/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp

Bug Summary

File:	lib/CodeGen/CodeGenPrepare.cpp
Warning:	line 3083, column 41 Called C++ object pointer is null
Annotated Source Code

Press '?' to see keyboard shortcuts
Show analyzer invocation
clang -cc1 -triple x86_64-pc-linux-gnu -analyze -disable-free -disable-llvm-verifier -discard-value-names -main-file-name CodeGenPrepare.cpp -analyzer-store=region -analyzer-opt-analyze-nested-blocks -analyzer-eagerly-assume -analyzer-checker=core -analyzer-checker=apiModeling -analyzer-checker=unix -analyzer-checker=deadcode -analyzer-checker=cplusplus -analyzer-checker=security.insecureAPI.UncheckedReturn -analyzer-checker=security.insecureAPI.getpw -analyzer-checker=security.insecureAPI.gets -analyzer-checker=security.insecureAPI.mktemp -analyzer-checker=security.insecureAPI.mkstemp -analyzer-checker=security.insecureAPI.vfork -analyzer-checker=nullability.NullPassedToNonnull -analyzer-checker=nullability.NullReturnedFromNonnull -analyzer-output plist -w -mrelocation-model pic -pic-level 2 -mthread-model posix -fmath-errno -masm-verbose -mconstructor-aliases -munwind-tables -fuse-init-array -target-cpu x86-64 -dwarf-column-info -debugger-tuning=gdb -momit-leaf-frame-pointer -ffunction-sections -fdata-sections -resource-dir /usr/lib/llvm-7/lib/clang/7.0.0 -D _DEBUG -D _GNU_SOURCE -D __STDC_CONSTANT_MACROS -D __STDC_FORMAT_MACROS -D __STDC_LIMIT_MACROS -I /build/llvm-toolchain-snapshot-7~svn326246/build-llvm/lib/CodeGen -I /build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen -I /build/llvm-toolchain-snapshot-7~svn326246/build-llvm/include -I /build/llvm-toolchain-snapshot-7~svn326246/include -U NDEBUG -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/c++/7.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/x86_64-linux-gnu/c++/7.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/x86_64-linux-gnu/c++/7.3.0 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/7.3.0/../../../../include/c++/7.3.0/backward -internal-isystem /usr/include/clang/7.0.0/include/ -internal-isystem /usr/local/include -internal-isystem /usr/lib/llvm-7/lib/clang/7.0.0/include -internal-externc-isystem /usr/include/x86_64-linux-gnu -internal-externc-isystem /include -internal-externc-isystem /usr/include -O2 -Wno-unused-parameter -Wwrite-strings -Wno-missing-field-initializers -Wno-long-long -Wno-maybe-uninitialized -Wno-comment -std=c++11 -fdeprecated-macro -fdebug-compilation-dir /build/llvm-toolchain-snapshot-7~svn326246/build-llvm/lib/CodeGen -ferror-limit 19 -fmessage-length 0 -fvisibility-inlines-hidden -fobjc-runtime=gcc -fdiagnostics-show-option -vectorize-loops -vectorize-slp -analyzer-checker optin.performance.Padding -analyzer-output=html -analyzer-config stable-report-filename=true -o /tmp/scan-build-2018-02-28-041547-14988-1 -x c++ /build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp
1//===- CodeGenPrepare.cpp - Prepare a function for code generation --------===//
2//
3//                     The LLVM Compiler Infrastructure
4//
5// This file is distributed under the University of Illinois Open Source
6// License. See LICENSE.TXT for details.
7//
8//===----------------------------------------------------------------------===//
9//
10// This pass munges the code in the input function to better prepare it for
11// SelectionDAG-based code generation. This works around limitations in it's
12// basic-block-at-a-time approach. It should eventually be removed.
13//
14//===----------------------------------------------------------------------===//

16#include "llvm/ADT/APInt.h"
17#include "llvm/ADT/ArrayRef.h"
18#include "llvm/ADT/DenseMap.h"
19#include "llvm/ADT/PointerIntPair.h"
20#include "llvm/ADT/STLExtras.h"
21#include "llvm/ADT/SmallPtrSet.h"
22#include "llvm/ADT/SmallVector.h"
23#include "llvm/ADT/Statistic.h"
24#include "llvm/Analysis/BlockFrequencyInfo.h"
25#include "llvm/Analysis/BranchProbabilityInfo.h"
26#include "llvm/Analysis/ConstantFolding.h"
27#include "llvm/Analysis/InstructionSimplify.h"
28#include "llvm/Analysis/LoopInfo.h"
29#include "llvm/Analysis/MemoryBuiltins.h"
30#include "llvm/Analysis/ProfileSummaryInfo.h"
31#include "llvm/Analysis/TargetLibraryInfo.h"
32#include "llvm/Analysis/TargetTransformInfo.h"
33#include "llvm/Analysis/ValueTracking.h"
34#include "llvm/CodeGen/Analysis.h"
35#include "llvm/CodeGen/ISDOpcodes.h"
36#include "llvm/CodeGen/MachineValueType.h"
37#include "llvm/CodeGen/SelectionDAGNodes.h"
38#include "llvm/CodeGen/TargetLowering.h"
39#include "llvm/CodeGen/TargetPassConfig.h"
40#include "llvm/CodeGen/TargetSubtargetInfo.h"
41#include "llvm/CodeGen/ValueTypes.h"
42#include "llvm/IR/Argument.h"
43#include "llvm/IR/Attributes.h"
44#include "llvm/IR/BasicBlock.h"
45#include "llvm/IR/CallSite.h"
46#include "llvm/IR/Constant.h"
47#include "llvm/IR/Constants.h"
48#include "llvm/IR/DataLayout.h"
49#include "llvm/IR/DerivedTypes.h"
50#include "llvm/IR/Dominators.h"
51#include "llvm/IR/Function.h"
52#include "llvm/IR/GetElementPtrTypeIterator.h"
53#include "llvm/IR/GlobalValue.h"
54#include "llvm/IR/GlobalVariable.h"
55#include "llvm/IR/IRBuilder.h"
56#include "llvm/IR/InlineAsm.h"
57#include "llvm/IR/InstrTypes.h"
58#include "llvm/IR/Instruction.h"
59#include "llvm/IR/Instructions.h"
60#include "llvm/IR/IntrinsicInst.h"
61#include "llvm/IR/Intrinsics.h"
62#include "llvm/IR/LLVMContext.h"
63#include "llvm/IR/MDBuilder.h"
64#include "llvm/IR/Module.h"
65#include "llvm/IR/Operator.h"
66#include "llvm/IR/PatternMatch.h"
67#include "llvm/IR/Statepoint.h"
68#include "llvm/IR/Type.h"
69#include "llvm/IR/Use.h"
70#include "llvm/IR/User.h"
71#include "llvm/IR/Value.h"
72#include "llvm/IR/ValueHandle.h"
73#include "llvm/IR/ValueMap.h"
74#include "llvm/Pass.h"
75#include "llvm/Support/BlockFrequency.h"
76#include "llvm/Support/BranchProbability.h"
77#include "llvm/Support/Casting.h"
78#include "llvm/Support/CommandLine.h"
79#include "llvm/Support/Compiler.h"
80#include "llvm/Support/Debug.h"
81#include "llvm/Support/ErrorHandling.h"
82#include "llvm/Support/MathExtras.h"
83#include "llvm/Support/raw_ostream.h"
84#include "llvm/Target/TargetMachine.h"
85#include "llvm/Target/TargetOptions.h"
86#include "llvm/Transforms/Utils/BasicBlockUtils.h"
87#include "llvm/Transforms/Utils/BypassSlowDivision.h"
88#include "llvm/Transforms/Utils/Local.h"
89#include "llvm/Transforms/Utils/SimplifyLibCalls.h"
90#include <algorithm>
91#include <cassert>
92#include <cstdint>
93#include <iterator>
94#include <limits>
95#include <memory>
96#include <utility>
97#include <vector>

99using namespace llvm;
100using namespace llvm::PatternMatch;

102#define DEBUG_TYPE"codegenprepare" "codegenprepare"

