Index: projects/clang380-import/contrib/llvm/include/llvm/IR/GlobalValue.h
===================================================================
--- projects/clang380-import/contrib/llvm/include/llvm/IR/GlobalValue.h	(revision 294176)
+++ projects/clang380-import/contrib/llvm/include/llvm/IR/GlobalValue.h	(revision 294177)
@@ -1,370 +1,374 @@
 //===-- llvm/GlobalValue.h - Class to represent a global value --*- C++ -*-===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This file is a common base class of all globally definable objects.  As such,
 // it is subclassed by GlobalVariable, GlobalAlias and by Function.  This is
 // used because you can do certain things with these global objects that you
 // can't do to anything else.  For example, use the address of one as a
 // constant.
 //
 //===----------------------------------------------------------------------===//
 
 #ifndef LLVM_IR_GLOBALVALUE_H
 #define LLVM_IR_GLOBALVALUE_H
 
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/DerivedTypes.h"
 #include <system_error>
 
 namespace llvm {
 
 class Comdat;
 class PointerType;
 class Module;
 
 namespace Intrinsic {
   enum ID : unsigned;
 }
 
 class GlobalValue : public Constant {
   GlobalValue(const GlobalValue &) = delete;
 public:
   /// @brief An enumeration for the kinds of linkage for global values.
   enum LinkageTypes {
     ExternalLinkage = 0,///< Externally visible function
     AvailableExternallyLinkage, ///< Available for inspection, not emission.
     LinkOnceAnyLinkage, ///< Keep one copy of function when linking (inline)
     LinkOnceODRLinkage, ///< Same, but only replaced by something equivalent.
     WeakAnyLinkage,     ///< Keep one copy of named function when linking (weak)
     WeakODRLinkage,     ///< Same, but only replaced by something equivalent.
     AppendingLinkage,   ///< Special purpose, only applies to global arrays
     InternalLinkage,    ///< Rename collisions when linking (static functions).
     PrivateLinkage,     ///< Like Internal, but omit from symbol table.
     ExternalWeakLinkage,///< ExternalWeak linkage description.
     CommonLinkage       ///< Tentative definitions.
   };
 
   /// @brief An enumeration for the kinds of visibility of global values.
   enum VisibilityTypes {
     DefaultVisibility = 0,  ///< The GV is visible
     HiddenVisibility,       ///< The GV is hidden
     ProtectedVisibility     ///< The GV is protected
   };
 
   /// @brief Storage classes of global values for PE targets.
   enum DLLStorageClassTypes {
     DefaultStorageClass   = 0,
     DLLImportStorageClass = 1, ///< Function to be imported from DLL
     DLLExportStorageClass = 2  ///< Function to be accessible from DLL.
   };
 
 protected:
   GlobalValue(Type *Ty, ValueTy VTy, Use *Ops, unsigned NumOps,
               LinkageTypes Linkage, const Twine &Name, unsigned AddressSpace)
       : Constant(PointerType::get(Ty, AddressSpace), VTy, Ops, NumOps),
         ValueType(Ty), Linkage(Linkage), Visibility(DefaultVisibility),
         UnnamedAddr(0), DllStorageClass(DefaultStorageClass),
         ThreadLocal(NotThreadLocal), IntID((Intrinsic::ID)0U), Parent(nullptr) {
     setName(Name);
   }
 
   Type *ValueType;
   // Note: VC++ treats enums as signed, so an extra bit is required to prevent
   // Linkage and Visibility from turning into negative values.
   LinkageTypes Linkage : 5;   // The linkage of this global
   unsigned Visibility : 2;    // The visibility style of this global
   unsigned UnnamedAddr : 1;   // This value's address is not significant
   unsigned DllStorageClass : 2; // DLL storage class
 
   unsigned ThreadLocal : 3; // Is this symbol "Thread Local", if so, what is
                             // the desired model?
   static const unsigned GlobalValueSubClassDataBits = 19;
 
 private:
   // Give subclasses access to what otherwise would be wasted padding.
   // (19 + 3 + 2 + 1 + 2 + 5) == 32.
   unsigned SubClassData : GlobalValueSubClassDataBits;
 
   friend class Constant;
   void destroyConstantImpl();
   Value *handleOperandChangeImpl(Value *From, Value *To, Use *U);
 
 protected:
   /// \brief The intrinsic ID for this subclass (which must be a Function).
   ///
   /// This member is defined by this class, but not used for anything.
   /// Subclasses can use it to store their intrinsic ID, if they have one.
   ///
   /// This is stored here to save space in Function on 64-bit hosts.
   Intrinsic::ID IntID;
 
   unsigned getGlobalValueSubClassData() const {
     return SubClassData;
   }
   void setGlobalValueSubClassData(unsigned V) {
     assert(V < (1 << GlobalValueSubClassDataBits) && "It will not fit");
     SubClassData = V;
   }
 
   Module *Parent;             // The containing module.
 public:
   enum ThreadLocalMode {
     NotThreadLocal = 0,
     GeneralDynamicTLSModel,
     LocalDynamicTLSModel,
     InitialExecTLSModel,
     LocalExecTLSModel
   };
 
   ~GlobalValue() override {
     removeDeadConstantUsers();   // remove any dead constants using this.
   }
 
   unsigned getAlignment() const;
 
   bool hasUnnamedAddr() const { return UnnamedAddr; }
   void setUnnamedAddr(bool Val) { UnnamedAddr = Val; }
 
   bool hasComdat() const { return getComdat() != nullptr; }
   Comdat *getComdat();
   const Comdat *getComdat() const {
     return const_cast<GlobalValue *>(this)->getComdat();
   }
 
   VisibilityTypes getVisibility() const { return VisibilityTypes(Visibility); }
   bool hasDefaultVisibility() const { return Visibility == DefaultVisibility; }
   bool hasHiddenVisibility() const { return Visibility == HiddenVisibility; }
   bool hasProtectedVisibility() const {
     return Visibility == ProtectedVisibility;
   }
   void setVisibility(VisibilityTypes V) {
     assert((!hasLocalLinkage() || V == DefaultVisibility) &&
            "local linkage requires default visibility");
     Visibility = V;
   }
 
   /// If the value is "Thread Local", its value isn't shared by the threads.
   bool isThreadLocal() const { return getThreadLocalMode() != NotThreadLocal; }
   void setThreadLocal(bool Val) {
     setThreadLocalMode(Val ? GeneralDynamicTLSModel : NotThreadLocal);
   }
   void setThreadLocalMode(ThreadLocalMode Val) {
     assert(Val == NotThreadLocal || getValueID() != Value::FunctionVal);
     ThreadLocal = Val;
   }
   ThreadLocalMode getThreadLocalMode() const {
     return static_cast<ThreadLocalMode>(ThreadLocal);
   }
 
   DLLStorageClassTypes getDLLStorageClass() const {
     return DLLStorageClassTypes(DllStorageClass);
   }
   bool hasDLLImportStorageClass() const {
     return DllStorageClass == DLLImportStorageClass;
   }
   bool hasDLLExportStorageClass() const {
     return DllStorageClass == DLLExportStorageClass;
   }
   void setDLLStorageClass(DLLStorageClassTypes C) { DllStorageClass = C; }
 
   bool hasSection() const { return !StringRef(getSection()).empty(); }
   // It is unfortunate that we have to use "char *" in here since this is
   // always non NULL, but:
   // * The C API expects a null terminated string, so we cannot use StringRef.
   // * The C API expects us to own it, so we cannot use a std:string.
   // * For GlobalAliases we can fail to find the section and we have to
   //   return "", so we cannot use a "const std::string &".
   const char *getSection() const;
 
   /// Global values are always pointers.
   PointerType *getType() const { return cast<PointerType>(User::getType()); }
 
   Type *getValueType() const { return ValueType; }
 
   static LinkageTypes getLinkOnceLinkage(bool ODR) {
     return ODR ? LinkOnceODRLinkage : LinkOnceAnyLinkage;
   }
   static LinkageTypes getWeakLinkage(bool ODR) {
     return ODR ? WeakODRLinkage : WeakAnyLinkage;
   }
 
   static bool isExternalLinkage(LinkageTypes Linkage) {
     return Linkage == ExternalLinkage;
   }
   static bool isAvailableExternallyLinkage(LinkageTypes Linkage) {
     return Linkage == AvailableExternallyLinkage;
   }
   static bool isLinkOnceODRLinkage(LinkageTypes Linkage) {
     return Linkage == LinkOnceODRLinkage;
   }
   static bool isLinkOnceLinkage(LinkageTypes Linkage) {
     return Linkage == LinkOnceAnyLinkage || Linkage == LinkOnceODRLinkage;
   }
   static bool isWeakAnyLinkage(LinkageTypes Linkage) {
     return Linkage == WeakAnyLinkage;
   }
   static bool isWeakODRLinkage(LinkageTypes Linkage) {
     return Linkage == WeakODRLinkage;
   }
   static bool isWeakLinkage(LinkageTypes Linkage) {
     return isWeakAnyLinkage(Linkage) || isWeakODRLinkage(Linkage);
   }
   static bool isAppendingLinkage(LinkageTypes Linkage) {
     return Linkage == AppendingLinkage;
   }
   static bool isInternalLinkage(LinkageTypes Linkage) {
     return Linkage == InternalLinkage;
   }
   static bool isPrivateLinkage(LinkageTypes Linkage) {
     return Linkage == PrivateLinkage;
   }
   static bool isLocalLinkage(LinkageTypes Linkage) {
     return isInternalLinkage(Linkage) || isPrivateLinkage(Linkage);
   }
   static bool isExternalWeakLinkage(LinkageTypes Linkage) {
     return Linkage == ExternalWeakLinkage;
   }
   static bool isCommonLinkage(LinkageTypes Linkage) {
     return Linkage == CommonLinkage;
   }
 
   /// Whether the definition of this global may be discarded if it is not used
   /// in its compilation unit.
   static bool isDiscardableIfUnused(LinkageTypes Linkage) {
     return isLinkOnceLinkage(Linkage) || isLocalLinkage(Linkage) ||
            isAvailableExternallyLinkage(Linkage);
   }
 
   /// Whether the definition of this global may be replaced by something
   /// non-equivalent at link time. For example, if a function has weak linkage
   /// then the code defining it may be replaced by different code.
   static bool mayBeOverridden(LinkageTypes Linkage) {
     return Linkage == WeakAnyLinkage || Linkage == LinkOnceAnyLinkage ||
            Linkage == CommonLinkage || Linkage == ExternalWeakLinkage;
   }
 
   /// Whether the definition of this global may be replaced at link time.  NB:
   /// Using this method outside of the code generators is almost always a
   /// mistake: when working at the IR level use mayBeOverridden instead as it
   /// knows about ODR semantics.
   static bool isWeakForLinker(LinkageTypes Linkage)  {
     return Linkage == WeakAnyLinkage || Linkage == WeakODRLinkage ||
            Linkage == LinkOnceAnyLinkage || Linkage == LinkOnceODRLinkage ||
            Linkage == CommonLinkage || Linkage == ExternalWeakLinkage;
   }
 
   bool hasExternalLinkage() const { return isExternalLinkage(Linkage); }
   bool hasAvailableExternallyLinkage() const {
     return isAvailableExternallyLinkage(Linkage);
   }
   bool hasLinkOnceLinkage() const {
     return isLinkOnceLinkage(Linkage);
   }
   bool hasLinkOnceODRLinkage() const { return isLinkOnceODRLinkage(Linkage); }
   bool hasWeakLinkage() const {
     return isWeakLinkage(Linkage);
   }
   bool hasWeakAnyLinkage() const {
     return isWeakAnyLinkage(Linkage);
   }
   bool hasWeakODRLinkage() const {
     return isWeakODRLinkage(Linkage);
   }
   bool hasAppendingLinkage() const { return isAppendingLinkage(Linkage); }
   bool hasInternalLinkage() const { return isInternalLinkage(Linkage); }
   bool hasPrivateLinkage() const { return isPrivateLinkage(Linkage); }
   bool hasLocalLinkage() const { return isLocalLinkage(Linkage); }
   bool hasExternalWeakLinkage() const { return isExternalWeakLinkage(Linkage); }
   bool hasCommonLinkage() const { return isCommonLinkage(Linkage); }
 
   void setLinkage(LinkageTypes LT) {
     if (isLocalLinkage(LT))
       Visibility = DefaultVisibility;
     Linkage = LT;
   }
   LinkageTypes getLinkage() const { return Linkage; }
 
   bool isDiscardableIfUnused() const {
     return isDiscardableIfUnused(Linkage);
   }
 
   bool mayBeOverridden() const { return mayBeOverridden(Linkage); }
 
   bool isWeakForLinker() const { return isWeakForLinker(Linkage); }
 
   /// Copy all additional attributes (those not needed to create a GlobalValue)
   /// from the GlobalValue Src to this one.
   virtual void copyAttributesFrom(const GlobalValue *Src);
 
   /// If special LLVM prefix that is used to inform the asm printer to not emit
   /// usual symbol prefix before the symbol name is used then return linkage
   /// name after skipping this special LLVM prefix.
   static StringRef getRealLinkageName(StringRef Name) {
     if (!Name.empty() && Name[0] == '\1')
       return Name.substr(1);
     return Name;
   }
 
 /// @name Materialization
 /// Materialization is used to construct functions only as they're needed. This
 /// is useful to reduce memory usage in LLVM or parsing work done by the
 /// BitcodeReader to load the Module.
 /// @{
 
   /// If this function's Module is being lazily streamed in functions from disk
   /// or some other source, this method can be used to check to see if the
   /// function has been read in yet or not.
   bool isMaterializable() const;
 
   /// Make sure this GlobalValue is fully read. If the module is corrupt, this
   /// returns true and fills in the optional string with information about the
   /// problem.  If successful, this returns false.
   std::error_code materialize();
 
 /// @}
 
   /// Return true if the primary definition of this global value is outside of
   /// the current translation unit.
   bool isDeclaration() const;
 
   bool isDeclarationForLinker() const {
     if (hasAvailableExternallyLinkage())
       return true;
 
     return isDeclaration();
   }
 
   /// Returns true if this global's definition will be the one chosen by the
   /// linker.
   bool isStrongDefinitionForLinker() const {
     return !(isDeclarationForLinker() || isWeakForLinker());
   }
 
+  // Returns true if the alignment of the value can be unilaterally
+  // increased.
+  bool canIncreaseAlignment() const;
+
   /// This method unlinks 'this' from the containing module, but does not delete
   /// it.
   virtual void removeFromParent() = 0;
 
   /// This method unlinks 'this' from the containing module and deletes it.
   virtual void eraseFromParent() = 0;
 
   /// Get the module that this global value is contained inside of...
   Module *getParent() { return Parent; }
   const Module *getParent() const { return Parent; }
 
   // Methods for support type inquiry through isa, cast, and dyn_cast:
   static bool classof(const Value *V) {
     return V->getValueID() == Value::FunctionVal ||
            V->getValueID() == Value::GlobalVariableVal ||
            V->getValueID() == Value::GlobalAliasVal;
   }
 };
 
 } // End llvm namespace
 
 #endif
Index: projects/clang380-import/contrib/llvm/lib/CodeGen/CodeGenPrepare.cpp
===================================================================
--- projects/clang380-import/contrib/llvm/lib/CodeGen/CodeGenPrepare.cpp	(revision 294176)
+++ projects/clang380-import/contrib/llvm/lib/CodeGen/CodeGenPrepare.cpp	(revision 294177)
@@ -1,5572 +1,5572 @@
 //===- CodeGenPrepare.cpp - Prepare a function for code generation --------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This pass munges the code in the input function to better prepare it for
 // SelectionDAG-based code generation. This works around limitations in it's
 // basic-block-at-a-time approach. It should eventually be removed.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GetElementPtrTypeIterator.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InlineAsm.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/MDBuilder.h"
 #include "llvm/IR/PatternMatch.h"
 #include "llvm/IR/Statepoint.h"
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/IR/ValueMap.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetLowering.h"
 #include "llvm/Target/TargetSubtargetInfo.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/BuildLibCalls.h"
 #include "llvm/Transforms/Utils/BypassSlowDivision.h"
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Transforms/Utils/SimplifyLibCalls.h"
 using namespace llvm;
 using namespace llvm::PatternMatch;
 
 #define DEBUG_TYPE "codegenprepare"
 
 STATISTIC(NumBlocksElim, "Number of blocks eliminated");
 STATISTIC(NumPHIsElim,   "Number of trivial PHIs eliminated");
 STATISTIC(NumGEPsElim,   "Number of GEPs converted to casts");
 STATISTIC(NumCmpUses, "Number of uses of Cmp expressions replaced with uses of "
                       "sunken Cmps");
 STATISTIC(NumCastUses, "Number of uses of Cast expressions replaced with uses "
                        "of sunken Casts");
 STATISTIC(NumMemoryInsts, "Number of memory instructions whose address "
                           "computations were sunk");
 STATISTIC(NumExtsMoved,  "Number of [s|z]ext instructions combined with loads");
 STATISTIC(NumExtUses,    "Number of uses of [s|z]ext instructions optimized");
 STATISTIC(NumAndsAdded,
           "Number of and mask instructions added to form ext loads");
 STATISTIC(NumAndUses, "Number of uses of and mask instructions optimized");
 STATISTIC(NumRetsDup,    "Number of return instructions duplicated");
 STATISTIC(NumDbgValueMoved, "Number of debug value instructions moved");
 STATISTIC(NumSelectsExpanded, "Number of selects turned into branches");
 STATISTIC(NumAndCmpsMoved, "Number of and/cmp's pushed into branches");
 STATISTIC(NumStoreExtractExposed, "Number of store(extractelement) exposed");
 
 static cl::opt<bool> DisableBranchOpts(
   "disable-cgp-branch-opts", cl::Hidden, cl::init(false),
   cl::desc("Disable branch optimizations in CodeGenPrepare"));
 
 static cl::opt<bool>
     DisableGCOpts("disable-cgp-gc-opts", cl::Hidden, cl::init(false),
                   cl::desc("Disable GC optimizations in CodeGenPrepare"));
 
 static cl::opt<bool> DisableSelectToBranch(
   "disable-cgp-select2branch", cl::Hidden, cl::init(false),
   cl::desc("Disable select to branch conversion."));
 
 static cl::opt<bool> AddrSinkUsingGEPs(
   "addr-sink-using-gep", cl::Hidden, cl::init(false),
   cl::desc("Address sinking in CGP using GEPs."));
 
 static cl::opt<bool> EnableAndCmpSinking(
    "enable-andcmp-sinking", cl::Hidden, cl::init(true),
    cl::desc("Enable sinkinig and/cmp into branches."));
 
 static cl::opt<bool> DisableStoreExtract(
     "disable-cgp-store-extract", cl::Hidden, cl::init(false),
     cl::desc("Disable store(extract) optimizations in CodeGenPrepare"));
 
 static cl::opt<bool> StressStoreExtract(
     "stress-cgp-store-extract", cl::Hidden, cl::init(false),
     cl::desc("Stress test store(extract) optimizations in CodeGenPrepare"));
 
 static cl::opt<bool> DisableExtLdPromotion(
     "disable-cgp-ext-ld-promotion", cl::Hidden, cl::init(false),
     cl::desc("Disable ext(promotable(ld)) -> promoted(ext(ld)) optimization in "
              "CodeGenPrepare"));
 
 static cl::opt<bool> StressExtLdPromotion(
     "stress-cgp-ext-ld-promotion", cl::Hidden, cl::init(false),
     cl::desc("Stress test ext(promotable(ld)) -> promoted(ext(ld)) "
              "optimization in CodeGenPrepare"));
 
 namespace {
 typedef SmallPtrSet<Instruction *, 16> SetOfInstrs;
 typedef PointerIntPair<Type *, 1, bool> TypeIsSExt;
 typedef DenseMap<Instruction *, TypeIsSExt> InstrToOrigTy;
 class TypePromotionTransaction;
 
   class CodeGenPrepare : public FunctionPass {
     const TargetMachine *TM;
     const TargetLowering *TLI;
     const TargetTransformInfo *TTI;
     const TargetLibraryInfo *TLInfo;
 
     /// As we scan instructions optimizing them, this is the next instruction
     /// to optimize. Transforms that can invalidate this should update it.
     BasicBlock::iterator CurInstIterator;
 
     /// Keeps track of non-local addresses that have been sunk into a block.
     /// This allows us to avoid inserting duplicate code for blocks with
     /// multiple load/stores of the same address.
     ValueMap<Value*, Value*> SunkAddrs;
 
     /// Keeps track of all instructions inserted for the current function.
     SetOfInstrs InsertedInsts;
     /// Keeps track of the type of the related instruction before their
     /// promotion for the current function.
     InstrToOrigTy PromotedInsts;
 
     /// True if CFG is modified in any way.
     bool ModifiedDT;
 
     /// True if optimizing for size.
     bool OptSize;
 
     /// DataLayout for the Function being processed.
     const DataLayout *DL;
 
   public:
     static char ID; // Pass identification, replacement for typeid
     explicit CodeGenPrepare(const TargetMachine *TM = nullptr)
         : FunctionPass(ID), TM(TM), TLI(nullptr), TTI(nullptr), DL(nullptr) {
         initializeCodeGenPreparePass(*PassRegistry::getPassRegistry());
       }
     bool runOnFunction(Function &F) override;
 
     const char *getPassName() const override { return "CodeGen Prepare"; }
 
     void getAnalysisUsage(AnalysisUsage &AU) const override {
       AU.addPreserved<DominatorTreeWrapperPass>();
       AU.addRequired<TargetLibraryInfoWrapperPass>();
       AU.addRequired<TargetTransformInfoWrapperPass>();
     }
 
   private:
     bool eliminateFallThrough(Function &F);
     bool eliminateMostlyEmptyBlocks(Function &F);
     bool canMergeBlocks(const BasicBlock *BB, const BasicBlock *DestBB) const;
     void eliminateMostlyEmptyBlock(BasicBlock *BB);
     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 moveExtToFormExtLoad(Instruction *&I);
     bool optimizeExtUses(Instruction *I);
     bool optimizeLoadExt(LoadInst *I);
     bool optimizeSelectInst(SelectInst *SI);
     bool optimizeShuffleVectorInst(ShuffleVectorInst *SI);
     bool optimizeSwitchInst(SwitchInst *CI);
     bool optimizeExtractElementInst(Instruction *Inst);
     bool dupRetToEnableTailCallOpts(BasicBlock *BB);
     bool placeDbgValues(Function &F);
     bool sinkAndCmp(Function &F);
     bool extLdPromotion(TypePromotionTransaction &TPT, LoadInst *&LI,
                         Instruction *&Inst,
                         const SmallVectorImpl<Instruction *> &Exts,
                         unsigned CreatedInstCost);
     bool splitBranchCondition(Function &F);
     bool simplifyOffsetableRelocate(Instruction &I);
     void stripInvariantGroupMetadata(Instruction &I);
   };
 }
 
 char CodeGenPrepare::ID = 0;
 INITIALIZE_TM_PASS(CodeGenPrepare, "codegenprepare",
                    "Optimize for code generation", false, false)
 
 FunctionPass *llvm::createCodeGenPreparePass(const TargetMachine *TM) {
   return new CodeGenPrepare(TM);
 }
 
 bool CodeGenPrepare::runOnFunction(Function &F) {
   if (skipOptnoneFunction(F))
     return false;
 
   DL = &F.getParent()->getDataLayout();
 
   bool EverMadeChange = false;
   // Clear per function information.
   InsertedInsts.clear();
   PromotedInsts.clear();
 
   ModifiedDT = false;
   if (TM)
     TLI = TM->getSubtargetImpl(F)->getTargetLowering();
   TLInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
   TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
   OptSize = F.optForSize();
 
   /// This optimization identifies DIV instructions that can be
   /// profitably bypassed and carried out with a shorter, faster divide.
   if (!OptSize && TLI && TLI->isSlowDivBypassed()) {
     const DenseMap<unsigned int, unsigned int> &BypassWidths =
        TLI->getBypassSlowDivWidths();
     BasicBlock* BB = &*F.begin();
     while (BB != nullptr) {
       // bypassSlowDivision may create new BBs, but we don't want to reapply the
       // optimization to those blocks.
       BasicBlock* Next = BB->getNextNode();
       EverMadeChange |= bypassSlowDivision(BB, BypassWidths);
       BB = Next;
     }
   }
 
   // Eliminate blocks that contain only PHI nodes and an
   // unconditional branch.
   EverMadeChange |= eliminateMostlyEmptyBlocks(F);
 
   // llvm.dbg.value is far away from the value then iSel may not be able
   // handle it properly. iSel will drop llvm.dbg.value if it can not
   // find a node corresponding to the value.
   EverMadeChange |= placeDbgValues(F);
 
   // If there is a mask, compare against zero, and branch that can be combined
   // into a single target instruction, push the mask and compare into branch
   // users. Do this before OptimizeBlock -> OptimizeInst ->
   // OptimizeCmpExpression, which perturbs the pattern being searched for.
   if (!DisableBranchOpts) {
     EverMadeChange |= sinkAndCmp(F);
     EverMadeChange |= splitBranchCondition(F);
   }
 
   bool MadeChange = true;
   while (MadeChange) {
     MadeChange = false;
     for (Function::iterator I = F.begin(); I != F.end(); ) {
       BasicBlock *BB = &*I++;
       bool ModifiedDTOnIteration = false;
       MadeChange |= optimizeBlock(*BB, ModifiedDTOnIteration);
 
       // Restart BB iteration if the dominator tree of the Function was changed
       if (ModifiedDTOnIteration)
         break;
     }
     EverMadeChange |= MadeChange;
   }
 
   SunkAddrs.clear();
 
   if (!DisableBranchOpts) {
     MadeChange = false;
     SmallPtrSet<BasicBlock*, 8> WorkList;
     for (BasicBlock &BB : F) {
       SmallVector<BasicBlock *, 2> Successors(succ_begin(&BB), succ_end(&BB));
       MadeChange |= ConstantFoldTerminator(&BB, true);
       if (!MadeChange) continue;
 
       for (SmallVectorImpl<BasicBlock*>::iterator
              II = Successors.begin(), IE = Successors.end(); II != IE; ++II)
         if (pred_begin(*II) == pred_end(*II))
           WorkList.insert(*II);
     }
 
     // Delete the dead blocks and any of their dead successors.
     MadeChange |= !WorkList.empty();
     while (!WorkList.empty()) {
       BasicBlock *BB = *WorkList.begin();
       WorkList.erase(BB);
       SmallVector<BasicBlock*, 2> Successors(succ_begin(BB), succ_end(BB));
 
       DeleteDeadBlock(BB);
 
       for (SmallVectorImpl<BasicBlock*>::iterator
              II = Successors.begin(), IE = Successors.end(); II != IE; ++II)
         if (pred_begin(*II) == pred_end(*II))
           WorkList.insert(*II);
     }
 
     // Merge pairs of basic blocks with unconditional branches, connected by
     // a single edge.
     if (EverMadeChange || MadeChange)
       MadeChange |= eliminateFallThrough(F);
 
     EverMadeChange |= MadeChange;
   }
 
   if (!DisableGCOpts) {
     SmallVector<Instruction *, 2> Statepoints;
     for (BasicBlock &BB : F)
       for (Instruction &I : BB)
         if (isStatepoint(I))
           Statepoints.push_back(&I);
     for (auto &I : Statepoints)
       EverMadeChange |= simplifyOffsetableRelocate(*I);
   }
 
   return EverMadeChange;
 }
 
 /// Merge basic blocks which are connected by a single edge, where one of the
 /// basic blocks has a single successor pointing to the other basic block,
 /// which has a single predecessor.
 bool CodeGenPrepare::eliminateFallThrough(Function &F) {
   bool Changed = false;
   // Scan all of the blocks in the function, except for the entry block.
   for (Function::iterator I = std::next(F.begin()), E = F.end(); I != E;) {
     BasicBlock *BB = &*I++;
     // If the destination block has a single pred, then this is a trivial
     // edge, just collapse it.
     BasicBlock *SinglePred = BB->getSinglePredecessor();
 
     // Don't merge if BB's address is taken.
     if (!SinglePred || SinglePred == BB || BB->hasAddressTaken()) continue;
 
     BranchInst *Term = dyn_cast<BranchInst>(SinglePred->getTerminator());
     if (Term && !Term->isConditional()) {
       Changed = true;
       DEBUG(dbgs() << "To merge:\n"<< *SinglePred << "\n\n\n");
       // Remember if SinglePred was the entry block of the function.
       // If so, we will need to move BB back to the entry position.
       bool isEntry = SinglePred == &SinglePred->getParent()->getEntryBlock();
       MergeBasicBlockIntoOnlyPred(BB, nullptr);
 
       if (isEntry && BB != &BB->getParent()->getEntryBlock())
         BB->moveBefore(&BB->getParent()->getEntryBlock());
 
       // We have erased a block. Update the iterator.
       I = BB->getIterator();
     }
   }
   return Changed;
 }
 
 /// Eliminate blocks that contain only PHI nodes, debug info directives, and an
 /// unconditional branch. Passes before isel (e.g. LSR/loopsimplify) often split
 /// edges in ways that are non-optimal for isel. Start by eliminating these
 /// blocks so we can split them the way we want them.
 bool CodeGenPrepare::eliminateMostlyEmptyBlocks(Function &F) {
   bool MadeChange = false;
   // Note that this intentionally skips the entry block.
   for (Function::iterator I = std::next(F.begin()), E = F.end(); I != E;) {
     BasicBlock *BB = &*I++;
 
     // If this block doesn't end with an uncond branch, ignore it.
     BranchInst *BI = dyn_cast<BranchInst>(BB->getTerminator());
     if (!BI || !BI->isUnconditional())
       continue;
 
     // If the instruction before the branch (skipping debug info) isn't a phi
     // node, then other stuff is happening here.
     BasicBlock::iterator BBI = BI->getIterator();
     if (BBI != BB->begin()) {
       --BBI;
       while (isa<DbgInfoIntrinsic>(BBI)) {
         if (BBI == BB->begin())
           break;
         --BBI;
       }
       if (!isa<DbgInfoIntrinsic>(BBI) && !isa<PHINode>(BBI))
         continue;
     }
 
     // Do not break infinite loops.
     BasicBlock *DestBB = BI->getSuccessor(0);
     if (DestBB == BB)
       continue;
 
     if (!canMergeBlocks(BB, DestBB))
       continue;
 
     eliminateMostlyEmptyBlock(BB);
     MadeChange = true;
   }
   return MadeChange;
 }
 
 /// Return true if we can merge BB into DestBB if there is a single
 /// unconditional branch between them, and BB contains no other non-phi
 /// instructions.
 bool CodeGenPrepare::canMergeBlocks(const BasicBlock *BB,
                                     const BasicBlock *DestBB) const {
   // We only want to eliminate blocks whose phi nodes are used by phi nodes in
   // the successor.  If there are more complex condition (e.g. preheaders),
   // don't mess around with them.
   BasicBlock::const_iterator BBI = BB->begin();
   while (const PHINode *PN = dyn_cast<PHINode>(BBI++)) {
     for (const User *U : PN->users()) {
       const Instruction *UI = cast<Instruction>(U);
       if (UI->getParent() != DestBB || !isa<PHINode>(UI))
         return false;
       // If User is inside DestBB block and it is a PHINode then check
       // incoming value. If incoming value is not from BB then this is
       // a complex condition (e.g. preheaders) we want to avoid here.
       if (UI->getParent() == DestBB) {
         if (const PHINode *UPN = dyn_cast<PHINode>(UI))
           for (unsigned I = 0, E = UPN->getNumIncomingValues(); I != E; ++I) {
             Instruction *Insn = dyn_cast<Instruction>(UPN->getIncomingValue(I));
             if (Insn && Insn->getParent() == BB &&
                 Insn->getParent() != UPN->getIncomingBlock(I))
               return false;
           }
       }
     }
   }
 
   // If BB and DestBB contain any common predecessors, then the phi nodes in BB
   // and DestBB may have conflicting incoming values for the block.  If so, we
   // can't merge the block.
   const PHINode *DestBBPN = dyn_cast<PHINode>(DestBB->begin());
   if (!DestBBPN) return true;  // no conflict.
 
   // Collect the preds of BB.
   SmallPtrSet<const BasicBlock*, 16> BBPreds;
   if (const PHINode *BBPN = dyn_cast<PHINode>(BB->begin())) {
     // It is faster to get preds from a PHI than with pred_iterator.
     for (unsigned i = 0, e = BBPN->getNumIncomingValues(); i != e; ++i)
       BBPreds.insert(BBPN->getIncomingBlock(i));
   } else {
     BBPreds.insert(pred_begin(BB), pred_end(BB));
   }
 
   // Walk the preds of DestBB.
   for (unsigned i = 0, e = DestBBPN->getNumIncomingValues(); i != e; ++i) {
     BasicBlock *Pred = DestBBPN->getIncomingBlock(i);
     if (BBPreds.count(Pred)) {   // Common predecessor?
       BBI = DestBB->begin();
       while (const PHINode *PN = dyn_cast<PHINode>(BBI++)) {
         const Value *V1 = PN->getIncomingValueForBlock(Pred);
         const Value *V2 = PN->getIncomingValueForBlock(BB);
 
         // If V2 is a phi node in BB, look up what the mapped value will be.
         if (const PHINode *V2PN = dyn_cast<PHINode>(V2))
           if (V2PN->getParent() == BB)
             V2 = V2PN->getIncomingValueForBlock(Pred);
 
         // If there is a conflict, bail out.
         if (V1 != V2) return false;
       }
     }
   }
 
   return true;
 }
 
 
 /// Eliminate a basic block that has only phi's and an unconditional branch in
 /// it.
 void CodeGenPrepare::eliminateMostlyEmptyBlock(BasicBlock *BB) {
   BranchInst *BI = cast<BranchInst>(BB->getTerminator());
   BasicBlock *DestBB = BI->getSuccessor(0);
 
   DEBUG(dbgs() << "MERGING MOSTLY EMPTY BLOCKS - BEFORE:\n" << *BB << *DestBB);
 
   // If the destination block has a single pred, then this is a trivial edge,
   // just collapse it.
   if (BasicBlock *SinglePred = DestBB->getSinglePredecessor()) {
     if (SinglePred != DestBB) {
       // Remember if SinglePred was the entry block of the function.  If so, we
       // will need to move BB back to the entry position.
       bool isEntry = SinglePred == &SinglePred->getParent()->getEntryBlock();
       MergeBasicBlockIntoOnlyPred(DestBB, nullptr);
 
       if (isEntry && BB != &BB->getParent()->getEntryBlock())
         BB->moveBefore(&BB->getParent()->getEntryBlock());
 
       DEBUG(dbgs() << "AFTER:\n" << *DestBB << "\n\n\n");
       return;
     }
   }
 
   // Otherwise, we have multiple predecessors of BB.  Update the PHIs in DestBB
   // to handle the new incoming edges it is about to have.
   PHINode *PN;
   for (BasicBlock::iterator BBI = DestBB->begin();
        (PN = dyn_cast<PHINode>(BBI)); ++BBI) {
     // Remove the incoming value for BB, and remember it.
     Value *InVal = PN->removeIncomingValue(BB, false);
 
     // Two options: either the InVal is a phi node defined in BB or it is some
     // value that dominates BB.
     PHINode *InValPhi = dyn_cast<PHINode>(InVal);
     if (InValPhi && InValPhi->getParent() == BB) {
       // Add all of the input values of the input PHI as inputs of this phi.
       for (unsigned i = 0, e = InValPhi->getNumIncomingValues(); i != e; ++i)
         PN->addIncoming(InValPhi->getIncomingValue(i),
                         InValPhi->getIncomingBlock(i));
     } else {
       // Otherwise, add one instance of the dominating value for each edge that
       // we will be adding.
       if (PHINode *BBPN = dyn_cast<PHINode>(BB->begin())) {
         for (unsigned i = 0, e = BBPN->getNumIncomingValues(); i != e; ++i)
           PN->addIncoming(InVal, BBPN->getIncomingBlock(i));
       } else {
         for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI)
           PN->addIncoming(InVal, *PI);
       }
     }
   }
 
   // The PHIs are now updated, change everything that refers to BB to use
   // DestBB and remove BB.
   BB->replaceAllUsesWith(DestBB);
   BB->eraseFromParent();
   ++NumBlocksElim;
 
   DEBUG(dbgs() << "AFTER:\n" << *DestBB << "\n\n\n");
 }
 
 // Computes a map of base pointer relocation instructions to corresponding
 // derived pointer relocation instructions given a vector of all relocate calls
 static void computeBaseDerivedRelocateMap(
     const SmallVectorImpl<GCRelocateInst *> &AllRelocateCalls,
     DenseMap<GCRelocateInst *, SmallVector<GCRelocateInst *, 2>>
         &RelocateInstMap) {
   // Collect information in two maps: one primarily for locating the base object
   // while filling the second map; the second map is the final structure holding
   // a mapping between Base and corresponding Derived relocate calls
   DenseMap<std::pair<unsigned, unsigned>, GCRelocateInst *> RelocateIdxMap;
   for (auto *ThisRelocate : AllRelocateCalls) {
     auto K = std::make_pair(ThisRelocate->getBasePtrIndex(),
                             ThisRelocate->getDerivedPtrIndex());
     RelocateIdxMap.insert(std::make_pair(K, ThisRelocate));
   }
   for (auto &Item : RelocateIdxMap) {
     std::pair<unsigned, unsigned> Key = Item.first;
     if (Key.first == Key.second)
       // Base relocation: nothing to insert
       continue;
 
     GCRelocateInst *I = Item.second;
     auto BaseKey = std::make_pair(Key.first, Key.first);
 
     // We're iterating over RelocateIdxMap so we cannot modify it.
     auto MaybeBase = RelocateIdxMap.find(BaseKey);
     if (MaybeBase == RelocateIdxMap.end())
       // TODO: We might want to insert a new base object relocate and gep off
       // that, if there are enough derived object relocates.
       continue;
 
     RelocateInstMap[MaybeBase->second].push_back(I);
   }
 }
 
 // Accepts a GEP and extracts the operands into a vector provided they're all
 // small integer constants
 static bool getGEPSmallConstantIntOffsetV(GetElementPtrInst *GEP,
                                           SmallVectorImpl<Value *> &OffsetV) {
   for (unsigned i = 1; i < GEP->getNumOperands(); i++) {
     // Only accept small constant integer operands
     auto Op = dyn_cast<ConstantInt>(GEP->getOperand(i));
     if (!Op || Op->getZExtValue() > 20)
       return false;
   }
 
   for (unsigned i = 1; i < GEP->getNumOperands(); i++)
     OffsetV.push_back(GEP->getOperand(i));
   return true;
 }
 
