>(I)->getArraySize())) {
        IFI.StaticAllocas.push_back(cast<AllocaInst>(I));
        ++I;
      }

      // Transfer all of the allocas over in a block.  Using splice means
      // that the instructions aren't removed from the symbol table, then
      // reinserted.
      Caller->getEntryBlock().getInstList().splice(InsertPoint,
                                                   FirstNewBlock->getInstList(),
                                                   AI, I);
    }
  }

  // If the inlined code contained dynamic alloca instructions, wrap the inlined
  // code with llvm.stacksave/llvm.stackrestore intrinsics.
  if (InlinedFunctionInfo.ContainsDynamicAllocas) {
    Module *M = Caller->getParent();
    // Get the two intrinsics we care about.