104STATISTIC(NumBlocksElim, "Number of blocks eliminated")static llvm::Statistic NumBlocksElim = {"codegenprepare", "NumBlocksElim"
, "Number of blocks eliminated", {0}, {false}};
105STATISTIC(NumPHIsElim,   "Number of trivial PHIs eliminated")static llvm::Statistic NumPHIsElim = {"codegenprepare", "NumPHIsElim"
, "Number of trivial PHIs eliminated", {0}, {false}};
106STATISTIC(NumGEPsElim,   "Number of GEPs converted to casts")static llvm::Statistic NumGEPsElim = {"codegenprepare", "NumGEPsElim"
, "Number of GEPs converted to casts", {0}, {false}};
107STATISTIC(NumCmpUses, "Number of uses of Cmp expressions replaced with uses of "static llvm::Statistic NumCmpUses = {"codegenprepare", "NumCmpUses"
, "Number of uses of Cmp expressions replaced with uses of " "sunken Cmps"
, {0}, {false}}
                    "sunken Cmps")static llvm::Statistic NumCmpUses = {"codegenprepare", "NumCmpUses"
, "Number of uses of Cmp expressions replaced with uses of " "sunken Cmps"
, {0}, {false}};
109STATISTIC(NumCastUses, "Number of uses of Cast expressions replaced with uses "static llvm::Statistic NumCastUses = {"codegenprepare", "NumCastUses"
, "Number of uses of Cast expressions replaced with uses " "of sunken Casts"
, {0}, {false}}
                     "of sunken Casts")static llvm::Statistic NumCastUses = {"codegenprepare", "NumCastUses"
, "Number of uses of Cast expressions replaced with uses " "of sunken Casts"
, {0}, {false}};
111STATISTIC(NumMemoryInsts, "Number of memory instructions whose address "static llvm::Statistic NumMemoryInsts = {"codegenprepare", "NumMemoryInsts"
, "Number of memory instructions whose address " "computations were sunk"
, {0}, {false}}
                        "computations were sunk")static llvm::Statistic NumMemoryInsts = {"codegenprepare", "NumMemoryInsts"
, "Number of memory instructions whose address " "computations were sunk"
, {0}, {false}};
113STATISTIC(NumMemoryInstsPhiCreated,static llvm::Statistic NumMemoryInstsPhiCreated = {"codegenprepare"
, "NumMemoryInstsPhiCreated", "Number of phis created when address "
 "computations were sunk to memory instructions", {0}, {false
}}
        "Number of phis created when address "static llvm::Statistic NumMemoryInstsPhiCreated = {"codegenprepare"
, "NumMemoryInstsPhiCreated", "Number of phis created when address "
 "computations were sunk to memory instructions", {0}, {false
}}
        "computations were sunk to memory instructions")static llvm::Statistic NumMemoryInstsPhiCreated = {"codegenprepare"
, "NumMemoryInstsPhiCreated", "Number of phis created when address "
 "computations were sunk to memory instructions", {0}, {false
}};
116STATISTIC(NumMemoryInstsSelectCreated,static llvm::Statistic NumMemoryInstsSelectCreated = {"codegenprepare"
, "NumMemoryInstsSelectCreated", "Number of select created when address "
 "computations were sunk to memory instructions", {0}, {false
}}
        "Number of select created when address "static llvm::Statistic NumMemoryInstsSelectCreated = {"codegenprepare"
, "NumMemoryInstsSelectCreated", "Number of select created when address "
 "computations were sunk to memory instructions", {0}, {false
}}
        "computations were sunk to memory instructions")static llvm::Statistic NumMemoryInstsSelectCreated = {"codegenprepare"
, "NumMemoryInstsSelectCreated", "Number of select created when address "
 "computations were sunk to memory instructions", {0}, {false
}};
119STATISTIC(NumExtsMoved,  "Number of [s|z]ext instructions combined with loads")static llvm::Statistic NumExtsMoved = {"codegenprepare", "NumExtsMoved"
, "Number of [s|z]ext instructions combined with loads", {0},
 {false}};
120STATISTIC(NumExtUses,    "Number of uses of [s|z]ext instructions optimized")static llvm::Statistic NumExtUses = {"codegenprepare", "NumExtUses"
, "Number of uses of [s|z]ext instructions optimized", {0}, {
false}};
121STATISTIC(NumAndsAdded,static llvm::Statistic NumAndsAdded = {"codegenprepare", "NumAndsAdded"
, "Number of and mask instructions added to form ext loads", {
0}, {false}}
        "Number of and mask instructions added to form ext loads")static llvm::Statistic NumAndsAdded = {"codegenprepare", "NumAndsAdded"
, "Number of and mask instructions added to form ext loads", {
0}, {false}};
123STATISTIC(NumAndUses, "Number of uses of and mask instructions optimized")static llvm::Statistic NumAndUses = {"codegenprepare", "NumAndUses"
, "Number of uses of and mask instructions optimized", {0}, {
false}};
124STATISTIC(NumRetsDup,    "Number of return instructions duplicated")static llvm::Statistic NumRetsDup = {"codegenprepare", "NumRetsDup"
, "Number of return instructions duplicated", {0}, {false}};
125STATISTIC(NumDbgValueMoved, "Number of debug value instructions moved")static llvm::Statistic NumDbgValueMoved = {"codegenprepare", "NumDbgValueMoved"
, "Number of debug value instructions moved", {0}, {false}};
126STATISTIC(NumSelectsExpanded, "Number of selects turned into branches")static llvm::Statistic NumSelectsExpanded = {"codegenprepare"
, "NumSelectsExpanded", "Number of selects turned into branches"
, {0}, {false}};
127STATISTIC(NumStoreExtractExposed, "Number of store(extractelement) exposed")static llvm::Statistic NumStoreExtractExposed = {"codegenprepare"
, "NumStoreExtractExposed", "Number of store(extractelement) exposed"
, {0}, {false}};

129static cl::opt<bool> DisableBranchOpts(
"disable-cgp-branch-opts", cl::Hidden, cl::init(false),
cl::desc("Disable branch optimizations in CodeGenPrepare"));

133static cl::opt<bool>
  DisableGCOpts("disable-cgp-gc-opts", cl::Hidden, cl::init(false),
                cl::desc("Disable GC optimizations in CodeGenPrepare"));

137static cl::opt<bool> DisableSelectToBranch(
"disable-cgp-select2branch", cl::Hidden, cl::init(false),
cl::desc("Disable select to branch conversion."));

141static cl::opt<bool> AddrSinkUsingGEPs(
"addr-sink-using-gep", cl::Hidden, cl::init(true),
cl::desc("Address sinking in CGP using GEPs."));

145static cl::opt<bool> EnableAndCmpSinking(
 "enable-andcmp-sinking", cl::Hidden, cl::init(true),
 cl::desc("Enable sinkinig and/cmp into branches."));

149static cl::opt<bool> DisableStoreExtract(
  "disable-cgp-store-extract", cl::Hidden, cl::init(false),
  cl::desc("Disable store(extract) optimizations in CodeGenPrepare"));

153static cl::opt<bool> StressStoreExtract(
  "stress-cgp-store-extract", cl::Hidden, cl::init(false),
  cl::desc("Stress test store(extract) optimizations in CodeGenPrepare"));

157static 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"));

162static 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"));

167static cl::opt<bool> DisablePreheaderProtect(
  "disable-preheader-prot", cl::Hidden, cl::init(false),
  cl::desc("Disable protection against removing loop preheaders"));

171static cl::opt<bool> ProfileGuidedSectionPrefix(
  "profile-guided-section-prefix", cl::Hidden, cl::init(true), cl::ZeroOrMore,
  cl::desc("Use profile info to add section prefix for hot/cold functions"));

175static cl::opt<unsigned> FreqRatioToSkipMerge(
  "cgp-freq-ratio-to-skip-merge", cl::Hidden, cl::init(2),
  cl::desc("Skip merging empty blocks if (frequency of empty block) / "
           "(frequency of destination block) is greater than this ratio"));

180static cl::opt<bool> ForceSplitStore(
  "force-split-store", cl::Hidden, cl::init(false),
  cl::desc("Force store splitting no matter what the target query says."));

184static cl::opt<bool>
185EnableTypePromotionMerge("cgp-type-promotion-merge", cl::Hidden,
  cl::desc("Enable merging of redundant sexts when one is dominating"
  " the other."), cl::init(true));

189static cl::opt<bool> DisableComplexAddrModes(
  "disable-complex-addr-modes", cl::Hidden, cl::init(false),
  cl::desc("Disables combining addressing modes with different parts "
           "in optimizeMemoryInst."));

194static cl::opt<bool>
195AddrSinkNewPhis("addr-sink-new-phis", cl::Hidden, cl::init(false),
              cl::desc("Allow creation of Phis in Address sinking."));

198static cl::opt<bool>
199AddrSinkNewSelects("addr-sink-new-select", cl::Hidden, cl::init(true),
                 cl::desc("Allow creation of selects in Address sinking."));

202static cl::opt<bool> AddrSinkCombineBaseReg(
  "addr-sink-combine-base-reg", cl::Hidden, cl::init(true),
  cl::desc("Allow combining of BaseReg field in Address sinking."));

206static cl::opt<bool> AddrSinkCombineBaseGV(
  "addr-sink-combine-base-gv", cl::Hidden, cl::init(true),
  cl::desc("Allow combining of BaseGV field in Address sinking."));

