vendor/llvm/llvm-trunk-r305145

1 files changed, 159 insertions, 135 deletions

diff --git a/lib/CodeGen/CodeGenPrepare.cpp b/lib/CodeGen/CodeGenPrepare.cpp
index 568b278dd47c..c2037cb7f1ae 100644
--- a/lib/CodeGen/CodeGenPrepare.cpp
+++ b/lib/CodeGen/CodeGenPrepare.cpp
@@ -13,8 +13,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/CodeGen/Passes.h"
-#include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/SmallSet.h"
@@ -31,6 +29,7 @@
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/Analysis.h"
 #include "llvm/CodeGen/Passes.h"
+#include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
@@ -236,12 +235,12 @@ class TypePromotionTransaction;
     void eliminateMostlyEmptyBlock(BasicBlock *BB);
     bool isMergingEmptyBlockProfitable(BasicBlock *BB, BasicBlock *DestBB,
                                        bool isPreheader);
-    bool optimizeBlock(BasicBlock &BB, bool& ModifiedDT);
-    bool optimizeInst(Instruction *I, bool& ModifiedDT);
+    bool optimizeBlock(BasicBlock &BB, bool &ModifiedDT);
+    bool optimizeInst(Instruction *I, bool &ModifiedDT);
     bool optimizeMemoryInst(Instruction *I, Value *Addr,
                             Type *AccessTy, unsigned AS);
     bool optimizeInlineAsmInst(CallInst *CS);
-    bool optimizeCallInst(CallInst *CI, bool& ModifiedDT);
+    bool optimizeCallInst(CallInst *CI, bool &ModifiedDT);
     bool optimizeExt(Instruction *&I);
     bool optimizeExtUses(Instruction *I);
     bool optimizeLoadExt(LoadInst *I);
@@ -1662,25 +1661,29 @@ class MemCmpExpansion {
   BasicBlock *EndBlock;
   PHINode *PhiRes;
   bool IsUsedForZeroCmp;
+  const DataLayout &DL;
+
   int calculateNumBlocks(unsigned Size);
   void createLoadCmpBlocks();
   void createResultBlock();
   void setupResultBlockPHINodes();
   void setupEndBlockPHINodes();
-  void emitLoadCompareBlock(unsigned Index, int LoadSize, int GEPIndex,
-                            bool IsLittleEndian);
+  void emitLoadCompareBlock(unsigned Index, int LoadSize, int GEPIndex);
+  Value *getCompareLoadPairs(unsigned Index, unsigned Size,
+                             unsigned &NumBytesProcessed, IRBuilder<> &Builder);
   void emitLoadCompareBlockMultipleLoads(unsigned Index, unsigned Size,
                                          unsigned &NumBytesProcessed);
   void emitLoadCompareByteBlock(unsigned Index, int GEPIndex);
-  void emitMemCmpResultBlock(bool IsLittleEndian);
-  Value *getMemCmpExpansionZeroCase(unsigned Size, bool IsLittleEndian);
+  void emitMemCmpResultBlock();
+  Value *getMemCmpExpansionZeroCase(unsigned Size);
+  Value *getMemCmpEqZeroOneBlock(unsigned Size);
   unsigned getLoadSize(unsigned Size);
   unsigned getNumLoads(unsigned Size);
 
 public:
-  MemCmpExpansion(CallInst *CI, unsigned MaxLoadSize,
-                  unsigned NumLoadsPerBlock);
-  Value *getMemCmpExpansion(bool IsLittleEndian);
+  MemCmpExpansion(CallInst *CI, uint64_t Size, unsigned MaxLoadSize,
+                  unsigned NumLoadsPerBlock, const DataLayout &DL);
+  Value *getMemCmpExpansion(uint64_t Size);
 };
 