 // Takes a RelocatedBase (base pointer relocation instruction) and Targets to
 // replace, computes a replacement, and affects it.
 static bool
 simplifyRelocatesOffABase(GCRelocateInst *RelocatedBase,
                           const SmallVectorImpl<GCRelocateInst *> &Targets) {
   bool MadeChange = false;
   for (GCRelocateInst *ToReplace : Targets) {
     assert(ToReplace->getBasePtrIndex() == RelocatedBase->getBasePtrIndex() &&
            "Not relocating a derived object of the original base object");
     if (ToReplace->getBasePtrIndex() == ToReplace->getDerivedPtrIndex()) {
       // A duplicate relocate call. TODO: coalesce duplicates.
       continue;
     }
 
     if (RelocatedBase->getParent() != ToReplace->getParent()) {
       // Base and derived relocates are in different basic blocks.
       // In this case transform is only valid when base dominates derived
       // relocate. However it would be too expensive to check dominance
       // for each such relocate, so we skip the whole transformation.
       continue;
     }
 
     Value *Base = ToReplace->getBasePtr();
     auto Derived = dyn_cast<GetElementPtrInst>(ToReplace->getDerivedPtr());
     if (!Derived || Derived->getPointerOperand() != Base)
       continue;
 
     SmallVector<Value *, 2> OffsetV;
     if (!getGEPSmallConstantIntOffsetV(Derived, OffsetV))
       continue;
 
     // Create a Builder and replace the target callsite with a gep
     assert(RelocatedBase->getNextNode() && "Should always have one since it's not a terminator");
 
     // Insert after RelocatedBase
     IRBuilder<> Builder(RelocatedBase->getNextNode());
     Builder.SetCurrentDebugLocation(ToReplace->getDebugLoc());
 
     // If gc_relocate does not match the actual type, cast it to the right type.
     // In theory, there must be a bitcast after gc_relocate if the type does not
     // match, and we should reuse it to get the derived pointer. But it could be
     // cases like this:
     // bb1:
     //  ...
     //  %g1 = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(...)
     //  br label %merge
     //
     // bb2:
     //  ...
     //  %g2 = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(...)
     //  br label %merge
     //
     // merge:
     //  %p1 = phi i8 addrspace(1)* [ %g1, %bb1 ], [ %g2, %bb2 ]
     //  %cast = bitcast i8 addrspace(1)* %p1 in to i32 addrspace(1)*
     //
     // In this case, we can not find the bitcast any more. So we insert a new bitcast
     // no matter there is already one or not. In this way, we can handle all cases, and
     // the extra bitcast should be optimized away in later passes.
     Value *ActualRelocatedBase = RelocatedBase;
     if (RelocatedBase->getType() != Base->getType()) {
       ActualRelocatedBase =
           Builder.CreateBitCast(RelocatedBase, Base->getType());
     }
     Value *Replacement = Builder.CreateGEP(
         Derived->getSourceElementType(), ActualRelocatedBase, makeArrayRef(OffsetV));
     Replacement->takeName(ToReplace);
     // If the newly generated derived pointer's type does not match the original derived
     // pointer's type, cast the new derived pointer to match it. Same reasoning as above.
     Value *ActualReplacement = Replacement;
     if (Replacement->getType() != ToReplace->getType()) {
       ActualReplacement =
           Builder.CreateBitCast(Replacement, ToReplace->getType());
     }
     ToReplace->replaceAllUsesWith(ActualReplacement);
     ToReplace->eraseFromParent();
 
     MadeChange = true;
   }
   return MadeChange;
 }
 
 // Turns this:
 //
 // %base = ...
 // %ptr = gep %base + 15
 // %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
 // %base' = relocate(%tok, i32 4, i32 4)
 // %ptr' = relocate(%tok, i32 4, i32 5)
 // %val = load %ptr'
 //
 // into this:
 //
 // %base = ...
 // %ptr = gep %base + 15
 // %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
 // %base' = gc.relocate(%tok, i32 4, i32 4)
 // %ptr' = gep %base' + 15
 // %val = load %ptr'
 bool CodeGenPrepare::simplifyOffsetableRelocate(Instruction &I) {
   bool MadeChange = false;
   SmallVector<GCRelocateInst *, 2> AllRelocateCalls;
 
   for (auto *U : I.users())
     if (GCRelocateInst *Relocate = dyn_cast<GCRelocateInst>(U))
       // Collect all the relocate calls associated with a statepoint
       AllRelocateCalls.push_back(Relocate);
 
   // We need atleast one base pointer relocation + one derived pointer
   // relocation to mangle
   if (AllRelocateCalls.size() < 2)
     return false;
 
   // RelocateInstMap is a mapping from the base relocate instruction to the
   // corresponding derived relocate instructions
   DenseMap<GCRelocateInst *, SmallVector<GCRelocateInst *, 2>> RelocateInstMap;
   computeBaseDerivedRelocateMap(AllRelocateCalls, RelocateInstMap);
   if (RelocateInstMap.empty())
     return false;
 
   for (auto &Item : RelocateInstMap)
     // Item.first is the RelocatedBase to offset against
     // Item.second is the vector of Targets to replace
     MadeChange = simplifyRelocatesOffABase(Item.first, Item.second);
   return MadeChange;
 }
 
 /// SinkCast - Sink the specified cast instruction into its user blocks
 static bool SinkCast(CastInst *CI) {
   BasicBlock *DefBB = CI->getParent();
 
   /// InsertedCasts - Only insert a cast in each block once.
   DenseMap<BasicBlock*, CastInst*> InsertedCasts;
 
   bool MadeChange = false;
   for (Value::user_iterator UI = CI->user_begin(), E = CI->user_end();
        UI != E; ) {
     Use &TheUse = UI.getUse();
     Instruction *User = cast<Instruction>(*UI);
 
     // Figure out which BB this cast is used in.  For PHI's this is the
     // appropriate predecessor block.
     BasicBlock *UserBB = User->getParent();
     if (PHINode *PN = dyn_cast<PHINode>(User)) {
       UserBB = PN->getIncomingBlock(TheUse);
     }
 
     // Preincrement use iterator so we don't invalidate it.
     ++UI;
 
     // If the block selected to receive the cast is an EH pad that does not
     // allow non-PHI instructions before the terminator, we can't sink the
     // cast.
     if (UserBB->getTerminator()->isEHPad())
       continue;
 
     // If this user is in the same block as the cast, don't change the cast.
     if (UserBB == DefBB) continue;
 
     // If we have already inserted a cast into this block, use it.
     CastInst *&InsertedCast = InsertedCasts[UserBB];
 
     if (!InsertedCast) {
       BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
       assert(InsertPt != UserBB->end());
       InsertedCast = CastInst::Create(CI->getOpcode(), CI->getOperand(0),
                                       CI->getType(), "", &*InsertPt);
     }
 
     // Replace a use of the cast with a use of the new cast.
     TheUse = InsertedCast;
     MadeChange = true;
     ++NumCastUses;
   }
 
   // If we removed all uses, nuke the cast.
   if (CI->use_empty()) {
     CI->eraseFromParent();
     MadeChange = true;
   }
 
   return MadeChange;
 }
 
 /// If the specified cast instruction is a noop copy (e.g. it's casting from
 /// one pointer type to another, i32->i8 on PPC), sink it into user blocks to
 /// reduce the number of virtual registers that must be created and coalesced.
 ///
 /// Return true if any changes are made.
 ///
 static bool OptimizeNoopCopyExpression(CastInst *CI, const TargetLowering &TLI,
                                        const DataLayout &DL) {
   // If this is a noop copy,
   EVT SrcVT = TLI.getValueType(DL, CI->getOperand(0)->getType());
   EVT DstVT = TLI.getValueType(DL, CI->getType());
 
   // This is an fp<->int conversion?
   if (SrcVT.isInteger() != DstVT.isInteger())
     return false;
 
   // If this is an extension, it will be a zero or sign extension, which
   // isn't a noop.
   if (SrcVT.bitsLT(DstVT)) return false;
 
   // If these values will be promoted, find out what they will be promoted
   // to.  This helps us consider truncates on PPC as noop copies when they
   // are.
   if (TLI.getTypeAction(CI->getContext(), SrcVT) ==
       TargetLowering::TypePromoteInteger)
     SrcVT = TLI.getTypeToTransformTo(CI->getContext(), SrcVT);
   if (TLI.getTypeAction(CI->getContext(), DstVT) ==
       TargetLowering::TypePromoteInteger)
     DstVT = TLI.getTypeToTransformTo(CI->getContext(), DstVT);
 
   // If, after promotion, these are the same types, this is a noop copy.
   if (SrcVT != DstVT)
     return false;
 
   return SinkCast(CI);
 }
 
 /// Try to combine CI into a call to the llvm.uadd.with.overflow intrinsic if
 /// possible.
 ///
 /// Return true if any changes were made.
 static bool CombineUAddWithOverflow(CmpInst *CI) {
   Value *A, *B;
   Instruction *AddI;
   if (!match(CI,
              m_UAddWithOverflow(m_Value(A), m_Value(B), m_Instruction(AddI))))
     return false;
 
   Type *Ty = AddI->getType();
   if (!isa<IntegerType>(Ty))
     return false;
 
   // We don't want to move around uses of condition values this late, so we we
   // check if it is legal to create the call to the intrinsic in the basic
   // block containing the icmp:
 
   if (AddI->getParent() != CI->getParent() && !AddI->hasOneUse())
     return false;
 
 #ifndef NDEBUG
   // Someday m_UAddWithOverflow may get smarter, but this is a safe assumption
   // for now:
   if (AddI->hasOneUse())
     assert(*AddI->user_begin() == CI && "expected!");
 #endif
 
   Module *M = CI->getModule();
   Value *F = Intrinsic::getDeclaration(M, Intrinsic::uadd_with_overflow, Ty);
 
   auto *InsertPt = AddI->hasOneUse() ? CI : AddI;
 
   auto *UAddWithOverflow =
       CallInst::Create(F, {A, B}, "uadd.overflow", InsertPt);
   auto *UAdd = ExtractValueInst::Create(UAddWithOverflow, 0, "uadd", InsertPt);
   auto *Overflow =
       ExtractValueInst::Create(UAddWithOverflow, 1, "overflow", InsertPt);
 
   CI->replaceAllUsesWith(Overflow);
   AddI->replaceAllUsesWith(UAdd);
   CI->eraseFromParent();
   AddI->eraseFromParent();
   return true;
 }
 
 /// Sink the given CmpInst into user blocks to reduce the number of virtual
 /// registers that must be created and coalesced. This is a clear win except on
 /// targets with multiple condition code registers (PowerPC), where it might
 /// lose; some adjustment may be wanted there.
 ///
 /// Return true if any changes are made.
 static bool SinkCmpExpression(CmpInst *CI) {
   BasicBlock *DefBB = CI->getParent();
 
   /// Only insert a cmp in each block once.
   DenseMap<BasicBlock*, CmpInst*> InsertedCmps;
 
   bool MadeChange = false;
   for (Value::user_iterator UI = CI->user_begin(), E = CI->user_end();
        UI != E; ) {
     Use &TheUse = UI.getUse();
     Instruction *User = cast<Instruction>(*UI);
 
     // Preincrement use iterator so we don't invalidate it.
     ++UI;
 
     // Don't bother for PHI nodes.
     if (isa<PHINode>(User))
       continue;
 
     // Figure out which BB this cmp is used in.
     BasicBlock *UserBB = User->getParent();
 
     // If this user is in the same block as the cmp, don't change the cmp.
     if (UserBB == DefBB) continue;
 
     // If we have already inserted a cmp into this block, use it.
     CmpInst *&InsertedCmp = InsertedCmps[UserBB];
 
     if (!InsertedCmp) {
       BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
       assert(InsertPt != UserBB->end());
       InsertedCmp =
           CmpInst::Create(CI->getOpcode(), CI->getPredicate(),
                           CI->getOperand(0), CI->getOperand(1), "", &*InsertPt);
     }
 
     // Replace a use of the cmp with a use of the new cmp.
     TheUse = InsertedCmp;
     MadeChange = true;
     ++NumCmpUses;
   }
 
   // If we removed all uses, nuke the cmp.
   if (CI->use_empty()) {
     CI->eraseFromParent();
     MadeChange = true;
   }
 
   return MadeChange;
 }
 
 static bool OptimizeCmpExpression(CmpInst *CI) {
   if (SinkCmpExpression(CI))
     return true;
 
   if (CombineUAddWithOverflow(CI))
     return true;
 
   return false;
 }
 
 /// Check if the candidates could be combined with a shift instruction, which
 /// includes:
 /// 1. Truncate instruction
 /// 2. And instruction and the imm is a mask of the low bits:
 /// imm & (imm+1) == 0
 static bool isExtractBitsCandidateUse(Instruction *User) {
   if (!isa<TruncInst>(User)) {
     if (User->getOpcode() != Instruction::And ||
         !isa<ConstantInt>(User->getOperand(1)))
       return false;
 
     const APInt &Cimm = cast<ConstantInt>(User->getOperand(1))->getValue();
 
     if ((Cimm & (Cimm + 1)).getBoolValue())
       return false;
   }
   return true;
 }
 
 /// Sink both shift and truncate instruction to the use of truncate's BB.
 static bool
 SinkShiftAndTruncate(BinaryOperator *ShiftI, Instruction *User, ConstantInt *CI,
                      DenseMap<BasicBlock *, BinaryOperator *> &InsertedShifts,
                      const TargetLowering &TLI, const DataLayout &DL) {
   BasicBlock *UserBB = User->getParent();
   DenseMap<BasicBlock *, CastInst *> InsertedTruncs;
   TruncInst *TruncI = dyn_cast<TruncInst>(User);
   bool MadeChange = false;
 
   for (Value::user_iterator TruncUI = TruncI->user_begin(),
                             TruncE = TruncI->user_end();
        TruncUI != TruncE;) {
 
     Use &TruncTheUse = TruncUI.getUse();
     Instruction *TruncUser = cast<Instruction>(*TruncUI);
     // Preincrement use iterator so we don't invalidate it.
 
     ++TruncUI;
 
     int ISDOpcode = TLI.InstructionOpcodeToISD(TruncUser->getOpcode());
     if (!ISDOpcode)
       continue;
 
     // If the use is actually a legal node, there will not be an
     // implicit truncate.
     // FIXME: always querying the result type is just an
     // approximation; some nodes' legality is determined by the
     // operand or other means. There's no good way to find out though.
     if (TLI.isOperationLegalOrCustom(
             ISDOpcode, TLI.getValueType(DL, TruncUser->getType(), true)))
       continue;
 
     // Don't bother for PHI nodes.
     if (isa<PHINode>(TruncUser))
       continue;
 
     BasicBlock *TruncUserBB = TruncUser->getParent();
 
     if (UserBB == TruncUserBB)
       continue;
 
     BinaryOperator *&InsertedShift = InsertedShifts[TruncUserBB];
     CastInst *&InsertedTrunc = InsertedTruncs[TruncUserBB];
 
     if (!InsertedShift && !InsertedTrunc) {
       BasicBlock::iterator InsertPt = TruncUserBB->getFirstInsertionPt();
       assert(InsertPt != TruncUserBB->end());
       // Sink the shift
       if (ShiftI->getOpcode() == Instruction::AShr)
         InsertedShift = BinaryOperator::CreateAShr(ShiftI->getOperand(0), CI,
                                                    "", &*InsertPt);
       else
         InsertedShift = BinaryOperator::CreateLShr(ShiftI->getOperand(0), CI,
                                                    "", &*InsertPt);
 
       // Sink the trunc
       BasicBlock::iterator TruncInsertPt = TruncUserBB->getFirstInsertionPt();
       TruncInsertPt++;
       assert(TruncInsertPt != TruncUserBB->end());
 
       InsertedTrunc = CastInst::Create(TruncI->getOpcode(), InsertedShift,
                                        TruncI->getType(), "", &*TruncInsertPt);
 
       MadeChange = true;
 
       TruncTheUse = InsertedTrunc;
     }
   }
   return MadeChange;
 }
 
 /// Sink the shift *right* instruction into user blocks if the uses could
 /// potentially be combined with this shift instruction and generate BitExtract
 /// instruction. It will only be applied if the architecture supports BitExtract
 /// instruction. Here is an example:
 /// BB1:
 ///   %x.extract.shift = lshr i64 %arg1, 32
 /// BB2:
 ///   %x.extract.trunc = trunc i64 %x.extract.shift to i16
 /// ==>
 ///
 /// BB2:
 ///   %x.extract.shift.1 = lshr i64 %arg1, 32
 ///   %x.extract.trunc = trunc i64 %x.extract.shift.1 to i16
 ///
 /// CodeGen will recoginze the pattern in BB2 and generate BitExtract
 /// instruction.
 /// Return true if any changes are made.
 static bool OptimizeExtractBits(BinaryOperator *ShiftI, ConstantInt *CI,
                                 const TargetLowering &TLI,
                                 const DataLayout &DL) {
   BasicBlock *DefBB = ShiftI->getParent();
 
   /// Only insert instructions in each block once.
   DenseMap<BasicBlock *, BinaryOperator *> InsertedShifts;
 
   bool shiftIsLegal = TLI.isTypeLegal(TLI.getValueType(DL, ShiftI->getType()));
 
   bool MadeChange = false;
   for (Value::user_iterator UI = ShiftI->user_begin(), E = ShiftI->user_end();
        UI != E;) {
     Use &TheUse = UI.getUse();
     Instruction *User = cast<Instruction>(*UI);
     // Preincrement use iterator so we don't invalidate it.
     ++UI;
 
     // Don't bother for PHI nodes.
     if (isa<PHINode>(User))
       continue;
 
     if (!isExtractBitsCandidateUse(User))
       continue;
 
     BasicBlock *UserBB = User->getParent();
 
     if (UserBB == DefBB) {
       // If the shift and truncate instruction are in the same BB. The use of
       // the truncate(TruncUse) may still introduce another truncate if not
       // legal. In this case, we would like to sink both shift and truncate
       // instruction to the BB of TruncUse.
       // for example:
       // BB1:
       // i64 shift.result = lshr i64 opnd, imm
       // trunc.result = trunc shift.result to i16
       //
       // BB2:
       //   ----> We will have an implicit truncate here if the architecture does
       //   not have i16 compare.
       // cmp i16 trunc.result, opnd2
       //
       if (isa<TruncInst>(User) && shiftIsLegal
           // If the type of the truncate is legal, no trucate will be
           // introduced in other basic blocks.
           &&
           (!TLI.isTypeLegal(TLI.getValueType(DL, User->getType()))))
         MadeChange =
             SinkShiftAndTruncate(ShiftI, User, CI, InsertedShifts, TLI, DL);
 
       continue;
     }
     // If we have already inserted a shift into this block, use it.
     BinaryOperator *&InsertedShift = InsertedShifts[UserBB];
 
     if (!InsertedShift) {
       BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
       assert(InsertPt != UserBB->end());
 
       if (ShiftI->getOpcode() == Instruction::AShr)
         InsertedShift = BinaryOperator::CreateAShr(ShiftI->getOperand(0), CI,
                                                    "", &*InsertPt);
       else
         InsertedShift = BinaryOperator::CreateLShr(ShiftI->getOperand(0), CI,
                                                    "", &*InsertPt);
 
       MadeChange = true;
     }
 
     // Replace a use of the shift with a use of the new shift.
     TheUse = InsertedShift;
   }
 
   // If we removed all uses, nuke the shift.
   if (ShiftI->use_empty())
     ShiftI->eraseFromParent();
 
   return MadeChange;
 }
 
 // Translate a masked load intrinsic like
 // <16 x i32 > @llvm.masked.load( <16 x i32>* %addr, i32 align,
 //                               <16 x i1> %mask, <16 x i32> %passthru)
 // to a chain of basic blocks, with loading element one-by-one if
 // the appropriate mask bit is set
 //
 //  %1 = bitcast i8* %addr to i32*
 //  %2 = extractelement <16 x i1> %mask, i32 0
 //  %3 = icmp eq i1 %2, true
 //  br i1 %3, label %cond.load, label %else
 //
 //cond.load:                                        ; preds = %0
 //  %4 = getelementptr i32* %1, i32 0
 //  %5 = load i32* %4
 //  %6 = insertelement <16 x i32> undef, i32 %5, i32 0
 //  br label %else
 //
 //else:                                             ; preds = %0, %cond.load
 //  %res.phi.else = phi <16 x i32> [ %6, %cond.load ], [ undef, %0 ]
 //  %7 = extractelement <16 x i1> %mask, i32 1
 //  %8 = icmp eq i1 %7, true
 //  br i1 %8, label %cond.load1, label %else2
 //
 //cond.load1:                                       ; preds = %else
 //  %9 = getelementptr i32* %1, i32 1
 //  %10 = load i32* %9
 //  %11 = insertelement <16 x i32> %res.phi.else, i32 %10, i32 1
 //  br label %else2
 //
 //else2:                                            ; preds = %else, %cond.load1
 //  %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
 //  %12 = extractelement <16 x i1> %mask, i32 2
 //  %13 = icmp eq i1 %12, true
 //  br i1 %13, label %cond.load4, label %else5
 //
 static void ScalarizeMaskedLoad(CallInst *CI) {
   Value *Ptr  = CI->getArgOperand(0);
   Value *Alignment = CI->getArgOperand(1);
   Value *Mask = CI->getArgOperand(2);
   Value *Src0 = CI->getArgOperand(3);
 
   unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
   VectorType *VecType = dyn_cast<VectorType>(CI->getType());
   assert(VecType && "Unexpected return type of masked load intrinsic");
 
   Type *EltTy = CI->getType()->getVectorElementType();
 
   IRBuilder<> Builder(CI->getContext());
   Instruction *InsertPt = CI;
   BasicBlock *IfBlock = CI->getParent();
   BasicBlock *CondBlock = nullptr;
   BasicBlock *PrevIfBlock = CI->getParent();
 
   Builder.SetInsertPoint(InsertPt);
   Builder.SetCurrentDebugLocation(CI->getDebugLoc());
 
   // Short-cut if the mask is all-true.
   bool IsAllOnesMask = isa<Constant>(Mask) &&
     cast<Constant>(Mask)->isAllOnesValue();
 
   if (IsAllOnesMask) {
     Value *NewI = Builder.CreateAlignedLoad(Ptr, AlignVal);
     CI->replaceAllUsesWith(NewI);
     CI->eraseFromParent();
     return;
   }
 
   // Adjust alignment for the scalar instruction.
   AlignVal = std::min(AlignVal, VecType->getScalarSizeInBits()/8);
   // Bitcast %addr fron i8* to EltTy*
   Type *NewPtrType =
     EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
   Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
   unsigned VectorWidth = VecType->getNumElements();
 
   Value *UndefVal = UndefValue::get(VecType);
 
   // The result vector
   Value *VResult = UndefVal;
 
   if (isa<ConstantVector>(Mask)) {
     for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
       if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
           continue;
       Value *Gep =
           Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
       LoadInst* Load = Builder.CreateAlignedLoad(Gep, AlignVal);
       VResult = Builder.CreateInsertElement(VResult, Load,
                                             Builder.getInt32(Idx));
     }
     Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
     CI->replaceAllUsesWith(NewI);
     CI->eraseFromParent();
     return;
   }
 
   PHINode *Phi = nullptr;
   Value *PrevPhi = UndefVal;
 
   for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
 
     // Fill the "else" block, created in the previous iteration
     //
     //  %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
     //  %mask_1 = extractelement <16 x i1> %mask, i32 Idx
     //  %to_load = icmp eq i1 %mask_1, true
     //  br i1 %to_load, label %cond.load, label %else
     //
     if (Idx > 0) {
       Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
       Phi->addIncoming(VResult, CondBlock);
       Phi->addIncoming(PrevPhi, PrevIfBlock);
       PrevPhi = Phi;
       VResult = Phi;
     }
 
     Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
     Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
                                     ConstantInt::get(Predicate->getType(), 1));
 
     // Create "cond" block
     //
     //  %EltAddr = getelementptr i32* %1, i32 0
     //  %Elt = load i32* %EltAddr
     //  VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
     //
     CondBlock = IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.load");
     Builder.SetInsertPoint(InsertPt);
 
     Value *Gep =
         Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
     LoadInst *Load = Builder.CreateAlignedLoad(Gep, AlignVal);
     VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
 
     // Create "else" block, fill it in the next iteration
     BasicBlock *NewIfBlock =
         CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
     Builder.SetInsertPoint(InsertPt);
     Instruction *OldBr = IfBlock->getTerminator();
     BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
     OldBr->eraseFromParent();
     PrevIfBlock = IfBlock;
     IfBlock = NewIfBlock;
   }
 
   Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
   Phi->addIncoming(VResult, CondBlock);
   Phi->addIncoming(PrevPhi, PrevIfBlock);
   Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
   CI->replaceAllUsesWith(NewI);
   CI->eraseFromParent();
 }
 
 // Translate a masked store intrinsic, like
 // void @llvm.masked.store(<16 x i32> %src, <16 x i32>* %addr, i32 align,
 //                               <16 x i1> %mask)
 // to a chain of basic blocks, that stores element one-by-one if
 // the appropriate mask bit is set
 //
 //   %1 = bitcast i8* %addr to i32*
 //   %2 = extractelement <16 x i1> %mask, i32 0
 //   %3 = icmp eq i1 %2, true
 //   br i1 %3, label %cond.store, label %else
 //
 // cond.store:                                       ; preds = %0
 //   %4 = extractelement <16 x i32> %val, i32 0
 //   %5 = getelementptr i32* %1, i32 0
 //   store i32 %4, i32* %5
 //   br label %else
 //
 // else:                                             ; preds = %0, %cond.store
 //   %6 = extractelement <16 x i1> %mask, i32 1
 //   %7 = icmp eq i1 %6, true
 //   br i1 %7, label %cond.store1, label %else2
 //
 // cond.store1:                                      ; preds = %else
 //   %8 = extractelement <16 x i32> %val, i32 1
 //   %9 = getelementptr i32* %1, i32 1
 //   store i32 %8, i32* %9
 //   br label %else2
 //   . . .
 static void ScalarizeMaskedStore(CallInst *CI) {
   Value *Src = CI->getArgOperand(0);
   Value *Ptr  = CI->getArgOperand(1);
   Value *Alignment = CI->getArgOperand(2);
   Value *Mask = CI->getArgOperand(3);
 
   unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
   VectorType *VecType = dyn_cast<VectorType>(Src->getType());
   assert(VecType && "Unexpected data type in masked store intrinsic");
 
   Type *EltTy = VecType->getElementType();
 
   IRBuilder<> Builder(CI->getContext());
   Instruction *InsertPt = CI;
   BasicBlock *IfBlock = CI->getParent();
   Builder.SetInsertPoint(InsertPt);
   Builder.SetCurrentDebugLocation(CI->getDebugLoc());
 
   // Short-cut if the mask is all-true.
   bool IsAllOnesMask = isa<Constant>(Mask) &&
     cast<Constant>(Mask)->isAllOnesValue();
 
   if (IsAllOnesMask) {
     Builder.CreateAlignedStore(Src, Ptr, AlignVal);
     CI->eraseFromParent();
     return;
   }
 
   // Adjust alignment for the scalar instruction.
   AlignVal = std::max(AlignVal, VecType->getScalarSizeInBits()/8);
   // Bitcast %addr fron i8* to EltTy*
   Type *NewPtrType =
     EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
   Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
   unsigned VectorWidth = VecType->getNumElements();
 
   if (isa<ConstantVector>(Mask)) {
     for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
       if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
           continue;
       Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
       Value *Gep =
           Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
       Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
     }
     CI->eraseFromParent();
     return;
   }
 
   for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
 
     // Fill the "else" block, created in the previous iteration
     //
     //  %mask_1 = extractelement <16 x i1> %mask, i32 Idx
     //  %to_store = icmp eq i1 %mask_1, true
     //  br i1 %to_store, label %cond.store, label %else
     //
     Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
     Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
                                     ConstantInt::get(Predicate->getType(), 1));
 
     // Create "cond" block
     //
     //  %OneElt = extractelement <16 x i32> %Src, i32 Idx
     //  %EltAddr = getelementptr i32* %1, i32 0
     //  %store i32 %OneElt, i32* %EltAddr
     //
     BasicBlock *CondBlock =
         IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.store");
     Builder.SetInsertPoint(InsertPt);
 
     Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
     Value *Gep =
         Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
     Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
 
     // Create "else" block, fill it in the next iteration
     BasicBlock *NewIfBlock =
         CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
     Builder.SetInsertPoint(InsertPt);
     Instruction *OldBr = IfBlock->getTerminator();
     BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
     OldBr->eraseFromParent();
     IfBlock = NewIfBlock;
   }
   CI->eraseFromParent();
 }
 
 // Translate a masked gather intrinsic like
 // <16 x i32 > @llvm.masked.gather.v16i32( <16 x i32*> %Ptrs, i32 4,
 //                               <16 x i1> %Mask, <16 x i32> %Src)
 // to a chain of basic blocks, with loading element one-by-one if
 // the appropriate mask bit is set
 //
 // % Ptrs = getelementptr i32, i32* %base, <16 x i64> %ind
 // % Mask0 = extractelement <16 x i1> %Mask, i32 0
 // % ToLoad0 = icmp eq i1 % Mask0, true
 // br i1 % ToLoad0, label %cond.load, label %else
 //
 // cond.load:
 // % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
 // % Load0 = load i32, i32* % Ptr0, align 4
 // % Res0 = insertelement <16 x i32> undef, i32 % Load0, i32 0
 // br label %else
 //
 // else:
 // %res.phi.else = phi <16 x i32>[% Res0, %cond.load], [undef, % 0]
 // % Mask1 = extractelement <16 x i1> %Mask, i32 1
 // % ToLoad1 = icmp eq i1 % Mask1, true
 // br i1 % ToLoad1, label %cond.load1, label %else2
 //
 // cond.load1:
 // % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
 // % Load1 = load i32, i32* % Ptr1, align 4
 // % Res1 = insertelement <16 x i32> %res.phi.else, i32 % Load1, i32 1
 // br label %else2
 // . . .
 // % Result = select <16 x i1> %Mask, <16 x i32> %res.phi.select, <16 x i32> %Src
 // ret <16 x i32> %Result
 static void ScalarizeMaskedGather(CallInst *CI) {
   Value *Ptrs = CI->getArgOperand(0);
   Value *Alignment = CI->getArgOperand(1);
   Value *Mask = CI->getArgOperand(2);
   Value *Src0 = CI->getArgOperand(3);
 
   VectorType *VecType = dyn_cast<VectorType>(CI->getType());
 
   assert(VecType && "Unexpected return type of masked load intrinsic");
 
   IRBuilder<> Builder(CI->getContext());
   Instruction *InsertPt = CI;
   BasicBlock *IfBlock = CI->getParent();
   BasicBlock *CondBlock = nullptr;
   BasicBlock *PrevIfBlock = CI->getParent();
   Builder.SetInsertPoint(InsertPt);
   unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
 
   Builder.SetCurrentDebugLocation(CI->getDebugLoc());
 
   Value *UndefVal = UndefValue::get(VecType);
 
   // The result vector
   Value *VResult = UndefVal;
   unsigned VectorWidth = VecType->getNumElements();
 
   // Shorten the way if the mask is a vector of constants.
   bool IsConstMask = isa<ConstantVector>(Mask);
 
   if (IsConstMask) {
     for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
       if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
         continue;
       Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
                                                 "Ptr" + Twine(Idx));
       LoadInst *Load = Builder.CreateAlignedLoad(Ptr, AlignVal,
                                                  "Load" + Twine(Idx));
       VResult = Builder.CreateInsertElement(VResult, Load,
                                             Builder.getInt32(Idx),
                                             "Res" + Twine(Idx));
     }
     Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
     CI->replaceAllUsesWith(NewI);
     CI->eraseFromParent();
     return;
   }
 
   PHINode *Phi = nullptr;
   Value *PrevPhi = UndefVal;
 
   for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
 
     // Fill the "else" block, created in the previous iteration
     //
     //  %Mask1 = extractelement <16 x i1> %Mask, i32 1
     //  %ToLoad1 = icmp eq i1 %Mask1, true
     //  br i1 %ToLoad1, label %cond.load, label %else
     //
     if (Idx > 0) {
       Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
       Phi->addIncoming(VResult, CondBlock);
       Phi->addIncoming(PrevPhi, PrevIfBlock);
       PrevPhi = Phi;
       VResult = Phi;
     }
 
     Value *Predicate = Builder.CreateExtractElement(Mask,
                                                     Builder.getInt32(Idx),
                                                     "Mask" + Twine(Idx));
     Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
                                     ConstantInt::get(Predicate->getType(), 1),
                                     "ToLoad" + Twine(Idx));
 
     // Create "cond" block
     //
     //  %EltAddr = getelementptr i32* %1, i32 0
     //  %Elt = load i32* %EltAddr
     //  VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
     //
     CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.load");
     Builder.SetInsertPoint(InsertPt);
 
     Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
                                               "Ptr" + Twine(Idx));
     LoadInst *Load = Builder.CreateAlignedLoad(Ptr, AlignVal,
                                                "Load" + Twine(Idx));
     VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx),
                                           "Res" + Twine(Idx));
 
     // Create "else" block, fill it in the next iteration
     BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
     Builder.SetInsertPoint(InsertPt);
     Instruction *OldBr = IfBlock->getTerminator();
     BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
     OldBr->eraseFromParent();
     PrevIfBlock = IfBlock;
     IfBlock = NewIfBlock;
   }
 
   Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
   Phi->addIncoming(VResult, CondBlock);
   Phi->addIncoming(PrevPhi, PrevIfBlock);
   Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
   CI->replaceAllUsesWith(NewI);
   CI->eraseFromParent();
 }
 
 // Translate a masked scatter intrinsic, like
 // void @llvm.masked.scatter.v16i32(<16 x i32> %Src, <16 x i32*>* %Ptrs, i32 4,
 //                                  <16 x i1> %Mask)
 // to a chain of basic blocks, that stores element one-by-one if
 // the appropriate mask bit is set.
 //
 // % Ptrs = getelementptr i32, i32* %ptr, <16 x i64> %ind
 // % Mask0 = extractelement <16 x i1> % Mask, i32 0
 // % ToStore0 = icmp eq i1 % Mask0, true
 // br i1 %ToStore0, label %cond.store, label %else
 //
 // cond.store:
 // % Elt0 = extractelement <16 x i32> %Src, i32 0
 // % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
 // store i32 %Elt0, i32* % Ptr0, align 4
 // br label %else
 //
 // else:
 // % Mask1 = extractelement <16 x i1> % Mask, i32 1
 // % ToStore1 = icmp eq i1 % Mask1, true
 // br i1 % ToStore1, label %cond.store1, label %else2
 //
 // cond.store1:
 // % Elt1 = extractelement <16 x i32> %Src, i32 1
 // % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
 // store i32 % Elt1, i32* % Ptr1, align 4
 // br label %else2
 //   . . .
 static void ScalarizeMaskedScatter(CallInst *CI) {
   Value *Src = CI->getArgOperand(0);
   Value *Ptrs = CI->getArgOperand(1);
   Value *Alignment = CI->getArgOperand(2);
   Value *Mask = CI->getArgOperand(3);
 
   assert(isa<VectorType>(Src->getType()) &&
          "Unexpected data type in masked scatter intrinsic");
   assert(isa<VectorType>(Ptrs->getType()) &&
          isa<PointerType>(Ptrs->getType()->getVectorElementType()) &&
          "Vector of pointers is expected in masked scatter intrinsic");
 
   IRBuilder<> Builder(CI->getContext());
   Instruction *InsertPt = CI;
   BasicBlock *IfBlock = CI->getParent();
   Builder.SetInsertPoint(InsertPt);
   Builder.SetCurrentDebugLocation(CI->getDebugLoc());
 
   unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
   unsigned VectorWidth = Src->getType()->getVectorNumElements();
 
   // Shorten the way if the mask is a vector of constants.
   bool IsConstMask = isa<ConstantVector>(Mask);
 
   if (IsConstMask) {
     for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
       if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
         continue;
       Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
                                                    "Elt" + Twine(Idx));
       Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
                                                 "Ptr" + Twine(Idx));
       Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
     }
     CI->eraseFromParent();
     return;
   }
   for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
     // Fill the "else" block, created in the previous iteration
     //
     //  % Mask1 = extractelement <16 x i1> % Mask, i32 Idx
     //  % ToStore = icmp eq i1 % Mask1, true
     //  br i1 % ToStore, label %cond.store, label %else
     //
     Value *Predicate = Builder.CreateExtractElement(Mask,
                                                     Builder.getInt32(Idx),
                                                     "Mask" + Twine(Idx));
     Value *Cmp =
        Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
                           ConstantInt::get(Predicate->getType(), 1),
                           "ToStore" + Twine(Idx));
 
     // Create "cond" block
     //
     //  % Elt1 = extractelement <16 x i32> %Src, i32 1
     //  % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
     //  %store i32 % Elt1, i32* % Ptr1
     //
     BasicBlock *CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
     Builder.SetInsertPoint(InsertPt);
 
     Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
                                                  "Elt" + Twine(Idx));
     Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
                                               "Ptr" + Twine(Idx));
     Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
 
     // Create "else" block, fill it in the next iteration
     BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
     Builder.SetInsertPoint(InsertPt);
     Instruction *OldBr = IfBlock->getTerminator();
     BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
     OldBr->eraseFromParent();
     IfBlock = NewIfBlock;
   }
   CI->eraseFromParent();
 }
 
 /// If counting leading or trailing zeros is an expensive operation and a zero
 /// input is defined, add a check for zero to avoid calling the intrinsic.
 ///
 /// We want to transform:
 ///     %z = call i64 @llvm.cttz.i64(i64 %A, i1 false)
 ///
 /// into:
 ///   entry:
 ///     %cmpz = icmp eq i64 %A, 0
 ///     br i1 %cmpz, label %cond.end, label %cond.false
 ///   cond.false:
 ///     %z = call i64 @llvm.cttz.i64(i64 %A, i1 true)
 ///     br label %cond.end
 ///   cond.end:
 ///     %ctz = phi i64 [ 64, %entry ], [ %z, %cond.false ]
 ///
 /// If the transform is performed, return true and set ModifiedDT to true.
 static bool despeculateCountZeros(IntrinsicInst *CountZeros,
                                   const TargetLowering *TLI,
                                   const DataLayout *DL,
                                   bool &ModifiedDT) {
   if (!TLI || !DL)
     return false;
 
   // If a zero input is undefined, it doesn't make sense to despeculate that.
   if (match(CountZeros->getOperand(1), m_One()))
     return false;
 
   // If it's cheap to speculate, there's nothing to do.
   auto IntrinsicID = CountZeros->getIntrinsicID();
   if ((IntrinsicID == Intrinsic::cttz && TLI->isCheapToSpeculateCttz()) ||
       (IntrinsicID == Intrinsic::ctlz && TLI->isCheapToSpeculateCtlz()))
     return false;
 
   // Only handle legal scalar cases. Anything else requires too much work.
   Type *Ty = CountZeros->getType();
   unsigned SizeInBits = Ty->getPrimitiveSizeInBits();
   if (Ty->isVectorTy() || SizeInBits > DL->getLargestLegalIntTypeSize())
     return false;
 
   // The intrinsic will be sunk behind a compare against zero and branch.
   BasicBlock *StartBlock = CountZeros->getParent();
   BasicBlock *CallBlock = StartBlock->splitBasicBlock(CountZeros, "cond.false");
 