210static cl::opt<bool> AddrSinkCombineBaseOffs(
  "addr-sink-combine-base-offs", cl::Hidden, cl::init(true),
  cl::desc("Allow combining of BaseOffs field in Address sinking."));

214static cl::opt<bool> AddrSinkCombineScaledReg(
  "addr-sink-combine-scaled-reg", cl::Hidden, cl::init(true),
  cl::desc("Allow combining of ScaledReg field in Address sinking."));

218namespace {

220using SetOfInstrs = SmallPtrSet<Instruction *, 16>;
221using TypeIsSExt = PointerIntPair<Type *, 1, bool>;
222using InstrToOrigTy = DenseMap<Instruction *, TypeIsSExt>;
223using SExts = SmallVector<Instruction *, 16>;
224using ValueToSExts = DenseMap<Value *, SExts>;

226class TypePromotionTransaction;

class CodeGenPrepare : public FunctionPass {
  const TargetMachine *TM = nullptr;
  const TargetSubtargetInfo *SubtargetInfo;
  const TargetLowering *TLI = nullptr;
  const TargetRegisterInfo *TRI;
  const TargetTransformInfo *TTI = nullptr;
  const TargetLibraryInfo *TLInfo;
  const LoopInfo *LI;
  std::unique_ptr<BlockFrequencyInfo> BFI;
  std::unique_ptr<BranchProbabilityInfo> BPI;

  /// 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. The usage of WeakTrackingVH
  /// enables SunkAddrs to be treated as a cache whose entries can be
  /// invalidated if a sunken address computation has been erased.
  ValueMap<Value*, WeakTrackingVH> 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;

  /// Keep track of instructions removed during promotion.
  SetOfInstrs RemovedInsts;

  /// Keep track of sext chains based on their initial value.
  DenseMap<Value *, Instruction *> SeenChainsForSExt;

  /// Keep track of SExt promoted.
  ValueToSExts ValToSExtendedUses;

  /// 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 = nullptr;

public:
  static char ID; // Pass identification, replacement for typeid

  CodeGenPrepare() : FunctionPass(ID) {
    initializeCodeGenPreparePass(*PassRegistry::getPassRegistry());
  }

  bool runOnFunction(Function &F) override;

  StringRef getPassName() const override { return "CodeGen Prepare"; }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    // FIXME: When we can selectively preserve passes, preserve the domtree.
    AU.addRequired<ProfileSummaryInfoWrapperPass>();
    AU.addRequired<TargetLibraryInfoWrapperPass>();
    AU.addRequired<TargetTransformInfoWrapperPass>();
    AU.addRequired<LoopInfoWrapperPass>();
  }

private:
  bool eliminateFallThrough(Function &F);
  bool eliminateMostlyEmptyBlocks(Function &F);
  BasicBlock *findDestBlockOfMergeableEmptyBlock(BasicBlock *BB);
  bool canMergeBlocks(const BasicBlock *BB, const BasicBlock *DestBB) const;
  void eliminateMostlyEmptyBlock(BasicBlock *BB);
  bool isMergingEmptyBlockProfitable(BasicBlock *BB, BasicBlock *DestBB,
                                     bool isPreheader);
  bool optimizeBlock(BasicBlock &BB, bool &ModifiedDT);
  bool optimizeInst(Instruction *I, bool &ModifiedDT);
  bool optimizeMemoryInst(Instruction *I, Value *Addr,
                          Type *AccessTy, unsigned AS);
  bool optimizeInlineAsmInst(CallInst *CS);
  bool optimizeCallInst(CallInst *CI, bool &ModifiedDT);
  bool optimizeExt(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 canFormExtLd(const SmallVectorImpl<Instruction *> &MovedExts,
                    LoadInst *&LI, Instruction *&Inst, bool HasPromoted);
  bool tryToPromoteExts(TypePromotionTransaction &TPT,
                        const SmallVectorImpl<Instruction *> &Exts,
                        SmallVectorImpl<Instruction *> &ProfitablyMovedExts,
                        unsigned CreatedInstsCost = 0);
  bool mergeSExts(Function &F);
  bool performAddressTypePromotion(
      Instruction *&Inst,
      bool AllowPromotionWithoutCommonHeader,
      bool HasPromoted, TypePromotionTransaction &TPT,
      SmallVectorImpl<Instruction *> &SpeculativelyMovedExts);
  bool splitBranchCondition(Function &F);
  bool simplifyOffsetableRelocate(Instruction &I);
};

333} // end anonymous namespace

335char CodeGenPrepare::ID = 0;

337INITIALIZE_PASS_BEGIN(CodeGenPrepare, DEBUG_TYPE,static void *initializeCodeGenPreparePassOnce(PassRegistry &
Registry) {
                    "Optimize for code generation", false, false)static void *initializeCodeGenPreparePassOnce(PassRegistry &
Registry) {
339INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)initializeProfileSummaryInfoWrapperPassPass(Registry);
340INITIALIZE_PASS_END(CodeGenPrepare, DEBUG_TYPE,PassInfo *PI = new PassInfo( "Optimize for code generation", "codegenprepare"
, &CodeGenPrepare::ID, PassInfo::NormalCtor_t(callDefaultCtor
<CodeGenPrepare>), false, false); Registry.registerPass
(*PI, true); return PI; } static llvm::once_flag InitializeCodeGenPreparePassFlag
; void llvm::initializeCodeGenPreparePass(PassRegistry &Registry
) { llvm::call_once(InitializeCodeGenPreparePassFlag, initializeCodeGenPreparePassOnce
, std::ref(Registry)); }
                  "Optimize for code generation", false, false)PassInfo *PI = new PassInfo( "Optimize for code generation", "codegenprepare"
, &CodeGenPrepare::ID, PassInfo::NormalCtor_t(callDefaultCtor
<CodeGenPrepare>), false, false); Registry.registerPass
(*PI, true); return PI; } static llvm::once_flag InitializeCodeGenPreparePassFlag
; void llvm::initializeCodeGenPreparePass(PassRegistry &Registry
) { llvm::call_once(InitializeCodeGenPreparePassFlag, initializeCodeGenPreparePassOnce
, std::ref(Registry)); }

343FunctionPass *llvm::createCodeGenPreparePass() { return new CodeGenPrepare(); }

345bool CodeGenPrepare::runOnFunction(Function &F) {
if (skipFunction(F))
  return false;

DL = &F.getParent()->getDataLayout();

bool EverMadeChange = false;
// Clear per function information.
InsertedInsts.clear();
PromotedInsts.clear();

ModifiedDT = false;
if (auto *TPC = getAnalysisIfAvailable<TargetPassConfig>()) {
  TM = &TPC->getTM<TargetMachine>();
  SubtargetInfo = TM->getSubtargetImpl(F);
  TLI = SubtargetInfo->getTargetLowering();
  TRI = SubtargetInfo->getRegisterInfo();
}
TLInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
BPI.reset(new BranchProbabilityInfo(F, *LI));
BFI.reset(new BlockFrequencyInfo(F, *BPI, *LI));
OptSize = F.optForSize();

ProfileSummaryInfo *PSI =
    getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
if (ProfileGuidedSectionPrefix) {
  if (PSI->isFunctionHotInCallGraph(&F, *BFI))
    F.setSectionPrefix(".hot");
  else if (PSI->isFunctionColdInCallGraph(&F, *BFI))
    F.setSectionPrefix(".unlikely");
}

/// This optimization identifies DIV instructions that can be
/// profitably bypassed and carried out with a shorter, faster divide.
if (!OptSize && !PSI->hasHugeWorkingSetSize() && 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 (!DisableBranchOpts)
  EverMadeChange |= splitBranchCondition(F);

// Split some critical edges where one of the sources is an indirect branch,
// to help generate sane code for PHIs involving such edges.
EverMadeChange |= SplitIndirectBrCriticalEdges(F);

bool MadeChange = true;
while (MadeChange) {
  MadeChange = false;
  SeenChainsForSExt.clear();
  ValToSExtendedUses.clear();
  RemovedInsts.clear();
  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;
  }
  if (EnableTypePromotionMerge && !ValToSExtendedUses.empty())
    MadeChange |= mergeSExts(F);

  // Really free removed instructions during promotion.
  for (Instruction *I : RemovedInsts)
    I->deleteValue();

  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;
486}

488/// Merge basic blocks which are connected by a single edge, where one of the
489/// basic blocks has a single successor pointing to the other basic block,
490/// which has a single predecessor.
491bool 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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "To merge:\n"<< *
SinglePred << "\n\n\n"; } } while (false);
    // 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;
520}

522/// Find a destination block from BB if BB is mergeable empty block.
523BasicBlock *CodeGenPrepare::findDestBlockOfMergeableEmptyBlock(BasicBlock *BB) {
// If this block doesn't end with an uncond branch, ignore it.
BranchInst *BI = dyn_cast<BranchInst>(BB->getTerminator());
if (!BI || !BI->isUnconditional())
  return nullptr;