 MemCmpExpansion::ResultBlock::ResultBlock()
@@ -1694,39 +1697,41 @@ MemCmpExpansion::ResultBlock::ResultBlock()
 // return from.
 // 3. ResultBlock, block to branch to for early exit when a
 // LoadCmpBlock finds a difference.
-MemCmpExpansion::MemCmpExpansion(CallInst *CI, unsigned MaxLoadSize,
-                                 unsigned NumLoadsPerBlock)
-    : CI(CI), MaxLoadSize(MaxLoadSize), NumLoadsPerBlock(NumLoadsPerBlock) {
-
-  IRBuilder<> Builder(CI->getContext());
-
-  BasicBlock *StartBlock = CI->getParent();
-  EndBlock = StartBlock->splitBasicBlock(CI, "endblock");
-  setupEndBlockPHINodes();
+MemCmpExpansion::MemCmpExpansion(CallInst *CI, uint64_t Size,
+                                 unsigned MaxLoadSize, unsigned LoadsPerBlock,
+                                 const DataLayout &TheDataLayout)
+    : CI(CI), MaxLoadSize(MaxLoadSize), NumLoadsPerBlock(LoadsPerBlock),
+      DL(TheDataLayout) {
+
+  // A memcmp with zero-comparison with only one block of load and compare does
+  // not need to set up any extra blocks. This case could be handled in the DAG,
+  // but since we have all of the machinery to flexibly expand any memcpy here,
+  // we choose to handle this case too to avoid fragmented lowering.
   IsUsedForZeroCmp = isOnlyUsedInZeroEqualityComparison(CI);
-
-  ConstantInt *SizeCast = dyn_cast<ConstantInt>(CI->getArgOperand(2));
-  uint64_t Size = SizeCast->getZExtValue();
-
-  // Calculate how many load compare blocks are required for an expansion of
-  // given Size.
   NumBlocks = calculateNumBlocks(Size);
-  createResultBlock();
+  if (!IsUsedForZeroCmp || NumBlocks != 1) {
+    BasicBlock *StartBlock = CI->getParent();
+    EndBlock = StartBlock->splitBasicBlock(CI, "endblock");
+    setupEndBlockPHINodes();
+    createResultBlock();
 
-  // If return value of memcmp is not used in a zero equality, we need to
-  // calculate which source was larger. The calculation requires the
-  // two loaded source values of each load compare block.
-  // These will be saved in the phi nodes created by setupResultBlockPHINodes.
-  if (!IsUsedForZeroCmp)
-    setupResultBlockPHINodes();
+    // If return value of memcmp is not used in a zero equality, we need to
+    // calculate which source was larger. The calculation requires the
+    // two loaded source values of each load compare block.
+    // These will be saved in the phi nodes created by setupResultBlockPHINodes.
+    if (!IsUsedForZeroCmp)
+      setupResultBlockPHINodes();
 
-  // Create the number of required load compare basic blocks.
-  createLoadCmpBlocks();
+    // Create the number of required load compare basic blocks.
+    createLoadCmpBlocks();
 
-  // Update the terminator added by splitBasicBlock to branch to the first
-  // LoadCmpBlock.
+    // Update the terminator added by splitBasicBlock to branch to the first
+    // LoadCmpBlock.
+    StartBlock->getTerminator()->setSuccessor(0, LoadCmpBlocks[0]);
+  }
+
+  IRBuilder<> Builder(CI->getContext());
   Builder.SetCurrentDebugLocation(CI->getDebugLoc());
-  StartBlock->getTerminator()->setSuccessor(0, LoadCmpBlocks[0]);
 }
 
 void MemCmpExpansion::createLoadCmpBlocks() {
@@ -1743,7 +1748,7 @@ void MemCmpExpansion::createResultBlock() {
 }
 
 // This function creates the IR instructions for loading and comparing 1 byte.
-// It loads 1 byte from each source of the memcmp paramters with the given
+// It loads 1 byte from each source of the memcmp parameters with the given
 // GEPIndex. It then subtracts the two loaded values and adds this result to the
 // final phi node for selecting the memcmp result.
 void MemCmpExpansion::emitLoadCompareByteBlock(unsigned Index, int GEPIndex) {
@@ -1754,13 +1759,13 @@ void MemCmpExpansion::emitLoadCompareByteBlock(unsigned Index, int GEPIndex) {
 