   // Create another block after the count zero intrinsic. A PHI will be added
   // in this block to select the result of the intrinsic or the bit-width
   // constant if the input to the intrinsic is zero.
   BasicBlock::iterator SplitPt = ++(BasicBlock::iterator(CountZeros));
   BasicBlock *EndBlock = CallBlock->splitBasicBlock(SplitPt, "cond.end");
 
   // Set up a builder to create a compare, conditional branch, and PHI.
   IRBuilder<> Builder(CountZeros->getContext());
   Builder.SetInsertPoint(StartBlock->getTerminator());
   Builder.SetCurrentDebugLocation(CountZeros->getDebugLoc());
 
   // Replace the unconditional branch that was created by the first split with
   // a compare against zero and a conditional branch.
   Value *Zero = Constant::getNullValue(Ty);
   Value *Cmp = Builder.CreateICmpEQ(CountZeros->getOperand(0), Zero, "cmpz");
   Builder.CreateCondBr(Cmp, EndBlock, CallBlock);
   StartBlock->getTerminator()->eraseFromParent();
 
   // Create a PHI in the end block to select either the output of the intrinsic
   // or the bit width of the operand.
   Builder.SetInsertPoint(&EndBlock->front());
   PHINode *PN = Builder.CreatePHI(Ty, 2, "ctz");
   CountZeros->replaceAllUsesWith(PN);
   Value *BitWidth = Builder.getInt(APInt(SizeInBits, SizeInBits));
   PN->addIncoming(BitWidth, StartBlock);
   PN->addIncoming(CountZeros, CallBlock);
 
   // We are explicitly handling the zero case, so we can set the intrinsic's
   // undefined zero argument to 'true'. This will also prevent reprocessing the
   // intrinsic; we only despeculate when a zero input is defined.
   CountZeros->setArgOperand(1, Builder.getTrue());
   ModifiedDT = true;
   return true;
 }
 
 bool CodeGenPrepare::optimizeCallInst(CallInst *CI, bool& ModifiedDT) {
   BasicBlock *BB = CI->getParent();
 
   // Lower inline assembly if we can.
   // If we found an inline asm expession, and if the target knows how to
   // lower it to normal LLVM code, do so now.
   if (TLI && isa<InlineAsm>(CI->getCalledValue())) {
     if (TLI->ExpandInlineAsm(CI)) {
       // Avoid invalidating the iterator.
       CurInstIterator = BB->begin();
       // Avoid processing instructions out of order, which could cause
       // reuse before a value is defined.
       SunkAddrs.clear();
       return true;
     }
     // Sink address computing for memory operands into the block.
     if (optimizeInlineAsmInst(CI))
       return true;
   }
 
   // Align the pointer arguments to this call if the target thinks it's a good
   // idea
   unsigned MinSize, PrefAlign;
   if (TLI && TLI->shouldAlignPointerArgs(CI, MinSize, PrefAlign)) {
     for (auto &Arg : CI->arg_operands()) {
       // We want to align both objects whose address is used directly and
       // objects whose address is used in casts and GEPs, though it only makes
       // sense for GEPs if the offset is a multiple of the desired alignment and
       // if size - offset meets the size threshold.
       if (!Arg->getType()->isPointerTy())
         continue;
       APInt Offset(DL->getPointerSizeInBits(
                        cast<PointerType>(Arg->getType())->getAddressSpace()),
                    0);
       Value *Val = Arg->stripAndAccumulateInBoundsConstantOffsets(*DL, Offset);
       uint64_t Offset2 = Offset.getLimitedValue();
       if ((Offset2 & (PrefAlign-1)) != 0)
         continue;
       AllocaInst *AI;
       if ((AI = dyn_cast<AllocaInst>(Val)) && AI->getAlignment() < PrefAlign &&
           DL->getTypeAllocSize(AI->getAllocatedType()) >= MinSize + Offset2)
         AI->setAlignment(PrefAlign);
       // Global variables can only be aligned if they are defined in this
       // object (i.e. they are uniquely initialized in this object), and
       // over-aligning global variables that have an explicit section is
       // forbidden.
       GlobalVariable *GV;
-      if ((GV = dyn_cast<GlobalVariable>(Val)) && GV->hasUniqueInitializer() &&
-          !GV->hasSection() && GV->getAlignment() < PrefAlign &&
+      if ((GV = dyn_cast<GlobalVariable>(Val)) && GV->canIncreaseAlignment() &&
+          GV->getAlignment() < PrefAlign &&
           DL->getTypeAllocSize(GV->getType()->getElementType()) >=
               MinSize + Offset2)
         GV->setAlignment(PrefAlign);
     }
     // If this is a memcpy (or similar) then we may be able to improve the
     // alignment
     if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(CI)) {
       unsigned Align = getKnownAlignment(MI->getDest(), *DL);
       if (MemTransferInst *MTI = dyn_cast<MemTransferInst>(MI))
         Align = std::min(Align, getKnownAlignment(MTI->getSource(), *DL));
       if (Align > MI->getAlignment())
         MI->setAlignment(ConstantInt::get(MI->getAlignmentType(), Align));
     }
   }
 
   IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
   if (II) {
     switch (II->getIntrinsicID()) {
     default: break;
     case Intrinsic::objectsize: {
       // Lower all uses of llvm.objectsize.*
       bool Min = (cast<ConstantInt>(II->getArgOperand(1))->getZExtValue() == 1);
       Type *ReturnTy = CI->getType();
       Constant *RetVal = ConstantInt::get(ReturnTy, Min ? 0 : -1ULL);
 
       // Substituting this can cause recursive simplifications, which can
       // invalidate our iterator.  Use a WeakVH to hold onto it in case this
       // happens.
       WeakVH IterHandle(&*CurInstIterator);
 
       replaceAndRecursivelySimplify(CI, RetVal,
                                     TLInfo, nullptr);
 
       // If the iterator instruction was recursively deleted, start over at the
       // start of the block.
       if (IterHandle != CurInstIterator.getNodePtrUnchecked()) {
         CurInstIterator = BB->begin();
         SunkAddrs.clear();
       }
       return true;
     }
     case Intrinsic::masked_load: {
       // Scalarize unsupported vector masked load
       if (!TTI->isLegalMaskedLoad(CI->getType())) {
         ScalarizeMaskedLoad(CI);
         ModifiedDT = true;
         return true;
       }
       return false;
     }
     case Intrinsic::masked_store: {
       if (!TTI->isLegalMaskedStore(CI->getArgOperand(0)->getType())) {
         ScalarizeMaskedStore(CI);
         ModifiedDT = true;
         return true;
       }
       return false;
     }
     case Intrinsic::masked_gather: {
       if (!TTI->isLegalMaskedGather(CI->getType())) {
         ScalarizeMaskedGather(CI);
         ModifiedDT = true;
         return true;
       }
       return false;
     }
     case Intrinsic::masked_scatter: {
       if (!TTI->isLegalMaskedScatter(CI->getArgOperand(0)->getType())) {
         ScalarizeMaskedScatter(CI);
         ModifiedDT = true;
         return true;
       }
       return false;
     }
     case Intrinsic::aarch64_stlxr:
     case Intrinsic::aarch64_stxr: {
       ZExtInst *ExtVal = dyn_cast<ZExtInst>(CI->getArgOperand(0));
       if (!ExtVal || !ExtVal->hasOneUse() ||
           ExtVal->getParent() == CI->getParent())
         return false;
       // Sink a zext feeding stlxr/stxr before it, so it can be folded into it.
       ExtVal->moveBefore(CI);
       // Mark this instruction as "inserted by CGP", so that other
       // optimizations don't touch it.
       InsertedInsts.insert(ExtVal);
       return true;
     }
     case Intrinsic::invariant_group_barrier:
       II->replaceAllUsesWith(II->getArgOperand(0));
       II->eraseFromParent();
       return true;
 
     case Intrinsic::cttz:
     case Intrinsic::ctlz:
       // If counting zeros is expensive, try to avoid it.
       return despeculateCountZeros(II, TLI, DL, ModifiedDT);
     }
 
     if (TLI) {
       // Unknown address space.
       // TODO: Target hook to pick which address space the intrinsic cares
       // about?
       unsigned AddrSpace = ~0u;
       SmallVector<Value*, 2> PtrOps;
       Type *AccessTy;
       if (TLI->GetAddrModeArguments(II, PtrOps, AccessTy, AddrSpace))
         while (!PtrOps.empty())
           if (optimizeMemoryInst(II, PtrOps.pop_back_val(), AccessTy, AddrSpace))
             return true;
     }
   }
 
   // From here on out we're working with named functions.
   if (!CI->getCalledFunction()) return false;
 
   // Lower all default uses of _chk calls.  This is very similar
   // to what InstCombineCalls does, but here we are only lowering calls
   // to fortified library functions (e.g. __memcpy_chk) that have the default
   // "don't know" as the objectsize.  Anything else should be left alone.
   FortifiedLibCallSimplifier Simplifier(TLInfo, true);
   if (Value *V = Simplifier.optimizeCall(CI)) {
     CI->replaceAllUsesWith(V);
     CI->eraseFromParent();
     return true;
   }
   return false;
 }
 
 /// Look for opportunities to duplicate return instructions to the predecessor
 /// to enable tail call optimizations. The case it is currently looking for is:
 /// @code
 /// bb0:
 ///   %tmp0 = tail call i32 @f0()
 ///   br label %return
 /// bb1:
 ///   %tmp1 = tail call i32 @f1()
 ///   br label %return
 /// bb2:
 ///   %tmp2 = tail call i32 @f2()
 ///   br label %return
 /// return:
 ///   %retval = phi i32 [ %tmp0, %bb0 ], [ %tmp1, %bb1 ], [ %tmp2, %bb2 ]
 ///   ret i32 %retval
 /// @endcode
 ///
 /// =>
 ///
 /// @code
 /// bb0:
 ///   %tmp0 = tail call i32 @f0()
 ///   ret i32 %tmp0
 /// bb1:
 ///   %tmp1 = tail call i32 @f1()
 ///   ret i32 %tmp1
 /// bb2:
 ///   %tmp2 = tail call i32 @f2()
 ///   ret i32 %tmp2
 /// @endcode
 bool CodeGenPrepare::dupRetToEnableTailCallOpts(BasicBlock *BB) {
   if (!TLI)
     return false;
 
   ReturnInst *RI = dyn_cast<ReturnInst>(BB->getTerminator());
   if (!RI)
     return false;
 
   PHINode *PN = nullptr;
   BitCastInst *BCI = nullptr;
   Value *V = RI->getReturnValue();
   if (V) {
     BCI = dyn_cast<BitCastInst>(V);
     if (BCI)
       V = BCI->getOperand(0);
 
     PN = dyn_cast<PHINode>(V);
     if (!PN)
       return false;
   }
 
   if (PN && PN->getParent() != BB)
     return false;
 
   // It's not safe to eliminate the sign / zero extension of the return value.
   // See llvm::isInTailCallPosition().
   const Function *F = BB->getParent();
   AttributeSet CallerAttrs = F->getAttributes();
   if (CallerAttrs.hasAttribute(AttributeSet::ReturnIndex, Attribute::ZExt) ||
       CallerAttrs.hasAttribute(AttributeSet::ReturnIndex, Attribute::SExt))
     return false;
 
   // Make sure there are no instructions between the PHI and return, or that the
   // return is the first instruction in the block.
   if (PN) {
     BasicBlock::iterator BI = BB->begin();
     do { ++BI; } while (isa<DbgInfoIntrinsic>(BI));
     if (&*BI == BCI)
       // Also skip over the bitcast.
       ++BI;
     if (&*BI != RI)
       return false;
   } else {
     BasicBlock::iterator BI = BB->begin();
     while (isa<DbgInfoIntrinsic>(BI)) ++BI;
     if (&*BI != RI)
       return false;
   }
 
   /// Only dup the ReturnInst if the CallInst is likely to be emitted as a tail
   /// call.
   SmallVector<CallInst*, 4> TailCalls;
   if (PN) {
     for (unsigned I = 0, E = PN->getNumIncomingValues(); I != E; ++I) {
       CallInst *CI = dyn_cast<CallInst>(PN->getIncomingValue(I));
       // Make sure the phi value is indeed produced by the tail call.
       if (CI && CI->hasOneUse() && CI->getParent() == PN->getIncomingBlock(I) &&
           TLI->mayBeEmittedAsTailCall(CI))
         TailCalls.push_back(CI);
     }
   } else {
     SmallPtrSet<BasicBlock*, 4> VisitedBBs;
     for (pred_iterator PI = pred_begin(BB), PE = pred_end(BB); PI != PE; ++PI) {
       if (!VisitedBBs.insert(*PI).second)
         continue;
 
       BasicBlock::InstListType &InstList = (*PI)->getInstList();
       BasicBlock::InstListType::reverse_iterator RI = InstList.rbegin();
       BasicBlock::InstListType::reverse_iterator RE = InstList.rend();
       do { ++RI; } while (RI != RE && isa<DbgInfoIntrinsic>(&*RI));
       if (RI == RE)
         continue;
 
       CallInst *CI = dyn_cast<CallInst>(&*RI);
       if (CI && CI->use_empty() && TLI->mayBeEmittedAsTailCall(CI))
         TailCalls.push_back(CI);
     }
   }
 
   bool Changed = false;
   for (unsigned i = 0, e = TailCalls.size(); i != e; ++i) {
     CallInst *CI = TailCalls[i];
     CallSite CS(CI);
 
     // Conservatively require the attributes of the call to match those of the
     // return. Ignore noalias because it doesn't affect the call sequence.
     AttributeSet CalleeAttrs = CS.getAttributes();
     if (AttrBuilder(CalleeAttrs, AttributeSet::ReturnIndex).
           removeAttribute(Attribute::NoAlias) !=
         AttrBuilder(CalleeAttrs, AttributeSet::ReturnIndex).
           removeAttribute(Attribute::NoAlias))
       continue;
 
     // Make sure the call instruction is followed by an unconditional branch to
     // the return block.
     BasicBlock *CallBB = CI->getParent();
     BranchInst *BI = dyn_cast<BranchInst>(CallBB->getTerminator());
     if (!BI || !BI->isUnconditional() || BI->getSuccessor(0) != BB)
       continue;
 
     // Duplicate the return into CallBB.
     (void)FoldReturnIntoUncondBranch(RI, BB, CallBB);
     ModifiedDT = Changed = true;
     ++NumRetsDup;
   }
 
   // If we eliminated all predecessors of the block, delete the block now.
   if (Changed && !BB->hasAddressTaken() && pred_begin(BB) == pred_end(BB))
     BB->eraseFromParent();
 
   return Changed;
 }
 
 //===----------------------------------------------------------------------===//
 // Memory Optimization
 //===----------------------------------------------------------------------===//
 
 namespace {
 
 /// This is an extended version of TargetLowering::AddrMode
 /// which holds actual Value*'s for register values.
 struct ExtAddrMode : public TargetLowering::AddrMode {
   Value *BaseReg;
   Value *ScaledReg;
   ExtAddrMode() : BaseReg(nullptr), ScaledReg(nullptr) {}
   void print(raw_ostream &OS) const;
   void dump() const;
 
   bool operator==(const ExtAddrMode& O) const {
     return (BaseReg == O.BaseReg) && (ScaledReg == O.ScaledReg) &&
            (BaseGV == O.BaseGV) && (BaseOffs == O.BaseOffs) &&
            (HasBaseReg == O.HasBaseReg) && (Scale == O.Scale);
   }
 };
 
 #ifndef NDEBUG
 static inline raw_ostream &operator<<(raw_ostream &OS, const ExtAddrMode &AM) {
   AM.print(OS);
   return OS;
 }
 #endif
 
 void ExtAddrMode::print(raw_ostream &OS) const {
   bool NeedPlus = false;
   OS << "[";
   if (BaseGV) {
     OS << (NeedPlus ? " + " : "")
        << "GV:";
     BaseGV->printAsOperand(OS, /*PrintType=*/false);
     NeedPlus = true;
   }
 
   if (BaseOffs) {
     OS << (NeedPlus ? " + " : "")
        << BaseOffs;
     NeedPlus = true;
   }
 
   if (BaseReg) {
     OS << (NeedPlus ? " + " : "")
        << "Base:";
     BaseReg->printAsOperand(OS, /*PrintType=*/false);
     NeedPlus = true;
   }
   if (Scale) {
     OS << (NeedPlus ? " + " : "")
        << Scale << "*";
     ScaledReg->printAsOperand(OS, /*PrintType=*/false);
   }
 
   OS << ']';
 }
 
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 void ExtAddrMode::dump() const {
   print(dbgs());
   dbgs() << '\n';
 }
 #endif
 
 /// \brief This class provides transaction based operation on the IR.
 /// Every change made through this class is recorded in the internal state and
 /// can be undone (rollback) until commit is called.
 class TypePromotionTransaction {
 
   /// \brief This represents the common interface of the individual transaction.
   /// Each class implements the logic for doing one specific modification on
   /// the IR via the TypePromotionTransaction.
   class TypePromotionAction {
   protected:
     /// The Instruction modified.
     Instruction *Inst;
 
   public:
     /// \brief Constructor of the action.
     /// The constructor performs the related action on the IR.
     TypePromotionAction(Instruction *Inst) : Inst(Inst) {}
 
     virtual ~TypePromotionAction() {}
 
     /// \brief Undo the modification done by this action.
     /// When this method is called, the IR must be in the same state as it was
     /// before this action was applied.
     /// \pre Undoing the action works if and only if the IR is in the exact same
     /// state as it was directly after this action was applied.
     virtual void undo() = 0;
 
     /// \brief Advocate every change made by this action.
     /// When the results on the IR of the action are to be kept, it is important
     /// to call this function, otherwise hidden information may be kept forever.
     virtual void commit() {
       // Nothing to be done, this action is not doing anything.
     }
   };
 
   /// \brief Utility to remember the position of an instruction.
   class InsertionHandler {
     /// Position of an instruction.
     /// Either an instruction:
     /// - Is the first in a basic block: BB is used.
     /// - Has a previous instructon: PrevInst is used.
     union {
       Instruction *PrevInst;
       BasicBlock *BB;
     } Point;
     /// Remember whether or not the instruction had a previous instruction.
     bool HasPrevInstruction;
 
   public:
     /// \brief Record the position of \p Inst.
     InsertionHandler(Instruction *Inst) {
       BasicBlock::iterator It = Inst->getIterator();
       HasPrevInstruction = (It != (Inst->getParent()->begin()));
       if (HasPrevInstruction)
         Point.PrevInst = &*--It;
       else
         Point.BB = Inst->getParent();
     }
 
     /// \brief Insert \p Inst at the recorded position.
     void insert(Instruction *Inst) {
       if (HasPrevInstruction) {
         if (Inst->getParent())
           Inst->removeFromParent();
         Inst->insertAfter(Point.PrevInst);
       } else {
         Instruction *Position = &*Point.BB->getFirstInsertionPt();
         if (Inst->getParent())
           Inst->moveBefore(Position);
         else
           Inst->insertBefore(Position);
       }
     }
   };
 
   /// \brief Move an instruction before another.
   class InstructionMoveBefore : public TypePromotionAction {
     /// Original position of the instruction.
     InsertionHandler Position;
 
   public:
     /// \brief Move \p Inst before \p Before.
     InstructionMoveBefore(Instruction *Inst, Instruction *Before)
         : TypePromotionAction(Inst), Position(Inst) {
       DEBUG(dbgs() << "Do: move: " << *Inst << "\nbefore: " << *Before << "\n");
       Inst->moveBefore(Before);
     }
 
     /// \brief Move the instruction back to its original position.
     void undo() override {
       DEBUG(dbgs() << "Undo: moveBefore: " << *Inst << "\n");
       Position.insert(Inst);
     }
   };
 
   /// \brief Set the operand of an instruction with a new value.
   class OperandSetter : public TypePromotionAction {
     /// Original operand of the instruction.
     Value *Origin;
     /// Index of the modified instruction.
     unsigned Idx;
 
   public:
     /// \brief Set \p Idx operand of \p Inst with \p NewVal.
     OperandSetter(Instruction *Inst, unsigned Idx, Value *NewVal)
         : TypePromotionAction(Inst), Idx(Idx) {
       DEBUG(dbgs() << "Do: setOperand: " << Idx << "\n"
                    << "for:" << *Inst << "\n"
                    << "with:" << *NewVal << "\n");
       Origin = Inst->getOperand(Idx);
       Inst->setOperand(Idx, NewVal);
     }
 
     /// \brief Restore the original value of the instruction.
     void undo() override {
       DEBUG(dbgs() << "Undo: setOperand:" << Idx << "\n"
                    << "for: " << *Inst << "\n"
                    << "with: " << *Origin << "\n");
       Inst->setOperand(Idx, Origin);
     }
   };
 
   /// \brief Hide the operands of an instruction.
   /// Do as if this instruction was not using any of its operands.
   class OperandsHider : public TypePromotionAction {
     /// The list of original operands.
     SmallVector<Value *, 4> OriginalValues;
 
   public:
     /// \brief Remove \p Inst from the uses of the operands of \p Inst.
     OperandsHider(Instruction *Inst) : TypePromotionAction(Inst) {
       DEBUG(dbgs() << "Do: OperandsHider: " << *Inst << "\n");
       unsigned NumOpnds = Inst->getNumOperands();
       OriginalValues.reserve(NumOpnds);
       for (unsigned It = 0; It < NumOpnds; ++It) {
         // Save the current operand.
         Value *Val = Inst->getOperand(It);
         OriginalValues.push_back(Val);
         // Set a dummy one.
         // We could use OperandSetter here, but that would imply an overhead
         // that we are not willing to pay.
         Inst->setOperand(It, UndefValue::get(Val->getType()));
       }
     }
 
     /// \brief Restore the original list of uses.
     void undo() override {
       DEBUG(dbgs() << "Undo: OperandsHider: " << *Inst << "\n");
       for (unsigned It = 0, EndIt = OriginalValues.size(); It != EndIt; ++It)
         Inst->setOperand(It, OriginalValues[It]);
     }
   };
 
   /// \brief Build a truncate instruction.
   class TruncBuilder : public TypePromotionAction {
     Value *Val;
   public:
     /// \brief Build a truncate instruction of \p Opnd producing a \p Ty
     /// result.
     /// trunc Opnd to Ty.
     TruncBuilder(Instruction *Opnd, Type *Ty) : TypePromotionAction(Opnd) {
       IRBuilder<> Builder(Opnd);
       Val = Builder.CreateTrunc(Opnd, Ty, "promoted");
       DEBUG(dbgs() << "Do: TruncBuilder: " << *Val << "\n");
     }
 
     /// \brief Get the built value.
     Value *getBuiltValue() { return Val; }
 
     /// \brief Remove the built instruction.
     void undo() override {
       DEBUG(dbgs() << "Undo: TruncBuilder: " << *Val << "\n");
       if (Instruction *IVal = dyn_cast<Instruction>(Val))
         IVal->eraseFromParent();
     }
   };
 
   /// \brief Build a sign extension instruction.
   class SExtBuilder : public TypePromotionAction {
     Value *Val;
   public:
     /// \brief Build a sign extension instruction of \p Opnd producing a \p Ty
     /// result.
     /// sext Opnd to Ty.
     SExtBuilder(Instruction *InsertPt, Value *Opnd, Type *Ty)
         : TypePromotionAction(InsertPt) {
       IRBuilder<> Builder(InsertPt);
       Val = Builder.CreateSExt(Opnd, Ty, "promoted");
       DEBUG(dbgs() << "Do: SExtBuilder: " << *Val << "\n");
     }
 
     /// \brief Get the built value.
     Value *getBuiltValue() { return Val; }
 
     /// \brief Remove the built instruction.
     void undo() override {
       DEBUG(dbgs() << "Undo: SExtBuilder: " << *Val << "\n");
       if (Instruction *IVal = dyn_cast<Instruction>(Val))
         IVal->eraseFromParent();
     }
   };
 
   /// \brief Build a zero extension instruction.
   class ZExtBuilder : public TypePromotionAction {
     Value *Val;
   public:
     /// \brief Build a zero extension instruction of \p Opnd producing a \p Ty
     /// result.
     /// zext Opnd to Ty.
     ZExtBuilder(Instruction *InsertPt, Value *Opnd, Type *Ty)
         : TypePromotionAction(InsertPt) {
       IRBuilder<> Builder(InsertPt);
       Val = Builder.CreateZExt(Opnd, Ty, "promoted");
       DEBUG(dbgs() << "Do: ZExtBuilder: " << *Val << "\n");
     }
 
     /// \brief Get the built value.
     Value *getBuiltValue() { return Val; }
 
     /// \brief Remove the built instruction.
     void undo() override {
       DEBUG(dbgs() << "Undo: ZExtBuilder: " << *Val << "\n");
       if (Instruction *IVal = dyn_cast<Instruction>(Val))
         IVal->eraseFromParent();
     }
   };
 
   /// \brief Mutate an instruction to another type.
   class TypeMutator : public TypePromotionAction {
     /// Record the original type.
     Type *OrigTy;
 
   public:
     /// \brief Mutate the type of \p Inst into \p NewTy.
     TypeMutator(Instruction *Inst, Type *NewTy)
         : TypePromotionAction(Inst), OrigTy(Inst->getType()) {
       DEBUG(dbgs() << "Do: MutateType: " << *Inst << " with " << *NewTy
                    << "\n");
       Inst->mutateType(NewTy);
     }
 
     /// \brief Mutate the instruction back to its original type.
     void undo() override {
       DEBUG(dbgs() << "Undo: MutateType: " << *Inst << " with " << *OrigTy
                    << "\n");
       Inst->mutateType(OrigTy);
     }
   };
 
   /// \brief Replace the uses of an instruction by another instruction.
   class UsesReplacer : public TypePromotionAction {
     /// Helper structure to keep track of the replaced uses.
     struct InstructionAndIdx {
       /// The instruction using the instruction.
       Instruction *Inst;
       /// The index where this instruction is used for Inst.
       unsigned Idx;
       InstructionAndIdx(Instruction *Inst, unsigned Idx)
           : Inst(Inst), Idx(Idx) {}
     };
 
     /// Keep track of the original uses (pair Instruction, Index).
     SmallVector<InstructionAndIdx, 4> OriginalUses;
     typedef SmallVectorImpl<InstructionAndIdx>::iterator use_iterator;
 
   public:
     /// \brief Replace all the use of \p Inst by \p New.
     UsesReplacer(Instruction *Inst, Value *New) : TypePromotionAction(Inst) {
       DEBUG(dbgs() << "Do: UsersReplacer: " << *Inst << " with " << *New
                    << "\n");
       // Record the original uses.
       for (Use &U : Inst->uses()) {
         Instruction *UserI = cast<Instruction>(U.getUser());
         OriginalUses.push_back(InstructionAndIdx(UserI, U.getOperandNo()));
       }
       // Now, we can replace the uses.
       Inst->replaceAllUsesWith(New);
     }
 
     /// \brief Reassign the original uses of Inst to Inst.
     void undo() override {
       DEBUG(dbgs() << "Undo: UsersReplacer: " << *Inst << "\n");
       for (use_iterator UseIt = OriginalUses.begin(),
                         EndIt = OriginalUses.end();
            UseIt != EndIt; ++UseIt) {
         UseIt->Inst->setOperand(UseIt->Idx, Inst);
       }
     }
   };
 
   /// \brief Remove an instruction from the IR.
   class InstructionRemover : public TypePromotionAction {
     /// Original position of the instruction.
     InsertionHandler Inserter;
     /// Helper structure to hide all the link to the instruction. In other
     /// words, this helps to do as if the instruction was removed.
     OperandsHider Hider;
     /// Keep track of the uses replaced, if any.
     UsesReplacer *Replacer;
 
   public:
     /// \brief Remove all reference of \p Inst and optinally replace all its
     /// uses with New.
     /// \pre If !Inst->use_empty(), then New != nullptr
     InstructionRemover(Instruction *Inst, Value *New = nullptr)
         : TypePromotionAction(Inst), Inserter(Inst), Hider(Inst),
           Replacer(nullptr) {
       if (New)
         Replacer = new UsesReplacer(Inst, New);
       DEBUG(dbgs() << "Do: InstructionRemover: " << *Inst << "\n");
       Inst->removeFromParent();
     }
 
     ~InstructionRemover() override { delete Replacer; }
 
     /// \brief Really remove the instruction.
     void commit() override { delete Inst; }
 
     /// \brief Resurrect the instruction and reassign it to the proper uses if
     /// new value was provided when build this action.
     void undo() override {
       DEBUG(dbgs() << "Undo: InstructionRemover: " << *Inst << "\n");
       Inserter.insert(Inst);
       if (Replacer)
         Replacer->undo();
       Hider.undo();
     }
   };
 
 public:
   /// Restoration point.
   /// The restoration point is a pointer to an action instead of an iterator
   /// because the iterator may be invalidated but not the pointer.
   typedef const TypePromotionAction *ConstRestorationPt;
   /// Advocate every changes made in that transaction.
   void commit();
   /// Undo all the changes made after the given point.
   void rollback(ConstRestorationPt Point);
   /// Get the current restoration point.
   ConstRestorationPt getRestorationPoint() const;
 
   /// \name API for IR modification with state keeping to support rollback.
   /// @{
   /// Same as Instruction::setOperand.
   void setOperand(Instruction *Inst, unsigned Idx, Value *NewVal);
   /// Same as Instruction::eraseFromParent.
   void eraseInstruction(Instruction *Inst, Value *NewVal = nullptr);
   /// Same as Value::replaceAllUsesWith.
   void replaceAllUsesWith(Instruction *Inst, Value *New);
   /// Same as Value::mutateType.
   void mutateType(Instruction *Inst, Type *NewTy);
   /// Same as IRBuilder::createTrunc.
   Value *createTrunc(Instruction *Opnd, Type *Ty);
   /// Same as IRBuilder::createSExt.
   Value *createSExt(Instruction *Inst, Value *Opnd, Type *Ty);
   /// Same as IRBuilder::createZExt.
   Value *createZExt(Instruction *Inst, Value *Opnd, Type *Ty);
   /// Same as Instruction::moveBefore.
   void moveBefore(Instruction *Inst, Instruction *Before);
   /// @}
 
 private:
   /// The ordered list of actions made so far.
   SmallVector<std::unique_ptr<TypePromotionAction>, 16> Actions;
   typedef SmallVectorImpl<std::unique_ptr<TypePromotionAction>>::iterator CommitPt;
 };
 
 void TypePromotionTransaction::setOperand(Instruction *Inst, unsigned Idx,
                                           Value *NewVal) {
   Actions.push_back(
       make_unique<TypePromotionTransaction::OperandSetter>(Inst, Idx, NewVal));
 }
 
 void TypePromotionTransaction::eraseInstruction(Instruction *Inst,
                                                 Value *NewVal) {
   Actions.push_back(
       make_unique<TypePromotionTransaction::InstructionRemover>(Inst, NewVal));
 }
 
 void TypePromotionTransaction::replaceAllUsesWith(Instruction *Inst,
                                                   Value *New) {
   Actions.push_back(make_unique<TypePromotionTransaction::UsesReplacer>(Inst, New));
 }
 
 void TypePromotionTransaction::mutateType(Instruction *Inst, Type *NewTy) {
   Actions.push_back(make_unique<TypePromotionTransaction::TypeMutator>(Inst, NewTy));
 }
 
 Value *TypePromotionTransaction::createTrunc(Instruction *Opnd,
                                              Type *Ty) {
   std::unique_ptr<TruncBuilder> Ptr(new TruncBuilder(Opnd, Ty));
   Value *Val = Ptr->getBuiltValue();
   Actions.push_back(std::move(Ptr));
   return Val;
 }
 
 Value *TypePromotionTransaction::createSExt(Instruction *Inst,
                                             Value *Opnd, Type *Ty) {
   std::unique_ptr<SExtBuilder> Ptr(new SExtBuilder(Inst, Opnd, Ty));
   Value *Val = Ptr->getBuiltValue();
   Actions.push_back(std::move(Ptr));
   return Val;
 }
 
 Value *TypePromotionTransaction::createZExt(Instruction *Inst,
                                             Value *Opnd, Type *Ty) {
   std::unique_ptr<ZExtBuilder> Ptr(new ZExtBuilder(Inst, Opnd, Ty));
   Value *Val = Ptr->getBuiltValue();
   Actions.push_back(std::move(Ptr));
   return Val;
 }
 
 void TypePromotionTransaction::moveBefore(Instruction *Inst,
                                           Instruction *Before) {
   Actions.push_back(
       make_unique<TypePromotionTransaction::InstructionMoveBefore>(Inst, Before));
 }
 
 TypePromotionTransaction::ConstRestorationPt
 TypePromotionTransaction::getRestorationPoint() const {
   return !Actions.empty() ? Actions.back().get() : nullptr;
 }
 
 void TypePromotionTransaction::commit() {
   for (CommitPt It = Actions.begin(), EndIt = Actions.end(); It != EndIt;
        ++It)
     (*It)->commit();
   Actions.clear();
 }
 
 void TypePromotionTransaction::rollback(
     TypePromotionTransaction::ConstRestorationPt Point) {
   while (!Actions.empty() && Point != Actions.back().get()) {
     std::unique_ptr<TypePromotionAction> Curr = Actions.pop_back_val();
     Curr->undo();
   }
 }
 
 /// \brief A helper class for matching addressing modes.
 ///
 /// This encapsulates the logic for matching the target-legal addressing modes.
 class AddressingModeMatcher {
   SmallVectorImpl<Instruction*> &AddrModeInsts;
   const TargetMachine &TM;
   const TargetLowering &TLI;
   const DataLayout &DL;
 
   /// AccessTy/MemoryInst - This is the type for the access (e.g. double) and
   /// the memory instruction that we're computing this address for.
   Type *AccessTy;
   unsigned AddrSpace;
   Instruction *MemoryInst;
 
   /// This is the addressing mode that we're building up. This is
   /// part of the return value of this addressing mode matching stuff.
   ExtAddrMode &AddrMode;
 
   /// The instructions inserted by other CodeGenPrepare optimizations.
   const SetOfInstrs &InsertedInsts;
   /// A map from the instructions to their type before promotion.
   InstrToOrigTy &PromotedInsts;
   /// The ongoing transaction where every action should be registered.
   TypePromotionTransaction &TPT;
 
   /// This is set to true when we should not do profitability checks.
   /// When true, IsProfitableToFoldIntoAddressingMode always returns true.
   bool IgnoreProfitability;
 
   AddressingModeMatcher(SmallVectorImpl<Instruction *> &AMI,
                         const TargetMachine &TM, Type *AT, unsigned AS,
                         Instruction *MI, ExtAddrMode &AM,
                         const SetOfInstrs &InsertedInsts,
                         InstrToOrigTy &PromotedInsts,
                         TypePromotionTransaction &TPT)
       : AddrModeInsts(AMI), TM(TM),
         TLI(*TM.getSubtargetImpl(*MI->getParent()->getParent())
                  ->getTargetLowering()),
         DL(MI->getModule()->getDataLayout()), AccessTy(AT), AddrSpace(AS),
         MemoryInst(MI), AddrMode(AM), InsertedInsts(InsertedInsts),
         PromotedInsts(PromotedInsts), TPT(TPT) {
     IgnoreProfitability = false;
   }
 public:
 
   /// Find the maximal addressing mode that a load/store of V can fold,
   /// give an access type of AccessTy.  This returns a list of involved
   /// instructions in AddrModeInsts.
   /// \p InsertedInsts The instructions inserted by other CodeGenPrepare
   /// optimizations.
   /// \p PromotedInsts maps the instructions to their type before promotion.
   /// \p The ongoing transaction where every action should be registered.
   static ExtAddrMode Match(Value *V, Type *AccessTy, unsigned AS,
                            Instruction *MemoryInst,
                            SmallVectorImpl<Instruction*> &AddrModeInsts,
                            const TargetMachine &TM,
                            const SetOfInstrs &InsertedInsts,
                            InstrToOrigTy &PromotedInsts,
                            TypePromotionTransaction &TPT) {
     ExtAddrMode Result;
 
     bool Success = AddressingModeMatcher(AddrModeInsts, TM, AccessTy, AS,
                                          MemoryInst, Result, InsertedInsts,
                                          PromotedInsts, TPT).matchAddr(V, 0);
     (void)Success; assert(Success && "Couldn't select *anything*?");
     return Result;
   }
 private:
   bool matchScaledValue(Value *ScaleReg, int64_t Scale, unsigned Depth);
   bool matchAddr(Value *V, unsigned Depth);
   bool matchOperationAddr(User *Operation, unsigned Opcode, unsigned Depth,
                           bool *MovedAway = nullptr);
   bool isProfitableToFoldIntoAddressingMode(Instruction *I,
                                             ExtAddrMode &AMBefore,
                                             ExtAddrMode &AMAfter);
   bool valueAlreadyLiveAtInst(Value *Val, Value *KnownLive1, Value *KnownLive2);
   bool isPromotionProfitable(unsigned NewCost, unsigned OldCost,
                              Value *PromotedOperand) const;
 };
 
 /// Try adding ScaleReg*Scale to the current addressing mode.
 /// Return true and update AddrMode if this addr mode is legal for the target,
 /// false if not.
 bool AddressingModeMatcher::matchScaledValue(Value *ScaleReg, int64_t Scale,
                                              unsigned Depth) {
   // If Scale is 1, then this is the same as adding ScaleReg to the addressing
   // mode.  Just process that directly.
   if (Scale == 1)
     return matchAddr(ScaleReg, Depth);
 
   // If the scale is 0, it takes nothing to add this.
   if (Scale == 0)
     return true;
 
   // If we already have a scale of this value, we can add to it, otherwise, we
   // need an available scale field.
   if (AddrMode.Scale != 0 && AddrMode.ScaledReg != ScaleReg)
     return false;
 
   ExtAddrMode TestAddrMode = AddrMode;
 
   // Add scale to turn X*4+X*3 -> X*7.  This could also do things like
   // [A+B + A*7] -> [B+A*8].
   TestAddrMode.Scale += Scale;
   TestAddrMode.ScaledReg = ScaleReg;
 
   // If the new address isn't legal, bail out.
   if (!TLI.isLegalAddressingMode(DL, TestAddrMode, AccessTy, AddrSpace))
     return false;
 
   // It was legal, so commit it.
   AddrMode = TestAddrMode;
 
   // Okay, we decided that we can add ScaleReg+Scale to AddrMode.  Check now
   // to see if ScaleReg is actually X+C.  If so, we can turn this into adding
   // X*Scale + C*Scale to addr mode.
   ConstantInt *CI = nullptr; Value *AddLHS = nullptr;
   if (isa<Instruction>(ScaleReg) &&  // not a constant expr.
       match(ScaleReg, m_Add(m_Value(AddLHS), m_ConstantInt(CI)))) {
     TestAddrMode.ScaledReg = AddLHS;
     TestAddrMode.BaseOffs += CI->getSExtValue()*TestAddrMode.Scale;
 