// 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))
    return nullptr;
}

// Do not break infinite loops.
BasicBlock *DestBB = BI->getSuccessor(0);
if (DestBB == BB)
  return nullptr;

if (!canMergeBlocks(BB, DestBB))
  DestBB = nullptr;

return DestBB;
552}

554/// Eliminate blocks that contain only PHI nodes, debug info directives, and an
555/// unconditional branch. Passes before isel (e.g. LSR/loopsimplify) often split
556/// edges in ways that are non-optimal for isel. Start by eliminating these
557/// blocks so we can split them the way we want them.
558bool CodeGenPrepare::eliminateMostlyEmptyBlocks(Function &F) {
SmallPtrSet<BasicBlock *, 16> Preheaders;
SmallVector<Loop *, 16> LoopList(LI->begin(), LI->end());
while (!LoopList.empty()) {
  Loop *L = LoopList.pop_back_val();
  LoopList.insert(LoopList.end(), L->begin(), L->end());
  if (BasicBlock *Preheader = L->getLoopPreheader())
    Preheaders.insert(Preheader);
}

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++;
  BasicBlock *DestBB = findDestBlockOfMergeableEmptyBlock(BB);
  if (!DestBB ||
      !isMergingEmptyBlockProfitable(BB, DestBB, Preheaders.count(BB)))
    continue;

  eliminateMostlyEmptyBlock(BB);
  MadeChange = true;
}
return MadeChange;
581}

583bool CodeGenPrepare::isMergingEmptyBlockProfitable(BasicBlock *BB,
                                                 BasicBlock *DestBB,
                                                 bool isPreheader) {
// Do not delete loop preheaders if doing so would create a critical edge.
// Loop preheaders can be good locations to spill registers. If the
// preheader is deleted and we create a critical edge, registers may be
// spilled in the loop body instead.
if (!DisablePreheaderProtect && isPreheader &&
    !(BB->getSinglePredecessor() &&
      BB->getSinglePredecessor()->getSingleSuccessor()))
  return false;

// Try to skip merging if the unique predecessor of BB is terminated by a
// switch or indirect branch instruction, and BB is used as an incoming block
// of PHIs in DestBB. In such case, merging BB and DestBB would cause ISel to
// add COPY instructions in the predecessor of BB instead of BB (if it is not
// merged). Note that the critical edge created by merging such blocks wont be
// split in MachineSink because the jump table is not analyzable. By keeping
// such empty block (BB), ISel will place COPY instructions in BB, not in the
// predecessor of BB.
BasicBlock *Pred = BB->getUniquePredecessor();
if (!Pred ||
    !(isa<SwitchInst>(Pred->getTerminator()) ||
      isa<IndirectBrInst>(Pred->getTerminator())))
  return true;

if (BB->getTerminator() != BB->getFirstNonPHI())
  return true;

// We use a simple cost heuristic which determine skipping merging is
// profitable if the cost of skipping merging is less than the cost of
// merging : Cost(skipping merging) < Cost(merging BB), where the
// Cost(skipping merging) is Freq(BB) * (Cost(Copy) + Cost(Branch)), and
// the Cost(merging BB) is Freq(Pred) * Cost(Copy).
// Assuming Cost(Copy) == Cost(Branch), we could simplify it to :
//   Freq(Pred) / Freq(BB) > 2.
// Note that if there are multiple empty blocks sharing the same incoming
// value for the PHIs in the DestBB, we consider them together. In such
// case, Cost(merging BB) will be the sum of their frequencies.

if (!isa<PHINode>(DestBB->begin()))
  return true;

SmallPtrSet<BasicBlock *, 16> SameIncomingValueBBs;

// Find all other incoming blocks from which incoming values of all PHIs in
// DestBB are the same as the ones from BB.
for (pred_iterator PI = pred_begin(DestBB), E = pred_end(DestBB); PI != E;
     ++PI) {
  BasicBlock *DestBBPred = *PI;
  if (DestBBPred == BB)
    continue;

  if (llvm::all_of(DestBB->phis(), [&](const PHINode &DestPN) {
        return DestPN.getIncomingValueForBlock(BB) ==
               DestPN.getIncomingValueForBlock(DestBBPred);
      }))
    SameIncomingValueBBs.insert(DestBBPred);
}

// See if all BB's incoming values are same as the value from Pred. In this
// case, no reason to skip merging because COPYs are expected to be place in
// Pred already.
if (SameIncomingValueBBs.count(Pred))
  return true;

BlockFrequency PredFreq = BFI->getBlockFreq(Pred);
BlockFrequency BBFreq = BFI->getBlockFreq(BB);

for (auto SameValueBB : SameIncomingValueBBs)
  if (SameValueBB->getUniquePredecessor() == Pred &&
      DestBB == findDestBlockOfMergeableEmptyBlock(SameValueBB))
    BBFreq += BFI->getBlockFreq(SameValueBB);

return PredFreq.getFrequency() <=
       BBFreq.getFrequency() * FreqRatioToSkipMerge;
659}

661/// Return true if we can merge BB into DestBB if there is a single
662/// unconditional branch between them, and BB contains no other non-phi
663/// instructions.
664bool 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.
for (const PHINode &PN : BB->phis()) {
  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?
    for (const PHINode &PN : DestBB->phis()) {
      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;
725}

727/// Eliminate a basic block that has only phi's and an unconditional branch in
728/// it.
729void 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)do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "MERGING MOSTLY EMPTY BLOCKS - BEFORE:\n"
 << *BB << *DestBB; } } while (false);

// 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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "AFTER:\n" << *DestBB
 << "\n\n\n"; } } while (false);
    return;
  }
}

// Otherwise, we have multiple predecessors of BB.  Update the PHIs in DestBB
// to handle the new incoming edges it is about to have.
for (PHINode &PN : DestBB->phis()) {
  // 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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "AFTER:\n" << *DestBB
 << "\n\n\n"; } } while (false);
786}

788// Computes a map of base pointer relocation instructions to corresponding
789// derived pointer relocation instructions given a vector of all relocate calls
790static 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);
}
821}

823// Accepts a GEP and extracts the operands into a vector provided they're all
824// small integer constants
825static 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;
837}

839// Takes a RelocatedBase (base pointer relocation instruction) and Targets to
840// replace, computes a replacement, and affects it.
841static bool
842simplifyRelocatesOffABase(GCRelocateInst *RelocatedBase,
                        const SmallVectorImpl<GCRelocateInst *> &Targets) {
bool MadeChange = false;
// We must ensure the relocation of derived pointer is defined after
// relocation of base pointer. If we find a relocation corresponding to base
// defined earlier than relocation of base then we move relocation of base
// right before found relocation. We consider only relocation in the same
// basic block as relocation of base. Relocations from other basic block will
// be skipped by optimization and we do not care about them.
for (auto R = RelocatedBase->getParent()->getFirstInsertionPt();
     &*R != RelocatedBase; ++R)
  if (auto RI = dyn_cast<GCRelocateInst>(R))
    if (RI->getStatepoint() == RelocatedBase->getStatepoint())
      if (RI->getBasePtrIndex() == RelocatedBase->getBasePtrIndex()) {
        RelocatedBase->moveBefore(RI);
        break;
      }

for (GCRelocateInst *ToReplace : Targets) {
  assert(ToReplace->getBasePtrIndex() == RelocatedBase->getBasePtrIndex() &&(static_cast <bool> (ToReplace->getBasePtrIndex() ==
 RelocatedBase->getBasePtrIndex() && "Not relocating a derived object of the original base object"
) ? void (0) : __assert_fail ("ToReplace->getBasePtrIndex() == RelocatedBase->getBasePtrIndex() && \"Not relocating a derived object of the original base object\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 862, __extension__ __PRETTY_FUNCTION__))
         "Not relocating a derived object of the original base object")(static_cast <bool> (ToReplace->getBasePtrIndex() ==
 RelocatedBase->getBasePtrIndex() && "Not relocating a derived object of the original base object"
) ? void (0) : __assert_fail ("ToReplace->getBasePtrIndex() == RelocatedBase->getBasePtrIndex() && \"Not relocating a derived object of the original base object\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 862, __extension__ __PRETTY_FUNCTION__));
  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() &&(static_cast <bool> (RelocatedBase->getNextNode() &&
 "Should always have one since it's not a terminator") ? void
 (0) : __assert_fail ("RelocatedBase->getNextNode() && \"Should always have one since it's not a terminator\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 887, __extension__ __PRETTY_FUNCTION__))
         "Should always have one since it's not a terminator")(static_cast <bool> (RelocatedBase->getNextNode() &&
 "Should always have one since it's not a terminator") ? void
 (0) : __assert_fail ("RelocatedBase->getNextNode() && \"Should always have one since it's not a terminator\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 887, __extension__ __PRETTY_FUNCTION__));