   Builder.SetInsertPoint(LoadCmpBlocks[Index]);
   Type *LoadSizeType = Type::getInt8Ty(CI->getContext());
-  // Cast source to LoadSizeType*
+  // Cast source to LoadSizeType*.
   if (Source1->getType() != LoadSizeType)
     Source1 = Builder.CreateBitCast(Source1, LoadSizeType->getPointerTo());
   if (Source2->getType() != LoadSizeType)
     Source2 = Builder.CreateBitCast(Source2, LoadSizeType->getPointerTo());
 
-  // Get the base address using the GEPIndex
+  // Get the base address using the GEPIndex.
   if (GEPIndex != 0) {
     Source1 = Builder.CreateGEP(LoadSizeType, Source1,
                                 ConstantInt::get(LoadSizeType, GEPIndex));
@@ -1778,16 +1783,15 @@ void MemCmpExpansion::emitLoadCompareByteBlock(unsigned Index, int GEPIndex) {
   PhiRes->addIncoming(Diff, LoadCmpBlocks[Index]);
 
   if (Index < (LoadCmpBlocks.size() - 1)) {
-    // Early exit branch if difference found to EndBlock, otherwise continue to
-    // next LoadCmpBlock
-
+    // Early exit branch if difference found to EndBlock. Otherwise, continue to
+    // next LoadCmpBlock,
     Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_NE, Diff,
                                     ConstantInt::get(Diff->getType(), 0));
     BranchInst *CmpBr =
         BranchInst::Create(EndBlock, LoadCmpBlocks[Index + 1], Cmp);
     Builder.Insert(CmpBr);
   } else {
-    // The last block has an unconditional branch to EndBlock
+    // The last block has an unconditional branch to EndBlock.
     BranchInst *CmpBr = BranchInst::Create(EndBlock);
     Builder.Insert(CmpBr);
   }
@@ -1801,11 +1805,12 @@ unsigned MemCmpExpansion::getLoadSize(unsigned Size) {
   return MinAlign(PowerOf2Floor(Size), MaxLoadSize);
 }
 
-void MemCmpExpansion::emitLoadCompareBlockMultipleLoads(
-    unsigned Index, unsigned Size, unsigned &NumBytesProcessed) {
-
-  IRBuilder<> Builder(CI->getContext());
-
+/// Generate an equality comparison for one or more pairs of loaded values.
+/// This is used in the case where the memcmp() call is compared equal or not
+/// equal to zero.
+Value *MemCmpExpansion::getCompareLoadPairs(unsigned Index, unsigned Size,
+                                            unsigned &NumBytesProcessed,
+                                            IRBuilder<> &Builder) {
   std::vector<Value *> XorList, OrList;
   Value *Diff;
 
@@ -1813,8 +1818,13 @@ void MemCmpExpansion::emitLoadCompareBlockMultipleLoads(
   unsigned NumLoadsRemaining = getNumLoads(RemainingBytes);
   unsigned NumLoads = std::min(NumLoadsRemaining, NumLoadsPerBlock);
 
-  Builder.SetInsertPoint(LoadCmpBlocks[Index]);
+  // For a single-block expansion, start inserting before the memcmp call.
+  if (LoadCmpBlocks.empty())
+    Builder.SetInsertPoint(CI);
+  else
+    Builder.SetInsertPoint(LoadCmpBlocks[Index]);
 
+  Value *Cmp = nullptr;
   for (unsigned i = 0; i < NumLoads; ++i) {
     unsigned LoadSize = getLoadSize(RemainingBytes);
     unsigned GEPIndex = NumBytesProcessed / LoadSize;
@@ -1827,13 +1837,13 @@ void MemCmpExpansion::emitLoadCompareBlockMultipleLoads(
     Value *Source1 = CI->getArgOperand(0);
     Value *Source2 = CI->getArgOperand(1);
 
-    // Cast source to LoadSizeType*
+    // Cast source to LoadSizeType*.
     if (Source1->getType() != LoadSizeType)
       Source1 = Builder.CreateBitCast(Source1, LoadSizeType->getPointerTo());
     if (Source2->getType() != LoadSizeType)
       Source2 = Builder.CreateBitCast(Source2, LoadSizeType->getPointerTo());
 