     // If this addressing mode is legal, commit it and remember that we folded
     // this instruction.
     if (TLI.isLegalAddressingMode(DL, TestAddrMode, AccessTy, AddrSpace)) {
       AddrModeInsts.push_back(cast<Instruction>(ScaleReg));
       AddrMode = TestAddrMode;
       return true;
     }
   }
 
   // Otherwise, not (x+c)*scale, just return what we have.
   return true;
 }
 
 /// This is a little filter, which returns true if an addressing computation
 /// involving I might be folded into a load/store accessing it.
 /// This doesn't need to be perfect, but needs to accept at least
 /// the set of instructions that MatchOperationAddr can.
 static bool MightBeFoldableInst(Instruction *I) {
   switch (I->getOpcode()) {
   case Instruction::BitCast:
   case Instruction::AddrSpaceCast:
     // Don't touch identity bitcasts.
     if (I->getType() == I->getOperand(0)->getType())
       return false;
     return I->getType()->isPointerTy() || I->getType()->isIntegerTy();
   case Instruction::PtrToInt:
     // PtrToInt is always a noop, as we know that the int type is pointer sized.
     return true;
   case Instruction::IntToPtr:
     // We know the input is intptr_t, so this is foldable.
     return true;
   case Instruction::Add:
     return true;
   case Instruction::Mul:
   case Instruction::Shl:
     // Can only handle X*C and X << C.
     return isa<ConstantInt>(I->getOperand(1));
   case Instruction::GetElementPtr:
     return true;
   default:
     return false;
   }
 }
 
 /// \brief Check whether or not \p Val is a legal instruction for \p TLI.
 /// \note \p Val is assumed to be the product of some type promotion.
 /// Therefore if \p Val has an undefined state in \p TLI, this is assumed
 /// to be legal, as the non-promoted value would have had the same state.
 static bool isPromotedInstructionLegal(const TargetLowering &TLI,
                                        const DataLayout &DL, Value *Val) {
   Instruction *PromotedInst = dyn_cast<Instruction>(Val);
   if (!PromotedInst)
     return false;
   int ISDOpcode = TLI.InstructionOpcodeToISD(PromotedInst->getOpcode());
   // If the ISDOpcode is undefined, it was undefined before the promotion.
   if (!ISDOpcode)
     return true;
   // Otherwise, check if the promoted instruction is legal or not.
   return TLI.isOperationLegalOrCustom(
       ISDOpcode, TLI.getValueType(DL, PromotedInst->getType()));
 }
 
 /// \brief Hepler class to perform type promotion.
 class TypePromotionHelper {
   /// \brief Utility function to check whether or not a sign or zero extension
   /// of \p Inst with \p ConsideredExtType can be moved through \p Inst by
   /// either using the operands of \p Inst or promoting \p Inst.
   /// The type of the extension is defined by \p IsSExt.
   /// In other words, check if:
   /// ext (Ty Inst opnd1 opnd2 ... opndN) to ConsideredExtType.
   /// #1 Promotion applies:
   /// ConsideredExtType Inst (ext opnd1 to ConsideredExtType, ...).
   /// #2 Operand reuses:
   /// ext opnd1 to ConsideredExtType.
   /// \p PromotedInsts maps the instructions to their type before promotion.
   static bool canGetThrough(const Instruction *Inst, Type *ConsideredExtType,
                             const InstrToOrigTy &PromotedInsts, bool IsSExt);
 
   /// \brief Utility function to determine if \p OpIdx should be promoted when
   /// promoting \p Inst.
   static bool shouldExtOperand(const Instruction *Inst, int OpIdx) {
     return !(isa<SelectInst>(Inst) && OpIdx == 0);
   }
 
   /// \brief Utility function to promote the operand of \p Ext when this
   /// operand is a promotable trunc or sext or zext.
   /// \p PromotedInsts maps the instructions to their type before promotion.
   /// \p CreatedInstsCost[out] contains the cost of all instructions
   /// created to promote the operand of Ext.
   /// Newly added extensions are inserted in \p Exts.
   /// Newly added truncates are inserted in \p Truncs.
   /// Should never be called directly.
   /// \return The promoted value which is used instead of Ext.
   static Value *promoteOperandForTruncAndAnyExt(
       Instruction *Ext, TypePromotionTransaction &TPT,
       InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
       SmallVectorImpl<Instruction *> *Exts,
       SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI);
 
   /// \brief Utility function to promote the operand of \p Ext when this
   /// operand is promotable and is not a supported trunc or sext.
   /// \p PromotedInsts maps the instructions to their type before promotion.
   /// \p CreatedInstsCost[out] contains the cost of all the instructions
   /// created to promote the operand of Ext.
   /// Newly added extensions are inserted in \p Exts.
   /// Newly added truncates are inserted in \p Truncs.
   /// Should never be called directly.
   /// \return The promoted value which is used instead of Ext.
   static Value *promoteOperandForOther(Instruction *Ext,
                                        TypePromotionTransaction &TPT,
                                        InstrToOrigTy &PromotedInsts,
                                        unsigned &CreatedInstsCost,
                                        SmallVectorImpl<Instruction *> *Exts,
                                        SmallVectorImpl<Instruction *> *Truncs,
                                        const TargetLowering &TLI, bool IsSExt);
 
   /// \see promoteOperandForOther.
   static Value *signExtendOperandForOther(
       Instruction *Ext, TypePromotionTransaction &TPT,
       InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
       SmallVectorImpl<Instruction *> *Exts,
       SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI) {
     return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInstsCost,
                                   Exts, Truncs, TLI, true);
   }
 
   /// \see promoteOperandForOther.
   static Value *zeroExtendOperandForOther(
       Instruction *Ext, TypePromotionTransaction &TPT,
       InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
       SmallVectorImpl<Instruction *> *Exts,
       SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI) {
     return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInstsCost,
                                   Exts, Truncs, TLI, false);
   }
 
 public:
   /// Type for the utility function that promotes the operand of Ext.
   typedef Value *(*Action)(Instruction *Ext, TypePromotionTransaction &TPT,
                            InstrToOrigTy &PromotedInsts,
                            unsigned &CreatedInstsCost,
                            SmallVectorImpl<Instruction *> *Exts,
                            SmallVectorImpl<Instruction *> *Truncs,
                            const TargetLowering &TLI);
   /// \brief Given a sign/zero extend instruction \p Ext, return the approriate
   /// action to promote the operand of \p Ext instead of using Ext.
   /// \return NULL if no promotable action is possible with the current
   /// sign extension.
   /// \p InsertedInsts keeps track of all the instructions inserted by the
   /// other CodeGenPrepare optimizations. This information is important
   /// because we do not want to promote these instructions as CodeGenPrepare
   /// will reinsert them later. Thus creating an infinite loop: create/remove.
   /// \p PromotedInsts maps the instructions to their type before promotion.
   static Action getAction(Instruction *Ext, const SetOfInstrs &InsertedInsts,
                           const TargetLowering &TLI,
                           const InstrToOrigTy &PromotedInsts);
 };
 
 bool TypePromotionHelper::canGetThrough(const Instruction *Inst,
                                         Type *ConsideredExtType,
                                         const InstrToOrigTy &PromotedInsts,
                                         bool IsSExt) {
   // The promotion helper does not know how to deal with vector types yet.
   // To be able to fix that, we would need to fix the places where we
   // statically extend, e.g., constants and such.
   if (Inst->getType()->isVectorTy())
     return false;
 
   // We can always get through zext.
   if (isa<ZExtInst>(Inst))
     return true;
 
   // sext(sext) is ok too.
   if (IsSExt && isa<SExtInst>(Inst))
     return true;
 
   // We can get through binary operator, if it is legal. In other words, the
   // binary operator must have a nuw or nsw flag.
   const BinaryOperator *BinOp = dyn_cast<BinaryOperator>(Inst);
   if (BinOp && isa<OverflowingBinaryOperator>(BinOp) &&
       ((!IsSExt && BinOp->hasNoUnsignedWrap()) ||
        (IsSExt && BinOp->hasNoSignedWrap())))
     return true;
 
   // Check if we can do the following simplification.
   // ext(trunc(opnd)) --> ext(opnd)
   if (!isa<TruncInst>(Inst))
     return false;
 
   Value *OpndVal = Inst->getOperand(0);
   // Check if we can use this operand in the extension.
   // If the type is larger than the result type of the extension, we cannot.
   if (!OpndVal->getType()->isIntegerTy() ||
       OpndVal->getType()->getIntegerBitWidth() >
           ConsideredExtType->getIntegerBitWidth())
     return false;
 
   // If the operand of the truncate is not an instruction, we will not have
   // any information on the dropped bits.
   // (Actually we could for constant but it is not worth the extra logic).
   Instruction *Opnd = dyn_cast<Instruction>(OpndVal);
   if (!Opnd)
     return false;
 
   // Check if the source of the type is narrow enough.
   // I.e., check that trunc just drops extended bits of the same kind of
   // the extension.
   // #1 get the type of the operand and check the kind of the extended bits.
   const Type *OpndType;
   InstrToOrigTy::const_iterator It = PromotedInsts.find(Opnd);
   if (It != PromotedInsts.end() && It->second.getInt() == IsSExt)
     OpndType = It->second.getPointer();
   else if ((IsSExt && isa<SExtInst>(Opnd)) || (!IsSExt && isa<ZExtInst>(Opnd)))
     OpndType = Opnd->getOperand(0)->getType();
   else
     return false;
 
   // #2 check that the truncate just drops extended bits.
   return Inst->getType()->getIntegerBitWidth() >=
          OpndType->getIntegerBitWidth();
 }
 
 TypePromotionHelper::Action TypePromotionHelper::getAction(
     Instruction *Ext, const SetOfInstrs &InsertedInsts,
     const TargetLowering &TLI, const InstrToOrigTy &PromotedInsts) {
   assert((isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) &&
          "Unexpected instruction type");
   Instruction *ExtOpnd = dyn_cast<Instruction>(Ext->getOperand(0));
   Type *ExtTy = Ext->getType();
   bool IsSExt = isa<SExtInst>(Ext);
   // If the operand of the extension is not an instruction, we cannot
   // get through.
   // If it, check we can get through.
   if (!ExtOpnd || !canGetThrough(ExtOpnd, ExtTy, PromotedInsts, IsSExt))
     return nullptr;
 
   // Do not promote if the operand has been added by codegenprepare.
   // Otherwise, it means we are undoing an optimization that is likely to be
   // redone, thus causing potential infinite loop.
   if (isa<TruncInst>(ExtOpnd) && InsertedInsts.count(ExtOpnd))
     return nullptr;
 
   // SExt or Trunc instructions.
   // Return the related handler.
   if (isa<SExtInst>(ExtOpnd) || isa<TruncInst>(ExtOpnd) ||
       isa<ZExtInst>(ExtOpnd))
     return promoteOperandForTruncAndAnyExt;
 
   // Regular instruction.
   // Abort early if we will have to insert non-free instructions.
   if (!ExtOpnd->hasOneUse() && !TLI.isTruncateFree(ExtTy, ExtOpnd->getType()))
     return nullptr;
   return IsSExt ? signExtendOperandForOther : zeroExtendOperandForOther;
 }
 
 Value *TypePromotionHelper::promoteOperandForTruncAndAnyExt(
     llvm::Instruction *SExt, TypePromotionTransaction &TPT,
     InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
     SmallVectorImpl<Instruction *> *Exts,
     SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI) {
   // By construction, the operand of SExt is an instruction. Otherwise we cannot
   // get through it and this method should not be called.
   Instruction *SExtOpnd = cast<Instruction>(SExt->getOperand(0));
   Value *ExtVal = SExt;
   bool HasMergedNonFreeExt = false;
   if (isa<ZExtInst>(SExtOpnd)) {
     // Replace s|zext(zext(opnd))
     // => zext(opnd).
     HasMergedNonFreeExt = !TLI.isExtFree(SExtOpnd);
     Value *ZExt =
         TPT.createZExt(SExt, SExtOpnd->getOperand(0), SExt->getType());
     TPT.replaceAllUsesWith(SExt, ZExt);
     TPT.eraseInstruction(SExt);
     ExtVal = ZExt;
   } else {
     // Replace z|sext(trunc(opnd)) or sext(sext(opnd))
     // => z|sext(opnd).
     TPT.setOperand(SExt, 0, SExtOpnd->getOperand(0));
   }
   CreatedInstsCost = 0;
 
   // Remove dead code.
   if (SExtOpnd->use_empty())
     TPT.eraseInstruction(SExtOpnd);
 
   // Check if the extension is still needed.
   Instruction *ExtInst = dyn_cast<Instruction>(ExtVal);
   if (!ExtInst || ExtInst->getType() != ExtInst->getOperand(0)->getType()) {
     if (ExtInst) {
       if (Exts)
         Exts->push_back(ExtInst);
       CreatedInstsCost = !TLI.isExtFree(ExtInst) && !HasMergedNonFreeExt;
     }
     return ExtVal;
   }
 
   // At this point we have: ext ty opnd to ty.
   // Reassign the uses of ExtInst to the opnd and remove ExtInst.
   Value *NextVal = ExtInst->getOperand(0);
   TPT.eraseInstruction(ExtInst, NextVal);
   return NextVal;
 }
 
 Value *TypePromotionHelper::promoteOperandForOther(
     Instruction *Ext, TypePromotionTransaction &TPT,
     InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
     SmallVectorImpl<Instruction *> *Exts,
     SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI,
     bool IsSExt) {
   // By construction, the operand of Ext is an instruction. Otherwise we cannot
   // get through it and this method should not be called.
   Instruction *ExtOpnd = cast<Instruction>(Ext->getOperand(0));
   CreatedInstsCost = 0;
   if (!ExtOpnd->hasOneUse()) {
     // ExtOpnd will be promoted.
     // All its uses, but Ext, will need to use a truncated value of the
     // promoted version.
     // Create the truncate now.
     Value *Trunc = TPT.createTrunc(Ext, ExtOpnd->getType());
     if (Instruction *ITrunc = dyn_cast<Instruction>(Trunc)) {
       ITrunc->removeFromParent();
       // Insert it just after the definition.
       ITrunc->insertAfter(ExtOpnd);
       if (Truncs)
         Truncs->push_back(ITrunc);
     }
 
     TPT.replaceAllUsesWith(ExtOpnd, Trunc);
     // Restore the operand of Ext (which has been replaced by the previous call
     // to replaceAllUsesWith) to avoid creating a cycle trunc <-> sext.
     TPT.setOperand(Ext, 0, ExtOpnd);
   }
 
   // Get through the Instruction:
   // 1. Update its type.
   // 2. Replace the uses of Ext by Inst.
   // 3. Extend each operand that needs to be extended.
 
   // Remember the original type of the instruction before promotion.
   // This is useful to know that the high bits are sign extended bits.
   PromotedInsts.insert(std::pair<Instruction *, TypeIsSExt>(
       ExtOpnd, TypeIsSExt(ExtOpnd->getType(), IsSExt)));
   // Step #1.
   TPT.mutateType(ExtOpnd, Ext->getType());
   // Step #2.
   TPT.replaceAllUsesWith(Ext, ExtOpnd);
   // Step #3.
   Instruction *ExtForOpnd = Ext;
 
   DEBUG(dbgs() << "Propagate Ext to operands\n");
   for (int OpIdx = 0, EndOpIdx = ExtOpnd->getNumOperands(); OpIdx != EndOpIdx;
        ++OpIdx) {
     DEBUG(dbgs() << "Operand:\n" << *(ExtOpnd->getOperand(OpIdx)) << '\n');
     if (ExtOpnd->getOperand(OpIdx)->getType() == Ext->getType() ||
         !shouldExtOperand(ExtOpnd, OpIdx)) {
       DEBUG(dbgs() << "No need to propagate\n");
       continue;
     }
     // Check if we can statically extend the operand.
     Value *Opnd = ExtOpnd->getOperand(OpIdx);
     if (const ConstantInt *Cst = dyn_cast<ConstantInt>(Opnd)) {
       DEBUG(dbgs() << "Statically extend\n");
       unsigned BitWidth = Ext->getType()->getIntegerBitWidth();
       APInt CstVal = IsSExt ? Cst->getValue().sext(BitWidth)
                             : Cst->getValue().zext(BitWidth);
       TPT.setOperand(ExtOpnd, OpIdx, ConstantInt::get(Ext->getType(), CstVal));
       continue;
     }
     // UndefValue are typed, so we have to statically sign extend them.
     if (isa<UndefValue>(Opnd)) {
       DEBUG(dbgs() << "Statically extend\n");
       TPT.setOperand(ExtOpnd, OpIdx, UndefValue::get(Ext->getType()));
       continue;
     }
 
     // Otherwise we have to explicity sign extend the operand.
     // Check if Ext was reused to extend an operand.
     if (!ExtForOpnd) {
       // If yes, create a new one.
       DEBUG(dbgs() << "More operands to ext\n");
       Value *ValForExtOpnd = IsSExt ? TPT.createSExt(Ext, Opnd, Ext->getType())
         : TPT.createZExt(Ext, Opnd, Ext->getType());
       if (!isa<Instruction>(ValForExtOpnd)) {
         TPT.setOperand(ExtOpnd, OpIdx, ValForExtOpnd);
         continue;
       }
       ExtForOpnd = cast<Instruction>(ValForExtOpnd);
     }
     if (Exts)
       Exts->push_back(ExtForOpnd);
     TPT.setOperand(ExtForOpnd, 0, Opnd);
 
     // Move the sign extension before the insertion point.
     TPT.moveBefore(ExtForOpnd, ExtOpnd);
     TPT.setOperand(ExtOpnd, OpIdx, ExtForOpnd);
     CreatedInstsCost += !TLI.isExtFree(ExtForOpnd);
     // If more sext are required, new instructions will have to be created.
     ExtForOpnd = nullptr;
   }
   if (ExtForOpnd == Ext) {
     DEBUG(dbgs() << "Extension is useless now\n");
     TPT.eraseInstruction(Ext);
   }
   return ExtOpnd;
 }
 
 /// Check whether or not promoting an instruction to a wider type is profitable.
 /// \p NewCost gives the cost of extension instructions created by the
 /// promotion.
 /// \p OldCost gives the cost of extension instructions before the promotion
 /// plus the number of instructions that have been
 /// matched in the addressing mode the promotion.
 /// \p PromotedOperand is the value that has been promoted.
 /// \return True if the promotion is profitable, false otherwise.
 bool AddressingModeMatcher::isPromotionProfitable(
     unsigned NewCost, unsigned OldCost, Value *PromotedOperand) const {
   DEBUG(dbgs() << "OldCost: " << OldCost << "\tNewCost: " << NewCost << '\n');
   // The cost of the new extensions is greater than the cost of the
   // old extension plus what we folded.
   // This is not profitable.
   if (NewCost > OldCost)
     return false;
   if (NewCost < OldCost)
     return true;
   // The promotion is neutral but it may help folding the sign extension in
   // loads for instance.
   // Check that we did not create an illegal instruction.
   return isPromotedInstructionLegal(TLI, DL, PromotedOperand);
 }
 
 /// Given an instruction or constant expr, see if we can fold the operation
 /// into the addressing mode. If so, update the addressing mode and return
 /// true, otherwise return false without modifying AddrMode.
 /// If \p MovedAway is not NULL, it contains the information of whether or
 /// not AddrInst has to be folded into the addressing mode on success.
 /// If \p MovedAway == true, \p AddrInst will not be part of the addressing
 /// because it has been moved away.
 /// Thus AddrInst must not be added in the matched instructions.
 /// This state can happen when AddrInst is a sext, since it may be moved away.
 /// Therefore, AddrInst may not be valid when MovedAway is true and it must
 /// not be referenced anymore.
 bool AddressingModeMatcher::matchOperationAddr(User *AddrInst, unsigned Opcode,
                                                unsigned Depth,
                                                bool *MovedAway) {
   // Avoid exponential behavior on extremely deep expression trees.
   if (Depth >= 5) return false;
 
   // By default, all matched instructions stay in place.
   if (MovedAway)
     *MovedAway = false;
 
   switch (Opcode) {
   case Instruction::PtrToInt:
     // PtrToInt is always a noop, as we know that the int type is pointer sized.
     return matchAddr(AddrInst->getOperand(0), Depth);
   case Instruction::IntToPtr: {
     auto AS = AddrInst->getType()->getPointerAddressSpace();
     auto PtrTy = MVT::getIntegerVT(DL.getPointerSizeInBits(AS));
     // This inttoptr is a no-op if the integer type is pointer sized.
     if (TLI.getValueType(DL, AddrInst->getOperand(0)->getType()) == PtrTy)
       return matchAddr(AddrInst->getOperand(0), Depth);
     return false;
   }
   case Instruction::BitCast:
     // BitCast is always a noop, and we can handle it as long as it is
     // int->int or pointer->pointer (we don't want int<->fp or something).
     if ((AddrInst->getOperand(0)->getType()->isPointerTy() ||
          AddrInst->getOperand(0)->getType()->isIntegerTy()) &&
         // Don't touch identity bitcasts.  These were probably put here by LSR,
         // and we don't want to mess around with them.  Assume it knows what it
         // is doing.
         AddrInst->getOperand(0)->getType() != AddrInst->getType())
       return matchAddr(AddrInst->getOperand(0), Depth);
     return false;
   case Instruction::AddrSpaceCast: {
     unsigned SrcAS
       = AddrInst->getOperand(0)->getType()->getPointerAddressSpace();
     unsigned DestAS = AddrInst->getType()->getPointerAddressSpace();
     if (TLI.isNoopAddrSpaceCast(SrcAS, DestAS))
       return matchAddr(AddrInst->getOperand(0), Depth);
     return false;
   }
   case Instruction::Add: {
     // Check to see if we can merge in the RHS then the LHS.  If so, we win.
     ExtAddrMode BackupAddrMode = AddrMode;
     unsigned OldSize = AddrModeInsts.size();
     // Start a transaction at this point.
     // The LHS may match but not the RHS.
     // Therefore, we need a higher level restoration point to undo partially
     // matched operation.
     TypePromotionTransaction::ConstRestorationPt LastKnownGood =
         TPT.getRestorationPoint();
 
     if (matchAddr(AddrInst->getOperand(1), Depth+1) &&
         matchAddr(AddrInst->getOperand(0), Depth+1))
       return true;
 
     // Restore the old addr mode info.
     AddrMode = BackupAddrMode;
     AddrModeInsts.resize(OldSize);
     TPT.rollback(LastKnownGood);
 
     // Otherwise this was over-aggressive.  Try merging in the LHS then the RHS.
     if (matchAddr(AddrInst->getOperand(0), Depth+1) &&
         matchAddr(AddrInst->getOperand(1), Depth+1))
       return true;
 
     // Otherwise we definitely can't merge the ADD in.
     AddrMode = BackupAddrMode;
     AddrModeInsts.resize(OldSize);
     TPT.rollback(LastKnownGood);
     break;
   }
   //case Instruction::Or:
   // TODO: We can handle "Or Val, Imm" iff this OR is equivalent to an ADD.
   //break;
   case Instruction::Mul:
   case Instruction::Shl: {
     // Can only handle X*C and X << C.
     ConstantInt *RHS = dyn_cast<ConstantInt>(AddrInst->getOperand(1));
     if (!RHS)
       return false;
     int64_t Scale = RHS->getSExtValue();
     if (Opcode == Instruction::Shl)
       Scale = 1LL << Scale;
 
     return matchScaledValue(AddrInst->getOperand(0), Scale, Depth);
   }
   case Instruction::GetElementPtr: {
     // Scan the GEP.  We check it if it contains constant offsets and at most
     // one variable offset.
     int VariableOperand = -1;
     unsigned VariableScale = 0;
 
     int64_t ConstantOffset = 0;
     gep_type_iterator GTI = gep_type_begin(AddrInst);
     for (unsigned i = 1, e = AddrInst->getNumOperands(); i != e; ++i, ++GTI) {
       if (StructType *STy = dyn_cast<StructType>(*GTI)) {
         const StructLayout *SL = DL.getStructLayout(STy);
         unsigned Idx =
           cast<ConstantInt>(AddrInst->getOperand(i))->getZExtValue();
         ConstantOffset += SL->getElementOffset(Idx);
       } else {
         uint64_t TypeSize = DL.getTypeAllocSize(GTI.getIndexedType());
         if (ConstantInt *CI = dyn_cast<ConstantInt>(AddrInst->getOperand(i))) {
           ConstantOffset += CI->getSExtValue()*TypeSize;
         } else if (TypeSize) {  // Scales of zero don't do anything.
           // We only allow one variable index at the moment.
           if (VariableOperand != -1)
             return false;
 
           // Remember the variable index.
           VariableOperand = i;
           VariableScale = TypeSize;
         }
       }
     }
 
     // A common case is for the GEP to only do a constant offset.  In this case,
     // just add it to the disp field and check validity.
     if (VariableOperand == -1) {
       AddrMode.BaseOffs += ConstantOffset;
       if (ConstantOffset == 0 ||
           TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace)) {
         // Check to see if we can fold the base pointer in too.
         if (matchAddr(AddrInst->getOperand(0), Depth+1))
           return true;
       }
       AddrMode.BaseOffs -= ConstantOffset;
       return false;
     }
 
     // Save the valid addressing mode in case we can't match.
     ExtAddrMode BackupAddrMode = AddrMode;
     unsigned OldSize = AddrModeInsts.size();
 
     // See if the scale and offset amount is valid for this target.
     AddrMode.BaseOffs += ConstantOffset;
 
     // Match the base operand of the GEP.
     if (!matchAddr(AddrInst->getOperand(0), Depth+1)) {
       // If it couldn't be matched, just stuff the value in a register.
       if (AddrMode.HasBaseReg) {
         AddrMode = BackupAddrMode;
         AddrModeInsts.resize(OldSize);
         return false;
       }
       AddrMode.HasBaseReg = true;
       AddrMode.BaseReg = AddrInst->getOperand(0);
     }
 
     // Match the remaining variable portion of the GEP.
     if (!matchScaledValue(AddrInst->getOperand(VariableOperand), VariableScale,
                           Depth)) {
       // If it couldn't be matched, try stuffing the base into a register
       // instead of matching it, and retrying the match of the scale.
       AddrMode = BackupAddrMode;
       AddrModeInsts.resize(OldSize);
       if (AddrMode.HasBaseReg)
         return false;
       AddrMode.HasBaseReg = true;
       AddrMode.BaseReg = AddrInst->getOperand(0);
       AddrMode.BaseOffs += ConstantOffset;
       if (!matchScaledValue(AddrInst->getOperand(VariableOperand),
                             VariableScale, Depth)) {
         // If even that didn't work, bail.
         AddrMode = BackupAddrMode;
         AddrModeInsts.resize(OldSize);
         return false;
       }
     }
 
     return true;
   }
   case Instruction::SExt:
   case Instruction::ZExt: {
     Instruction *Ext = dyn_cast<Instruction>(AddrInst);
     if (!Ext)
       return false;
 
     // Try to move this ext out of the way of the addressing mode.
     // Ask for a method for doing so.
     TypePromotionHelper::Action TPH =
         TypePromotionHelper::getAction(Ext, InsertedInsts, TLI, PromotedInsts);
     if (!TPH)
       return false;
 
     TypePromotionTransaction::ConstRestorationPt LastKnownGood =
         TPT.getRestorationPoint();
     unsigned CreatedInstsCost = 0;
     unsigned ExtCost = !TLI.isExtFree(Ext);
     Value *PromotedOperand =
         TPH(Ext, TPT, PromotedInsts, CreatedInstsCost, nullptr, nullptr, TLI);
     // SExt has been moved away.
     // Thus either it will be rematched later in the recursive calls or it is
     // gone. Anyway, we must not fold it into the addressing mode at this point.
     // E.g.,
     // op = add opnd, 1
     // idx = ext op
     // addr = gep base, idx
     // is now:
     // promotedOpnd = ext opnd            <- no match here
     // op = promoted_add promotedOpnd, 1  <- match (later in recursive calls)
     // addr = gep base, op                <- match
     if (MovedAway)
       *MovedAway = true;
 
     assert(PromotedOperand &&
            "TypePromotionHelper should have filtered out those cases");
 
     ExtAddrMode BackupAddrMode = AddrMode;
     unsigned OldSize = AddrModeInsts.size();
 
     if (!matchAddr(PromotedOperand, Depth) ||
         // The total of the new cost is equal to the cost of the created
         // instructions.
         // The total of the old cost is equal to the cost of the extension plus
         // what we have saved in the addressing mode.
         !isPromotionProfitable(CreatedInstsCost,
                                ExtCost + (AddrModeInsts.size() - OldSize),
                                PromotedOperand)) {
       AddrMode = BackupAddrMode;
       AddrModeInsts.resize(OldSize);
       DEBUG(dbgs() << "Sign extension does not pay off: rollback\n");
       TPT.rollback(LastKnownGood);
       return false;
     }
     return true;
   }
   }
   return false;
 }
 
 /// If we can, try to add the value of 'Addr' into the current addressing mode.
 /// If Addr can't be added to AddrMode this returns false and leaves AddrMode
 /// unmodified. This assumes that Addr is either a pointer type or intptr_t
 /// for the target.
 ///
 bool AddressingModeMatcher::matchAddr(Value *Addr, unsigned Depth) {
   // Start a transaction at this point that we will rollback if the matching
   // fails.
   TypePromotionTransaction::ConstRestorationPt LastKnownGood =
       TPT.getRestorationPoint();
   if (ConstantInt *CI = dyn_cast<ConstantInt>(Addr)) {
     // Fold in immediates if legal for the target.
     AddrMode.BaseOffs += CI->getSExtValue();
     if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
       return true;
     AddrMode.BaseOffs -= CI->getSExtValue();
   } else if (GlobalValue *GV = dyn_cast<GlobalValue>(Addr)) {
     // If this is a global variable, try to fold it into the addressing mode.
     if (!AddrMode.BaseGV) {
       AddrMode.BaseGV = GV;
       if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
         return true;
       AddrMode.BaseGV = nullptr;
     }
   } else if (Instruction *I = dyn_cast<Instruction>(Addr)) {
     ExtAddrMode BackupAddrMode = AddrMode;
     unsigned OldSize = AddrModeInsts.size();
 
     // Check to see if it is possible to fold this operation.
     bool MovedAway = false;
     if (matchOperationAddr(I, I->getOpcode(), Depth, &MovedAway)) {
       // This instruction may have been moved away. If so, there is nothing
       // to check here.
       if (MovedAway)
         return true;
       // Okay, it's possible to fold this.  Check to see if it is actually
       // *profitable* to do so.  We use a simple cost model to avoid increasing
       // register pressure too much.
       if (I->hasOneUse() ||
           isProfitableToFoldIntoAddressingMode(I, BackupAddrMode, AddrMode)) {
         AddrModeInsts.push_back(I);
         return true;
       }
 
       // It isn't profitable to do this, roll back.
       //cerr << "NOT FOLDING: " << *I;
       AddrMode = BackupAddrMode;
       AddrModeInsts.resize(OldSize);
       TPT.rollback(LastKnownGood);
     }
   } else if (ConstantExpr *CE = dyn_cast<ConstantExpr>(Addr)) {
     if (matchOperationAddr(CE, CE->getOpcode(), Depth))
       return true;
     TPT.rollback(LastKnownGood);
   } else if (isa<ConstantPointerNull>(Addr)) {
     // Null pointer gets folded without affecting the addressing mode.
     return true;
   }
 
   // Worse case, the target should support [reg] addressing modes. :)
   if (!AddrMode.HasBaseReg) {
     AddrMode.HasBaseReg = true;
     AddrMode.BaseReg = Addr;
     // Still check for legality in case the target supports [imm] but not [i+r].
     if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
       return true;
     AddrMode.HasBaseReg = false;
     AddrMode.BaseReg = nullptr;
   }
 
   // If the base register is already taken, see if we can do [r+r].
   if (AddrMode.Scale == 0) {
     AddrMode.Scale = 1;
     AddrMode.ScaledReg = Addr;
     if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
       return true;
     AddrMode.Scale = 0;
     AddrMode.ScaledReg = nullptr;
   }
   // Couldn't match.
   TPT.rollback(LastKnownGood);
   return false;
 }
 
 /// Check to see if all uses of OpVal by the specified inline asm call are due
 /// to memory operands. If so, return true, otherwise return false.
 static bool IsOperandAMemoryOperand(CallInst *CI, InlineAsm *IA, Value *OpVal,
                                     const TargetMachine &TM) {
   const Function *F = CI->getParent()->getParent();
   const TargetLowering *TLI = TM.getSubtargetImpl(*F)->getTargetLowering();
   const TargetRegisterInfo *TRI = TM.getSubtargetImpl(*F)->getRegisterInfo();
   TargetLowering::AsmOperandInfoVector TargetConstraints =
       TLI->ParseConstraints(F->getParent()->getDataLayout(), TRI,
                             ImmutableCallSite(CI));
   for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
     TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];
 
     // Compute the constraint code and ConstraintType to use.
     TLI->ComputeConstraintToUse(OpInfo, SDValue());
 
     // If this asm operand is our Value*, and if it isn't an indirect memory
     // operand, we can't fold it!
     if (OpInfo.CallOperandVal == OpVal &&
         (OpInfo.ConstraintType != TargetLowering::C_Memory ||
          !OpInfo.isIndirect))
       return false;
   }
 
   return true;
 }
 
 /// Recursively walk all the uses of I until we find a memory use.
 /// If we find an obviously non-foldable instruction, return true.
 /// Add the ultimately found memory instructions to MemoryUses.
 static bool FindAllMemoryUses(
     Instruction *I,
     SmallVectorImpl<std::pair<Instruction *, unsigned>> &MemoryUses,
     SmallPtrSetImpl<Instruction *> &ConsideredInsts, const TargetMachine &TM) {
   // If we already considered this instruction, we're done.
   if (!ConsideredInsts.insert(I).second)
     return false;
 
   // If this is an obviously unfoldable instruction, bail out.
   if (!MightBeFoldableInst(I))
     return true;
 
   // Loop over all the uses, recursively processing them.
   for (Use &U : I->uses()) {
     Instruction *UserI = cast<Instruction>(U.getUser());
 
     if (LoadInst *LI = dyn_cast<LoadInst>(UserI)) {
       MemoryUses.push_back(std::make_pair(LI, U.getOperandNo()));
       continue;
     }
 
     if (StoreInst *SI = dyn_cast<StoreInst>(UserI)) {
       unsigned opNo = U.getOperandNo();
       if (opNo == 0) return true; // Storing addr, not into addr.
       MemoryUses.push_back(std::make_pair(SI, opNo));
       continue;
     }
 
     if (CallInst *CI = dyn_cast<CallInst>(UserI)) {
       InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue());
       if (!IA) return true;
 
       // If this is a memory operand, we're cool, otherwise bail out.
       if (!IsOperandAMemoryOperand(CI, IA, I, TM))
         return true;
       continue;
     }
 
     if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TM))
       return true;
   }
 
   return false;
 }
 
 /// Return true if Val is already known to be live at the use site that we're
 /// folding it into. If so, there is no cost to include it in the addressing
 /// mode. KnownLive1 and KnownLive2 are two values that we know are live at the
 /// instruction already.
 bool AddressingModeMatcher::valueAlreadyLiveAtInst(Value *Val,Value *KnownLive1,
                                                    Value *KnownLive2) {
   // If Val is either of the known-live values, we know it is live!
   if (Val == nullptr || Val == KnownLive1 || Val == KnownLive2)
     return true;
 
   // All values other than instructions and arguments (e.g. constants) are live.
   if (!isa<Instruction>(Val) && !isa<Argument>(Val)) return true;
 
   // If Val is a constant sized alloca in the entry block, it is live, this is
   // true because it is just a reference to the stack/frame pointer, which is
   // live for the whole function.
   if (AllocaInst *AI = dyn_cast<AllocaInst>(Val))
     if (AI->isStaticAlloca())
       return true;
 
   // Check to see if this value is already used in the memory instruction's
   // block.  If so, it's already live into the block at the very least, so we
   // can reasonably fold it.
   return Val->isUsedInBasicBlock(MemoryInst->getParent());
 }
 
 /// It is possible for the addressing mode of the machine to fold the specified
 /// instruction into a load or store that ultimately uses it.
 /// However, the specified instruction has multiple uses.
 /// Given this, it may actually increase register pressure to fold it
 /// into the load. For example, consider this code:
 ///
 ///     X = ...
 ///     Y = X+1
 ///     use(Y)   -> nonload/store
 ///     Z = Y+1
 ///     load Z
 ///
 /// In this case, Y has multiple uses, and can be folded into the load of Z
 /// (yielding load [X+2]).  However, doing this will cause both "X" and "X+1" to
 /// be live at the use(Y) line.  If we don't fold Y into load Z, we use one
 /// fewer register.  Since Y can't be folded into "use(Y)" we don't increase the
 /// number of computations either.
 ///
 /// Note that this (like most of CodeGenPrepare) is just a rough heuristic.  If
 /// X was live across 'load Z' for other reasons, we actually *would* want to
 /// fold the addressing mode in the Z case.  This would make Y die earlier.
 bool AddressingModeMatcher::
 isProfitableToFoldIntoAddressingMode(Instruction *I, ExtAddrMode &AMBefore,
                                      ExtAddrMode &AMAfter) {
   if (IgnoreProfitability) return true;
 
   // AMBefore is the addressing mode before this instruction was folded into it,
   // and AMAfter is the addressing mode after the instruction was folded.  Get
   // the set of registers referenced by AMAfter and subtract out those
   // referenced by AMBefore: this is the set of values which folding in this
   // address extends the lifetime of.
   //
   // Note that there are only two potential values being referenced here,
   // BaseReg and ScaleReg (global addresses are always available, as are any
   // folded immediates).
   Value *BaseReg = AMAfter.BaseReg, *ScaledReg = AMAfter.ScaledReg;
 
   // If the BaseReg or ScaledReg was referenced by the previous addrmode, their
   // lifetime wasn't extended by adding this instruction.
   if (valueAlreadyLiveAtInst(BaseReg, AMBefore.BaseReg, AMBefore.ScaledReg))
     BaseReg = nullptr;
   if (valueAlreadyLiveAtInst(ScaledReg, AMBefore.BaseReg, AMBefore.ScaledReg))
     ScaledReg = nullptr;
 
   // If folding this instruction (and it's subexprs) didn't extend any live
   // ranges, we're ok with it.
   if (!BaseReg && !ScaledReg)
     return true;
 
   // If all uses of this instruction are ultimately load/store/inlineasm's,
   // check to see if their addressing modes will include this instruction.  If
   // so, we can fold it into all uses, so it doesn't matter if it has multiple
   // uses.
   SmallVector<std::pair<Instruction*,unsigned>, 16> MemoryUses;
   SmallPtrSet<Instruction*, 16> ConsideredInsts;
   if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TM))
     return false;  // Has a non-memory, non-foldable use!
 