  // 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;
935}

937// Turns this:
938//
939// %base = ...
940// %ptr = gep %base + 15
941// %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
942// %base' = relocate(%tok, i32 4, i32 4)
943// %ptr' = relocate(%tok, i32 4, i32 5)
944// %val = load %ptr'
945//
946// into this:
947//
948// %base = ...
949// %ptr = gep %base + 15
950// %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
951// %base' = gc.relocate(%tok, i32 4, i32 4)
952// %ptr' = gep %base' + 15
953// %val = load %ptr'
954bool 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;
980}

982/// SinkCast - Sink the specified cast instruction into its user blocks
983static 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;

  // The first insertion point of a block containing an EH pad is after the
  // pad.  If the pad is the user, we cannot sink the cast past the pad.
  if (User->isEHPad())
    continue;

  // 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())(static_cast <bool> (InsertPt != UserBB->end()) ? void
 (0) : __assert_fail ("InsertPt != UserBB->end()", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1024, __extension__ __PRETTY_FUNCTION__));
    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()) {
  salvageDebugInfo(*CI);
  CI->eraseFromParent();
  MadeChange = true;
}

return MadeChange;
1043}

1045/// If the specified cast instruction is a noop copy (e.g. it's casting from
1046/// one pointer type to another, i32->i8 on PPC), sink it into user blocks to
1047/// reduce the number of virtual registers that must be created and coalesced.
1048///
1049/// Return true if any changes are made.
1050static bool OptimizeNoopCopyExpression(CastInst *CI, const TargetLowering &TLI,
                                     const DataLayout &DL) {
// Sink only "cheap" (or nop) address-space casts.  This is a weaker condition
// than sinking only nop casts, but is helpful on some platforms.
if (auto *ASC = dyn_cast<AddrSpaceCastInst>(CI)) {
  if (!TLI.isCheapAddrSpaceCast(ASC->getSrcAddressSpace(),
                                ASC->getDestAddressSpace()))
    return false;
}

// 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);
1087}

1089/// Try to combine CI into a call to the llvm.uadd.with.overflow intrinsic if
1090/// possible.
1091///
1092/// Return true if any changes were made.
1093static 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;

1111#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!")(static_cast <bool> (*AddI->user_begin() == CI &&
 "expected!") ? void (0) : __assert_fail ("*AddI->user_begin() == CI && \"expected!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1115, __extension__ __PRETTY_FUNCTION__));
1116#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;
1134}

1136/// Sink the given CmpInst into user blocks to reduce the number of virtual
1137/// registers that must be created and coalesced. This is a clear win except on
1138/// targets with multiple condition code registers (PowerPC), where it might
1139/// lose; some adjustment may be wanted there.
1140///
1141/// Return true if any changes are made.
1142static bool SinkCmpExpression(CmpInst *CI, const TargetLowering *TLI) {
BasicBlock *DefBB = CI->getParent();

// Avoid sinking soft-FP comparisons, since this can move them into a loop.
if (TLI && TLI->useSoftFloat() && isa<FCmpInst>(CI))
  return false;

// 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())(static_cast <bool> (InsertPt != UserBB->end()) ? void
 (0) : __assert_fail ("InsertPt != UserBB->end()", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1176, __extension__ __PRETTY_FUNCTION__));
    InsertedCmp =
        CmpInst::Create(CI->getOpcode(), CI->getPredicate(),
                        CI->getOperand(0), CI->getOperand(1), "", &*InsertPt);
    // Propagate the debug info.
    InsertedCmp->setDebugLoc(CI->getDebugLoc());
  }

  // 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;
1197}

1199static bool OptimizeCmpExpression(CmpInst *CI, const TargetLowering *TLI) {
if (SinkCmpExpression(CI, TLI))
  return true;

if (CombineUAddWithOverflow(CI))
  return true;

return false;
1207}

1209/// Duplicate and sink the given 'and' instruction into user blocks where it is
1210/// used in a compare to allow isel to generate better code for targets where
1211/// this operation can be combined.
1212///
1213/// Return true if any changes are made.
1214static bool sinkAndCmp0Expression(Instruction *AndI,
                                const TargetLowering &TLI,
                                SetOfInstrs &InsertedInsts) {
// Double-check that we're not trying to optimize an instruction that was
// already optimized by some other part of this pass.
assert(!InsertedInsts.count(AndI) &&(static_cast <bool> (!InsertedInsts.count(AndI) &&
 "Attempting to optimize already optimized and instruction") ?
 void (0) : __assert_fail ("!InsertedInsts.count(AndI) && \"Attempting to optimize already optimized and instruction\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1220, __extension__ __PRETTY_FUNCTION__))
       "Attempting to optimize already optimized and instruction")(static_cast <bool> (!InsertedInsts.count(AndI) &&
 "Attempting to optimize already optimized and instruction") ?
 void (0) : __assert_fail ("!InsertedInsts.count(AndI) && \"Attempting to optimize already optimized and instruction\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1220, __extension__ __PRETTY_FUNCTION__));
(void) InsertedInsts;

// Nothing to do for single use in same basic block.
if (AndI->hasOneUse() &&
    AndI->getParent() == cast<Instruction>(*AndI->user_begin())->getParent())
  return false;

// Try to avoid cases where sinking/duplicating is likely to increase register
// pressure.
if (!isa<ConstantInt>(AndI->getOperand(0)) &&
    !isa<ConstantInt>(AndI->getOperand(1)) &&
    AndI->getOperand(0)->hasOneUse() && AndI->getOperand(1)->hasOneUse())
  return false;

for (auto *U : AndI->users()) {
  Instruction *User = cast<Instruction>(U);

  // Only sink for and mask feeding icmp with 0.
  if (!isa<ICmpInst>(User))
    return false;

  auto *CmpC = dyn_cast<ConstantInt>(User->getOperand(1));
  if (!CmpC || !CmpC->isZero())
    return false;
}

if (!TLI.isMaskAndCmp0FoldingBeneficial(*AndI))
  return false;

DEBUG(dbgs() << "found 'and' feeding only icmp 0;\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "found 'and' feeding only icmp 0;\n"
; } } while (false);
DEBUG(AndI->getParent()->dump())do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { AndI->getParent()->dump(); } } while
 (false);

// Push the 'and' into the same block as the icmp 0.  There should only be
// one (icmp (and, 0)) in each block, since CSE/GVN should have removed any
// others, so we don't need to keep track of which BBs we insert into.
for (Value::user_iterator UI = AndI->user_begin(), E = AndI->user_end();
     UI != E; ) {
  Use &TheUse = UI.getUse();
  Instruction *User = cast<Instruction>(*UI);

  // Preincrement use iterator so we don't invalidate it.
  ++UI;

  DEBUG(dbgs() << "sinking 'and' use: " << *User << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "sinking 'and' use: " <<
 *User << "\n"; } } while (false);

  // Keep the 'and' in the same place if the use is already in the same block.
  Instruction *InsertPt =
      User->getParent() == AndI->getParent() ? AndI : User;
  Instruction *InsertedAnd =
      BinaryOperator::Create(Instruction::And, AndI->getOperand(0),
                             AndI->getOperand(1), "", InsertPt);
  // Propagate the debug info.
  InsertedAnd->setDebugLoc(AndI->getDebugLoc());

  // Replace a use of the 'and' with a use of the new 'and'.
  TheUse = InsertedAnd;
  ++NumAndUses;
  DEBUG(User->getParent()->dump())do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { User->getParent()->dump(); } } while
 (false);
}

// We removed all uses, nuke the and.
AndI->eraseFromParent();
return true;
1284}

1286/// Check if the candidates could be combined with a shift instruction, which
1287/// includes:
1288/// 1. Truncate instruction
1289/// 2. And instruction and the imm is a mask of the low bits:
1290/// imm & (imm+1) == 0
1291static 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;
1303}

1305/// Sink both shift and truncate instruction to the use of truncate's BB.
1306static bool
1307SinkShiftAndTruncate(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())(static_cast <bool> (InsertPt != TruncUserBB->end())
 ? void (0) : __assert_fail ("InsertPt != TruncUserBB->end()"
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1352, __extension__ __PRETTY_FUNCTION__));
    // 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())(static_cast <bool> (TruncInsertPt != TruncUserBB->end
()) ? void (0) : __assert_fail ("TruncInsertPt != TruncUserBB->end()"
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1364, __extension__ __PRETTY_FUNCTION__));

    InsertedTrunc = CastInst::Create(TruncI->getOpcode(), InsertedShift,
                                     TruncI->getType(), "", &*TruncInsertPt);

    MadeChange = true;