-    // Get the base address using the GEPIndex
+    // Get the base address using the GEPIndex.
     if (GEPIndex != 0) {
       Source1 = Builder.CreateGEP(LoadSizeType, Source1,
                                   ConstantInt::get(LoadSizeType, GEPIndex));
@@ -1841,16 +1851,23 @@ void MemCmpExpansion::emitLoadCompareBlockMultipleLoads(
                                   ConstantInt::get(LoadSizeType, GEPIndex));
     }
 
-    // Load LoadSizeType from the base address
+    // Load LoadSizeType from the base address.
     Value *LoadSrc1 = Builder.CreateLoad(LoadSizeType, Source1);
     Value *LoadSrc2 = Builder.CreateLoad(LoadSizeType, Source2);
-    if (LoadSizeType != MaxLoadType) {
-      LoadSrc1 = Builder.CreateZExtOrTrunc(LoadSrc1, MaxLoadType);
-      LoadSrc2 = Builder.CreateZExtOrTrunc(LoadSrc2, MaxLoadType);
+    if (NumLoads != 1) {
+      if (LoadSizeType != MaxLoadType) {
+        LoadSrc1 = Builder.CreateZExtOrTrunc(LoadSrc1, MaxLoadType);
+        LoadSrc2 = Builder.CreateZExtOrTrunc(LoadSrc2, MaxLoadType);
+      }
+      // If we have multiple loads per block, we need to generate a composite
+      // comparison using xor+or.
+      Diff = Builder.CreateXor(LoadSrc1, LoadSrc2);
+      Diff = Builder.CreateZExtOrTrunc(Diff, MaxLoadType);
+      XorList.push_back(Diff);
+    } else {
+      // If there's only one load per block, we just compare the loaded values.
+      Cmp = Builder.CreateICmpNE(LoadSrc1, LoadSrc2);
     }
-    Diff = Builder.CreateXor(LoadSrc1, LoadSrc2);
-    Diff = Builder.CreateZExtOrTrunc(Diff, MaxLoadType);
-    XorList.push_back(Diff);
   }
 
   auto pairWiseOr = [&](std::vector<Value *> &InList) -> std::vector<Value *> {
@@ -1864,27 +1881,36 @@ void MemCmpExpansion::emitLoadCompareBlockMultipleLoads(
     return OutList;
   };
 
-  // Pair wise OR the XOR results
-  OrList = pairWiseOr(XorList);
+  if (!Cmp) {
+    // Pairwise OR the XOR results.
+    OrList = pairWiseOr(XorList);
 
-  // Pair wise OR the OR results until one result left
-  while (OrList.size() != 1) {
-    OrList = pairWiseOr(OrList);
+    // Pairwise OR the OR results until one result left.
+    while (OrList.size() != 1) {
+      OrList = pairWiseOr(OrList);
+    }
+    Cmp = Builder.CreateICmpNE(OrList[0], ConstantInt::get(Diff->getType(), 0));
   }
 
-  Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_NE, OrList[0],
-                                  ConstantInt::get(Diff->getType(), 0));
+  return Cmp;
+}
+
+void MemCmpExpansion::emitLoadCompareBlockMultipleLoads(
+    unsigned Index, unsigned Size, unsigned &NumBytesProcessed) {
+  IRBuilder<> Builder(CI->getContext());
+  Value *Cmp = getCompareLoadPairs(Index, Size, NumBytesProcessed, Builder);
+
   BasicBlock *NextBB = (Index == (LoadCmpBlocks.size() - 1))
                            ? EndBlock
                            : LoadCmpBlocks[Index + 1];
-  // Early exit branch if difference found to ResultBlock, otherwise continue to
-  // next LoadCmpBlock or EndBlock.
+  // Early exit branch if difference found to ResultBlock. Otherwise,
+  // continue to next LoadCmpBlock or EndBlock.
   BranchInst *CmpBr = BranchInst::Create(ResBlock.BB, NextBB, Cmp);
   Builder.Insert(CmpBr);
 