   // Now that we know that all uses of this instruction are part of a chain of
   // computation involving only operations that could theoretically be folded
   // into a memory use, loop over each of these uses and see if they could
   // *actually* fold the instruction.
   SmallVector<Instruction*, 32> MatchedAddrModeInsts;
   for (unsigned i = 0, e = MemoryUses.size(); i != e; ++i) {
     Instruction *User = MemoryUses[i].first;
     unsigned OpNo = MemoryUses[i].second;
 
     // Get the access type of this use.  If the use isn't a pointer, we don't
     // know what it accesses.
     Value *Address = User->getOperand(OpNo);
     PointerType *AddrTy = dyn_cast<PointerType>(Address->getType());
     if (!AddrTy)
       return false;
     Type *AddressAccessTy = AddrTy->getElementType();
     unsigned AS = AddrTy->getAddressSpace();
 
     // Do a match against the root of this address, ignoring profitability. This
     // will tell us if the addressing mode for the memory operation will
     // *actually* cover the shared instruction.
     ExtAddrMode Result;
     TypePromotionTransaction::ConstRestorationPt LastKnownGood =
         TPT.getRestorationPoint();
     AddressingModeMatcher Matcher(MatchedAddrModeInsts, TM, AddressAccessTy, AS,
                                   MemoryInst, Result, InsertedInsts,
                                   PromotedInsts, TPT);
     Matcher.IgnoreProfitability = true;
     bool Success = Matcher.matchAddr(Address, 0);
     (void)Success; assert(Success && "Couldn't select *anything*?");
 
     // The match was to check the profitability, the changes made are not
     // part of the original matcher. Therefore, they should be dropped
     // otherwise the original matcher will not present the right state.
     TPT.rollback(LastKnownGood);
 
     // If the match didn't cover I, then it won't be shared by it.
     if (std::find(MatchedAddrModeInsts.begin(), MatchedAddrModeInsts.end(),
                   I) == MatchedAddrModeInsts.end())
       return false;
 
     MatchedAddrModeInsts.clear();
   }
 
   return true;
 }
 
 } // end anonymous namespace
 
 /// Return true if the specified values are defined in a
 /// different basic block than BB.
 static bool IsNonLocalValue(Value *V, BasicBlock *BB) {
   if (Instruction *I = dyn_cast<Instruction>(V))
     return I->getParent() != BB;
   return false;
 }
 
 /// Load and Store Instructions often have addressing modes that can do
 /// significant amounts of computation. As such, instruction selection will try
 /// to get the load or store to do as much computation as possible for the
 /// program. The problem is that isel can only see within a single block. As
 /// such, we sink as much legal addressing mode work into the block as possible.
 ///
 /// This method is used to optimize both load/store and inline asms with memory
 /// operands.
 bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
                                         Type *AccessTy, unsigned AddrSpace) {
   Value *Repl = Addr;
 
   // Try to collapse single-value PHI nodes.  This is necessary to undo
   // unprofitable PRE transformations.
   SmallVector<Value*, 8> worklist;
   SmallPtrSet<Value*, 16> Visited;
   worklist.push_back(Addr);
 
   // Use a worklist to iteratively look through PHI nodes, and ensure that
   // the addressing mode obtained from the non-PHI roots of the graph
   // are equivalent.
   Value *Consensus = nullptr;
   unsigned NumUsesConsensus = 0;
   bool IsNumUsesConsensusValid = false;
   SmallVector<Instruction*, 16> AddrModeInsts;
   ExtAddrMode AddrMode;
   TypePromotionTransaction TPT;
   TypePromotionTransaction::ConstRestorationPt LastKnownGood =
       TPT.getRestorationPoint();
   while (!worklist.empty()) {
     Value *V = worklist.back();
     worklist.pop_back();
 
     // Break use-def graph loops.
     if (!Visited.insert(V).second) {
       Consensus = nullptr;
       break;
     }
 
     // For a PHI node, push all of its incoming values.
     if (PHINode *P = dyn_cast<PHINode>(V)) {
       for (Value *IncValue : P->incoming_values())
         worklist.push_back(IncValue);
       continue;
     }
 
     // For non-PHIs, determine the addressing mode being computed.
     SmallVector<Instruction*, 16> NewAddrModeInsts;
     ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
       V, AccessTy, AddrSpace, MemoryInst, NewAddrModeInsts, *TM,
       InsertedInsts, PromotedInsts, TPT);
 
     // This check is broken into two cases with very similar code to avoid using
     // getNumUses() as much as possible. Some values have a lot of uses, so
     // calling getNumUses() unconditionally caused a significant compile-time
     // regression.
     if (!Consensus) {
       Consensus = V;
       AddrMode = NewAddrMode;
       AddrModeInsts = NewAddrModeInsts;
       continue;
     } else if (NewAddrMode == AddrMode) {
       if (!IsNumUsesConsensusValid) {
         NumUsesConsensus = Consensus->getNumUses();
         IsNumUsesConsensusValid = true;
       }
 
       // Ensure that the obtained addressing mode is equivalent to that obtained
       // for all other roots of the PHI traversal.  Also, when choosing one
       // such root as representative, select the one with the most uses in order
       // to keep the cost modeling heuristics in AddressingModeMatcher
       // applicable.
       unsigned NumUses = V->getNumUses();
       if (NumUses > NumUsesConsensus) {
         Consensus = V;
         NumUsesConsensus = NumUses;
         AddrModeInsts = NewAddrModeInsts;
       }
       continue;
     }
 
     Consensus = nullptr;
     break;
   }
 
   // If the addressing mode couldn't be determined, or if multiple different
   // ones were determined, bail out now.
   if (!Consensus) {
     TPT.rollback(LastKnownGood);
     return false;
   }
   TPT.commit();
 
   // Check to see if any of the instructions supersumed by this addr mode are
   // non-local to I's BB.
   bool AnyNonLocal = false;
   for (unsigned i = 0, e = AddrModeInsts.size(); i != e; ++i) {
     if (IsNonLocalValue(AddrModeInsts[i], MemoryInst->getParent())) {
       AnyNonLocal = true;
       break;
     }
   }
 
   // If all the instructions matched are already in this BB, don't do anything.
   if (!AnyNonLocal) {
     DEBUG(dbgs() << "CGP: Found      local addrmode: " << AddrMode << "\n");
     return false;
   }
 
   // Insert this computation right after this user.  Since our caller is
   // scanning from the top of the BB to the bottom, reuse of the expr are
   // guaranteed to happen later.
   IRBuilder<> Builder(MemoryInst);
 
   // Now that we determined the addressing expression we want to use and know
   // that we have to sink it into this block.  Check to see if we have already
   // done this for some other load/store instr in this block.  If so, reuse the
   // computation.
   Value *&SunkAddr = SunkAddrs[Addr];
   if (SunkAddr) {
     DEBUG(dbgs() << "CGP: Reusing nonlocal addrmode: " << AddrMode << " for "
                  << *MemoryInst << "\n");
     if (SunkAddr->getType() != Addr->getType())
       SunkAddr = Builder.CreateBitCast(SunkAddr, Addr->getType());
   } else if (AddrSinkUsingGEPs ||
              (!AddrSinkUsingGEPs.getNumOccurrences() && TM &&
               TM->getSubtargetImpl(*MemoryInst->getParent()->getParent())
                   ->useAA())) {
     // By default, we use the GEP-based method when AA is used later. This
     // prevents new inttoptr/ptrtoint pairs from degrading AA capabilities.
     DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "
                  << *MemoryInst << "\n");
     Type *IntPtrTy = DL->getIntPtrType(Addr->getType());
     Value *ResultPtr = nullptr, *ResultIndex = nullptr;
 
     // First, find the pointer.
     if (AddrMode.BaseReg && AddrMode.BaseReg->getType()->isPointerTy()) {
       ResultPtr = AddrMode.BaseReg;
       AddrMode.BaseReg = nullptr;
     }
 
     if (AddrMode.Scale && AddrMode.ScaledReg->getType()->isPointerTy()) {
       // We can't add more than one pointer together, nor can we scale a
       // pointer (both of which seem meaningless).
       if (ResultPtr || AddrMode.Scale != 1)
         return false;
 
       ResultPtr = AddrMode.ScaledReg;
       AddrMode.Scale = 0;
     }
 
     if (AddrMode.BaseGV) {
       if (ResultPtr)
         return false;
 
       ResultPtr = AddrMode.BaseGV;
     }
 
     // If the real base value actually came from an inttoptr, then the matcher
     // will look through it and provide only the integer value. In that case,
     // use it here.
     if (!ResultPtr && AddrMode.BaseReg) {
       ResultPtr =
         Builder.CreateIntToPtr(AddrMode.BaseReg, Addr->getType(), "sunkaddr");
       AddrMode.BaseReg = nullptr;
     } else if (!ResultPtr && AddrMode.Scale == 1) {
       ResultPtr =
         Builder.CreateIntToPtr(AddrMode.ScaledReg, Addr->getType(), "sunkaddr");
       AddrMode.Scale = 0;
     }
 
     if (!ResultPtr &&
         !AddrMode.BaseReg && !AddrMode.Scale && !AddrMode.BaseOffs) {
       SunkAddr = Constant::getNullValue(Addr->getType());
     } else if (!ResultPtr) {
       return false;
     } else {
       Type *I8PtrTy =
           Builder.getInt8PtrTy(Addr->getType()->getPointerAddressSpace());
       Type *I8Ty = Builder.getInt8Ty();
 
       // Start with the base register. Do this first so that subsequent address
       // matching finds it last, which will prevent it from trying to match it
       // as the scaled value in case it happens to be a mul. That would be
       // problematic if we've sunk a different mul for the scale, because then
       // we'd end up sinking both muls.
       if (AddrMode.BaseReg) {
         Value *V = AddrMode.BaseReg;
         if (V->getType() != IntPtrTy)
           V = Builder.CreateIntCast(V, IntPtrTy, /*isSigned=*/true, "sunkaddr");
 
         ResultIndex = V;
       }
 
       // Add the scale value.
       if (AddrMode.Scale) {
         Value *V = AddrMode.ScaledReg;
         if (V->getType() == IntPtrTy) {
           // done.
         } else if (cast<IntegerType>(IntPtrTy)->getBitWidth() <
                    cast<IntegerType>(V->getType())->getBitWidth()) {
           V = Builder.CreateTrunc(V, IntPtrTy, "sunkaddr");
         } else {
           // It is only safe to sign extend the BaseReg if we know that the math
           // required to create it did not overflow before we extend it. Since
           // the original IR value was tossed in favor of a constant back when
           // the AddrMode was created we need to bail out gracefully if widths
           // do not match instead of extending it.
           Instruction *I = dyn_cast_or_null<Instruction>(ResultIndex);
           if (I && (ResultIndex != AddrMode.BaseReg))
             I->eraseFromParent();
           return false;
         }
 
         if (AddrMode.Scale != 1)
           V = Builder.CreateMul(V, ConstantInt::get(IntPtrTy, AddrMode.Scale),
                                 "sunkaddr");
         if (ResultIndex)
           ResultIndex = Builder.CreateAdd(ResultIndex, V, "sunkaddr");
         else
           ResultIndex = V;
       }
 
       // Add in the Base Offset if present.
       if (AddrMode.BaseOffs) {
         Value *V = ConstantInt::get(IntPtrTy, AddrMode.BaseOffs);
         if (ResultIndex) {
           // We need to add this separately from the scale above to help with
           // SDAG consecutive load/store merging.
           if (ResultPtr->getType() != I8PtrTy)
             ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
           ResultPtr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
         }
 
         ResultIndex = V;
       }
 
       if (!ResultIndex) {
         SunkAddr = ResultPtr;
       } else {
         if (ResultPtr->getType() != I8PtrTy)
           ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
         SunkAddr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
       }
 
       if (SunkAddr->getType() != Addr->getType())
         SunkAddr = Builder.CreateBitCast(SunkAddr, Addr->getType());
     }
   } else {
     DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "
                  << *MemoryInst << "\n");
     Type *IntPtrTy = DL->getIntPtrType(Addr->getType());
     Value *Result = nullptr;
 
     // Start with the base register. Do this first so that subsequent address
     // matching finds it last, which will prevent it from trying to match it
     // as the scaled value in case it happens to be a mul. That would be
     // problematic if we've sunk a different mul for the scale, because then
     // we'd end up sinking both muls.
     if (AddrMode.BaseReg) {
       Value *V = AddrMode.BaseReg;
       if (V->getType()->isPointerTy())
         V = Builder.CreatePtrToInt(V, IntPtrTy, "sunkaddr");
       if (V->getType() != IntPtrTy)
         V = Builder.CreateIntCast(V, IntPtrTy, /*isSigned=*/true, "sunkaddr");
       Result = V;
     }
 
     // Add the scale value.
     if (AddrMode.Scale) {
       Value *V = AddrMode.ScaledReg;
       if (V->getType() == IntPtrTy) {
         // done.
       } else if (V->getType()->isPointerTy()) {
         V = Builder.CreatePtrToInt(V, IntPtrTy, "sunkaddr");
       } else if (cast<IntegerType>(IntPtrTy)->getBitWidth() <
                  cast<IntegerType>(V->getType())->getBitWidth()) {
         V = Builder.CreateTrunc(V, IntPtrTy, "sunkaddr");
       } else {
         // It is only safe to sign extend the BaseReg if we know that the math
         // required to create it did not overflow before we extend it. Since
         // the original IR value was tossed in favor of a constant back when
         // the AddrMode was created we need to bail out gracefully if widths
         // do not match instead of extending it.
         Instruction *I = dyn_cast_or_null<Instruction>(Result);
         if (I && (Result != AddrMode.BaseReg))
           I->eraseFromParent();
         return false;
       }
       if (AddrMode.Scale != 1)
         V = Builder.CreateMul(V, ConstantInt::get(IntPtrTy, AddrMode.Scale),
                               "sunkaddr");
       if (Result)
         Result = Builder.CreateAdd(Result, V, "sunkaddr");
       else
         Result = V;
     }
 
     // Add in the BaseGV if present.
     if (AddrMode.BaseGV) {
       Value *V = Builder.CreatePtrToInt(AddrMode.BaseGV, IntPtrTy, "sunkaddr");
       if (Result)
         Result = Builder.CreateAdd(Result, V, "sunkaddr");
       else
         Result = V;
     }
 
     // Add in the Base Offset if present.
     if (AddrMode.BaseOffs) {
       Value *V = ConstantInt::get(IntPtrTy, AddrMode.BaseOffs);
       if (Result)
         Result = Builder.CreateAdd(Result, V, "sunkaddr");
       else
         Result = V;
     }
 
     if (!Result)
       SunkAddr = Constant::getNullValue(Addr->getType());
     else
       SunkAddr = Builder.CreateIntToPtr(Result, Addr->getType(), "sunkaddr");
   }
 
   MemoryInst->replaceUsesOfWith(Repl, SunkAddr);
 
   // If we have no uses, recursively delete the value and all dead instructions
   // using it.
   if (Repl->use_empty()) {
     // This can cause recursive deletion, which can invalidate our iterator.
     // Use a WeakVH to hold onto it in case this happens.
     WeakVH IterHandle(&*CurInstIterator);
     BasicBlock *BB = CurInstIterator->getParent();
 
     RecursivelyDeleteTriviallyDeadInstructions(Repl, TLInfo);
 
     if (IterHandle != CurInstIterator.getNodePtrUnchecked()) {
       // If the iterator instruction was recursively deleted, start over at the
       // start of the block.
       CurInstIterator = BB->begin();
       SunkAddrs.clear();
     }
   }
   ++NumMemoryInsts;
   return true;
 }
 
 /// If there are any memory operands, use OptimizeMemoryInst to sink their
 /// address computing into the block when possible / profitable.
 bool CodeGenPrepare::optimizeInlineAsmInst(CallInst *CS) {
   bool MadeChange = false;
 
   const TargetRegisterInfo *TRI =
       TM->getSubtargetImpl(*CS->getParent()->getParent())->getRegisterInfo();
   TargetLowering::AsmOperandInfoVector TargetConstraints =
       TLI->ParseConstraints(*DL, TRI, CS);
   unsigned ArgNo = 0;
   for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
     TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];
 
     // Compute the constraint code and ConstraintType to use.
     TLI->ComputeConstraintToUse(OpInfo, SDValue());
 
     if (OpInfo.ConstraintType == TargetLowering::C_Memory &&
         OpInfo.isIndirect) {
       Value *OpVal = CS->getArgOperand(ArgNo++);
       MadeChange |= optimizeMemoryInst(CS, OpVal, OpVal->getType(), ~0u);
     } else if (OpInfo.Type == InlineAsm::isInput)
       ArgNo++;
   }
 
   return MadeChange;
 }
 
 /// \brief Check if all the uses of \p Inst are equivalent (or free) zero or
 /// sign extensions.
 static bool hasSameExtUse(Instruction *Inst, const TargetLowering &TLI) {
   assert(!Inst->use_empty() && "Input must have at least one use");
   const Instruction *FirstUser = cast<Instruction>(*Inst->user_begin());
   bool IsSExt = isa<SExtInst>(FirstUser);
   Type *ExtTy = FirstUser->getType();
   for (const User *U : Inst->users()) {
     const Instruction *UI = cast<Instruction>(U);
     if ((IsSExt && !isa<SExtInst>(UI)) || (!IsSExt && !isa<ZExtInst>(UI)))
       return false;
     Type *CurTy = UI->getType();
     // Same input and output types: Same instruction after CSE.
     if (CurTy == ExtTy)
       continue;
 
     // If IsSExt is true, we are in this situation:
     // a = Inst
     // b = sext ty1 a to ty2
     // c = sext ty1 a to ty3
     // Assuming ty2 is shorter than ty3, this could be turned into:
     // a = Inst
     // b = sext ty1 a to ty2
     // c = sext ty2 b to ty3
     // However, the last sext is not free.
     if (IsSExt)
       return false;
 
     // This is a ZExt, maybe this is free to extend from one type to another.
     // In that case, we would not account for a different use.
     Type *NarrowTy;
     Type *LargeTy;
     if (ExtTy->getScalarType()->getIntegerBitWidth() >
         CurTy->getScalarType()->getIntegerBitWidth()) {
       NarrowTy = CurTy;
       LargeTy = ExtTy;
     } else {
       NarrowTy = ExtTy;
       LargeTy = CurTy;
     }
 
     if (!TLI.isZExtFree(NarrowTy, LargeTy))
       return false;
   }
   // All uses are the same or can be derived from one another for free.
   return true;
 }
 
 /// \brief Try to form ExtLd by promoting \p Exts until they reach a
 /// load instruction.
 /// If an ext(load) can be formed, it is returned via \p LI for the load
 /// and \p Inst for the extension.
 /// Otherwise LI == nullptr and Inst == nullptr.
 /// When some promotion happened, \p TPT contains the proper state to
 /// revert them.
 ///
 /// \return true when promoting was necessary to expose the ext(load)
 /// opportunity, false otherwise.
 ///
 /// Example:
 /// \code
 /// %ld = load i32* %addr
 /// %add = add nuw i32 %ld, 4
 /// %zext = zext i32 %add to i64
 /// \endcode
 /// =>
 /// \code
 /// %ld = load i32* %addr
 /// %zext = zext i32 %ld to i64
 /// %add = add nuw i64 %zext, 4
 /// \encode
 /// Thanks to the promotion, we can match zext(load i32*) to i64.
 bool CodeGenPrepare::extLdPromotion(TypePromotionTransaction &TPT,
                                     LoadInst *&LI, Instruction *&Inst,
                                     const SmallVectorImpl<Instruction *> &Exts,
                                     unsigned CreatedInstsCost = 0) {
   // Iterate over all the extensions to see if one form an ext(load).
   for (auto I : Exts) {
     // Check if we directly have ext(load).
     if ((LI = dyn_cast<LoadInst>(I->getOperand(0)))) {
       Inst = I;
       // No promotion happened here.
       return false;
     }
     // Check whether or not we want to do any promotion.
     if (!TLI || !TLI->enableExtLdPromotion() || DisableExtLdPromotion)
       continue;
     // Get the action to perform the promotion.
     TypePromotionHelper::Action TPH = TypePromotionHelper::getAction(
         I, InsertedInsts, *TLI, PromotedInsts);
     // Check if we can promote.
     if (!TPH)
       continue;
     // Save the current state.
     TypePromotionTransaction::ConstRestorationPt LastKnownGood =
         TPT.getRestorationPoint();
     SmallVector<Instruction *, 4> NewExts;
     unsigned NewCreatedInstsCost = 0;
     unsigned ExtCost = !TLI->isExtFree(I);
     // Promote.
     Value *PromotedVal = TPH(I, TPT, PromotedInsts, NewCreatedInstsCost,
                              &NewExts, nullptr, *TLI);
     assert(PromotedVal &&
            "TypePromotionHelper should have filtered out those cases");
 
     // We would be able to merge only one extension in a load.
     // Therefore, if we have more than 1 new extension we heuristically
     // cut this search path, because it means we degrade the code quality.
     // With exactly 2, the transformation is neutral, because we will merge
     // one extension but leave one. However, we optimistically keep going,
     // because the new extension may be removed too.
     long long TotalCreatedInstsCost = CreatedInstsCost + NewCreatedInstsCost;
     TotalCreatedInstsCost -= ExtCost;
     if (!StressExtLdPromotion &&
         (TotalCreatedInstsCost > 1 ||
          !isPromotedInstructionLegal(*TLI, *DL, PromotedVal))) {
       // The promotion is not profitable, rollback to the previous state.
       TPT.rollback(LastKnownGood);
       continue;
     }
     // The promotion is profitable.
     // Check if it exposes an ext(load).
     (void)extLdPromotion(TPT, LI, Inst, NewExts, TotalCreatedInstsCost);
     if (LI && (StressExtLdPromotion || NewCreatedInstsCost <= ExtCost ||
                // If we have created a new extension, i.e., now we have two
                // extensions. We must make sure one of them is merged with
                // the load, otherwise we may degrade the code quality.
                (LI->hasOneUse() || hasSameExtUse(LI, *TLI))))
       // Promotion happened.
       return true;
     // If this does not help to expose an ext(load) then, rollback.
     TPT.rollback(LastKnownGood);
   }
   // None of the extension can form an ext(load).
   LI = nullptr;
   Inst = nullptr;
   return false;
 }
 
 /// Move a zext or sext fed by a load into the same basic block as the load,
 /// unless conditions are unfavorable. This allows SelectionDAG to fold the
 /// extend into the load.
 /// \p I[in/out] the extension may be modified during the process if some
 /// promotions apply.
 ///
 bool CodeGenPrepare::moveExtToFormExtLoad(Instruction *&I) {
   // Try to promote a chain of computation if it allows to form
   // an extended load.
   TypePromotionTransaction TPT;
   TypePromotionTransaction::ConstRestorationPt LastKnownGood =
     TPT.getRestorationPoint();
   SmallVector<Instruction *, 1> Exts;
   Exts.push_back(I);
   // Look for a load being extended.
   LoadInst *LI = nullptr;
   Instruction *OldExt = I;
   bool HasPromoted = extLdPromotion(TPT, LI, I, Exts);
   if (!LI || !I) {
     assert(!HasPromoted && !LI && "If we did not match any load instruction "
                                   "the code must remain the same");
     I = OldExt;
     return false;
   }
 
   // If they're already in the same block, there's nothing to do.
   // Make the cheap checks first if we did not promote.
   // If we promoted, we need to check if it is indeed profitable.
   if (!HasPromoted && LI->getParent() == I->getParent())
     return false;
 
   EVT VT = TLI->getValueType(*DL, I->getType());
   EVT LoadVT = TLI->getValueType(*DL, LI->getType());
 
   // If the load has other users and the truncate is not free, this probably
   // isn't worthwhile.
   if (!LI->hasOneUse() && TLI &&
       (TLI->isTypeLegal(LoadVT) || !TLI->isTypeLegal(VT)) &&
       !TLI->isTruncateFree(I->getType(), LI->getType())) {
     I = OldExt;
     TPT.rollback(LastKnownGood);
     return false;
   }
 
   // Check whether the target supports casts folded into loads.
   unsigned LType;
   if (isa<ZExtInst>(I))
     LType = ISD::ZEXTLOAD;
   else {
     assert(isa<SExtInst>(I) && "Unexpected ext type!");
     LType = ISD::SEXTLOAD;
   }
   if (TLI && !TLI->isLoadExtLegal(LType, VT, LoadVT)) {
     I = OldExt;
     TPT.rollback(LastKnownGood);
     return false;
   }
 
   // Move the extend into the same block as the load, so that SelectionDAG
   // can fold it.
   TPT.commit();
   I->removeFromParent();
   I->insertAfter(LI);
   ++NumExtsMoved;
   return true;
 }
 
 bool CodeGenPrepare::optimizeExtUses(Instruction *I) {
   BasicBlock *DefBB = I->getParent();
 
   // If the result of a {s|z}ext and its source are both live out, rewrite all
   // other uses of the source with result of extension.
   Value *Src = I->getOperand(0);
   if (Src->hasOneUse())
     return false;
 
   // Only do this xform if truncating is free.
   if (TLI && !TLI->isTruncateFree(I->getType(), Src->getType()))
     return false;
 
   // Only safe to perform the optimization if the source is also defined in
   // this block.
   if (!isa<Instruction>(Src) || DefBB != cast<Instruction>(Src)->getParent())
     return false;
 
   bool DefIsLiveOut = false;
   for (User *U : I->users()) {
     Instruction *UI = cast<Instruction>(U);
 
     // Figure out which BB this ext is used in.
     BasicBlock *UserBB = UI->getParent();
     if (UserBB == DefBB) continue;
     DefIsLiveOut = true;
     break;
   }
   if (!DefIsLiveOut)
     return false;
 
   // Make sure none of the uses are PHI nodes.
   for (User *U : Src->users()) {
     Instruction *UI = cast<Instruction>(U);
     BasicBlock *UserBB = UI->getParent();
     if (UserBB == DefBB) continue;
     // Be conservative. We don't want this xform to end up introducing
     // reloads just before load / store instructions.
     if (isa<PHINode>(UI) || isa<LoadInst>(UI) || isa<StoreInst>(UI))
       return false;
   }
 
   // InsertedTruncs - Only insert one trunc in each block once.
   DenseMap<BasicBlock*, Instruction*> InsertedTruncs;
 
   bool MadeChange = false;
   for (Use &U : Src->uses()) {
     Instruction *User = cast<Instruction>(U.getUser());
 
     // Figure out which BB this ext is used in.
     BasicBlock *UserBB = User->getParent();
     if (UserBB == DefBB) continue;
 
     // Both src and def are live in this block. Rewrite the use.
     Instruction *&InsertedTrunc = InsertedTruncs[UserBB];
 
     if (!InsertedTrunc) {
       BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
       assert(InsertPt != UserBB->end());
       InsertedTrunc = new TruncInst(I, Src->getType(), "", &*InsertPt);
       InsertedInsts.insert(InsertedTrunc);
     }
 
     // Replace a use of the {s|z}ext source with a use of the result.
     U = InsertedTrunc;
     ++NumExtUses;
     MadeChange = true;
   }
 
   return MadeChange;
 }
 
 // Find loads whose uses only use some of the loaded value's bits.  Add an "and"
 // just after the load if the target can fold this into one extload instruction,
 // with the hope of eliminating some of the other later "and" instructions using
 // the loaded value.  "and"s that are made trivially redundant by the insertion
 // of the new "and" are removed by this function, while others (e.g. those whose
 // path from the load goes through a phi) are left for isel to potentially
 // remove.
 //
 // For example:
 //
 // b0:
 //   x = load i32
 //   ...
 // b1:
 //   y = and x, 0xff
 //   z = use y
 //
 // becomes:
 //
 // b0:
 //   x = load i32
 //   x' = and x, 0xff
 //   ...
 // b1:
 //   z = use x'
 //
 // whereas:
 //
 // b0:
 //   x1 = load i32
 //   ...
 // b1:
 //   x2 = load i32
 //   ...
 // b2:
 //   x = phi x1, x2
 //   y = and x, 0xff
 //
 // becomes (after a call to optimizeLoadExt for each load):
 //
 // b0:
 //   x1 = load i32
 //   x1' = and x1, 0xff
 //   ...
 // b1:
 //   x2 = load i32
 //   x2' = and x2, 0xff
 //   ...
 // b2:
 //   x = phi x1', x2'
 //   y = and x, 0xff
 //
 
 bool CodeGenPrepare::optimizeLoadExt(LoadInst *Load) {
 
   if (!Load->isSimple() ||
       !(Load->getType()->isIntegerTy() || Load->getType()->isPointerTy()))
     return false;
 
   // Skip loads we've already transformed or have no reason to transform.
   if (Load->hasOneUse()) {
     User *LoadUser = *Load->user_begin();
     if (cast<Instruction>(LoadUser)->getParent() == Load->getParent() &&
         !dyn_cast<PHINode>(LoadUser))
       return false;
   }
 
   // Look at all uses of Load, looking through phis, to determine how many bits
   // of the loaded value are needed.
   SmallVector<Instruction *, 8> WorkList;
   SmallPtrSet<Instruction *, 16> Visited;
   SmallVector<Instruction *, 8> AndsToMaybeRemove;
   for (auto *U : Load->users())
     WorkList.push_back(cast<Instruction>(U));
 
   EVT LoadResultVT = TLI->getValueType(*DL, Load->getType());
   unsigned BitWidth = LoadResultVT.getSizeInBits();
   APInt DemandBits(BitWidth, 0);
   APInt WidestAndBits(BitWidth, 0);
 
   while (!WorkList.empty()) {
     Instruction *I = WorkList.back();
     WorkList.pop_back();
 
     // Break use-def graph loops.
     if (!Visited.insert(I).second)
       continue;
 
     // For a PHI node, push all of its users.
     if (auto *Phi = dyn_cast<PHINode>(I)) {
       for (auto *U : Phi->users())
         WorkList.push_back(cast<Instruction>(U));
       continue;
     }
 
     switch (I->getOpcode()) {
     case llvm::Instruction::And: {
       auto *AndC = dyn_cast<ConstantInt>(I->getOperand(1));
       if (!AndC)
         return false;
       APInt AndBits = AndC->getValue();
       DemandBits |= AndBits;
       // Keep track of the widest and mask we see.
       if (AndBits.ugt(WidestAndBits))
         WidestAndBits = AndBits;
       if (AndBits == WidestAndBits && I->getOperand(0) == Load)
         AndsToMaybeRemove.push_back(I);
       break;
     }
 
     case llvm::Instruction::Shl: {
       auto *ShlC = dyn_cast<ConstantInt>(I->getOperand(1));
       if (!ShlC)
         return false;
       uint64_t ShiftAmt = ShlC->getLimitedValue(BitWidth - 1);
       auto ShlDemandBits = APInt::getAllOnesValue(BitWidth).lshr(ShiftAmt);
       DemandBits |= ShlDemandBits;
       break;
     }
 
     case llvm::Instruction::Trunc: {
       EVT TruncVT = TLI->getValueType(*DL, I->getType());
       unsigned TruncBitWidth = TruncVT.getSizeInBits();
       auto TruncBits = APInt::getAllOnesValue(TruncBitWidth).zext(BitWidth);
       DemandBits |= TruncBits;
       break;
     }
 
     default:
       return false;
     }
   }
 
   uint32_t ActiveBits = DemandBits.getActiveBits();
   // Avoid hoisting (and (load x) 1) since it is unlikely to be folded by the
   // target even if isLoadExtLegal says an i1 EXTLOAD is valid.  For example,
   // for the AArch64 target isLoadExtLegal(ZEXTLOAD, i32, i1) returns true, but
   // (and (load x) 1) is not matched as a single instruction, rather as a LDR
   // followed by an AND.
   // TODO: Look into removing this restriction by fixing backends to either
   // return false for isLoadExtLegal for i1 or have them select this pattern to
   // a single instruction.
   //
   // Also avoid hoisting if we didn't see any ands with the exact DemandBits
   // mask, since these are the only ands that will be removed by isel.
   if (ActiveBits <= 1 || !APIntOps::isMask(ActiveBits, DemandBits) ||
       WidestAndBits != DemandBits)
     return false;
 
   LLVMContext &Ctx = Load->getType()->getContext();
   Type *TruncTy = Type::getIntNTy(Ctx, ActiveBits);
   EVT TruncVT = TLI->getValueType(*DL, TruncTy);
 
   // Reject cases that won't be matched as extloads.
   if (!LoadResultVT.bitsGT(TruncVT) || !TruncVT.isRound() ||
       !TLI->isLoadExtLegal(ISD::ZEXTLOAD, LoadResultVT, TruncVT))
     return false;
 
   IRBuilder<> Builder(Load->getNextNode());
   auto *NewAnd = dyn_cast<Instruction>(
       Builder.CreateAnd(Load, ConstantInt::get(Ctx, DemandBits)));
 
   // Replace all uses of load with new and (except for the use of load in the
   // new and itself).
   Load->replaceAllUsesWith(NewAnd);
   NewAnd->setOperand(0, Load);
 
   // Remove any and instructions that are now redundant.
   for (auto *And : AndsToMaybeRemove)
     // Check that the and mask is the same as the one we decided to put on the
     // new and.
     if (cast<ConstantInt>(And->getOperand(1))->getValue() == DemandBits) {
       And->replaceAllUsesWith(NewAnd);
       if (&*CurInstIterator == And)
         CurInstIterator = std::next(And->getIterator());
       And->eraseFromParent();
       ++NumAndUses;
     }
 
   ++NumAndsAdded;
   return true;
 }
 
 /// Check if V (an operand of a select instruction) is an expensive instruction
 /// that is only used once.
 static bool sinkSelectOperand(const TargetTransformInfo *TTI, Value *V) {
   auto *I = dyn_cast<Instruction>(V);
   // If it's safe to speculatively execute, then it should not have side
   // effects; therefore, it's safe to sink and possibly *not* execute.
   return I && I->hasOneUse() && isSafeToSpeculativelyExecute(I) &&
          TTI->getUserCost(I) >= TargetTransformInfo::TCC_Expensive;
 }
 
 /// Returns true if a SelectInst should be turned into an explicit branch.
 static bool isFormingBranchFromSelectProfitable(const TargetTransformInfo *TTI,
                                                 SelectInst *SI) {
   // FIXME: This should use the same heuristics as IfConversion to determine
   // whether a select is better represented as a branch.  This requires that
   // branch probability metadata is preserved for the select, which is not the
   // case currently.
 
   CmpInst *Cmp = dyn_cast<CmpInst>(SI->getCondition());
 
   // If a branch is predictable, an out-of-order CPU can avoid blocking on its
   // comparison condition. If the compare has more than one use, there's
   // probably another cmov or setcc around, so it's not worth emitting a branch.
   if (!Cmp || !Cmp->hasOneUse())
     return false;
 
   Value *CmpOp0 = Cmp->getOperand(0);
   Value *CmpOp1 = Cmp->getOperand(1);
 
   // Emit "cmov on compare with a memory operand" as a branch to avoid stalls
   // on a load from memory. But if the load is used more than once, do not
   // change the select to a branch because the load is probably needed
   // regardless of whether the branch is taken or not.
   if ((isa<LoadInst>(CmpOp0) && CmpOp0->hasOneUse()) ||
       (isa<LoadInst>(CmpOp1) && CmpOp1->hasOneUse()))
     return true;
 
   // If either operand of the select is expensive and only needed on one side
   // of the select, we should form a branch.
   if (sinkSelectOperand(TTI, SI->getTrueValue()) ||
       sinkSelectOperand(TTI, SI->getFalseValue()))
     return true;
 
   return false;
 }
 
 
 /// If we have a SelectInst that will likely profit from branch prediction,
 /// turn it into a branch.
 bool CodeGenPrepare::optimizeSelectInst(SelectInst *SI) {
   bool VectorCond = !SI->getCondition()->getType()->isIntegerTy(1);
 
   // Can we convert the 'select' to CF ?
   if (DisableSelectToBranch || OptSize || !TLI || VectorCond)
     return false;
 
   TargetLowering::SelectSupportKind SelectKind;
   if (VectorCond)
     SelectKind = TargetLowering::VectorMaskSelect;
   else if (SI->getType()->isVectorTy())
     SelectKind = TargetLowering::ScalarCondVectorVal;
   else
     SelectKind = TargetLowering::ScalarValSelect;
 
   // Do we have efficient codegen support for this kind of 'selects' ?
   if (TLI->isSelectSupported(SelectKind)) {
     // We have efficient codegen support for the select instruction.
     // Check if it is profitable to keep this 'select'.
     if (!TLI->isPredictableSelectExpensive() ||
         !isFormingBranchFromSelectProfitable(TTI, SI))
       return false;
   }
 
   ModifiedDT = true;
 
   // Transform a sequence like this:
   //    start:
   //       %cmp = cmp uge i32 %a, %b
   //       %sel = select i1 %cmp, i32 %c, i32 %d
   //
   // Into:
   //    start:
   //       %cmp = cmp uge i32 %a, %b
   //       br i1 %cmp, label %select.true, label %select.false
   //    select.true:
   //       br label %select.end
   //    select.false:
   //       br label %select.end
   //    select.end:
   //       %sel = phi i32 [ %c, %select.true ], [ %d, %select.false ]
   //
   // In addition, we may sink instructions that produce %c or %d from
   // the entry block into the destination(s) of the new branch.
   // If the true or false blocks do not contain a sunken instruction, that
   // block and its branch may be optimized away. In that case, one side of the
   // first branch will point directly to select.end, and the corresponding PHI
   // predecessor block will be the start block.
 