    TruncTheUse = InsertedTrunc;
  }
}
return MadeChange;
1375}

1377/// Sink the shift *right* instruction into user blocks if the uses could
1378/// potentially be combined with this shift instruction and generate BitExtract
1379/// instruction. It will only be applied if the architecture supports BitExtract
1380/// instruction. Here is an example:
1381/// BB1:
1382///   %x.extract.shift = lshr i64 %arg1, 32
1383/// BB2:
1384///   %x.extract.trunc = trunc i64 %x.extract.shift to i16
1385/// ==>
1386///
1387/// BB2:
1388///   %x.extract.shift.1 = lshr i64 %arg1, 32
1389///   %x.extract.trunc = trunc i64 %x.extract.shift.1 to i16
1390///
1391/// CodeGen will recoginze the pattern in BB2 and generate BitExtract
1392/// instruction.
1393/// Return true if any changes are made.
1394static 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())(static_cast <bool> (InsertPt != UserBB->end()) ? void
 (0) : __assert_fail ("InsertPt != UserBB->end()", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1451, __extension__ __PRETTY_FUNCTION__));

    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;
1472}

1474/// If counting leading or trailing zeros is an expensive operation and a zero
1475/// input is defined, add a check for zero to avoid calling the intrinsic.
1476///
1477/// We want to transform:
1478///     %z = call i64 @llvm.cttz.i64(i64 %A, i1 false)
1479///
1480/// into:
1481///   entry:
1482///     %cmpz = icmp eq i64 %A, 0
1483///     br i1 %cmpz, label %cond.end, label %cond.false
1484///   cond.false:
1485///     %z = call i64 @llvm.cttz.i64(i64 %A, i1 true)
1486///     br label %cond.end
1487///   cond.end:
1488///     %ctz = phi i64 [ 64, %entry ], [ %z, %cond.false ]
1489///
1490/// If the transform is performed, return true and set ModifiedDT to true.
1491static 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->getLargestLegalIntTypeSizeInBits())
  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;
1551}

1553bool 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->getIndexSizeInBits(
                     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->canIncreaseAlignment() &&
        GV->getPointerAlignment(*DL) < PrefAlign &&
        DL->getTypeAllocSize(GV->getValueType()) >=
            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 DestAlign = getKnownAlignment(MI->getDest(), *DL);
    if (DestAlign > MI->getDestAlignment())
      MI->setDestAlignment(DestAlign);
    if (MemTransferInst *MTI = dyn_cast<MemTransferInst>(MI)) {
      unsigned SrcAlign = getKnownAlignment(MTI->getSource(), *DL);
      if (SrcAlign > MTI->getSourceAlignment())
        MTI->setSourceAlignment(SrcAlign);
    }
  }
}

// If we have a cold call site, try to sink addressing computation into the
// cold block.  This interacts with our handling for loads and stores to
// ensure that we can fold all uses of a potential addressing computation
// into their uses.  TODO: generalize this to work over profiling data
if (!OptSize && CI->hasFnAttr(Attribute::Cold))
  for (auto &Arg : CI->arg_operands()) {
    if (!Arg->getType()->isPointerTy())
      continue;
    unsigned AS = Arg->getType()->getPointerAddressSpace();
    return optimizeMemoryInst(CI, Arg, Arg->getType(), AS);
  }

IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
if (II) {
  switch (II->getIntrinsicID()) {
  default: break;
  case Intrinsic::objectsize: {
    // Lower all uses of llvm.objectsize.*
    ConstantInt *RetVal =
        lowerObjectSizeCall(II, *DL, TLInfo, /*MustSucceed=*/true);
    // Substituting this can cause recursive simplifications, which can
    // invalidate our iterator.  Use a WeakTrackingVH to hold onto it in case
    // this
    // happens.
    Value *CurValue = &*CurInstIterator;
    WeakTrackingVH IterHandle(CurValue);

    replaceAndRecursivelySimplify(CI, RetVal, TLInfo, nullptr);

    // If the iterator instruction was recursively deleted, start over at the
    // start of the block.
    if (IterHandle != CurValue) {
      CurInstIterator = BB->begin();
      SunkAddrs.clear();
    }
    return true;
  }
  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) {
    SmallVector<Value*, 2> PtrOps;
    Type *AccessTy;
    if (TLI->getAddrModeArguments(II, PtrOps, AccessTy))
      while (!PtrOps.empty()) {
        Value *PtrVal = PtrOps.pop_back_val();
        unsigned AS = PtrVal->getType()->getPointerAddressSpace();
        if (optimizeMemoryInst(II, PtrVal, AccessTy, AS))
          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;
1709}

1711/// Look for opportunities to duplicate return instructions to the predecessor
1712/// to enable tail call optimizations. The case it is currently looking for is:
1713/// @code
1714/// bb0:
1715///   %tmp0 = tail call i32 @f0()
1716///   br label %return
1717/// bb1:
1718///   %tmp1 = tail call i32 @f1()
1719///   br label %return
1720/// bb2:
1721///   %tmp2 = tail call i32 @f2()
1722///   br label %return
1723/// return:
1724///   %retval = phi i32 [ %tmp0, %bb0 ], [ %tmp1, %bb1 ], [ %tmp2, %bb2 ]
1725///   ret i32 %retval
1726/// @endcode
1727///
1728/// =>
1729///
1730/// @code
1731/// bb0:
1732///   %tmp0 = tail call i32 @f0()
1733///   ret i32 %tmp0
1734/// bb1:
1735///   %tmp1 = tail call i32 @f1()
1736///   ret i32 %tmp1
1737/// bb2:
1738///   %tmp2 = tail call i32 @f2()
1739///   ret i32 %tmp2
1740/// @endcode
1741bool CodeGenPrepare::dupRetToEnableTailCallOpts(BasicBlock *BB) {
if (!TLI)
  return false;

ReturnInst *RetI = dyn_cast<ReturnInst>(BB->getTerminator());
if (!RetI)
  return false;

PHINode *PN = nullptr;
BitCastInst *BCI = nullptr;
Value *V = RetI->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;

// 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 != RetI)
    return false;
} else {
  BasicBlock::iterator BI = BB->begin();
  while (isa<DbgInfoIntrinsic>(BI)) ++BI;
  if (&*BI != RetI)
    return false;
}

/// Only dup the ReturnInst if the CallInst is likely to be emitted as a tail
/// call.
const Function *F = BB->getParent();
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) &&
        attributesPermitTailCall(F, CI, RetI, *TLI))
      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) &&
        attributesPermitTailCall(F, CI, RetI, *TLI))
      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.
  AttributeList CalleeAttrs = CS.getAttributes();
  if (AttrBuilder(CalleeAttrs, AttributeList::ReturnIndex)
          .removeAttribute(Attribute::NoAlias) !=
      AttrBuilder(CalleeAttrs, AttributeList::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(RetI, 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;
1847}

1849//===----------------------------------------------------------------------===//
1850// Memory Optimization
1851//===----------------------------------------------------------------------===//

1853namespace {

1855/// This is an extended version of TargetLowering::AddrMode
1856/// which holds actual Value*'s for register values.
1857struct ExtAddrMode : public TargetLowering::AddrMode {
Value *BaseReg = nullptr;
Value *ScaledReg = nullptr;
Value *OriginalValue = nullptr;

enum FieldName {
  NoField        = 0x00,
  BaseRegField   = 0x01,
  BaseGVField    = 0x02,
  BaseOffsField  = 0x04,
  ScaledRegField = 0x08,
  ScaleField     = 0x10,
  MultipleFields = 0xff
};

ExtAddrMode() = default;

void print(raw_ostream &OS) const;
void dump() const;

FieldName compare(const ExtAddrMode &other) {
  // First check that the types are the same on each field, as differing types
  // is something we can't cope with later on.
  if (BaseReg && other.BaseReg &&
      BaseReg->getType() != other.BaseReg->getType())
    return MultipleFields;
  if (BaseGV && other.BaseGV &&
      BaseGV->getType() != other.BaseGV->getType())
    return MultipleFields;
  if (ScaledReg && other.ScaledReg &&
      ScaledReg->getType() != other.ScaledReg->getType())
    return MultipleFields;

  // Check each field to see if it differs.
  unsigned Result = NoField;
  if (BaseReg != other.BaseReg)
    Result |= BaseRegField;
  if (BaseGV != other.BaseGV)
    Result |= BaseGVField;
  if (BaseOffs != other.BaseOffs)
    Result |= BaseOffsField;
  if (ScaledReg != other.ScaledReg)
    Result |= ScaledRegField;
  // Don't count 0 as being a different scale, because that actually means
  // unscaled (which will already be counted by having no ScaledReg).
  if (Scale && other.Scale && Scale != other.Scale)
    Result |= ScaleField;

  if (countPopulation(Result) > 1)
    return MultipleFields;
  else
    return static_cast<FieldName>(Result);
}