   // Add a phi edge for the last LoadCmpBlock to Endblock with a value of 0
   // since early exit to ResultBlock was not taken (no difference was found in
-  // any of the bytes)
+  // any of the bytes).
   if (Index == LoadCmpBlocks.size() - 1) {
     Value *Zero = ConstantInt::get(Type::getInt32Ty(CI->getContext()), 0);
     PhiRes->addIncoming(Zero, LoadCmpBlocks[Index]);
@@ -1901,7 +1927,7 @@ void MemCmpExpansion::emitLoadCompareBlockMultipleLoads(
 // a special case through emitLoadCompareByteBlock. The special handling can
 // simply subtract the loaded values and add it to the result phi node.
 void MemCmpExpansion::emitLoadCompareBlock(unsigned Index, int LoadSize,
-                                           int GEPIndex, bool IsLittleEndian) {
+                                           int GEPIndex) {
   if (LoadSize == 1) {
     MemCmpExpansion::emitLoadCompareByteBlock(Index, GEPIndex);
     return;
@@ -1916,13 +1942,13 @@ void MemCmpExpansion::emitLoadCompareBlock(unsigned Index, int LoadSize,
   Value *Source2 = CI->getArgOperand(1);
 
   Builder.SetInsertPoint(LoadCmpBlocks[Index]);
-  // Cast source to LoadSizeType*
+  // Cast source to LoadSizeType*.
   if (Source1->getType() != LoadSizeType)
     Source1 = Builder.CreateBitCast(Source1, LoadSizeType->getPointerTo());
   if (Source2->getType() != LoadSizeType)
     Source2 = Builder.CreateBitCast(Source2, LoadSizeType->getPointerTo());
 
-  // Get the base address using the GEPIndex
+  // Get the base address using the GEPIndex.
   if (GEPIndex != 0) {
     Source1 = Builder.CreateGEP(LoadSizeType, Source1,
                                 ConstantInt::get(LoadSizeType, GEPIndex));
@@ -1930,11 +1956,11 @@ void MemCmpExpansion::emitLoadCompareBlock(unsigned Index, int LoadSize,
                                 ConstantInt::get(LoadSizeType, GEPIndex));
   }
 
-  // Load LoadSizeType from the base address
+  // Load LoadSizeType from the base address.
   Value *LoadSrc1 = Builder.CreateLoad(LoadSizeType, Source1);
   Value *LoadSrc2 = Builder.CreateLoad(LoadSizeType, Source2);
 
-  if (IsLittleEndian) {
+  if (DL.isLittleEndian()) {
     Function *F = LoadCmpBlocks[Index]->getParent();
 
     Function *Bswap = Intrinsic::getDeclaration(F->getParent(),
@@ -1962,14 +1988,14 @@ void MemCmpExpansion::emitLoadCompareBlock(unsigned Index, int LoadSize,
   BasicBlock *NextBB = (Index == (LoadCmpBlocks.size() - 1))
                            ? EndBlock
                            : LoadCmpBlocks[Index + 1];
-  // Early exit branch if difference found to ResultBlock, otherwise continue to
-  // next LoadCmpBlock or EndBlock.
+  // Early exit branch if difference found to ResultBlock. Otherwise, continue
+  // to next LoadCmpBlock or EndBlock.
   BranchInst *CmpBr = BranchInst::Create(ResBlock.BB, NextBB, Cmp);
   Builder.Insert(CmpBr);
 
   // Add a phi edge for the last LoadCmpBlock to Endblock with a value of 0
   // since early exit to ResultBlock was not taken (no difference was found in
-  // any of the bytes)
+  // any of the bytes).
   if (Index == LoadCmpBlocks.size() - 1) {
     Value *Zero = ConstantInt::get(Type::getInt32Ty(CI->getContext()), 0);
     PhiRes->addIncoming(Zero, LoadCmpBlocks[Index]);
@@ -1979,7 +2005,7 @@ void MemCmpExpansion::emitLoadCompareBlock(unsigned Index, int LoadSize,
 // This function populates the ResultBlock with a sequence to calculate the
 // memcmp result. It compares the two loaded source values and returns -1 if
 // src1 < src2 and 1 if src1 > src2.
-void MemCmpExpansion::emitMemCmpResultBlock(bool IsLittleEndian) {
+void MemCmpExpansion::emitMemCmpResultBlock() {
   IRBuilder<> Builder(CI->getContext());
 