   // First, we split the block containing the select into 2 blocks.
   BasicBlock *StartBlock = SI->getParent();
   BasicBlock::iterator SplitPt = ++(BasicBlock::iterator(SI));
   BasicBlock *EndBlock = StartBlock->splitBasicBlock(SplitPt, "select.end");
 
   // Delete the unconditional branch that was just created by the split.
   StartBlock->getTerminator()->eraseFromParent();
 
   // These are the new basic blocks for the conditional branch.
   // At least one will become an actual new basic block.
   BasicBlock *TrueBlock = nullptr;
   BasicBlock *FalseBlock = nullptr;
 
   // Sink expensive instructions into the conditional blocks to avoid executing
   // them speculatively.
   if (sinkSelectOperand(TTI, SI->getTrueValue())) {
     TrueBlock = BasicBlock::Create(SI->getContext(), "select.true.sink",
                                    EndBlock->getParent(), EndBlock);
     auto *TrueBranch = BranchInst::Create(EndBlock, TrueBlock);
     auto *TrueInst = cast<Instruction>(SI->getTrueValue());
     TrueInst->moveBefore(TrueBranch);
   }
   if (sinkSelectOperand(TTI, SI->getFalseValue())) {
     FalseBlock = BasicBlock::Create(SI->getContext(), "select.false.sink",
                                     EndBlock->getParent(), EndBlock);
     auto *FalseBranch = BranchInst::Create(EndBlock, FalseBlock);
     auto *FalseInst = cast<Instruction>(SI->getFalseValue());
     FalseInst->moveBefore(FalseBranch);
   }
 
   // If there was nothing to sink, then arbitrarily choose the 'false' side
   // for a new input value to the PHI.
   if (TrueBlock == FalseBlock) {
     assert(TrueBlock == nullptr &&
            "Unexpected basic block transform while optimizing select");
 
     FalseBlock = BasicBlock::Create(SI->getContext(), "select.false",
                                     EndBlock->getParent(), EndBlock);
     BranchInst::Create(EndBlock, FalseBlock);
   }
 
   // Insert the real conditional branch based on the original condition.
   // If we did not create a new block for one of the 'true' or 'false' paths
   // of the condition, it means that side of the branch goes to the end block
   // directly and the path originates from the start block from the point of
   // view of the new PHI.
   if (TrueBlock == nullptr) {
     BranchInst::Create(EndBlock, FalseBlock, SI->getCondition(), SI);
     TrueBlock = StartBlock;
   } else if (FalseBlock == nullptr) {
     BranchInst::Create(TrueBlock, EndBlock, SI->getCondition(), SI);
     FalseBlock = StartBlock;
   } else {
     BranchInst::Create(TrueBlock, FalseBlock, SI->getCondition(), SI);
   }
 
   // The select itself is replaced with a PHI Node.
   PHINode *PN = PHINode::Create(SI->getType(), 2, "", &EndBlock->front());
   PN->takeName(SI);
   PN->addIncoming(SI->getTrueValue(), TrueBlock);
   PN->addIncoming(SI->getFalseValue(), FalseBlock);
 
   SI->replaceAllUsesWith(PN);
   SI->eraseFromParent();
 
   // Instruct OptimizeBlock to skip to the next block.
   CurInstIterator = StartBlock->end();
   ++NumSelectsExpanded;
   return true;
 }
 
 static bool isBroadcastShuffle(ShuffleVectorInst *SVI) {
   SmallVector<int, 16> Mask(SVI->getShuffleMask());
   int SplatElem = -1;
   for (unsigned i = 0; i < Mask.size(); ++i) {
     if (SplatElem != -1 && Mask[i] != -1 && Mask[i] != SplatElem)
       return false;
     SplatElem = Mask[i];
   }
 
   return true;
 }
 
 /// Some targets have expensive vector shifts if the lanes aren't all the same
 /// (e.g. x86 only introduced "vpsllvd" and friends with AVX2). In these cases
 /// it's often worth sinking a shufflevector splat down to its use so that
 /// codegen can spot all lanes are identical.
 bool CodeGenPrepare::optimizeShuffleVectorInst(ShuffleVectorInst *SVI) {
   BasicBlock *DefBB = SVI->getParent();
 
   // Only do this xform if variable vector shifts are particularly expensive.
   if (!TLI || !TLI->isVectorShiftByScalarCheap(SVI->getType()))
     return false;
 
   // We only expect better codegen by sinking a shuffle if we can recognise a
   // constant splat.
   if (!isBroadcastShuffle(SVI))
     return false;
 
   // InsertedShuffles - Only insert a shuffle in each block once.
   DenseMap<BasicBlock*, Instruction*> InsertedShuffles;
 
   bool MadeChange = false;
   for (User *U : SVI->users()) {
     Instruction *UI = cast<Instruction>(U);
 
     // Figure out which BB this ext is used in.
     BasicBlock *UserBB = UI->getParent();
     if (UserBB == DefBB) continue;
 
     // For now only apply this when the splat is used by a shift instruction.
     if (!UI->isShift()) continue;
 
     // Everything checks out, sink the shuffle if the user's block doesn't
     // already have a copy.
     Instruction *&InsertedShuffle = InsertedShuffles[UserBB];
 
     if (!InsertedShuffle) {
       BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
       assert(InsertPt != UserBB->end());
       InsertedShuffle =
           new ShuffleVectorInst(SVI->getOperand(0), SVI->getOperand(1),
                                 SVI->getOperand(2), "", &*InsertPt);
     }
 
     UI->replaceUsesOfWith(SVI, InsertedShuffle);
     MadeChange = true;
   }
 
   // If we removed all uses, nuke the shuffle.
   if (SVI->use_empty()) {
     SVI->eraseFromParent();
     MadeChange = true;
   }
 
   return MadeChange;
 }
 
 bool CodeGenPrepare::optimizeSwitchInst(SwitchInst *SI) {
   if (!TLI || !DL)
     return false;
 
   Value *Cond = SI->getCondition();
   Type *OldType = Cond->getType();
   LLVMContext &Context = Cond->getContext();
   MVT RegType = TLI->getRegisterType(Context, TLI->getValueType(*DL, OldType));
   unsigned RegWidth = RegType.getSizeInBits();
 
   if (RegWidth <= cast<IntegerType>(OldType)->getBitWidth())
     return false;
 
   // If the register width is greater than the type width, expand the condition
   // of the switch instruction and each case constant to the width of the
   // register. By widening the type of the switch condition, subsequent
   // comparisons (for case comparisons) will not need to be extended to the
   // preferred register width, so we will potentially eliminate N-1 extends,
   // where N is the number of cases in the switch.
   auto *NewType = Type::getIntNTy(Context, RegWidth);
 
   // Zero-extend the switch condition and case constants unless the switch
   // condition is a function argument that is already being sign-extended.
   // In that case, we can avoid an unnecessary mask/extension by sign-extending
   // everything instead.
   Instruction::CastOps ExtType = Instruction::ZExt;
   if (auto *Arg = dyn_cast<Argument>(Cond))
     if (Arg->hasSExtAttr())
       ExtType = Instruction::SExt;
 
   auto *ExtInst = CastInst::Create(ExtType, Cond, NewType);
   ExtInst->insertBefore(SI);
   SI->setCondition(ExtInst);
   for (SwitchInst::CaseIt Case : SI->cases()) {
     APInt NarrowConst = Case.getCaseValue()->getValue();
     APInt WideConst = (ExtType == Instruction::ZExt) ?
                       NarrowConst.zext(RegWidth) : NarrowConst.sext(RegWidth);
     Case.setValue(ConstantInt::get(Context, WideConst));
   }
 
   return true;
 }
 
 namespace {
 /// \brief Helper class to promote a scalar operation to a vector one.
 /// This class is used to move downward extractelement transition.
 /// E.g.,
 /// a = vector_op <2 x i32>
 /// b = extractelement <2 x i32> a, i32 0
 /// c = scalar_op b
 /// store c
 ///
 /// =>
 /// a = vector_op <2 x i32>
 /// c = vector_op a (equivalent to scalar_op on the related lane)
 /// * d = extractelement <2 x i32> c, i32 0
 /// * store d
 /// Assuming both extractelement and store can be combine, we get rid of the
 /// transition.
 class VectorPromoteHelper {
   /// DataLayout associated with the current module.
   const DataLayout &DL;
 
   /// Used to perform some checks on the legality of vector operations.
   const TargetLowering &TLI;
 
   /// Used to estimated the cost of the promoted chain.
   const TargetTransformInfo &TTI;
 
   /// The transition being moved downwards.
   Instruction *Transition;
   /// The sequence of instructions to be promoted.
   SmallVector<Instruction *, 4> InstsToBePromoted;
   /// Cost of combining a store and an extract.
   unsigned StoreExtractCombineCost;
   /// Instruction that will be combined with the transition.
   Instruction *CombineInst;
 
   /// \brief The instruction that represents the current end of the transition.
   /// Since we are faking the promotion until we reach the end of the chain
   /// of computation, we need a way to get the current end of the transition.
   Instruction *getEndOfTransition() const {
     if (InstsToBePromoted.empty())
       return Transition;
     return InstsToBePromoted.back();
   }
 
   /// \brief Return the index of the original value in the transition.
   /// E.g., for "extractelement <2 x i32> c, i32 1" the original value,
   /// c, is at index 0.
   unsigned getTransitionOriginalValueIdx() const {
     assert(isa<ExtractElementInst>(Transition) &&
            "Other kind of transitions are not supported yet");
     return 0;
   }
 
   /// \brief Return the index of the index in the transition.
   /// E.g., for "extractelement <2 x i32> c, i32 0" the index
   /// is at index 1.
   unsigned getTransitionIdx() const {
     assert(isa<ExtractElementInst>(Transition) &&
            "Other kind of transitions are not supported yet");
     return 1;
   }
 
   /// \brief Get the type of the transition.
   /// This is the type of the original value.
   /// E.g., for "extractelement <2 x i32> c, i32 1" the type of the
   /// transition is <2 x i32>.
   Type *getTransitionType() const {
     return Transition->getOperand(getTransitionOriginalValueIdx())->getType();
   }
 
   /// \brief Promote \p ToBePromoted by moving \p Def downward through.
   /// I.e., we have the following sequence:
   /// Def = Transition <ty1> a to <ty2>
   /// b = ToBePromoted <ty2> Def, ...
   /// =>
   /// b = ToBePromoted <ty1> a, ...
   /// Def = Transition <ty1> ToBePromoted to <ty2>
   void promoteImpl(Instruction *ToBePromoted);
 
   /// \brief Check whether or not it is profitable to promote all the
   /// instructions enqueued to be promoted.
   bool isProfitableToPromote() {
     Value *ValIdx = Transition->getOperand(getTransitionOriginalValueIdx());
     unsigned Index = isa<ConstantInt>(ValIdx)
                          ? cast<ConstantInt>(ValIdx)->getZExtValue()
                          : -1;
     Type *PromotedType = getTransitionType();
 
     StoreInst *ST = cast<StoreInst>(CombineInst);
     unsigned AS = ST->getPointerAddressSpace();
     unsigned Align = ST->getAlignment();
     // Check if this store is supported.
     if (!TLI.allowsMisalignedMemoryAccesses(
             TLI.getValueType(DL, ST->getValueOperand()->getType()), AS,
             Align)) {
       // If this is not supported, there is no way we can combine
       // the extract with the store.
       return false;
     }
 
     // The scalar chain of computation has to pay for the transition
     // scalar to vector.
     // The vector chain has to account for the combining cost.
     uint64_t ScalarCost =
         TTI.getVectorInstrCost(Transition->getOpcode(), PromotedType, Index);
     uint64_t VectorCost = StoreExtractCombineCost;
     for (const auto &Inst : InstsToBePromoted) {
       // Compute the cost.
       // By construction, all instructions being promoted are arithmetic ones.
       // Moreover, one argument is a constant that can be viewed as a splat
       // constant.
       Value *Arg0 = Inst->getOperand(0);
       bool IsArg0Constant = isa<UndefValue>(Arg0) || isa<ConstantInt>(Arg0) ||
                             isa<ConstantFP>(Arg0);
       TargetTransformInfo::OperandValueKind Arg0OVK =
           IsArg0Constant ? TargetTransformInfo::OK_UniformConstantValue
                          : TargetTransformInfo::OK_AnyValue;
       TargetTransformInfo::OperandValueKind Arg1OVK =
           !IsArg0Constant ? TargetTransformInfo::OK_UniformConstantValue
                           : TargetTransformInfo::OK_AnyValue;
       ScalarCost += TTI.getArithmeticInstrCost(
           Inst->getOpcode(), Inst->getType(), Arg0OVK, Arg1OVK);
       VectorCost += TTI.getArithmeticInstrCost(Inst->getOpcode(), PromotedType,
                                                Arg0OVK, Arg1OVK);
     }
     DEBUG(dbgs() << "Estimated cost of computation to be promoted:\nScalar: "
                  << ScalarCost << "\nVector: " << VectorCost << '\n');
     return ScalarCost > VectorCost;
   }
 
   /// \brief Generate a constant vector with \p Val with the same
   /// number of elements as the transition.
   /// \p UseSplat defines whether or not \p Val should be replicated
   /// across the whole vector.
   /// In other words, if UseSplat == true, we generate <Val, Val, ..., Val>,
   /// otherwise we generate a vector with as many undef as possible:
   /// <undef, ..., undef, Val, undef, ..., undef> where \p Val is only
   /// used at the index of the extract.
   Value *getConstantVector(Constant *Val, bool UseSplat) const {
     unsigned ExtractIdx = UINT_MAX;
     if (!UseSplat) {
       // If we cannot determine where the constant must be, we have to
       // use a splat constant.
       Value *ValExtractIdx = Transition->getOperand(getTransitionIdx());
       if (ConstantInt *CstVal = dyn_cast<ConstantInt>(ValExtractIdx))
         ExtractIdx = CstVal->getSExtValue();
       else
         UseSplat = true;
     }
 
     unsigned End = getTransitionType()->getVectorNumElements();
     if (UseSplat)
       return ConstantVector::getSplat(End, Val);
 
     SmallVector<Constant *, 4> ConstVec;
     UndefValue *UndefVal = UndefValue::get(Val->getType());
     for (unsigned Idx = 0; Idx != End; ++Idx) {
       if (Idx == ExtractIdx)
         ConstVec.push_back(Val);
       else
         ConstVec.push_back(UndefVal);
     }
     return ConstantVector::get(ConstVec);
   }
 
   /// \brief Check if promoting to a vector type an operand at \p OperandIdx
   /// in \p Use can trigger undefined behavior.
   static bool canCauseUndefinedBehavior(const Instruction *Use,
                                         unsigned OperandIdx) {
     // This is not safe to introduce undef when the operand is on
     // the right hand side of a division-like instruction.
     if (OperandIdx != 1)
       return false;
     switch (Use->getOpcode()) {
     default:
       return false;
     case Instruction::SDiv:
     case Instruction::UDiv:
     case Instruction::SRem:
     case Instruction::URem:
       return true;
     case Instruction::FDiv:
     case Instruction::FRem:
       return !Use->hasNoNaNs();
     }
     llvm_unreachable(nullptr);
   }
 
 public:
   VectorPromoteHelper(const DataLayout &DL, const TargetLowering &TLI,
                       const TargetTransformInfo &TTI, Instruction *Transition,
                       unsigned CombineCost)
       : DL(DL), TLI(TLI), TTI(TTI), Transition(Transition),
         StoreExtractCombineCost(CombineCost), CombineInst(nullptr) {
     assert(Transition && "Do not know how to promote null");
   }
 
   /// \brief Check if we can promote \p ToBePromoted to \p Type.
   bool canPromote(const Instruction *ToBePromoted) const {
     // We could support CastInst too.
     return isa<BinaryOperator>(ToBePromoted);
   }
 
   /// \brief Check if it is profitable to promote \p ToBePromoted
   /// by moving downward the transition through.
   bool shouldPromote(const Instruction *ToBePromoted) const {
     // Promote only if all the operands can be statically expanded.
     // Indeed, we do not want to introduce any new kind of transitions.
     for (const Use &U : ToBePromoted->operands()) {
       const Value *Val = U.get();
       if (Val == getEndOfTransition()) {
         // If the use is a division and the transition is on the rhs,
         // we cannot promote the operation, otherwise we may create a
         // division by zero.
         if (canCauseUndefinedBehavior(ToBePromoted, U.getOperandNo()))
           return false;
         continue;
       }
       if (!isa<ConstantInt>(Val) && !isa<UndefValue>(Val) &&
           !isa<ConstantFP>(Val))
         return false;
     }
     // Check that the resulting operation is legal.
     int ISDOpcode = TLI.InstructionOpcodeToISD(ToBePromoted->getOpcode());
     if (!ISDOpcode)
       return false;
     return StressStoreExtract ||
            TLI.isOperationLegalOrCustom(
                ISDOpcode, TLI.getValueType(DL, getTransitionType(), true));
   }
 
   /// \brief Check whether or not \p Use can be combined
   /// with the transition.
   /// I.e., is it possible to do Use(Transition) => AnotherUse?
   bool canCombine(const Instruction *Use) { return isa<StoreInst>(Use); }
 
   /// \brief Record \p ToBePromoted as part of the chain to be promoted.
   void enqueueForPromotion(Instruction *ToBePromoted) {
     InstsToBePromoted.push_back(ToBePromoted);
   }
 
   /// \brief Set the instruction that will be combined with the transition.
   void recordCombineInstruction(Instruction *ToBeCombined) {
     assert(canCombine(ToBeCombined) && "Unsupported instruction to combine");
     CombineInst = ToBeCombined;
   }
 
   /// \brief Promote all the instructions enqueued for promotion if it is
   /// is profitable.
   /// \return True if the promotion happened, false otherwise.
   bool promote() {
     // Check if there is something to promote.
     // Right now, if we do not have anything to combine with,
     // we assume the promotion is not profitable.
     if (InstsToBePromoted.empty() || !CombineInst)
       return false;
 
     // Check cost.
     if (!StressStoreExtract && !isProfitableToPromote())
       return false;
 
     // Promote.
     for (auto &ToBePromoted : InstsToBePromoted)
       promoteImpl(ToBePromoted);
     InstsToBePromoted.clear();
     return true;
   }
 };
 } // End of anonymous namespace.
 
 void VectorPromoteHelper::promoteImpl(Instruction *ToBePromoted) {
   // At this point, we know that all the operands of ToBePromoted but Def
   // can be statically promoted.
   // For Def, we need to use its parameter in ToBePromoted:
   // b = ToBePromoted ty1 a
   // Def = Transition ty1 b to ty2
   // Move the transition down.
   // 1. Replace all uses of the promoted operation by the transition.
   // = ... b => = ... Def.
   assert(ToBePromoted->getType() == Transition->getType() &&
          "The type of the result of the transition does not match "
          "the final type");
   ToBePromoted->replaceAllUsesWith(Transition);
   // 2. Update the type of the uses.
   // b = ToBePromoted ty2 Def => b = ToBePromoted ty1 Def.
   Type *TransitionTy = getTransitionType();
   ToBePromoted->mutateType(TransitionTy);
   // 3. Update all the operands of the promoted operation with promoted
   // operands.
   // b = ToBePromoted ty1 Def => b = ToBePromoted ty1 a.
   for (Use &U : ToBePromoted->operands()) {
     Value *Val = U.get();
     Value *NewVal = nullptr;
     if (Val == Transition)
       NewVal = Transition->getOperand(getTransitionOriginalValueIdx());
     else if (isa<UndefValue>(Val) || isa<ConstantInt>(Val) ||
              isa<ConstantFP>(Val)) {
       // Use a splat constant if it is not safe to use undef.
       NewVal = getConstantVector(
           cast<Constant>(Val),
           isa<UndefValue>(Val) ||
               canCauseUndefinedBehavior(ToBePromoted, U.getOperandNo()));
     } else
       llvm_unreachable("Did you modified shouldPromote and forgot to update "
                        "this?");
     ToBePromoted->setOperand(U.getOperandNo(), NewVal);
   }
   Transition->removeFromParent();
   Transition->insertAfter(ToBePromoted);
   Transition->setOperand(getTransitionOriginalValueIdx(), ToBePromoted);
 }
 
 /// Some targets can do store(extractelement) with one instruction.
 /// Try to push the extractelement towards the stores when the target
 /// has this feature and this is profitable.
 bool CodeGenPrepare::optimizeExtractElementInst(Instruction *Inst) {
   unsigned CombineCost = UINT_MAX;
   if (DisableStoreExtract || !TLI ||
       (!StressStoreExtract &&
        !TLI->canCombineStoreAndExtract(Inst->getOperand(0)->getType(),
                                        Inst->getOperand(1), CombineCost)))
     return false;
 
   // At this point we know that Inst is a vector to scalar transition.
   // Try to move it down the def-use chain, until:
   // - We can combine the transition with its single use
   //   => we got rid of the transition.
   // - We escape the current basic block
   //   => we would need to check that we are moving it at a cheaper place and
   //      we do not do that for now.
   BasicBlock *Parent = Inst->getParent();
   DEBUG(dbgs() << "Found an interesting transition: " << *Inst << '\n');
   VectorPromoteHelper VPH(*DL, *TLI, *TTI, Inst, CombineCost);
   // If the transition has more than one use, assume this is not going to be
   // beneficial.
   while (Inst->hasOneUse()) {
     Instruction *ToBePromoted = cast<Instruction>(*Inst->user_begin());
     DEBUG(dbgs() << "Use: " << *ToBePromoted << '\n');
 
     if (ToBePromoted->getParent() != Parent) {
       DEBUG(dbgs() << "Instruction to promote is in a different block ("
                    << ToBePromoted->getParent()->getName()
                    << ") than the transition (" << Parent->getName() << ").\n");
       return false;
     }
 
     if (VPH.canCombine(ToBePromoted)) {
       DEBUG(dbgs() << "Assume " << *Inst << '\n'
                    << "will be combined with: " << *ToBePromoted << '\n');
       VPH.recordCombineInstruction(ToBePromoted);
       bool Changed = VPH.promote();
       NumStoreExtractExposed += Changed;
       return Changed;
     }
 
     DEBUG(dbgs() << "Try promoting.\n");
     if (!VPH.canPromote(ToBePromoted) || !VPH.shouldPromote(ToBePromoted))
       return false;
 
     DEBUG(dbgs() << "Promoting is possible... Enqueue for promotion!\n");
 
     VPH.enqueueForPromotion(ToBePromoted);
     Inst = ToBePromoted;
   }
   return false;
 }
 
 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))
     return false;
 
   if (PHINode *P = dyn_cast<PHINode>(I)) {
     // It is possible for very late stage optimizations (such as SimplifyCFG)
     // to introduce PHI nodes too late to be cleaned up.  If we detect such a
     // trivial PHI, go ahead and zap it here.
     if (Value *V = SimplifyInstruction(P, *DL, TLInfo, nullptr)) {
       P->replaceAllUsesWith(V);
       P->eraseFromParent();
       ++NumPHIsElim;
       return true;
     }
     return false;
   }
 
   if (CastInst *CI = dyn_cast<CastInst>(I)) {
     // If the source of the cast is a constant, then this should have
     // already been constant folded.  The only reason NOT to constant fold
     // it is if something (e.g. LSR) was careful to place the constant
     // evaluation in a block other than then one that uses it (e.g. to hoist
     // the address of globals out of a loop).  If this is the case, we don't
     // want to forward-subst the cast.
     if (isa<Constant>(CI->getOperand(0)))
       return false;
 
     if (TLI && OptimizeNoopCopyExpression(CI, *TLI, *DL))
       return true;
 
     if (isa<ZExtInst>(I) || isa<SExtInst>(I)) {
       /// Sink a zext or sext into its user blocks if the target type doesn't
       /// fit in one register
       if (TLI &&
           TLI->getTypeAction(CI->getContext(),
                              TLI->getValueType(*DL, CI->getType())) ==
               TargetLowering::TypeExpandInteger) {
         return SinkCast(CI);
       } else {
         bool MadeChange = moveExtToFormExtLoad(I);
         return MadeChange | optimizeExtUses(I);
       }
     }
     return false;
   }
 
   if (CmpInst *CI = dyn_cast<CmpInst>(I))
     if (!TLI || !TLI->hasMultipleConditionRegisters())
       return OptimizeCmpExpression(CI);
 
   if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
     stripInvariantGroupMetadata(*LI);
     if (TLI) {
       bool Modified = optimizeLoadExt(LI);
       unsigned AS = LI->getPointerAddressSpace();
       Modified |= optimizeMemoryInst(I, I->getOperand(0), LI->getType(), AS);
       return Modified;
     }
     return false;
   }
 
   if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
     stripInvariantGroupMetadata(*SI);
     if (TLI) {
       unsigned AS = SI->getPointerAddressSpace();
       return optimizeMemoryInst(I, SI->getOperand(1),
                                 SI->getOperand(0)->getType(), AS);
     }
     return false;
   }
 
   BinaryOperator *BinOp = dyn_cast<BinaryOperator>(I);
 
   if (BinOp && (BinOp->getOpcode() == Instruction::AShr ||
                 BinOp->getOpcode() == Instruction::LShr)) {
     ConstantInt *CI = dyn_cast<ConstantInt>(BinOp->getOperand(1));
     if (TLI && CI && TLI->hasExtractBitsInsn())
       return OptimizeExtractBits(BinOp, CI, *TLI, *DL);
 
     return false;
   }
 
   if (GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(I)) {
     if (GEPI->hasAllZeroIndices()) {
       /// The GEP operand must be a pointer, so must its result -> BitCast
       Instruction *NC = new BitCastInst(GEPI->getOperand(0), GEPI->getType(),
                                         GEPI->getName(), GEPI);
       GEPI->replaceAllUsesWith(NC);
       GEPI->eraseFromParent();
       ++NumGEPsElim;
       optimizeInst(NC, ModifiedDT);
       return true;
     }
     return false;
   }
 
   if (CallInst *CI = dyn_cast<CallInst>(I))
     return optimizeCallInst(CI, ModifiedDT);
 
   if (SelectInst *SI = dyn_cast<SelectInst>(I))
     return optimizeSelectInst(SI);
 
   if (ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(I))
     return optimizeShuffleVectorInst(SVI);
 
   if (auto *Switch = dyn_cast<SwitchInst>(I))
     return optimizeSwitchInst(Switch);
 
   if (isa<ExtractElementInst>(I))
     return optimizeExtractElementInst(I);
 
   return false;
 }
 
 // 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) {
   SunkAddrs.clear();
   bool MadeChange = false;
 
   CurInstIterator = BB.begin();
   while (CurInstIterator != BB.end()) {
     MadeChange |= optimizeInst(&*CurInstIterator++, ModifiedDT);
     if (ModifiedDT)
       return true;
   }
   MadeChange |= dupRetToEnableTailCallOpts(&BB);
 
   return MadeChange;
 }
 
 // llvm.dbg.value is far away from the value then iSel may not be able
 // handle it properly. iSel will drop llvm.dbg.value if it can not
 // find a node corresponding to the value.
 bool CodeGenPrepare::placeDbgValues(Function &F) {
   bool MadeChange = false;
   for (BasicBlock &BB : F) {
     Instruction *PrevNonDbgInst = nullptr;
     for (BasicBlock::iterator BI = BB.begin(), BE = BB.end(); BI != BE;) {
       Instruction *Insn = &*BI++;
       DbgValueInst *DVI = dyn_cast<DbgValueInst>(Insn);
       // Leave dbg.values that refer to an alloca alone. These
       // instrinsics describe the address of a variable (= the alloca)
       // being taken.  They should not be moved next to the alloca
       // (and to the beginning of the scope), but rather stay close to
       // where said address is used.
       if (!DVI || (DVI->getValue() && isa<AllocaInst>(DVI->getValue()))) {
         PrevNonDbgInst = Insn;
         continue;
       }
 
       Instruction *VI = dyn_cast_or_null<Instruction>(DVI->getValue());
       if (VI && VI != PrevNonDbgInst && !VI->isTerminator()) {
         // If VI is a phi in a block with an EHPad terminator, we can't insert
         // after it.
         if (isa<PHINode>(VI) && VI->getParent()->getTerminator()->isEHPad())
           continue;
         DEBUG(dbgs() << "Moving Debug Value before :\n" << *DVI << ' ' << *VI);
         DVI->removeFromParent();
         if (isa<PHINode>(VI))
           DVI->insertBefore(&*VI->getParent()->getFirstInsertionPt());
         else
           DVI->insertAfter(VI);
         MadeChange = true;
         ++NumDbgValueMoved;
       }
     }
   }
   return MadeChange;
 }
 
 // If there is a sequence that branches based on comparing a single bit
 // against zero that can be combined into a single instruction, and the
 // target supports folding these into a single instruction, sink the
 // mask and compare into the branch uses. Do this before OptimizeBlock ->
 // OptimizeInst -> OptimizeCmpExpression, which perturbs the pattern being
 // searched for.
 bool CodeGenPrepare::sinkAndCmp(Function &F) {
   if (!EnableAndCmpSinking)
     return false;
   if (!TLI || !TLI->isMaskAndBranchFoldingLegal())
     return false;
   bool MadeChange = false;
   for (Function::iterator I = F.begin(), E = F.end(); I != E; ) {
     BasicBlock *BB = &*I++;
 
     // Does this BB end with the following?
     //   %andVal = and %val, #single-bit-set
     //   %icmpVal = icmp %andResult, 0
     //   br i1 %cmpVal label %dest1, label %dest2"
     BranchInst *Brcc = dyn_cast<BranchInst>(BB->getTerminator());
     if (!Brcc || !Brcc->isConditional())
       continue;
     ICmpInst *Cmp = dyn_cast<ICmpInst>(Brcc->getOperand(0));
     if (!Cmp || Cmp->getParent() != BB)
       continue;
     ConstantInt *Zero = dyn_cast<ConstantInt>(Cmp->getOperand(1));
     if (!Zero || !Zero->isZero())
       continue;
     Instruction *And = dyn_cast<Instruction>(Cmp->getOperand(0));
     if (!And || And->getOpcode() != Instruction::And || And->getParent() != BB)
       continue;
     ConstantInt* Mask = dyn_cast<ConstantInt>(And->getOperand(1));
     if (!Mask || !Mask->getUniqueInteger().isPowerOf2())
       continue;
     DEBUG(dbgs() << "found and; icmp ?,0; brcc\n"); DEBUG(BB->dump());
 
     // Push the "and; icmp" for any users that are conditional branches.
     // Since there can only be one branch use per BB, we don't need to keep
     // track of which BBs we insert into.
     for (Value::use_iterator UI = Cmp->use_begin(), E = Cmp->use_end();
          UI != E; ) {
       Use &TheUse = *UI;
       // Find brcc use.
       BranchInst *BrccUser = dyn_cast<BranchInst>(*UI);
       ++UI;
       if (!BrccUser || !BrccUser->isConditional())
         continue;
       BasicBlock *UserBB = BrccUser->getParent();
       if (UserBB == BB) continue;
       DEBUG(dbgs() << "found Brcc use\n");
 
       // Sink the "and; icmp" to use.
       MadeChange = true;
       BinaryOperator *NewAnd =
         BinaryOperator::CreateAnd(And->getOperand(0), And->getOperand(1), "",
                                   BrccUser);
       CmpInst *NewCmp =
         CmpInst::Create(Cmp->getOpcode(), Cmp->getPredicate(), NewAnd, Zero,
                         "", BrccUser);
       TheUse = NewCmp;
       ++NumAndCmpsMoved;
       DEBUG(BrccUser->getParent()->dump());
     }
   }
   return MadeChange;
 }
 
 /// \brief Retrieve the probabilities of a conditional branch. Returns true on
 /// success, or returns false if no or invalid metadata was found.
 static bool extractBranchMetadata(BranchInst *BI,
                                   uint64_t &ProbTrue, uint64_t &ProbFalse) {
   assert(BI->isConditional() &&
          "Looking for probabilities on unconditional branch?");
   auto *ProfileData = BI->getMetadata(LLVMContext::MD_prof);
   if (!ProfileData || ProfileData->getNumOperands() != 3)
     return false;
 
   const auto *CITrue =
       mdconst::dyn_extract<ConstantInt>(ProfileData->getOperand(1));
   const auto *CIFalse =
       mdconst::dyn_extract<ConstantInt>(ProfileData->getOperand(2));
   if (!CITrue || !CIFalse)
     return false;
 
   ProbTrue = CITrue->getValue().getZExtValue();
   ProbFalse = CIFalse->getValue().getZExtValue();
 
   return true;
 }
 
 /// \brief Scale down both weights to fit into uint32_t.
 static void scaleWeights(uint64_t &NewTrue, uint64_t &NewFalse) {
   uint64_t NewMax = (NewTrue > NewFalse) ? NewTrue : NewFalse;
   uint32_t Scale = (NewMax / UINT32_MAX) + 1;
   NewTrue = NewTrue / Scale;
   NewFalse = NewFalse / Scale;
 }
 
 /// \brief Some targets prefer to split a conditional branch like:
 /// \code
 ///   %0 = icmp ne i32 %a, 0
 ///   %1 = icmp ne i32 %b, 0
 ///   %or.cond = or i1 %0, %1
 ///   br i1 %or.cond, label %TrueBB, label %FalseBB
 /// \endcode
 /// into multiple branch instructions like:
 /// \code
 ///   bb1:
 ///     %0 = icmp ne i32 %a, 0
 ///     br i1 %0, label %TrueBB, label %bb2
 ///   bb2:
 ///     %1 = icmp ne i32 %b, 0
 ///     br i1 %1, label %TrueBB, label %FalseBB
 /// \endcode
 /// This usually allows instruction selection to do even further optimizations
 /// and combine the compare with the branch instruction. Currently this is
 /// applied for targets which have "cheap" jump instructions.
 ///
 /// FIXME: Remove the (equivalent?) implementation in SelectionDAG.
 ///
 bool CodeGenPrepare::splitBranchCondition(Function &F) {
   if (!TM || !TM->Options.EnableFastISel || !TLI || TLI->isJumpExpensive())
     return false;
 
   bool MadeChange = false;
   for (auto &BB : F) {
     // Does this BB end with the following?
     //   %cond1 = icmp|fcmp|binary instruction ...
     //   %cond2 = icmp|fcmp|binary instruction ...
     //   %cond.or = or|and i1 %cond1, cond2
     //   br i1 %cond.or label %dest1, label %dest2"
     BinaryOperator *LogicOp;
     BasicBlock *TBB, *FBB;
     if (!match(BB.getTerminator(), m_Br(m_OneUse(m_BinOp(LogicOp)), TBB, FBB)))
       continue;
 
     auto *Br1 = cast<BranchInst>(BB.getTerminator());
     if (Br1->getMetadata(LLVMContext::MD_unpredictable))
       continue;
 
     unsigned Opc;
     Value *Cond1, *Cond2;
     if (match(LogicOp, m_And(m_OneUse(m_Value(Cond1)),
                              m_OneUse(m_Value(Cond2)))))
       Opc = Instruction::And;
     else if (match(LogicOp, m_Or(m_OneUse(m_Value(Cond1)),
                                  m_OneUse(m_Value(Cond2)))))
       Opc = Instruction::Or;
     else
       continue;
 
     if (!match(Cond1, m_CombineOr(m_Cmp(), m_BinOp())) ||
         !match(Cond2, m_CombineOr(m_Cmp(), m_BinOp()))   )
       continue;
 
     DEBUG(dbgs() << "Before branch condition splitting\n"; BB.dump());
 
     // Create a new BB.
     auto *InsertBefore = std::next(Function::iterator(BB))
         .getNodePtrUnchecked();
     auto TmpBB = BasicBlock::Create(BB.getContext(),
                                     BB.getName() + ".cond.split",
                                     BB.getParent(), InsertBefore);
 
     // Update original basic block by using the first condition directly by the
     // branch instruction and removing the no longer needed and/or instruction.
     Br1->setCondition(Cond1);
     LogicOp->eraseFromParent();
 
     // Depending on the conditon we have to either replace the true or the false
     // successor of the original branch instruction.
     if (Opc == Instruction::And)
       Br1->setSuccessor(0, TmpBB);
     else
       Br1->setSuccessor(1, TmpBB);
 
     // Fill in the new basic block.
     auto *Br2 = IRBuilder<>(TmpBB).CreateCondBr(Cond2, TBB, FBB);
     if (auto *I = dyn_cast<Instruction>(Cond2)) {
       I->removeFromParent();
       I->insertBefore(Br2);
     }
 
     // Update PHI nodes in both successors. The original BB needs to be
     // replaced in one succesor's PHI nodes, because the branch comes now from
     // the newly generated BB (NewBB). In the other successor we need to add one
     // incoming edge to the PHI nodes, because both branch instructions target
     // now the same successor. Depending on the original branch condition
     // (and/or) we have to swap the successors (TrueDest, FalseDest), so that
     // we perfrom the correct update for the PHI nodes.
     // This doesn't change the successor order of the just created branch
     // instruction (or any other instruction).
     if (Opc == Instruction::Or)
       std::swap(TBB, FBB);
 
     // Replace the old BB with the new BB.
     for (auto &I : *TBB) {
       PHINode *PN = dyn_cast<PHINode>(&I);
       if (!PN)
         break;
       int i;
       while ((i = PN->getBasicBlockIndex(&BB)) >= 0)
         PN->setIncomingBlock(i, TmpBB);
     }
 
     // Add another incoming edge form the new BB.
     for (auto &I : *FBB) {
       PHINode *PN = dyn_cast<PHINode>(&I);
       if (!PN)
         break;
       auto *Val = PN->getIncomingValueForBlock(&BB);
       PN->addIncoming(Val, TmpBB);
     }
 
     // Update the branch weights (from SelectionDAGBuilder::
     // FindMergedConditions).
     if (Opc == Instruction::Or) {
       // Codegen X | Y as:
       // BB1:
       //   jmp_if_X TBB
       //   jmp TmpBB
       // TmpBB:
       //   jmp_if_Y TBB
       //   jmp FBB
       //
 
       // We have flexibility in setting Prob for BB1 and Prob for NewBB.
       // The requirement is that
       //   TrueProb for BB1 + (FalseProb for BB1 * TrueProb for TmpBB)
       //     = TrueProb for orignal BB.
       // Assuming the orignal weights are A and B, one choice is to set BB1's
       // weights to A and A+2B, and set TmpBB's weights to A and 2B. This choice
       // assumes that
       //   TrueProb for BB1 == FalseProb for BB1 * TrueProb for TmpBB.
       // Another choice is to assume TrueProb for BB1 equals to TrueProb for
       // TmpBB, but the math is more complicated.
       uint64_t TrueWeight, FalseWeight;
       if (extractBranchMetadata(Br1, TrueWeight, FalseWeight)) {
         uint64_t NewTrueWeight = TrueWeight;
         uint64_t NewFalseWeight = TrueWeight + 2 * FalseWeight;
         scaleWeights(NewTrueWeight, NewFalseWeight);
         Br1->setMetadata(LLVMContext::MD_prof, MDBuilder(Br1->getContext())
                          .createBranchWeights(TrueWeight, FalseWeight));
 
         NewTrueWeight = TrueWeight;
         NewFalseWeight = 2 * FalseWeight;
         scaleWeights(NewTrueWeight, NewFalseWeight);
         Br2->setMetadata(LLVMContext::MD_prof, MDBuilder(Br2->getContext())
                          .createBranchWeights(TrueWeight, FalseWeight));
       }
     } else {
       // Codegen X & Y as:
       // BB1:
       //   jmp_if_X TmpBB
       //   jmp FBB
       // TmpBB:
       //   jmp_if_Y TBB
       //   jmp FBB
       //
       //  This requires creation of TmpBB after CurBB.
 