// An AddrMode is trivial if it involves no calculation i.e. it is just a base
// with no offset.
bool isTrivial() {
  // An AddrMode is (BaseGV + BaseReg + BaseOffs + ScaleReg * Scale) so it is
  // trivial if at most one of these terms is nonzero, except that BaseGV and
  // BaseReg both being zero actually means a null pointer value, which we
  // consider to be 'non-zero' here.
  return !BaseOffs && !Scale && !(BaseGV && BaseReg);
}

Value *GetFieldAsValue(FieldName Field, Type *IntPtrTy) {
  switch (Field) {
  default:
    return nullptr;
  case BaseRegField:
    return BaseReg;
  case BaseGVField:
    return BaseGV;
  case ScaledRegField:
    return ScaledReg;
  case BaseOffsField:
    return ConstantInt::get(IntPtrTy, BaseOffs);
  }
}

void SetCombinedField(FieldName Field, Value *V,
                      const SmallVectorImpl<ExtAddrMode> &AddrModes) {
  switch (Field) {
  default:
    llvm_unreachable("Unhandled fields are expected to be rejected earlier")::llvm::llvm_unreachable_internal("Unhandled fields are expected to be rejected earlier"
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1940);
    break;
  case ExtAddrMode::BaseRegField:
    BaseReg = V;
    break;
  case ExtAddrMode::BaseGVField:
    // A combined BaseGV is an Instruction, not a GlobalValue, so it goes
    // in the BaseReg field.
    assert(BaseReg == nullptr)(static_cast <bool> (BaseReg == nullptr) ? void (0) : __assert_fail
 ("BaseReg == nullptr", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1948, __extension__ __PRETTY_FUNCTION__));
    BaseReg = V;
    BaseGV = nullptr;
    break;
  case ExtAddrMode::ScaledRegField:
    ScaledReg = V;
    // If we have a mix of scaled and unscaled addrmodes then we want scale
    // to be the scale and not zero.
    if (!Scale)
      for (const ExtAddrMode &AM : AddrModes)
        if (AM.Scale) {
          Scale = AM.Scale;
          break;
        }
    break;
  case ExtAddrMode::BaseOffsField:
    // The offset is no longer a constant, so it goes in ScaledReg with a
    // scale of 1.
    assert(ScaledReg == nullptr)(static_cast <bool> (ScaledReg == nullptr) ? void (0) :
 __assert_fail ("ScaledReg == nullptr", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 1966, __extension__ __PRETTY_FUNCTION__));
    ScaledReg = V;
    Scale = 1;
    BaseOffs = 0;
    break;
  }
}
1973};

1975} // end anonymous namespace

1977#ifndef NDEBUG
1978static inline raw_ostream &operator<<(raw_ostream &OS, const ExtAddrMode &AM) {
AM.print(OS);
return OS;
1981}
1982#endif

1984#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
1985void 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 << ']';
2014}

2016LLVM_DUMP_METHOD__attribute__((noinline)) __attribute__((__used__)) void ExtAddrMode::dump() const {
print(dbgs());
dbgs() << '\n';
2019}
2020#endif

2022namespace {

2024/// \brief This class provides transaction based operation on the IR.
2025/// Every change made through this class is recorded in the internal state and
2026/// can be undone (rollback) until commit is called.
2027class 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() = default;

  /// \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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: move: " << *
Inst << "\nbefore: " << *Before << "\n"; } }
 while (false);
    Inst->moveBefore(Before);
  }

  /// \brief Move the instruction back to its original position.
  void undo() override {
    DEBUG(dbgs() << "Undo: moveBefore: " << *Inst << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: moveBefore: " <<
 *Inst << "\n"; } } while (false);
    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"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: setOperand: " <<
 Idx << "\n" << "for:" << *Inst << "\n"
 << "with:" << *NewVal << "\n"; } } while (
false)
                 << "for:" << *Inst << "\n"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: setOperand: " <<
 Idx << "\n" << "for:" << *Inst << "\n"
 << "with:" << *NewVal << "\n"; } } while (
false)
                 << "with:" << *NewVal << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: setOperand: " <<
 Idx << "\n" << "for:" << *Inst << "\n"
 << "with:" << *NewVal << "\n"; } } while (
false);
    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"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: setOperand:" <<
 Idx << "\n" << "for: " << *Inst << "\n"
 << "with: " << *Origin << "\n"; } } while (
false)
                 << "for: " << *Inst << "\n"do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: setOperand:" <<
 Idx << "\n" << "for: " << *Inst << "\n"
 << "with: " << *Origin << "\n"; } } while (
false)
                 << "with: " << *Origin << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: setOperand:" <<
 Idx << "\n" << "for: " << *Inst << "\n"
 << "with: " << *Origin << "\n"; } } while (
false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: OperandsHider: " <<
 *Inst << "\n"; } } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: OperandsHider: "
 << *Inst << "\n"; } } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: TruncBuilder: " <<
 *Val << "\n"; } } while (false);
  }

  /// \brief Get the built value.
  Value *getBuiltValue() { return Val; }

  /// \brief Remove the built instruction.
  void undo() override {
    DEBUG(dbgs() << "Undo: TruncBuilder: " << *Val << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: TruncBuilder: " <<
 *Val << "\n"; } } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: SExtBuilder: " <<
 *Val << "\n"; } } while (false);
  }

  /// \brief Get the built value.
  Value *getBuiltValue() { return Val; }

  /// \brief Remove the built instruction.
  void undo() override {
    DEBUG(dbgs() << "Undo: SExtBuilder: " << *Val << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: SExtBuilder: " <<
 *Val << "\n"; } } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: ZExtBuilder: " <<
 *Val << "\n"; } } while (false);
  }

  /// \brief Get the built value.
  Value *getBuiltValue() { return Val; }

  /// \brief Remove the built instruction.
  void undo() override {
    DEBUG(dbgs() << "Undo: ZExtBuilder: " << *Val << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: ZExtBuilder: " <<
 *Val << "\n"; } } while (false);
    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 " << *NewTydo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: MutateType: " <<
 *Inst << " with " << *NewTy << "\n"; } } while
 (false)
                 << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: MutateType: " <<
 *Inst << " with " << *NewTy << "\n"; } } while
 (false);
    Inst->mutateType(NewTy);
  }

  /// \brief Mutate the instruction back to its original type.
  void undo() override {
    DEBUG(dbgs() << "Undo: MutateType: " << *Inst << " with " << *OrigTydo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: MutateType: " <<
 *Inst << " with " << *OrigTy << "\n"; } } while
 (false)
                 << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: MutateType: " <<
 *Inst << " with " << *OrigTy << "\n"; } } while
 (false);
    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;

  using use_iterator = SmallVectorImpl<InstructionAndIdx>::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 " << *Newdo { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: UsersReplacer: " <<
 *Inst << " with " << *New << "\n"; } } while
 (false)
                 << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: UsersReplacer: " <<
 *Inst << " with " << *New << "\n"; } } while
 (false);
    // 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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: UsersReplacer: "
 << *Inst << "\n"; } } while (false);
    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 = nullptr;

  /// Keep track of instructions removed.
  SetOfInstrs &RemovedInsts;

public:
  /// \brief Remove all reference of \p Inst and optinally replace all its
  /// uses with New.
  /// \p RemovedInsts Keep track of the instructions removed by this Action.
  /// \pre If !Inst->use_empty(), then New != nullptr
  InstructionRemover(Instruction *Inst, SetOfInstrs &RemovedInsts,
                     Value *New = nullptr)
      : TypePromotionAction(Inst), Inserter(Inst), Hider(Inst),
        RemovedInsts(RemovedInsts) {
    if (New)
      Replacer = new UsesReplacer(Inst, New);
    DEBUG(dbgs() << "Do: InstructionRemover: " << *Inst << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Do: InstructionRemover: "
 << *Inst << "\n"; } } while (false);
    RemovedInsts.insert(Inst);
    /// The instructions removed here will be freed after completing
    /// optimizeBlock() for all blocks as we need to keep track of the
    /// removed instructions during promotion.
    Inst->removeFromParent();
  }

  ~InstructionRemover() override { delete Replacer; }

  /// \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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Undo: InstructionRemover: "
 << *Inst << "\n"; } } while (false);
    Inserter.insert(Inst);
    if (Replacer)
      Replacer->undo();
    Hider.undo();
    RemovedInsts.erase(Inst);
  }
};

2369public:
/// 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.
using ConstRestorationPt = const TypePromotionAction *;

TypePromotionTransaction(SetOfInstrs &RemovedInsts)
    : RemovedInsts(RemovedInsts) {}