   // Special case: if memcmp result is used in a zero equality, result does not
@@ -2010,17 +2036,17 @@ void MemCmpExpansion::emitMemCmpResultBlock(bool IsLittleEndian) {
 
 int MemCmpExpansion::calculateNumBlocks(unsigned Size) {
   int NumBlocks = 0;
-  bool haveOneByteLoad = false;
+  bool HaveOneByteLoad = false;
   unsigned RemainingSize = Size;
   unsigned LoadSize = MaxLoadSize;
   while (RemainingSize) {
     if (LoadSize == 1)
-      haveOneByteLoad = true;
+      HaveOneByteLoad = true;
     NumBlocks += RemainingSize / LoadSize;
     RemainingSize = RemainingSize % LoadSize;
     LoadSize = LoadSize / 2;
   }
-  NumBlocksNonOneByte = haveOneByteLoad ? (NumBlocks - 1) : NumBlocks;
+  NumBlocksNonOneByte = HaveOneByteLoad ? (NumBlocks - 1) : NumBlocks;
 
   if (IsUsedForZeroCmp)
     NumBlocks = NumBlocks / NumLoadsPerBlock +
@@ -2046,63 +2072,66 @@ void MemCmpExpansion::setupEndBlockPHINodes() {
   PhiRes = Builder.CreatePHI(Type::getInt32Ty(CI->getContext()), 2, "phi.res");
 }
 
-Value *MemCmpExpansion::getMemCmpExpansionZeroCase(unsigned Size,
-                                                   bool IsLittleEndian) {
+Value *MemCmpExpansion::getMemCmpExpansionZeroCase(unsigned Size) {
   unsigned NumBytesProcessed = 0;
-  // This loop populates each of the LoadCmpBlocks with IR sequence to handle
-  // multiple loads per block
-  for (unsigned i = 0; i < NumBlocks; ++i) {
+  // This loop populates each of the LoadCmpBlocks with the IR sequence to
+  // handle multiple loads per block.
+  for (unsigned i = 0; i < NumBlocks; ++i)
     emitLoadCompareBlockMultipleLoads(i, Size, NumBytesProcessed);
-  }
 
-  emitMemCmpResultBlock(IsLittleEndian);
+  emitMemCmpResultBlock();
   return PhiRes;
 }
 
+/// A memcmp expansion that compares equality with 0 and only has one block of
+/// load and compare can bypass the compare, branch, and phi IR that is required
+/// in the general case.
+Value *MemCmpExpansion::getMemCmpEqZeroOneBlock(unsigned Size) {
+  unsigned NumBytesProcessed = 0;
+  IRBuilder<> Builder(CI->getContext());
+  Value *Cmp = getCompareLoadPairs(0, Size, NumBytesProcessed, Builder);
+  return Builder.CreateZExt(Cmp, Type::getInt32Ty(CI->getContext()));
+}
+
 // This function expands the memcmp call into an inline expansion and returns
 // the memcmp result.
-Value *MemCmpExpansion::getMemCmpExpansion(bool IsLittleEndian) {
-
-  ConstantInt *SizeCast = dyn_cast<ConstantInt>(CI->getArgOperand(2));
-  uint64_t Size = SizeCast->getZExtValue();
+Value *MemCmpExpansion::getMemCmpExpansion(uint64_t Size) {
+  if (IsUsedForZeroCmp)
+    return NumBlocks == 1 ? getMemCmpEqZeroOneBlock(Size) :
+                            getMemCmpExpansionZeroCase(Size);
 