       // We have flexibility in setting Prob for BB1 and Prob for TmpBB.
       // The requirement is that
       //   FalseProb for BB1 + (TrueProb for BB1 * FalseProb for TmpBB)
       //     = FalseProb for orignal BB.
       // Assuming the orignal weights are A and B, one choice is to set BB1's
       // weights to 2A+B and B, and set TmpBB's weights to 2A and B. This choice
       // assumes that
       //   FalseProb for BB1 == TrueProb for BB1 * FalseProb for TmpBB.
       uint64_t TrueWeight, FalseWeight;
       if (extractBranchMetadata(Br1, TrueWeight, FalseWeight)) {
         uint64_t NewTrueWeight = 2 * TrueWeight + FalseWeight;
         uint64_t NewFalseWeight = FalseWeight;
         scaleWeights(NewTrueWeight, NewFalseWeight);
         Br1->setMetadata(LLVMContext::MD_prof, MDBuilder(Br1->getContext())
                          .createBranchWeights(TrueWeight, FalseWeight));
 
         NewTrueWeight = 2 * TrueWeight;
         NewFalseWeight = FalseWeight;
         scaleWeights(NewTrueWeight, NewFalseWeight);
         Br2->setMetadata(LLVMContext::MD_prof, MDBuilder(Br2->getContext())
                          .createBranchWeights(TrueWeight, FalseWeight));
       }
     }
 
     // Note: No point in getting fancy here, since the DT info is never
     // available to CodeGenPrepare.
     ModifiedDT = true;
 
     MadeChange = true;
 
     DEBUG(dbgs() << "After branch condition splitting\n"; BB.dump();
           TmpBB->dump());
   }
   return MadeChange;
 }
 
 void CodeGenPrepare::stripInvariantGroupMetadata(Instruction &I) {
   if (auto *InvariantMD = I.getMetadata(LLVMContext::MD_invariant_group))
     I.dropUnknownNonDebugMetadata(InvariantMD->getMetadataID());
 }
Index: projects/clang380-import/contrib/llvm/lib/IR/Globals.cpp
===================================================================
--- projects/clang380-import/contrib/llvm/lib/IR/Globals.cpp	(revision 294176)
+++ projects/clang380-import/contrib/llvm/lib/IR/Globals.cpp	(revision 294177)
@@ -1,285 +1,327 @@
 //===-- Globals.cpp - Implement the GlobalValue & GlobalVariable class ----===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements the GlobalValue & GlobalVariable classes for the IR
 // library.
 //
 //===----------------------------------------------------------------------===//
 
-#include "llvm/IR/GlobalValue.h"
 #include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/Triple.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/GlobalAlias.h"
+#include "llvm/IR/GlobalValue.h"
 #include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/Support/ErrorHandling.h"
 using namespace llvm;
 
 //===----------------------------------------------------------------------===//
 //                            GlobalValue Class
 //===----------------------------------------------------------------------===//
 
 bool GlobalValue::isMaterializable() const {
   if (const Function *F = dyn_cast<Function>(this))
     return F->isMaterializable();
   return false;
 }
 std::error_code GlobalValue::materialize() {
   return getParent()->materialize(this);
 }
 
 /// Override destroyConstantImpl to make sure it doesn't get called on
 /// GlobalValue's because they shouldn't be treated like other constants.
 void GlobalValue::destroyConstantImpl() {
   llvm_unreachable("You can't GV->destroyConstantImpl()!");
 }
 
 Value *GlobalValue::handleOperandChangeImpl(Value *From, Value *To, Use *U) {
   llvm_unreachable("Unsupported class for handleOperandChange()!");
 }
 
 /// copyAttributesFrom - copy all additional attributes (those not needed to
 /// create a GlobalValue) from the GlobalValue Src to this one.
 void GlobalValue::copyAttributesFrom(const GlobalValue *Src) {
   setVisibility(Src->getVisibility());
   setUnnamedAddr(Src->hasUnnamedAddr());
   setDLLStorageClass(Src->getDLLStorageClass());
 }
 
 unsigned GlobalValue::getAlignment() const {
   if (auto *GA = dyn_cast<GlobalAlias>(this)) {
     // In general we cannot compute this at the IR level, but we try.
     if (const GlobalObject *GO = GA->getBaseObject())
       return GO->getAlignment();
 
     // FIXME: we should also be able to handle:
     // Alias = Global + Offset
     // Alias = Absolute
     return 0;
   }
   return cast<GlobalObject>(this)->getAlignment();
 }
 
 void GlobalObject::setAlignment(unsigned Align) {
   assert((Align & (Align-1)) == 0 && "Alignment is not a power of 2!");
   assert(Align <= MaximumAlignment &&
          "Alignment is greater than MaximumAlignment!");
   unsigned AlignmentData = Log2_32(Align) + 1;
   unsigned OldData = getGlobalValueSubClassData();
   setGlobalValueSubClassData((OldData & ~AlignmentMask) | AlignmentData);
   assert(getAlignment() == Align && "Alignment representation error!");
 }
 
 unsigned GlobalObject::getGlobalObjectSubClassData() const {
   unsigned ValueData = getGlobalValueSubClassData();
   return ValueData >> AlignmentBits;
 }
 
 void GlobalObject::setGlobalObjectSubClassData(unsigned Val) {
   unsigned OldData = getGlobalValueSubClassData();
   setGlobalValueSubClassData((OldData & AlignmentMask) |
                              (Val << AlignmentBits));
   assert(getGlobalObjectSubClassData() == Val && "representation error");
 }
 
 void GlobalObject::copyAttributesFrom(const GlobalValue *Src) {
   GlobalValue::copyAttributesFrom(Src);
   if (const auto *GV = dyn_cast<GlobalObject>(Src)) {
     setAlignment(GV->getAlignment());
     setSection(GV->getSection());
   }
 }
 
 const char *GlobalValue::getSection() const {
   if (auto *GA = dyn_cast<GlobalAlias>(this)) {
     // In general we cannot compute this at the IR level, but we try.
     if (const GlobalObject *GO = GA->getBaseObject())
       return GO->getSection();
     return "";
   }
   return cast<GlobalObject>(this)->getSection();
 }
 
 Comdat *GlobalValue::getComdat() {
   if (auto *GA = dyn_cast<GlobalAlias>(this)) {
     // In general we cannot compute this at the IR level, but we try.
     if (const GlobalObject *GO = GA->getBaseObject())
       return const_cast<GlobalObject *>(GO)->getComdat();
     return nullptr;
   }
   return cast<GlobalObject>(this)->getComdat();
 }
 
 void GlobalObject::setSection(StringRef S) { Section = S; }
 
 bool GlobalValue::isDeclaration() const {
   // Globals are definitions if they have an initializer.
   if (const GlobalVariable *GV = dyn_cast<GlobalVariable>(this))
     return GV->getNumOperands() == 0;
 
   // Functions are definitions if they have a body.
   if (const Function *F = dyn_cast<Function>(this))
     return F->empty() && !F->isMaterializable();
 
   // Aliases are always definitions.
   assert(isa<GlobalAlias>(this));
   return false;
+}
+
+bool GlobalValue::canIncreaseAlignment() const {
+  // Firstly, can only increase the alignment of a global if it
+  // is a strong definition.
+  if (!isStrongDefinitionForLinker())
+    return false;
+
+  // It also has to either not have a section defined, or, not have
+  // alignment specified. (If it is assigned a section, the global
+  // could be densely packed with other objects in the section, and
+  // increasing the alignment could cause padding issues.)
+  if (hasSection() && getAlignment() > 0)
+    return false;
+
+  // On ELF platforms, we're further restricted in that we can't
+  // increase the alignment of any variable which might be emitted
+  // into a shared library, and which is exported. If the main
+  // executable accesses a variable found in a shared-lib, the main
+  // exe actually allocates memory for and exports the symbol ITSELF,
+  // overriding the symbol found in the library. That is, at link
+  // time, the observed alignment of the variable is copied into the
+  // executable binary. (A COPY relocation is also generated, to copy
+  // the initial data from the shadowed variable in the shared-lib
+  // into the location in the main binary, before running code.)
+  //
+  // And thus, even though you might think you are defining the
+  // global, and allocating the memory for the global in your object
+  // file, and thus should be able to set the alignment arbitrarily,
+  // that's not actually true. Doing so can cause an ABI breakage; an
+  // executable might have already been built with the previous
+  // alignment of the variable, and then assuming an increased
+  // alignment will be incorrect.
+
+  // Conservatively assume ELF if there's no parent pointer.
+  bool isELF =
+      (!Parent || Triple(Parent->getTargetTriple()).isOSBinFormatELF());
+  if (isELF && hasDefaultVisibility() && !hasLocalLinkage())
+    return false;
+
+  return true;
 }
 
 //===----------------------------------------------------------------------===//
 // GlobalVariable Implementation
 //===----------------------------------------------------------------------===//
 
 GlobalVariable::GlobalVariable(Type *Ty, bool constant, LinkageTypes Link,
                                Constant *InitVal, const Twine &Name,
                                ThreadLocalMode TLMode, unsigned AddressSpace,
                                bool isExternallyInitialized)
     : GlobalObject(Ty, Value::GlobalVariableVal,
                    OperandTraits<GlobalVariable>::op_begin(this),
                    InitVal != nullptr, Link, Name, AddressSpace),
       isConstantGlobal(constant),
       isExternallyInitializedConstant(isExternallyInitialized) {
   setThreadLocalMode(TLMode);
   if (InitVal) {
     assert(InitVal->getType() == Ty &&
            "Initializer should be the same type as the GlobalVariable!");
     Op<0>() = InitVal;
   }
 }
 
 GlobalVariable::GlobalVariable(Module &M, Type *Ty, bool constant,
                                LinkageTypes Link, Constant *InitVal,
                                const Twine &Name, GlobalVariable *Before,
                                ThreadLocalMode TLMode, unsigned AddressSpace,
                                bool isExternallyInitialized)
     : GlobalObject(Ty, Value::GlobalVariableVal,
                    OperandTraits<GlobalVariable>::op_begin(this),
                    InitVal != nullptr, Link, Name, AddressSpace),
       isConstantGlobal(constant),
       isExternallyInitializedConstant(isExternallyInitialized) {
   setThreadLocalMode(TLMode);
   if (InitVal) {
     assert(InitVal->getType() == Ty &&
            "Initializer should be the same type as the GlobalVariable!");
     Op<0>() = InitVal;
   }
 
   if (Before)
     Before->getParent()->getGlobalList().insert(Before->getIterator(), this);
   else
     M.getGlobalList().push_back(this);
 }
 
 void GlobalVariable::setParent(Module *parent) {
   Parent = parent;
 }
 
 void GlobalVariable::removeFromParent() {
   getParent()->getGlobalList().remove(getIterator());
 }
 
 void GlobalVariable::eraseFromParent() {
   getParent()->getGlobalList().erase(getIterator());
 }
 
 void GlobalVariable::setInitializer(Constant *InitVal) {
   if (!InitVal) {
     if (hasInitializer()) {
       // Note, the num operands is used to compute the offset of the operand, so
       // the order here matters.  Clearing the operand then clearing the num
       // operands ensures we have the correct offset to the operand.
       Op<0>().set(nullptr);
       setGlobalVariableNumOperands(0);
     }
   } else {
     assert(InitVal->getType() == getType()->getElementType() &&
            "Initializer type must match GlobalVariable type");
     // Note, the num operands is used to compute the offset of the operand, so
     // the order here matters.  We need to set num operands to 1 first so that
     // we get the correct offset to the first operand when we set it.
     if (!hasInitializer())
       setGlobalVariableNumOperands(1);
     Op<0>().set(InitVal);
   }
 }
 
 /// Copy all additional attributes (those not needed to create a GlobalVariable)
 /// from the GlobalVariable Src to this one.
 void GlobalVariable::copyAttributesFrom(const GlobalValue *Src) {
   GlobalObject::copyAttributesFrom(Src);
   if (const GlobalVariable *SrcVar = dyn_cast<GlobalVariable>(Src)) {
     setThreadLocalMode(SrcVar->getThreadLocalMode());
     setExternallyInitialized(SrcVar->isExternallyInitialized());
   }
 }
 
 
 //===----------------------------------------------------------------------===//
 // GlobalAlias Implementation
 //===----------------------------------------------------------------------===//
 
 GlobalAlias::GlobalAlias(Type *Ty, unsigned AddressSpace, LinkageTypes Link,
                          const Twine &Name, Constant *Aliasee,
                          Module *ParentModule)
     : GlobalValue(Ty, Value::GlobalAliasVal, &Op<0>(), 1, Link, Name,
                   AddressSpace) {
   Op<0>() = Aliasee;
 
   if (ParentModule)
     ParentModule->getAliasList().push_back(this);
 }
 
 GlobalAlias *GlobalAlias::create(Type *Ty, unsigned AddressSpace,
                                  LinkageTypes Link, const Twine &Name,
                                  Constant *Aliasee, Module *ParentModule) {
   return new GlobalAlias(Ty, AddressSpace, Link, Name, Aliasee, ParentModule);
 }
 
 GlobalAlias *GlobalAlias::create(Type *Ty, unsigned AddressSpace,
                                  LinkageTypes Linkage, const Twine &Name,
                                  Module *Parent) {
   return create(Ty, AddressSpace, Linkage, Name, nullptr, Parent);
 }
 
 GlobalAlias *GlobalAlias::create(Type *Ty, unsigned AddressSpace,
                                  LinkageTypes Linkage, const Twine &Name,
                                  GlobalValue *Aliasee) {
   return create(Ty, AddressSpace, Linkage, Name, Aliasee, Aliasee->getParent());
 }
 
 GlobalAlias *GlobalAlias::create(LinkageTypes Link, const Twine &Name,
                                  GlobalValue *Aliasee) {
   PointerType *PTy = Aliasee->getType();
   return create(PTy->getElementType(), PTy->getAddressSpace(), Link, Name,
                 Aliasee);
 }
 
 GlobalAlias *GlobalAlias::create(const Twine &Name, GlobalValue *Aliasee) {
   return create(Aliasee->getLinkage(), Name, Aliasee);
 }
 
 void GlobalAlias::setParent(Module *parent) {
   Parent = parent;
 }
 
 void GlobalAlias::removeFromParent() {
   getParent()->getAliasList().remove(getIterator());
 }
 
 void GlobalAlias::eraseFromParent() {
   getParent()->getAliasList().erase(getIterator());
 }
 
 void GlobalAlias::setAliasee(Constant *Aliasee) {
   assert((!Aliasee || Aliasee->getType() == getType()) &&
          "Alias and aliasee types should match!");
   setOperand(0, Aliasee);
 }
Index: projects/clang380-import/contrib/llvm/lib/Transforms/Utils/Local.cpp
===================================================================
--- projects/clang380-import/contrib/llvm/lib/Transforms/Utils/Local.cpp	(revision 294176)
+++ projects/clang380-import/contrib/llvm/lib/Transforms/Utils/Local.cpp	(revision 294177)
@@ -1,1587 +1,1594 @@
 //===-- Local.cpp - Functions to perform local transformations ------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This family of functions perform various local transformations to the
 // program.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/EHPersonalities.h"
 #include "llvm/Analysis/InstructionSimplify.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
 #include "llvm/Analysis/LazyValueInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/CFG.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DIBuilder.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DebugInfo.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/GetElementPtrTypeIterator.h"
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/MDBuilder.h"
 #include "llvm/IR/Metadata.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
 using namespace llvm;
 
 #define DEBUG_TYPE "local"
 
 STATISTIC(NumRemoved, "Number of unreachable basic blocks removed");
 
 //===----------------------------------------------------------------------===//
 //  Local constant propagation.
 //
 
 /// ConstantFoldTerminator - If a terminator instruction is predicated on a
 /// constant value, convert it into an unconditional branch to the constant
 /// destination.  This is a nontrivial operation because the successors of this
 /// basic block must have their PHI nodes updated.
 /// Also calls RecursivelyDeleteTriviallyDeadInstructions() on any branch/switch
 /// conditions and indirectbr addresses this might make dead if
 /// DeleteDeadConditions is true.
 bool llvm::ConstantFoldTerminator(BasicBlock *BB, bool DeleteDeadConditions,
                                   const TargetLibraryInfo *TLI) {
   TerminatorInst *T = BB->getTerminator();
   IRBuilder<> Builder(T);
 
   // Branch - See if we are conditional jumping on constant
   if (BranchInst *BI = dyn_cast<BranchInst>(T)) {
     if (BI->isUnconditional()) return false;  // Can't optimize uncond branch
     BasicBlock *Dest1 = BI->getSuccessor(0);
     BasicBlock *Dest2 = BI->getSuccessor(1);
 
     if (ConstantInt *Cond = dyn_cast<ConstantInt>(BI->getCondition())) {
       // Are we branching on constant?
       // YES.  Change to unconditional branch...
       BasicBlock *Destination = Cond->getZExtValue() ? Dest1 : Dest2;
       BasicBlock *OldDest     = Cond->getZExtValue() ? Dest2 : Dest1;
 
       //cerr << "Function: " << T->getParent()->getParent()
       //     << "\nRemoving branch from " << T->getParent()
       //     << "\n\nTo: " << OldDest << endl;
 
       // Let the basic block know that we are letting go of it.  Based on this,
       // it will adjust it's PHI nodes.
       OldDest->removePredecessor(BB);
 
       // Replace the conditional branch with an unconditional one.
       Builder.CreateBr(Destination);
       BI->eraseFromParent();
       return true;
     }
 
     if (Dest2 == Dest1) {       // Conditional branch to same location?
       // This branch matches something like this:
       //     br bool %cond, label %Dest, label %Dest
       // and changes it into:  br label %Dest
 
       // Let the basic block know that we are letting go of one copy of it.
       assert(BI->getParent() && "Terminator not inserted in block!");
       Dest1->removePredecessor(BI->getParent());
 
       // Replace the conditional branch with an unconditional one.
       Builder.CreateBr(Dest1);
       Value *Cond = BI->getCondition();
       BI->eraseFromParent();
       if (DeleteDeadConditions)
         RecursivelyDeleteTriviallyDeadInstructions(Cond, TLI);
       return true;
     }
     return false;
   }
 
   if (SwitchInst *SI = dyn_cast<SwitchInst>(T)) {
     // If we are switching on a constant, we can convert the switch to an
     // unconditional branch.
     ConstantInt *CI = dyn_cast<ConstantInt>(SI->getCondition());
     BasicBlock *DefaultDest = SI->getDefaultDest();
     BasicBlock *TheOnlyDest = DefaultDest;
 
     // If the default is unreachable, ignore it when searching for TheOnlyDest.
     if (isa<UnreachableInst>(DefaultDest->getFirstNonPHIOrDbg()) &&
         SI->getNumCases() > 0) {
       TheOnlyDest = SI->case_begin().getCaseSuccessor();
     }
 
     // Figure out which case it goes to.
     for (SwitchInst::CaseIt i = SI->case_begin(), e = SI->case_end();
          i != e; ++i) {
       // Found case matching a constant operand?
       if (i.getCaseValue() == CI) {
         TheOnlyDest = i.getCaseSuccessor();
         break;
       }
 
       // Check to see if this branch is going to the same place as the default
       // dest.  If so, eliminate it as an explicit compare.
       if (i.getCaseSuccessor() == DefaultDest) {
         MDNode *MD = SI->getMetadata(LLVMContext::MD_prof);
         unsigned NCases = SI->getNumCases();
         // Fold the case metadata into the default if there will be any branches
         // left, unless the metadata doesn't match the switch.
         if (NCases > 1 && MD && MD->getNumOperands() == 2 + NCases) {
           // Collect branch weights into a vector.
           SmallVector<uint32_t, 8> Weights;
           for (unsigned MD_i = 1, MD_e = MD->getNumOperands(); MD_i < MD_e;
                ++MD_i) {
             ConstantInt *CI =
                 mdconst::dyn_extract<ConstantInt>(MD->getOperand(MD_i));
             assert(CI);
             Weights.push_back(CI->getValue().getZExtValue());
           }
           // Merge weight of this case to the default weight.
           unsigned idx = i.getCaseIndex();
           Weights[0] += Weights[idx+1];
           // Remove weight for this case.
           std::swap(Weights[idx+1], Weights.back());
           Weights.pop_back();
           SI->setMetadata(LLVMContext::MD_prof,
                           MDBuilder(BB->getContext()).
                           createBranchWeights(Weights));
         }
         // Remove this entry.
         DefaultDest->removePredecessor(SI->getParent());
         SI->removeCase(i);
         --i; --e;
         continue;
       }
 
       // Otherwise, check to see if the switch only branches to one destination.
       // We do this by reseting "TheOnlyDest" to null when we find two non-equal
       // destinations.
       if (i.getCaseSuccessor() != TheOnlyDest) TheOnlyDest = nullptr;
     }
 
     if (CI && !TheOnlyDest) {
       // Branching on a constant, but not any of the cases, go to the default
       // successor.
       TheOnlyDest = SI->getDefaultDest();
     }
 
     // If we found a single destination that we can fold the switch into, do so
     // now.
     if (TheOnlyDest) {
       // Insert the new branch.
       Builder.CreateBr(TheOnlyDest);
       BasicBlock *BB = SI->getParent();
 
       // Remove entries from PHI nodes which we no longer branch to...
       for (BasicBlock *Succ : SI->successors()) {
         // Found case matching a constant operand?
         if (Succ == TheOnlyDest)
           TheOnlyDest = nullptr; // Don't modify the first branch to TheOnlyDest
         else
           Succ->removePredecessor(BB);
       }
 
       // Delete the old switch.
       Value *Cond = SI->getCondition();
       SI->eraseFromParent();
       if (DeleteDeadConditions)
         RecursivelyDeleteTriviallyDeadInstructions(Cond, TLI);
       return true;
     }
 
     if (SI->getNumCases() == 1) {
       // Otherwise, we can fold this switch into a conditional branch
       // instruction if it has only one non-default destination.
       SwitchInst::CaseIt FirstCase = SI->case_begin();
       Value *Cond = Builder.CreateICmpEQ(SI->getCondition(),
           FirstCase.getCaseValue(), "cond");
 
       // Insert the new branch.
       BranchInst *NewBr = Builder.CreateCondBr(Cond,
                                                FirstCase.getCaseSuccessor(),
                                                SI->getDefaultDest());
       MDNode *MD = SI->getMetadata(LLVMContext::MD_prof);
       if (MD && MD->getNumOperands() == 3) {
         ConstantInt *SICase =
             mdconst::dyn_extract<ConstantInt>(MD->getOperand(2));
         ConstantInt *SIDef =
             mdconst::dyn_extract<ConstantInt>(MD->getOperand(1));
         assert(SICase && SIDef);
         // The TrueWeight should be the weight for the single case of SI.
         NewBr->setMetadata(LLVMContext::MD_prof,
                         MDBuilder(BB->getContext()).
                         createBranchWeights(SICase->getValue().getZExtValue(),
                                             SIDef->getValue().getZExtValue()));
       }
 
       // Update make.implicit metadata to the newly-created conditional branch.
       MDNode *MakeImplicitMD = SI->getMetadata(LLVMContext::MD_make_implicit);
       if (MakeImplicitMD)
         NewBr->setMetadata(LLVMContext::MD_make_implicit, MakeImplicitMD);
 
       // Delete the old switch.
       SI->eraseFromParent();
       return true;
     }
     return false;
   }
 
   if (IndirectBrInst *IBI = dyn_cast<IndirectBrInst>(T)) {
     // indirectbr blockaddress(@F, @BB) -> br label @BB
     if (BlockAddress *BA =
           dyn_cast<BlockAddress>(IBI->getAddress()->stripPointerCasts())) {
       BasicBlock *TheOnlyDest = BA->getBasicBlock();
       // Insert the new branch.
       Builder.CreateBr(TheOnlyDest);
 
       for (unsigned i = 0, e = IBI->getNumDestinations(); i != e; ++i) {
         if (IBI->getDestination(i) == TheOnlyDest)
           TheOnlyDest = nullptr;
         else
           IBI->getDestination(i)->removePredecessor(IBI->getParent());
       }
       Value *Address = IBI->getAddress();
       IBI->eraseFromParent();
       if (DeleteDeadConditions)
         RecursivelyDeleteTriviallyDeadInstructions(Address, TLI);
 
       // If we didn't find our destination in the IBI successor list, then we
       // have undefined behavior.  Replace the unconditional branch with an
       // 'unreachable' instruction.
       if (TheOnlyDest) {
         BB->getTerminator()->eraseFromParent();
         new UnreachableInst(BB->getContext(), BB);
       }
 
       return true;
     }
   }
 
   return false;
 }
 
 
 //===----------------------------------------------------------------------===//
 //  Local dead code elimination.
 //
 
 /// isInstructionTriviallyDead - Return true if the result produced by the
 /// instruction is not used, and the instruction has no side effects.
 ///
 bool llvm::isInstructionTriviallyDead(Instruction *I,
                                       const TargetLibraryInfo *TLI) {
   if (!I->use_empty() || isa<TerminatorInst>(I)) return false;
 
   // We don't want the landingpad-like instructions removed by anything this
   // general.
   if (I->isEHPad())
     return false;
 
   // We don't want debug info removed by anything this general, unless
   // debug info is empty.
   if (DbgDeclareInst *DDI = dyn_cast<DbgDeclareInst>(I)) {
     if (DDI->getAddress())
       return false;
     return true;
   }
   if (DbgValueInst *DVI = dyn_cast<DbgValueInst>(I)) {
     if (DVI->getValue())
       return false;
     return true;
   }
 
   if (!I->mayHaveSideEffects()) return true;
 
   // Special case intrinsics that "may have side effects" but can be deleted
   // when dead.
   if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
     // Safe to delete llvm.stacksave if dead.
     if (II->getIntrinsicID() == Intrinsic::stacksave)
       return true;
 
     // Lifetime intrinsics are dead when their right-hand is undef.
     if (II->getIntrinsicID() == Intrinsic::lifetime_start ||
         II->getIntrinsicID() == Intrinsic::lifetime_end)
       return isa<UndefValue>(II->getArgOperand(1));
 
     // Assumptions are dead if their condition is trivially true.
     if (II->getIntrinsicID() == Intrinsic::assume) {
       if (ConstantInt *Cond = dyn_cast<ConstantInt>(II->getArgOperand(0)))
         return !Cond->isZero();
 
       return false;
     }
   }
 
   if (isAllocLikeFn(I, TLI)) return true;
 
   if (CallInst *CI = isFreeCall(I, TLI))
     if (Constant *C = dyn_cast<Constant>(CI->getArgOperand(0)))
       return C->isNullValue() || isa<UndefValue>(C);
 
   return false;
 }
 
 /// RecursivelyDeleteTriviallyDeadInstructions - If the specified value is a
 /// trivially dead instruction, delete it.  If that makes any of its operands
 /// trivially dead, delete them too, recursively.  Return true if any
 /// instructions were deleted.
 bool
 llvm::RecursivelyDeleteTriviallyDeadInstructions(Value *V,
                                                  const TargetLibraryInfo *TLI) {
   Instruction *I = dyn_cast<Instruction>(V);
   if (!I || !I->use_empty() || !isInstructionTriviallyDead(I, TLI))
     return false;
 
   SmallVector<Instruction*, 16> DeadInsts;
   DeadInsts.push_back(I);
 
   do {
     I = DeadInsts.pop_back_val();
 
     // Null out all of the instruction's operands to see if any operand becomes
     // dead as we go.
     for (unsigned i = 0, e = I->getNumOperands(); i != e; ++i) {
       Value *OpV = I->getOperand(i);
       I->setOperand(i, nullptr);
 
       if (!OpV->use_empty()) continue;
 
       // If the operand is an instruction that became dead as we nulled out the
       // operand, and if it is 'trivially' dead, delete it in a future loop
       // iteration.
       if (Instruction *OpI = dyn_cast<Instruction>(OpV))
         if (isInstructionTriviallyDead(OpI, TLI))
           DeadInsts.push_back(OpI);
     }
 
     I->eraseFromParent();
   } while (!DeadInsts.empty());
 
   return true;
 }
 
 /// areAllUsesEqual - Check whether the uses of a value are all the same.
 /// This is similar to Instruction::hasOneUse() except this will also return
 /// true when there are no uses or multiple uses that all refer to the same
 /// value.
 static bool areAllUsesEqual(Instruction *I) {
   Value::user_iterator UI = I->user_begin();
   Value::user_iterator UE = I->user_end();
   if (UI == UE)
     return true;
 
   User *TheUse = *UI;
   for (++UI; UI != UE; ++UI) {
     if (*UI != TheUse)
       return false;
   }
   return true;
 }
 
 /// RecursivelyDeleteDeadPHINode - If the specified value is an effectively
 /// dead PHI node, due to being a def-use chain of single-use nodes that
 /// either forms a cycle or is terminated by a trivially dead instruction,
 /// delete it.  If that makes any of its operands trivially dead, delete them
 /// too, recursively.  Return true if a change was made.
 bool llvm::RecursivelyDeleteDeadPHINode(PHINode *PN,
                                         const TargetLibraryInfo *TLI) {
   SmallPtrSet<Instruction*, 4> Visited;
   for (Instruction *I = PN; areAllUsesEqual(I) && !I->mayHaveSideEffects();
        I = cast<Instruction>(*I->user_begin())) {
     if (I->use_empty())
       return RecursivelyDeleteTriviallyDeadInstructions(I, TLI);
 
     // If we find an instruction more than once, we're on a cycle that
     // won't prove fruitful.
     if (!Visited.insert(I).second) {
       // Break the cycle and delete the instruction and its operands.
       I->replaceAllUsesWith(UndefValue::get(I->getType()));
       (void)RecursivelyDeleteTriviallyDeadInstructions(I, TLI);
       return true;
     }
   }
   return false;
 }
 
 static bool
 simplifyAndDCEInstruction(Instruction *I,
                           SmallSetVector<Instruction *, 16> &WorkList,
                           const DataLayout &DL,
                           const TargetLibraryInfo *TLI) {
   if (isInstructionTriviallyDead(I, TLI)) {
     // Null out all of the instruction's operands to see if any operand becomes
     // dead as we go.
     for (unsigned i = 0, e = I->getNumOperands(); i != e; ++i) {
       Value *OpV = I->getOperand(i);
       I->setOperand(i, nullptr);
 
       if (!OpV->use_empty() || I == OpV)
         continue;
 
       // If the operand is an instruction that became dead as we nulled out the
       // operand, and if it is 'trivially' dead, delete it in a future loop
       // iteration.
       if (Instruction *OpI = dyn_cast<Instruction>(OpV))
         if (isInstructionTriviallyDead(OpI, TLI))
           WorkList.insert(OpI);
     }
 
     I->eraseFromParent();
 
     return true;
   }
 
   if (Value *SimpleV = SimplifyInstruction(I, DL)) {
     // Add the users to the worklist. CAREFUL: an instruction can use itself,
     // in the case of a phi node.
     for (User *U : I->users())
       if (U != I)
         WorkList.insert(cast<Instruction>(U));
 
     // Replace the instruction with its simplified value.
     I->replaceAllUsesWith(SimpleV);
     I->eraseFromParent();
     return true;
   }
   return false;
 }
 
 /// SimplifyInstructionsInBlock - Scan the specified basic block and try to
 /// simplify any instructions in it and recursively delete dead instructions.
 ///
 /// This returns true if it changed the code, note that it can delete
 /// instructions in other blocks as well in this block.
 bool llvm::SimplifyInstructionsInBlock(BasicBlock *BB,
                                        const TargetLibraryInfo *TLI) {
   bool MadeChange = false;
   const DataLayout &DL = BB->getModule()->getDataLayout();
 
 #ifndef NDEBUG
   // In debug builds, ensure that the terminator of the block is never replaced
   // or deleted by these simplifications. The idea of simplification is that it
   // cannot introduce new instructions, and there is no way to replace the
   // terminator of a block without introducing a new instruction.
   AssertingVH<Instruction> TerminatorVH(&BB->back());
 #endif
 
   SmallSetVector<Instruction *, 16> WorkList;
   // Iterate over the original function, only adding insts to the worklist
   // if they actually need to be revisited. This avoids having to pre-init
   // the worklist with the entire function's worth of instructions.
   for (BasicBlock::iterator BI = BB->begin(), E = std::prev(BB->end()); BI != E;) {
     assert(!BI->isTerminator());
     Instruction *I = &*BI;
     ++BI;
 
     // We're visiting this instruction now, so make sure it's not in the
     // worklist from an earlier visit.
     if (!WorkList.count(I))
       MadeChange |= simplifyAndDCEInstruction(I, WorkList, DL, TLI);
   }
 
   while (!WorkList.empty()) {
     Instruction *I = WorkList.pop_back_val();
     MadeChange |= simplifyAndDCEInstruction(I, WorkList, DL, TLI);
   }
   return MadeChange;
 }
 
 //===----------------------------------------------------------------------===//
 //  Control Flow Graph Restructuring.
 //
 
 
 /// RemovePredecessorAndSimplify - Like BasicBlock::removePredecessor, this
 /// method is called when we're about to delete Pred as a predecessor of BB.  If
 /// BB contains any PHI nodes, this drops the entries in the PHI nodes for Pred.
 ///
 /// Unlike the removePredecessor method, this attempts to simplify uses of PHI
 /// nodes that collapse into identity values.  For example, if we have:
 ///   x = phi(1, 0, 0, 0)
 ///   y = and x, z
 ///
 /// .. and delete the predecessor corresponding to the '1', this will attempt to
 /// recursively fold the and to 0.
 void llvm::RemovePredecessorAndSimplify(BasicBlock *BB, BasicBlock *Pred) {
   // This only adjusts blocks with PHI nodes.
   if (!isa<PHINode>(BB->begin()))
     return;
 
   // Remove the entries for Pred from the PHI nodes in BB, but do not simplify
   // them down.  This will leave us with single entry phi nodes and other phis
   // that can be removed.
   BB->removePredecessor(Pred, true);
 
   WeakVH PhiIt = &BB->front();
   while (PHINode *PN = dyn_cast<PHINode>(PhiIt)) {
     PhiIt = &*++BasicBlock::iterator(cast<Instruction>(PhiIt));
     Value *OldPhiIt = PhiIt;
 
     if (!recursivelySimplifyInstruction(PN))
       continue;
 
     // If recursive simplification ended up deleting the next PHI node we would
     // iterate to, then our iterator is invalid, restart scanning from the top
     // of the block.
     if (PhiIt != OldPhiIt) PhiIt = &BB->front();
   }
 }
 
 
 /// MergeBasicBlockIntoOnlyPred - DestBB is a block with one predecessor and its
 /// predecessor is known to have one successor (DestBB!).  Eliminate the edge
 /// between them, moving the instructions in the predecessor into DestBB and
 /// deleting the predecessor block.
 ///
 void llvm::MergeBasicBlockIntoOnlyPred(BasicBlock *DestBB, DominatorTree *DT) {
   // If BB has single-entry PHI nodes, fold them.
   while (PHINode *PN = dyn_cast<PHINode>(DestBB->begin())) {
     Value *NewVal = PN->getIncomingValue(0);
     // Replace self referencing PHI with undef, it must be dead.
     if (NewVal == PN) NewVal = UndefValue::get(PN->getType());
     PN->replaceAllUsesWith(NewVal);
     PN->eraseFromParent();
   }
 
   BasicBlock *PredBB = DestBB->getSinglePredecessor();
   assert(PredBB && "Block doesn't have a single predecessor!");
 
   // Zap anything that took the address of DestBB.  Not doing this will give the
   // address an invalid value.
   if (DestBB->hasAddressTaken()) {
     BlockAddress *BA = BlockAddress::get(DestBB);
     Constant *Replacement =
       ConstantInt::get(llvm::Type::getInt32Ty(BA->getContext()), 1);
     BA->replaceAllUsesWith(ConstantExpr::getIntToPtr(Replacement,
                                                      BA->getType()));
     BA->destroyConstant();
   }
 
   // Anything that branched to PredBB now branches to DestBB.
   PredBB->replaceAllUsesWith(DestBB);
 
   // Splice all the instructions from PredBB to DestBB.
   PredBB->getTerminator()->eraseFromParent();
   DestBB->getInstList().splice(DestBB->begin(), PredBB->getInstList());
 
   // If the PredBB is the entry block of the function, move DestBB up to
   // become the entry block after we erase PredBB.
   if (PredBB == &DestBB->getParent()->getEntryBlock())
     DestBB->moveAfter(PredBB);
 
   if (DT) {
     BasicBlock *PredBBIDom = DT->getNode(PredBB)->getIDom()->getBlock();
     DT->changeImmediateDominator(DestBB, PredBBIDom);
     DT->eraseNode(PredBB);
   }
   // Nuke BB.
   PredBB->eraseFromParent();
 }
 
 /// CanMergeValues - Return true if we can choose one of these values to use
 /// in place of the other. Note that we will always choose the non-undef
 /// value to keep.
 static bool CanMergeValues(Value *First, Value *Second) {
   return First == Second || isa<UndefValue>(First) || isa<UndefValue>(Second);
 }
 
 /// CanPropagatePredecessorsForPHIs - Return true if we can fold BB, an
 /// almost-empty BB ending in an unconditional branch to Succ, into Succ.
 ///
 /// Assumption: Succ is the single successor for BB.
 ///
 static bool CanPropagatePredecessorsForPHIs(BasicBlock *BB, BasicBlock *Succ) {
   assert(*succ_begin(BB) == Succ && "Succ is not successor of BB!");
 
   DEBUG(dbgs() << "Looking to fold " << BB->getName() << " into "
         << Succ->getName() << "\n");
   // Shortcut, if there is only a single predecessor it must be BB and merging
   // is always safe
   if (Succ->getSinglePredecessor()) return true;
 
   // Make a list of the predecessors of BB
   SmallPtrSet<BasicBlock*, 16> BBPreds(pred_begin(BB), pred_end(BB));
 
   // Look at all the phi nodes in Succ, to see if they present a conflict when
   // merging these blocks
   for (BasicBlock::iterator I = Succ->begin(); isa<PHINode>(I); ++I) {
     PHINode *PN = cast<PHINode>(I);
 
     // If the incoming value from BB is again a PHINode in
     // BB which has the same incoming value for *PI as PN does, we can
     // merge the phi nodes and then the blocks can still be merged
     PHINode *BBPN = dyn_cast<PHINode>(PN->getIncomingValueForBlock(BB));
     if (BBPN && BBPN->getParent() == BB) {
       for (unsigned PI = 0, PE = PN->getNumIncomingValues(); PI != PE; ++PI) {
         BasicBlock *IBB = PN->getIncomingBlock(PI);
         if (BBPreds.count(IBB) &&
             !CanMergeValues(BBPN->getIncomingValueForBlock(IBB),
                             PN->getIncomingValue(PI))) {
           DEBUG(dbgs() << "Can't fold, phi node " << PN->getName() << " in "
                 << Succ->getName() << " is conflicting with "
                 << BBPN->getName() << " with regard to common predecessor "
                 << IBB->getName() << "\n");
           return false;
         }
       }
     } else {
       Value* Val = PN->getIncomingValueForBlock(BB);
       for (unsigned PI = 0, PE = PN->getNumIncomingValues(); PI != PE; ++PI) {
         // See if the incoming value for the common predecessor is equal to the
         // one for BB, in which case this phi node will not prevent the merging
         // of the block.
         BasicBlock *IBB = PN->getIncomingBlock(PI);
         if (BBPreds.count(IBB) &&
             !CanMergeValues(Val, PN->getIncomingValue(PI))) {
           DEBUG(dbgs() << "Can't fold, phi node " << PN->getName() << " in "
                 << Succ->getName() << " is conflicting with regard to common "
                 << "predecessor " << IBB->getName() << "\n");
           return false;
         }
       }
     }
   }
 
   return true;
 }
 
 typedef SmallVector<BasicBlock *, 16> PredBlockVector;
 typedef DenseMap<BasicBlock *, Value *> IncomingValueMap;
 