+  // This loop calls emitLoadCompareBlock for comparing Size bytes of the two
+  // memcmp sources. It starts with loading using the maximum load size set by
+  // the target. It processes any remaining bytes using a load size which is the
+  // next smallest power of 2.
   int LoadSize = MaxLoadSize;
   int NumBytesToBeProcessed = Size;
-
-  if (IsUsedForZeroCmp) {
-    return getMemCmpExpansionZeroCase(Size, IsLittleEndian);
-  }
-
   unsigned Index = 0;
-  // This loop calls emitLoadCompareBlock for comparing SizeVal bytes of the two
-  // memcmp source. It starts with loading using the maximum load size set by
-  // the target. It processes any remaining bytes using a load size which is the
-  // next smallest power of 2.
   while (NumBytesToBeProcessed) {
-    // Calculate how many blocks we can create with the current load size
+    // Calculate how many blocks we can create with the current load size.
     int NumBlocks = NumBytesToBeProcessed / LoadSize;
     int GEPIndex = (Size - NumBytesToBeProcessed) / LoadSize;
     NumBytesToBeProcessed = NumBytesToBeProcessed % LoadSize;
 
     // For each NumBlocks, populate the instruction sequence for loading and
-    // comparing LoadSize bytes
+    // comparing LoadSize bytes.
     while (NumBlocks--) {
-      emitLoadCompareBlock(Index, LoadSize, GEPIndex, IsLittleEndian);
+      emitLoadCompareBlock(Index, LoadSize, GEPIndex);
       Index++;
       GEPIndex++;
     }
-    // Get the next LoadSize to use
+    // Get the next LoadSize to use.
     LoadSize = LoadSize / 2;
   }
 
-  emitMemCmpResultBlock(IsLittleEndian);
+  emitMemCmpResultBlock();
   return PhiRes;
 }
 
 // This function checks to see if an expansion of memcmp can be generated.
 // It checks for constant compare size that is less than the max inline size.
 // If an expansion cannot occur, returns false to leave as a library call.
-// Otherwise, the library call is replaced wtih new IR instruction sequence.
+// Otherwise, the library call is replaced with a new IR instruction sequence.
 /// We want to transform:
 /// %call = call signext i32 @memcmp(i8* %0, i8* %1, i64 15)
 /// To:
@@ -2177,27 +2206,25 @@ static bool expandMemCmp(CallInst *CI, const TargetTransformInfo *TTI,
   NumMemCmpCalls++;
   IRBuilder<> Builder(CI->getContext());
 
-  // TTI call to check if target would like to expand memcmp and get the
-  // MaxLoadSize
+  // TTI call to check if target would like to expand memcmp. Also, get the
+  // MaxLoadSize.
   unsigned MaxLoadSize;
   if (!TTI->expandMemCmp(CI, MaxLoadSize))
     return false;
 
-  // Early exit from expansion if -Oz
-  if (CI->getParent()->getParent()->optForMinSize()) {
+  // Early exit from expansion if -Oz.
+  if (CI->getFunction()->optForMinSize())
     return false;
-  }
 
-  // Early exit from expansion if size is not a constant
+  // Early exit from expansion if size is not a constant.
   ConstantInt *SizeCast = dyn_cast<ConstantInt>(CI->getArgOperand(2));
   if (!SizeCast) {
     NumMemCmpNotConstant++;
     return false;
   }
 
-  // Early exit from expansion if size greater than max bytes to load
+  // Early exit from expansion if size greater than max bytes to load.
   uint64_t SizeVal = SizeCast->getZExtValue();
-
   unsigned NumLoads = 0;
   unsigned RemainingSize = SizeVal;
   unsigned LoadSize = MaxLoadSize;
@@ -2207,29 +2234,28 @@ static bool expandMemCmp(CallInst *CI, const TargetTransformInfo *TTI,
     LoadSize = LoadSize / 2;
   }
 
-  if (NumLoads >
-      TLI->getMaxExpandSizeMemcmp(CI->getParent()->getParent()->optForSize())) {
+  if (NumLoads > TLI->getMaxExpandSizeMemcmp(CI->getFunction()->optForSize())) {
     NumMemCmpGreaterThanMax++;
     return false;
   }
 
   NumMemCmpInlined++;
 
-  // MemCmpHelper object, creates and sets up basic blocks required for
-  // expanding memcmp with size SizeVal
+  // MemCmpHelper object creates and sets up basic blocks required for
+  // expanding memcmp with size SizeVal.
   unsigned NumLoadsPerBlock = MemCmpNumLoadsPerBlock;
-  MemCmpExpansion MemCmpHelper(CI, MaxLoadSize, NumLoadsPerBlock);
+  MemCmpExpansion MemCmpHelper(CI, SizeVal, MaxLoadSize, NumLoadsPerBlock, *DL);
 
-  Value *Res = MemCmpHelper.getMemCmpExpansion(DL->isLittleEndian());
+  Value *Res = MemCmpHelper.getMemCmpExpansion(SizeVal);
 
-  // Replace call with result of expansion and erarse call.
+  // Replace call with result of expansion and erase call.
   CI->replaceAllUsesWith(Res);
   CI->eraseFromParent();
 
   return true;
 }
 
-bool CodeGenPrepare::optimizeCallInst(CallInst *CI, bool& ModifiedDT) {
+bool CodeGenPrepare::optimizeCallInst(CallInst *CI, bool &ModifiedDT) {
   BasicBlock *BB = CI->getParent();
 
   // Lower inline assembly if we can.
@@ -2382,12 +2408,10 @@ bool CodeGenPrepare::optimizeCallInst(CallInst *CI, bool& ModifiedDT) {
   }
 
   LibFunc Func;
-  if (TLInfo->getLibFunc(*CI->getCalledFunction(), Func) &&
-      Func == LibFunc_memcmp) {
-    if (expandMemCmp(CI, TTI, TLI, DL)) {
-      ModifiedDT = true;
-      return true;
-    }
+  if (TLInfo->getLibFunc(ImmutableCallSite(CI), Func) &&
+      Func == LibFunc_memcmp && expandMemCmp(CI, TTI, TLI, DL)) {
+    ModifiedDT = true;
+    return true;
   }
   return false;
 }
@@ -3934,7 +3958,7 @@ bool AddressingModeMatcher::matchAddr(Value *Addr, unsigned Depth) {
 static bool IsOperandAMemoryOperand(CallInst *CI, InlineAsm *IA, Value *OpVal,
                                     const TargetLowering &TLI,
                                     const TargetRegisterInfo &TRI) {
-  const Function *F = CI->getParent()->getParent();
+  const Function *F = CI->getFunction();
   TargetLowering::AsmOperandInfoVector TargetConstraints =
       TLI.ParseConstraints(F->getParent()->getDataLayout(), &TRI,
                             ImmutableCallSite(CI));
@@ -4531,7 +4555,7 @@ bool CodeGenPrepare::optimizeInlineAsmInst(CallInst *CS) {
   bool MadeChange = false;
 
   const TargetRegisterInfo *TRI =
-      TM->getSubtargetImpl(*CS->getParent()->getParent())->getRegisterInfo();
+      TM->getSubtargetImpl(*CS->getFunction())->getRegisterInfo();
   TargetLowering::AsmOperandInfoVector TargetConstraints =
       TLI->ParseConstraints(*DL, TRI, CS);
   unsigned ArgNo = 0;
@@ -6015,7 +6039,7 @@ static bool splitMergedValStore(StoreInst &SI, const DataLayout &DL,
   return true;
 }
 
-bool CodeGenPrepare::optimizeInst(Instruction *I, bool& ModifiedDT) {
+bool CodeGenPrepare::optimizeInst(Instruction *I, bool &ModifiedDT) {
   // Bail out if we inserted the instruction to prevent optimizations from
   // stepping on each other's toes.
   if (InsertedInsts.count(I))
@@ -6170,7 +6194,7 @@ static bool makeBitReverse(Instruction &I, const DataLayout &DL,
 // In this pass we look for GEP and cast instructions that are used
 // across basic blocks and rewrite them to improve basic-block-at-a-time
 // selection.
-bool CodeGenPrepare::optimizeBlock(BasicBlock &BB, bool& ModifiedDT) {
+bool CodeGenPrepare::optimizeBlock(BasicBlock &BB, bool &ModifiedDT) {
   SunkAddrs.clear();
   bool MadeChange = false;