 /// \brief Determines the value to use as the phi node input for a block.
 ///
 /// Select between \p OldVal any value that we know flows from \p BB
 /// to a particular phi on the basis of which one (if either) is not
 /// undef. Update IncomingValues based on the selected value.
 ///
 /// \param OldVal The value we are considering selecting.
 /// \param BB The block that the value flows in from.
 /// \param IncomingValues A map from block-to-value for other phi inputs
 /// that we have examined.
 ///
 /// \returns the selected value.
 static Value *selectIncomingValueForBlock(Value *OldVal, BasicBlock *BB,
                                           IncomingValueMap &IncomingValues) {
   if (!isa<UndefValue>(OldVal)) {
     assert((!IncomingValues.count(BB) ||
             IncomingValues.find(BB)->second == OldVal) &&
            "Expected OldVal to match incoming value from BB!");
 
     IncomingValues.insert(std::make_pair(BB, OldVal));
     return OldVal;
   }
 
   IncomingValueMap::const_iterator It = IncomingValues.find(BB);
   if (It != IncomingValues.end()) return It->second;
 
   return OldVal;
 }
 
 /// \brief Create a map from block to value for the operands of a
 /// given phi.
 ///
 /// Create a map from block to value for each non-undef value flowing
 /// into \p PN.
 ///
 /// \param PN The phi we are collecting the map for.
 /// \param IncomingValues [out] The map from block to value for this phi.
 static void gatherIncomingValuesToPhi(PHINode *PN,
                                       IncomingValueMap &IncomingValues) {
   for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
     BasicBlock *BB = PN->getIncomingBlock(i);
     Value *V = PN->getIncomingValue(i);
 
     if (!isa<UndefValue>(V))
       IncomingValues.insert(std::make_pair(BB, V));
   }
 }
 
 /// \brief Replace the incoming undef values to a phi with the values
 /// from a block-to-value map.
 ///
 /// \param PN The phi we are replacing the undefs in.
 /// \param IncomingValues A map from block to value.
 static void replaceUndefValuesInPhi(PHINode *PN,
                                     const IncomingValueMap &IncomingValues) {
   for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
     Value *V = PN->getIncomingValue(i);
 
     if (!isa<UndefValue>(V)) continue;
 
     BasicBlock *BB = PN->getIncomingBlock(i);
     IncomingValueMap::const_iterator It = IncomingValues.find(BB);
     if (It == IncomingValues.end()) continue;
 
     PN->setIncomingValue(i, It->second);
   }
 }
 
 /// \brief Replace a value flowing from a block to a phi with
 /// potentially multiple instances of that value flowing from the
 /// block's predecessors to the phi.
 ///
 /// \param BB The block with the value flowing into the phi.
 /// \param BBPreds The predecessors of BB.
 /// \param PN The phi that we are updating.
 static void redirectValuesFromPredecessorsToPhi(BasicBlock *BB,
                                                 const PredBlockVector &BBPreds,
                                                 PHINode *PN) {
   Value *OldVal = PN->removeIncomingValue(BB, false);
   assert(OldVal && "No entry in PHI for Pred BB!");
 
   IncomingValueMap IncomingValues;
 
   // We are merging two blocks - BB, and the block containing PN - and
   // as a result we need to redirect edges from the predecessors of BB
   // to go to the block containing PN, and update PN
   // accordingly. Since we allow merging blocks in the case where the
   // predecessor and successor blocks both share some predecessors,
   // and where some of those common predecessors might have undef
   // values flowing into PN, we want to rewrite those values to be
   // consistent with the non-undef values.
 
   gatherIncomingValuesToPhi(PN, IncomingValues);
 
   // If this incoming value is one of the PHI nodes in BB, the new entries
   // in the PHI node are the entries from the old PHI.
   if (isa<PHINode>(OldVal) && cast<PHINode>(OldVal)->getParent() == BB) {
     PHINode *OldValPN = cast<PHINode>(OldVal);
     for (unsigned i = 0, e = OldValPN->getNumIncomingValues(); i != e; ++i) {
       // Note that, since we are merging phi nodes and BB and Succ might
       // have common predecessors, we could end up with a phi node with
       // identical incoming branches. This will be cleaned up later (and
       // will trigger asserts if we try to clean it up now, without also
       // simplifying the corresponding conditional branch).
       BasicBlock *PredBB = OldValPN->getIncomingBlock(i);
       Value *PredVal = OldValPN->getIncomingValue(i);
       Value *Selected = selectIncomingValueForBlock(PredVal, PredBB,
                                                     IncomingValues);
 
       // And add a new incoming value for this predecessor for the
       // newly retargeted branch.
       PN->addIncoming(Selected, PredBB);
     }
   } else {
     for (unsigned i = 0, e = BBPreds.size(); i != e; ++i) {
       // Update existing incoming values in PN for this
       // predecessor of BB.
       BasicBlock *PredBB = BBPreds[i];
       Value *Selected = selectIncomingValueForBlock(OldVal, PredBB,
                                                     IncomingValues);
 
       // And add a new incoming value for this predecessor for the
       // newly retargeted branch.
       PN->addIncoming(Selected, PredBB);
     }
   }
 
   replaceUndefValuesInPhi(PN, IncomingValues);
 }
 
 /// TryToSimplifyUncondBranchFromEmptyBlock - BB is known to contain an
 /// unconditional branch, and contains no instructions other than PHI nodes,
 /// potential side-effect free intrinsics and the branch.  If possible,
 /// eliminate BB by rewriting all the predecessors to branch to the successor
 /// block and return true.  If we can't transform, return false.
 bool llvm::TryToSimplifyUncondBranchFromEmptyBlock(BasicBlock *BB) {
   assert(BB != &BB->getParent()->getEntryBlock() &&
          "TryToSimplifyUncondBranchFromEmptyBlock called on entry block!");
 
   // We can't eliminate infinite loops.
   BasicBlock *Succ = cast<BranchInst>(BB->getTerminator())->getSuccessor(0);
   if (BB == Succ) return false;
 
   // Check to see if merging these blocks would cause conflicts for any of the
   // phi nodes in BB or Succ. If not, we can safely merge.
   if (!CanPropagatePredecessorsForPHIs(BB, Succ)) return false;
 
   // Check for cases where Succ has multiple predecessors and a PHI node in BB
   // has uses which will not disappear when the PHI nodes are merged.  It is
   // possible to handle such cases, but difficult: it requires checking whether
   // BB dominates Succ, which is non-trivial to calculate in the case where
   // Succ has multiple predecessors.  Also, it requires checking whether
   // constructing the necessary self-referential PHI node doesn't introduce any
   // conflicts; this isn't too difficult, but the previous code for doing this
   // was incorrect.
   //
   // Note that if this check finds a live use, BB dominates Succ, so BB is
   // something like a loop pre-header (or rarely, a part of an irreducible CFG);
   // folding the branch isn't profitable in that case anyway.
   if (!Succ->getSinglePredecessor()) {
     BasicBlock::iterator BBI = BB->begin();
     while (isa<PHINode>(*BBI)) {
       for (Use &U : BBI->uses()) {
         if (PHINode* PN = dyn_cast<PHINode>(U.getUser())) {
           if (PN->getIncomingBlock(U) != BB)
             return false;
         } else {
           return false;
         }
       }
       ++BBI;
     }
   }
 
   DEBUG(dbgs() << "Killing Trivial BB: \n" << *BB);
 
   if (isa<PHINode>(Succ->begin())) {
     // If there is more than one pred of succ, and there are PHI nodes in
     // the successor, then we need to add incoming edges for the PHI nodes
     //
     const PredBlockVector BBPreds(pred_begin(BB), pred_end(BB));
 
     // Loop over all of the PHI nodes in the successor of BB.
     for (BasicBlock::iterator I = Succ->begin(); isa<PHINode>(I); ++I) {
       PHINode *PN = cast<PHINode>(I);
 
       redirectValuesFromPredecessorsToPhi(BB, BBPreds, PN);
     }
   }
 
   if (Succ->getSinglePredecessor()) {
     // BB is the only predecessor of Succ, so Succ will end up with exactly
     // the same predecessors BB had.
 
     // Copy over any phi, debug or lifetime instruction.
     BB->getTerminator()->eraseFromParent();
     Succ->getInstList().splice(Succ->getFirstNonPHI()->getIterator(),
                                BB->getInstList());
   } else {
     while (PHINode *PN = dyn_cast<PHINode>(&BB->front())) {
       // We explicitly check for such uses in CanPropagatePredecessorsForPHIs.
       assert(PN->use_empty() && "There shouldn't be any uses here!");
       PN->eraseFromParent();
     }
   }
 
   // Everything that jumped to BB now goes to Succ.
   BB->replaceAllUsesWith(Succ);
   if (!Succ->hasName()) Succ->takeName(BB);
   BB->eraseFromParent();              // Delete the old basic block.
   return true;
 }
 
 /// EliminateDuplicatePHINodes - Check for and eliminate duplicate PHI
 /// nodes in this block. This doesn't try to be clever about PHI nodes
 /// which differ only in the order of the incoming values, but instcombine
 /// orders them so it usually won't matter.
 ///
 bool llvm::EliminateDuplicatePHINodes(BasicBlock *BB) {
   // This implementation doesn't currently consider undef operands
   // specially. Theoretically, two phis which are identical except for
   // one having an undef where the other doesn't could be collapsed.
 
   struct PHIDenseMapInfo {
     static PHINode *getEmptyKey() {
       return DenseMapInfo<PHINode *>::getEmptyKey();
     }
     static PHINode *getTombstoneKey() {
       return DenseMapInfo<PHINode *>::getTombstoneKey();
     }
     static unsigned getHashValue(PHINode *PN) {
       // Compute a hash value on the operands. Instcombine will likely have
       // sorted them, which helps expose duplicates, but we have to check all
       // the operands to be safe in case instcombine hasn't run.
       return static_cast<unsigned>(hash_combine(
           hash_combine_range(PN->value_op_begin(), PN->value_op_end()),
           hash_combine_range(PN->block_begin(), PN->block_end())));
     }
     static bool isEqual(PHINode *LHS, PHINode *RHS) {
       if (LHS == getEmptyKey() || LHS == getTombstoneKey() ||
           RHS == getEmptyKey() || RHS == getTombstoneKey())
         return LHS == RHS;
       return LHS->isIdenticalTo(RHS);
     }
   };
 
   // Set of unique PHINodes.
   DenseSet<PHINode *, PHIDenseMapInfo> PHISet;
 
   // Examine each PHI.
   bool Changed = false;
   for (auto I = BB->begin(); PHINode *PN = dyn_cast<PHINode>(I++);) {
     auto Inserted = PHISet.insert(PN);
     if (!Inserted.second) {
       // A duplicate. Replace this PHI with its duplicate.
       PN->replaceAllUsesWith(*Inserted.first);
       PN->eraseFromParent();
       Changed = true;
 
       // The RAUW can change PHIs that we already visited. Start over from the
       // beginning.
       PHISet.clear();
       I = BB->begin();
     }
   }
 
   return Changed;
 }
 
 /// enforceKnownAlignment - If the specified pointer points to an object that
 /// we control, modify the object's alignment to PrefAlign. This isn't
 /// often possible though. If alignment is important, a more reliable approach
 /// is to simply align all global variables and allocation instructions to
 /// their preferred alignment from the beginning.
 ///
 static unsigned enforceKnownAlignment(Value *V, unsigned Align,
                                       unsigned PrefAlign,
                                       const DataLayout &DL) {
+  assert(PrefAlign > Align);
+
   V = V->stripPointerCasts();
 
   if (AllocaInst *AI = dyn_cast<AllocaInst>(V)) {
+    // TODO: ideally, computeKnownBits ought to have used
+    // AllocaInst::getAlignment() in its computation already, making
+    // the below max redundant. But, as it turns out,
+    // stripPointerCasts recurses through infinite layers of bitcasts,
+    // while computeKnownBits is not allowed to traverse more than 6
+    // levels.
+    Align = std::max(AI->getAlignment(), Align);
+    if (PrefAlign <= Align)
+      return Align;
+
     // If the preferred alignment is greater than the natural stack alignment
     // then don't round up. This avoids dynamic stack realignment.
     if (DL.exceedsNaturalStackAlignment(PrefAlign))
       return Align;
-    // If there is a requested alignment and if this is an alloca, round up.
-    if (AI->getAlignment() >= PrefAlign)
-      return AI->getAlignment();
     AI->setAlignment(PrefAlign);
     return PrefAlign;
   }
 
   if (auto *GO = dyn_cast<GlobalObject>(V)) {
+    // TODO: as above, this shouldn't be necessary.
+    Align = std::max(GO->getAlignment(), Align);
+    if (PrefAlign <= Align)
+      return Align;
+
     // If there is a large requested alignment and we can, bump up the alignment
     // of the global.  If the memory we set aside for the global may not be the
     // memory used by the final program then it is impossible for us to reliably
     // enforce the preferred alignment.
-    if (!GO->isStrongDefinitionForLinker())
+    if (!GO->canIncreaseAlignment())
       return Align;
 
-    if (GO->getAlignment() >= PrefAlign)
-      return GO->getAlignment();
-    // We can only increase the alignment of the global if it has no alignment
-    // specified or if it is not assigned a section.  If it is assigned a
-    // section, the global could be densely packed with other objects in the
-    // section, increasing the alignment could cause padding issues.
-    if (!GO->hasSection() || GO->getAlignment() == 0)
-      GO->setAlignment(PrefAlign);
-    return GO->getAlignment();
+    GO->setAlignment(PrefAlign);
+    return PrefAlign;
   }
 
   return Align;
 }
 
 /// getOrEnforceKnownAlignment - If the specified pointer has an alignment that
 /// we can determine, return it, otherwise return 0.  If PrefAlign is specified,
 /// and it is more than the alignment of the ultimate object, see if we can
 /// increase the alignment of the ultimate object, making this check succeed.
 unsigned llvm::getOrEnforceKnownAlignment(Value *V, unsigned PrefAlign,
                                           const DataLayout &DL,
                                           const Instruction *CxtI,
                                           AssumptionCache *AC,
                                           const DominatorTree *DT) {
   assert(V->getType()->isPointerTy() &&
          "getOrEnforceKnownAlignment expects a pointer!");
   unsigned BitWidth = DL.getPointerTypeSizeInBits(V->getType());
 
   APInt KnownZero(BitWidth, 0), KnownOne(BitWidth, 0);
   computeKnownBits(V, KnownZero, KnownOne, DL, 0, AC, CxtI, DT);
   unsigned TrailZ = KnownZero.countTrailingOnes();
 
   // Avoid trouble with ridiculously large TrailZ values, such as
   // those computed from a null pointer.
   TrailZ = std::min(TrailZ, unsigned(sizeof(unsigned) * CHAR_BIT - 1));
 
   unsigned Align = 1u << std::min(BitWidth - 1, TrailZ);
 
   // LLVM doesn't support alignments larger than this currently.
   Align = std::min(Align, +Value::MaximumAlignment);
 
   if (PrefAlign > Align)
     Align = enforceKnownAlignment(V, Align, PrefAlign, DL);
 
   // We don't need to make any adjustment.
   return Align;
 }
 
 ///===---------------------------------------------------------------------===//
 ///  Dbg Intrinsic utilities
 ///
 
 /// See if there is a dbg.value intrinsic for DIVar before I.
 static bool LdStHasDebugValue(const DILocalVariable *DIVar, Instruction *I) {
   // Since we can't guarantee that the original dbg.declare instrinsic
   // is removed by LowerDbgDeclare(), we need to make sure that we are
   // not inserting the same dbg.value intrinsic over and over.
   llvm::BasicBlock::InstListType::iterator PrevI(I);
   if (PrevI != I->getParent()->getInstList().begin()) {
     --PrevI;
     if (DbgValueInst *DVI = dyn_cast<DbgValueInst>(PrevI))
       if (DVI->getValue() == I->getOperand(0) &&
           DVI->getOffset() == 0 &&
           DVI->getVariable() == DIVar)
         return true;
   }
   return false;
 }
 
 /// Inserts a llvm.dbg.value intrinsic before a store to an alloca'd value
 /// that has an associated llvm.dbg.decl intrinsic.
 bool llvm::ConvertDebugDeclareToDebugValue(DbgDeclareInst *DDI,
                                            StoreInst *SI, DIBuilder &Builder) {
   auto *DIVar = DDI->getVariable();
   auto *DIExpr = DDI->getExpression();
   assert(DIVar && "Missing variable");
 
   if (LdStHasDebugValue(DIVar, SI))
     return true;
 
   // If an argument is zero extended then use argument directly. The ZExt
   // may be zapped by an optimization pass in future.
   Argument *ExtendedArg = nullptr;
   if (ZExtInst *ZExt = dyn_cast<ZExtInst>(SI->getOperand(0)))
     ExtendedArg = dyn_cast<Argument>(ZExt->getOperand(0));
   if (SExtInst *SExt = dyn_cast<SExtInst>(SI->getOperand(0)))
     ExtendedArg = dyn_cast<Argument>(SExt->getOperand(0));
   if (ExtendedArg) {
     // We're now only describing a subset of the variable. The piece we're
     // describing will always be smaller than the variable size, because
     // VariableSize == Size of Alloca described by DDI. Since SI stores
     // to the alloca described by DDI, if it's first operand is an extend,
     // we're guaranteed that before extension, the value was narrower than
     // the size of the alloca, hence the size of the described variable.
     SmallVector<uint64_t, 3> NewDIExpr;
     unsigned PieceOffset = 0;
     // If this already is a bit piece, we drop the bit piece from the expression
     // and record the offset.
     if (DIExpr->isBitPiece()) {
       NewDIExpr.append(DIExpr->elements_begin(), DIExpr->elements_end()-3);
       PieceOffset = DIExpr->getBitPieceOffset();
     } else {
       NewDIExpr.append(DIExpr->elements_begin(), DIExpr->elements_end());
     }
     NewDIExpr.push_back(dwarf::DW_OP_bit_piece);
     NewDIExpr.push_back(PieceOffset); //Offset
     const DataLayout &DL = DDI->getModule()->getDataLayout();
     NewDIExpr.push_back(DL.getTypeSizeInBits(ExtendedArg->getType())); // Size
     Builder.insertDbgValueIntrinsic(ExtendedArg, 0, DIVar,
                                     Builder.createExpression(NewDIExpr),
                                     DDI->getDebugLoc(), SI);
   }
   else
     Builder.insertDbgValueIntrinsic(SI->getOperand(0), 0, DIVar, DIExpr,
                                     DDI->getDebugLoc(), SI);
   return true;
 }
 
 /// Inserts a llvm.dbg.value intrinsic before a load of an alloca'd value
 /// that has an associated llvm.dbg.decl intrinsic.
 bool llvm::ConvertDebugDeclareToDebugValue(DbgDeclareInst *DDI,
                                            LoadInst *LI, DIBuilder &Builder) {
   auto *DIVar = DDI->getVariable();
   auto *DIExpr = DDI->getExpression();
   assert(DIVar && "Missing variable");
 
   if (LdStHasDebugValue(DIVar, LI))
     return true;
 
   // We are now tracking the loaded value instead of the address. In the
   // future if multi-location support is added to the IR, it might be
   // preferable to keep tracking both the loaded value and the original
   // address in case the alloca can not be elided.
   Instruction *DbgValue = Builder.insertDbgValueIntrinsic(
       LI, 0, DIVar, DIExpr, DDI->getDebugLoc(), (Instruction *)nullptr);
   DbgValue->insertAfter(LI);
   return true;
 }
 
 /// Determine whether this alloca is either a VLA or an array.
 static bool isArray(AllocaInst *AI) {
   return AI->isArrayAllocation() ||
     AI->getType()->getElementType()->isArrayTy();
 }
 
 /// LowerDbgDeclare - Lowers llvm.dbg.declare intrinsics into appropriate set
 /// of llvm.dbg.value intrinsics.
 bool llvm::LowerDbgDeclare(Function &F) {
   DIBuilder DIB(*F.getParent(), /*AllowUnresolved*/ false);
   SmallVector<DbgDeclareInst *, 4> Dbgs;
   for (auto &FI : F)
     for (Instruction &BI : FI)
       if (auto DDI = dyn_cast<DbgDeclareInst>(&BI))
         Dbgs.push_back(DDI);
 
   if (Dbgs.empty())
     return false;
 
   for (auto &I : Dbgs) {
     DbgDeclareInst *DDI = I;
     AllocaInst *AI = dyn_cast_or_null<AllocaInst>(DDI->getAddress());
     // If this is an alloca for a scalar variable, insert a dbg.value
     // at each load and store to the alloca and erase the dbg.declare.
     // The dbg.values allow tracking a variable even if it is not
     // stored on the stack, while the dbg.declare can only describe
     // the stack slot (and at a lexical-scope granularity). Later
     // passes will attempt to elide the stack slot.
     if (AI && !isArray(AI)) {
       for (User *U : AI->users())
         if (StoreInst *SI = dyn_cast<StoreInst>(U))
           ConvertDebugDeclareToDebugValue(DDI, SI, DIB);
         else if (LoadInst *LI = dyn_cast<LoadInst>(U))
           ConvertDebugDeclareToDebugValue(DDI, LI, DIB);
         else if (CallInst *CI = dyn_cast<CallInst>(U)) {
           // This is a call by-value or some other instruction that
           // takes a pointer to the variable. Insert a *value*
           // intrinsic that describes the alloca.
           SmallVector<uint64_t, 1> NewDIExpr;
           auto *DIExpr = DDI->getExpression();
           NewDIExpr.push_back(dwarf::DW_OP_deref);
           NewDIExpr.append(DIExpr->elements_begin(), DIExpr->elements_end());
           DIB.insertDbgValueIntrinsic(AI, 0, DDI->getVariable(),
                                       DIB.createExpression(NewDIExpr),
                                       DDI->getDebugLoc(), CI);
         }
       DDI->eraseFromParent();
     }
   }
   return true;
 }
 
 /// FindAllocaDbgDeclare - Finds the llvm.dbg.declare intrinsic describing the
 /// alloca 'V', if any.
 DbgDeclareInst *llvm::FindAllocaDbgDeclare(Value *V) {
   if (auto *L = LocalAsMetadata::getIfExists(V))
     if (auto *MDV = MetadataAsValue::getIfExists(V->getContext(), L))
       for (User *U : MDV->users())
         if (DbgDeclareInst *DDI = dyn_cast<DbgDeclareInst>(U))
           return DDI;
 
   return nullptr;
 }
 
 bool llvm::replaceDbgDeclare(Value *Address, Value *NewAddress,
                              Instruction *InsertBefore, DIBuilder &Builder,
                              bool Deref, int Offset) {
   DbgDeclareInst *DDI = FindAllocaDbgDeclare(Address);
   if (!DDI)
     return false;
   DebugLoc Loc = DDI->getDebugLoc();
   auto *DIVar = DDI->getVariable();
   auto *DIExpr = DDI->getExpression();
   assert(DIVar && "Missing variable");
 
   if (Deref || Offset) {
     // Create a copy of the original DIDescriptor for user variable, prepending
     // "deref" operation to a list of address elements, as new llvm.dbg.declare
     // will take a value storing address of the memory for variable, not
     // alloca itself.
     SmallVector<uint64_t, 4> NewDIExpr;
     if (Deref)
       NewDIExpr.push_back(dwarf::DW_OP_deref);
     if (Offset > 0) {
       NewDIExpr.push_back(dwarf::DW_OP_plus);
       NewDIExpr.push_back(Offset);
     } else if (Offset < 0) {
       NewDIExpr.push_back(dwarf::DW_OP_minus);
       NewDIExpr.push_back(-Offset);
     }
     if (DIExpr)
       NewDIExpr.append(DIExpr->elements_begin(), DIExpr->elements_end());
     DIExpr = Builder.createExpression(NewDIExpr);
   }
 
   // Insert llvm.dbg.declare immediately after the original alloca, and remove
   // old llvm.dbg.declare.
   Builder.insertDeclare(NewAddress, DIVar, DIExpr, Loc, InsertBefore);
   DDI->eraseFromParent();
   return true;
 }
 
 bool llvm::replaceDbgDeclareForAlloca(AllocaInst *AI, Value *NewAllocaAddress,
                                       DIBuilder &Builder, bool Deref, int Offset) {
   return replaceDbgDeclare(AI, NewAllocaAddress, AI->getNextNode(), Builder,
                            Deref, Offset);
 }
 
 void llvm::changeToUnreachable(Instruction *I, bool UseLLVMTrap) {
   BasicBlock *BB = I->getParent();
   // Loop over all of the successors, removing BB's entry from any PHI
   // nodes.
   for (succ_iterator SI = succ_begin(BB), SE = succ_end(BB); SI != SE; ++SI)
     (*SI)->removePredecessor(BB);
 
   // Insert a call to llvm.trap right before this.  This turns the undefined
   // behavior into a hard fail instead of falling through into random code.
   if (UseLLVMTrap) {
     Function *TrapFn =
       Intrinsic::getDeclaration(BB->getParent()->getParent(), Intrinsic::trap);
     CallInst *CallTrap = CallInst::Create(TrapFn, "", I);
     CallTrap->setDebugLoc(I->getDebugLoc());
   }
   new UnreachableInst(I->getContext(), I);
 
   // All instructions after this are dead.
   BasicBlock::iterator BBI = I->getIterator(), BBE = BB->end();
   while (BBI != BBE) {
     if (!BBI->use_empty())
       BBI->replaceAllUsesWith(UndefValue::get(BBI->getType()));
     BB->getInstList().erase(BBI++);
   }
 }
 
 /// changeToCall - Convert the specified invoke into a normal call.
 static void changeToCall(InvokeInst *II) {
   SmallVector<Value*, 8> Args(II->arg_begin(), II->arg_end());
   SmallVector<OperandBundleDef, 1> OpBundles;
   II->getOperandBundlesAsDefs(OpBundles);
   CallInst *NewCall = CallInst::Create(II->getCalledValue(), Args, OpBundles,
                                        "", II);
   NewCall->takeName(II);
   NewCall->setCallingConv(II->getCallingConv());
   NewCall->setAttributes(II->getAttributes());
   NewCall->setDebugLoc(II->getDebugLoc());
   II->replaceAllUsesWith(NewCall);
 
   // Follow the call by a branch to the normal destination.
   BranchInst::Create(II->getNormalDest(), II);
 
   // Update PHI nodes in the unwind destination
   II->getUnwindDest()->removePredecessor(II->getParent());
   II->eraseFromParent();
 }
 
 static bool markAliveBlocks(Function &F,
                             SmallPtrSetImpl<BasicBlock*> &Reachable) {
 
   SmallVector<BasicBlock*, 128> Worklist;
   BasicBlock *BB = &F.front();
   Worklist.push_back(BB);
   Reachable.insert(BB);
   bool Changed = false;
   do {
     BB = Worklist.pop_back_val();
 
     // Do a quick scan of the basic block, turning any obviously unreachable
     // instructions into LLVM unreachable insts.  The instruction combining pass
     // canonicalizes unreachable insts into stores to null or undef.
     for (BasicBlock::iterator BBI = BB->begin(), E = BB->end(); BBI != E;++BBI){
       // Assumptions that are known to be false are equivalent to unreachable.
       // Also, if the condition is undefined, then we make the choice most
       // beneficial to the optimizer, and choose that to also be unreachable.
       if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(BBI))
         if (II->getIntrinsicID() == Intrinsic::assume) {
           bool MakeUnreachable = false;
           if (isa<UndefValue>(II->getArgOperand(0)))
             MakeUnreachable = true;
           else if (ConstantInt *Cond =
                    dyn_cast<ConstantInt>(II->getArgOperand(0)))
             MakeUnreachable = Cond->isZero();
 
           if (MakeUnreachable) {
             // Don't insert a call to llvm.trap right before the unreachable.
             changeToUnreachable(&*BBI, false);
             Changed = true;
             break;
           }
         }
 
       if (CallInst *CI = dyn_cast<CallInst>(BBI)) {
         if (CI->doesNotReturn()) {
           // If we found a call to a no-return function, insert an unreachable
           // instruction after it.  Make sure there isn't *already* one there
           // though.
           ++BBI;
           if (!isa<UnreachableInst>(BBI)) {
             // Don't insert a call to llvm.trap right before the unreachable.
             changeToUnreachable(&*BBI, false);
             Changed = true;
           }
           break;
         }
       }
 
       // Store to undef and store to null are undefined and used to signal that
       // they should be changed to unreachable by passes that can't modify the
       // CFG.
       if (StoreInst *SI = dyn_cast<StoreInst>(BBI)) {
         // Don't touch volatile stores.
         if (SI->isVolatile()) continue;
 
         Value *Ptr = SI->getOperand(1);
 
         if (isa<UndefValue>(Ptr) ||
             (isa<ConstantPointerNull>(Ptr) &&
              SI->getPointerAddressSpace() == 0)) {
           changeToUnreachable(SI, true);
           Changed = true;
           break;
         }
       }
     }
 
     TerminatorInst *Terminator = BB->getTerminator();
     if (auto *II = dyn_cast<InvokeInst>(Terminator)) {
       // Turn invokes that call 'nounwind' functions into ordinary calls.
       Value *Callee = II->getCalledValue();
       if (isa<ConstantPointerNull>(Callee) || isa<UndefValue>(Callee)) {
         changeToUnreachable(II, true);
         Changed = true;
       } else if (II->doesNotThrow() && canSimplifyInvokeNoUnwind(&F)) {
         if (II->use_empty() && II->onlyReadsMemory()) {
           // jump to the normal destination branch.
           BranchInst::Create(II->getNormalDest(), II);
           II->getUnwindDest()->removePredecessor(II->getParent());
           II->eraseFromParent();
         } else
           changeToCall(II);
         Changed = true;
       }
     } else if (auto *CatchSwitch = dyn_cast<CatchSwitchInst>(Terminator)) {
       // Remove catchpads which cannot be reached.
       struct CatchPadDenseMapInfo {
         static CatchPadInst *getEmptyKey() {
           return DenseMapInfo<CatchPadInst *>::getEmptyKey();
         }
         static CatchPadInst *getTombstoneKey() {
           return DenseMapInfo<CatchPadInst *>::getTombstoneKey();
         }
         static unsigned getHashValue(CatchPadInst *CatchPad) {
           return static_cast<unsigned>(hash_combine_range(
               CatchPad->value_op_begin(), CatchPad->value_op_end()));
         }
         static bool isEqual(CatchPadInst *LHS, CatchPadInst *RHS) {
           if (LHS == getEmptyKey() || LHS == getTombstoneKey() ||
               RHS == getEmptyKey() || RHS == getTombstoneKey())
             return LHS == RHS;
           return LHS->isIdenticalTo(RHS);
         }
       };
 
       // Set of unique CatchPads.
       SmallDenseMap<CatchPadInst *, detail::DenseSetEmpty, 4,
                     CatchPadDenseMapInfo, detail::DenseSetPair<CatchPadInst *>>
           HandlerSet;
       detail::DenseSetEmpty Empty;
       for (CatchSwitchInst::handler_iterator I = CatchSwitch->handler_begin(),
                                              E = CatchSwitch->handler_end();
            I != E; ++I) {
         BasicBlock *HandlerBB = *I;
         auto *CatchPad = cast<CatchPadInst>(HandlerBB->getFirstNonPHI());
         if (!HandlerSet.insert({CatchPad, Empty}).second) {
           CatchSwitch->removeHandler(I);
           --I;
           --E;
           Changed = true;
         }
       }
     }
 
     Changed |= ConstantFoldTerminator(BB, true);
     for (succ_iterator SI = succ_begin(BB), SE = succ_end(BB); SI != SE; ++SI)
       if (Reachable.insert(*SI).second)
         Worklist.push_back(*SI);
   } while (!Worklist.empty());
   return Changed;
 }
 
 void llvm::removeUnwindEdge(BasicBlock *BB) {
   TerminatorInst *TI = BB->getTerminator();
 
   if (auto *II = dyn_cast<InvokeInst>(TI)) {
     changeToCall(II);
     return;
   }
 
   TerminatorInst *NewTI;
   BasicBlock *UnwindDest;
 
   if (auto *CRI = dyn_cast<CleanupReturnInst>(TI)) {
     NewTI = CleanupReturnInst::Create(CRI->getCleanupPad(), nullptr, CRI);
     UnwindDest = CRI->getUnwindDest();
   } else if (auto *CatchSwitch = dyn_cast<CatchSwitchInst>(TI)) {
     auto *NewCatchSwitch = CatchSwitchInst::Create(
         CatchSwitch->getParentPad(), nullptr, CatchSwitch->getNumHandlers(),
         CatchSwitch->getName(), CatchSwitch);
     for (BasicBlock *PadBB : CatchSwitch->handlers())
       NewCatchSwitch->addHandler(PadBB);
 
     NewTI = NewCatchSwitch;
     UnwindDest = CatchSwitch->getUnwindDest();
   } else {
     llvm_unreachable("Could not find unwind successor");
   }
 
   NewTI->takeName(TI);
   NewTI->setDebugLoc(TI->getDebugLoc());
   UnwindDest->removePredecessor(BB);
   TI->replaceAllUsesWith(NewTI);
   TI->eraseFromParent();
 }
 
 /// removeUnreachableBlocksFromFn - Remove blocks that are not reachable, even
 /// if they are in a dead cycle.  Return true if a change was made, false
 /// otherwise.
 bool llvm::removeUnreachableBlocks(Function &F, LazyValueInfo *LVI) {
   SmallPtrSet<BasicBlock*, 128> Reachable;
   bool Changed = markAliveBlocks(F, Reachable);
 
   // If there are unreachable blocks in the CFG...
   if (Reachable.size() == F.size())
     return Changed;
 
   assert(Reachable.size() < F.size());
   NumRemoved += F.size()-Reachable.size();
 
   // Loop over all of the basic blocks that are not reachable, dropping all of
   // their internal references...
   for (Function::iterator BB = ++F.begin(), E = F.end(); BB != E; ++BB) {
     if (Reachable.count(&*BB))
       continue;
 
     for (succ_iterator SI = succ_begin(&*BB), SE = succ_end(&*BB); SI != SE;
          ++SI)
       if (Reachable.count(*SI))
         (*SI)->removePredecessor(&*BB);
     if (LVI)
       LVI->eraseBlock(&*BB);
     BB->dropAllReferences();
   }
 
   for (Function::iterator I = ++F.begin(); I != F.end();)
     if (!Reachable.count(&*I))
       I = F.getBasicBlockList().erase(I);
     else
       ++I;
 
   return true;
 }
 
 void llvm::combineMetadata(Instruction *K, const Instruction *J,
                            ArrayRef<unsigned> KnownIDs) {
   SmallVector<std::pair<unsigned, MDNode *>, 4> Metadata;
   K->dropUnknownNonDebugMetadata(KnownIDs);
   K->getAllMetadataOtherThanDebugLoc(Metadata);
   for (unsigned i = 0, n = Metadata.size(); i < n; ++i) {
     unsigned Kind = Metadata[i].first;
     MDNode *JMD = J->getMetadata(Kind);
     MDNode *KMD = Metadata[i].second;
 
     switch (Kind) {
       default:
         K->setMetadata(Kind, nullptr); // Remove unknown metadata
         break;
       case LLVMContext::MD_dbg:
         llvm_unreachable("getAllMetadataOtherThanDebugLoc returned a MD_dbg");
       case LLVMContext::MD_tbaa:
         K->setMetadata(Kind, MDNode::getMostGenericTBAA(JMD, KMD));
         break;
       case LLVMContext::MD_alias_scope:
         K->setMetadata(Kind, MDNode::getMostGenericAliasScope(JMD, KMD));
         break;
       case LLVMContext::MD_noalias:
         K->setMetadata(Kind, MDNode::intersect(JMD, KMD));
         break;
       case LLVMContext::MD_range:
         K->setMetadata(Kind, MDNode::getMostGenericRange(JMD, KMD));
         break;
       case LLVMContext::MD_fpmath:
         K->setMetadata(Kind, MDNode::getMostGenericFPMath(JMD, KMD));
         break;
       case LLVMContext::MD_invariant_load:
         // Only set the !invariant.load if it is present in both instructions.
         K->setMetadata(Kind, JMD);
         break;
       case LLVMContext::MD_nonnull:
         // Only set the !nonnull if it is present in both instructions.
         K->setMetadata(Kind, JMD);
         break;
       case LLVMContext::MD_invariant_group:
         // Preserve !invariant.group in K.
         break;
       case LLVMContext::MD_align:
         K->setMetadata(Kind, 
           MDNode::getMostGenericAlignmentOrDereferenceable(JMD, KMD));
         break;
       case LLVMContext::MD_dereferenceable:
       case LLVMContext::MD_dereferenceable_or_null:
         K->setMetadata(Kind, 
           MDNode::getMostGenericAlignmentOrDereferenceable(JMD, KMD));
         break;
     }
   }
   // Set !invariant.group from J if J has it. If both instructions have it
   // then we will just pick it from J - even when they are different.
   // Also make sure that K is load or store - f.e. combining bitcast with load
   // could produce bitcast with invariant.group metadata, which is invalid.
   // FIXME: we should try to preserve both invariant.group md if they are
   // different, but right now instruction can only have one invariant.group.
   if (auto *JMD = J->getMetadata(LLVMContext::MD_invariant_group))
     if (isa<LoadInst>(K) || isa<StoreInst>(K))
       K->setMetadata(LLVMContext::MD_invariant_group, JMD);
 }
 
 unsigned llvm::replaceDominatedUsesWith(Value *From, Value *To,
                                         DominatorTree &DT,
                                         const BasicBlockEdge &Root) {
   assert(From->getType() == To->getType());
   
   unsigned Count = 0;
   for (Value::use_iterator UI = From->use_begin(), UE = From->use_end();
        UI != UE; ) {
     Use &U = *UI++;
     if (DT.dominates(Root, U)) {
       U.set(To);
       DEBUG(dbgs() << "Replace dominated use of '"
             << From->getName() << "' as "
             << *To << " in " << *U << "\n");
       ++Count;
     }
   }
   return Count;
 }
 
 unsigned llvm::replaceDominatedUsesWith(Value *From, Value *To,
                                         DominatorTree &DT,
                                         const BasicBlock *BB) {
   assert(From->getType() == To->getType());
 
   unsigned Count = 0;
   for (Value::use_iterator UI = From->use_begin(), UE = From->use_end();
        UI != UE;) {
     Use &U = *UI++;
     auto *I = cast<Instruction>(U.getUser());
     if (DT.dominates(BB, I->getParent())) {
       U.set(To);
       DEBUG(dbgs() << "Replace dominated use of '" << From->getName() << "' as "
                    << *To << " in " << *U << "\n");
       ++Count;
     }
   }
   return Count;
 }
 
 bool llvm::callsGCLeafFunction(ImmutableCallSite CS) {
   if (isa<IntrinsicInst>(CS.getInstruction()))
     // Most LLVM intrinsics are things which can never take a safepoint.
     // As a result, we don't need to have the stack parsable at the
     // callsite.  This is a highly useful optimization since intrinsic
     // calls are fairly prevalent, particularly in debug builds.
     return true;
 
   // Check if the function is specifically marked as a gc leaf function.
   if (CS.hasFnAttr("gc-leaf-function"))
     return true;
   if (const Function *F = CS.getCalledFunction())
     return F->hasFnAttribute("gc-leaf-function");
 
   return false;
 }