/// 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);
/// @}

2414private:
/// The ordered list of actions made so far.
SmallVector<std::unique_ptr<TypePromotionAction>, 16> Actions;

using CommitPt = SmallVectorImpl<std::unique_ptr<TypePromotionAction>>::iterator;

SetOfInstrs &RemovedInsts;
2421};

2423} // end anonymous namespace

2425void TypePromotionTransaction::setOperand(Instruction *Inst, unsigned Idx,
                                        Value *NewVal) {
Actions.push_back(llvm::make_unique<TypePromotionTransaction::OperandSetter>(
    Inst, Idx, NewVal));
2429}

2431void TypePromotionTransaction::eraseInstruction(Instruction *Inst,
                                              Value *NewVal) {
Actions.push_back(
    llvm::make_unique<TypePromotionTransaction::InstructionRemover>(
        Inst, RemovedInsts, NewVal));
2436}

2438void TypePromotionTransaction::replaceAllUsesWith(Instruction *Inst,
                                                Value *New) {
Actions.push_back(
    llvm::make_unique<TypePromotionTransaction::UsesReplacer>(Inst, New));
2442}

2444void TypePromotionTransaction::mutateType(Instruction *Inst, Type *NewTy) {
Actions.push_back(
    llvm::make_unique<TypePromotionTransaction::TypeMutator>(Inst, NewTy));
2447}

2449Value *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;
2455}

2457Value *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;
2463}

2465Value *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;
2471}

2473void TypePromotionTransaction::moveBefore(Instruction *Inst,
                                        Instruction *Before) {
Actions.push_back(
    llvm::make_unique<TypePromotionTransaction::InstructionMoveBefore>(
        Inst, Before));
2478}

2480TypePromotionTransaction::ConstRestorationPt
2481TypePromotionTransaction::getRestorationPoint() const {
return !Actions.empty() ? Actions.back().get() : nullptr;
2483}

2485void TypePromotionTransaction::commit() {
for (CommitPt It = Actions.begin(), EndIt = Actions.end(); It != EndIt;
     ++It)
  (*It)->commit();
Actions.clear();
2490}

2492void TypePromotionTransaction::rollback(
  TypePromotionTransaction::ConstRestorationPt Point) {
while (!Actions.empty() && Point != Actions.back().get()) {
  std::unique_ptr<TypePromotionAction> Curr = Actions.pop_back_val();
  Curr->undo();
}
2498}

2500namespace {

2502/// \brief A helper class for matching addressing modes.
2503///
2504/// This encapsulates the logic for matching the target-legal addressing modes.
2505class AddressingModeMatcher {
SmallVectorImpl<Instruction*> &AddrModeInsts;
const TargetLowering &TLI;
const TargetRegisterInfo &TRI;
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 TargetLowering &TLI,
                      const TargetRegisterInfo &TRI,
                      Type *AT, unsigned AS,
                      Instruction *MI, ExtAddrMode &AM,
                      const SetOfInstrs &InsertedInsts,
                      InstrToOrigTy &PromotedInsts,
                      TypePromotionTransaction &TPT)
    : AddrModeInsts(AMI), TLI(TLI), TRI(TRI),
      DL(MI->getModule()->getDataLayout()), AccessTy(AT), AddrSpace(AS),
      MemoryInst(MI), AddrMode(AM), InsertedInsts(InsertedInsts),
      PromotedInsts(PromotedInsts), TPT(TPT) {
  IgnoreProfitability = false;
}

2549public:
/// 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 TargetLowering &TLI,
                         const TargetRegisterInfo &TRI,
                         const SetOfInstrs &InsertedInsts,
                         InstrToOrigTy &PromotedInsts,
                         TypePromotionTransaction &TPT) {
  ExtAddrMode Result;

  bool Success = AddressingModeMatcher(AddrModeInsts, TLI, TRI,
                                       AccessTy, AS,
                                       MemoryInst, Result, InsertedInsts,
                                       PromotedInsts, TPT).matchAddr(V, 0);
  (void)Success; assert(Success && "Couldn't select *anything*?")(static_cast <bool> (Success && "Couldn't select *anything*?"
) ? void (0) : __assert_fail ("Success && \"Couldn't select *anything*?\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 2571, __extension__ __PRETTY_FUNCTION__));
  return Result;
}

2575private:
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;
2586};

2588/// \brief Keep track of simplification of Phi nodes.
2589/// Accept the set of all phi nodes and erase phi node from this set
2590/// if it is simplified.
2591class SimplificationTracker {
DenseMap<Value *, Value *> Storage;
const SimplifyQuery &SQ;
SmallPtrSetImpl<PHINode *> &AllPhiNodes;
SmallPtrSetImpl<SelectInst *> &AllSelectNodes;

2597public:
SimplificationTracker(const SimplifyQuery &sq,
                      SmallPtrSetImpl<PHINode *> &APN,
                      SmallPtrSetImpl<SelectInst *> &ASN)
    : SQ(sq), AllPhiNodes(APN), AllSelectNodes(ASN) {}

Value *Get(Value *V) {
  do {
    auto SV = Storage.find(V);
    if (SV == Storage.end())
      return V;
    V = SV->second;
  } while (true);
}

Value *Simplify(Value *Val) {
  SmallVector<Value *, 32> WorkList;
  SmallPtrSet<Value *, 32> Visited;
  WorkList.push_back(Val);
  while (!WorkList.empty()) {
    auto P = WorkList.pop_back_val();
    if (!Visited.insert(P).second)
      continue;
    if (auto *PI = dyn_cast<Instruction>(P))
      if (Value *V = SimplifyInstruction(cast<Instruction>(PI), SQ)) {
        for (auto *U : PI->users())
          WorkList.push_back(cast<Value>(U));
        Put(PI, V);
        PI->replaceAllUsesWith(V);
        if (auto *PHI = dyn_cast<PHINode>(PI))
          AllPhiNodes.erase(PHI);
        if (auto *Select = dyn_cast<SelectInst>(PI))
          AllSelectNodes.erase(Select);
        PI->eraseFromParent();
      }
  }
  return Get(Val);
}

void Put(Value *From, Value *To) {
  Storage.insert({ From, To });
}
2639};

2641/// \brief A helper class for combining addressing modes.
2642class AddressingModeCombiner {
typedef std::pair<Value *, BasicBlock *> ValueInBB;
typedef DenseMap<ValueInBB, Value *> FoldAddrToValueMapping;
typedef std::pair<PHINode *, PHINode *> PHIPair;

2647private:
/// The addressing modes we've collected.
SmallVector<ExtAddrMode, 16> AddrModes;

/// The field in which the AddrModes differ, when we have more than one.
ExtAddrMode::FieldName DifferentField = ExtAddrMode::NoField;

/// Are the AddrModes that we have all just equal to their original values?
bool AllAddrModesTrivial = true;

/// Common Type for all different fields in addressing modes.
Type *CommonType;

/// SimplifyQuery for simplifyInstruction utility.
const SimplifyQuery &SQ;

/// Original Address.
ValueInBB Original;

2666public:
AddressingModeCombiner(const SimplifyQuery &_SQ, ValueInBB OriginalValue)
    : CommonType(nullptr), SQ(_SQ), Original(OriginalValue) {}

/// \brief Get the combined AddrMode
const ExtAddrMode &getAddrMode() const {
  return AddrModes[0];
}

/// \brief Add a new AddrMode if it's compatible with the AddrModes we already
/// have.
/// \return True iff we succeeded in doing so.
bool addNewAddrMode(ExtAddrMode &NewAddrMode) {
  // Take note of if we have any non-trivial AddrModes, as we need to detect
  // when all AddrModes are trivial as then we would introduce a phi or select
  // which just duplicates what's already there.
  AllAddrModesTrivial = AllAddrModesTrivial && NewAddrMode.isTrivial();

  // If this is the first addrmode then everything is fine.
  if (AddrModes.empty()) {
    AddrModes.emplace_back(NewAddrMode);
    return true;
  }

  // Figure out how different this is from the other address modes, which we
  // can do just by comparing against the first one given that we only care
  // about the cumulative difference.
  ExtAddrMode::FieldName ThisDifferentField =
    AddrModes[0].compare(NewAddrMode);
  if (DifferentField == ExtAddrMode::NoField)
    DifferentField = ThisDifferentField;
  else if (DifferentField != ThisDifferentField)
    DifferentField = ExtAddrMode::MultipleFields;

  // If NewAddrMode differs in more than one dimension we cannot handle it.
  bool CanHandle = DifferentField != ExtAddrMode::MultipleFields;

  // If Scale Field is different then we reject.
  CanHandle = CanHandle && DifferentField != ExtAddrMode::ScaleField;

  // We also must reject the case when base offset is different and
  // scale reg is not null, we cannot handle this case due to merge of
  // different offsets will be used as ScaleReg.
  CanHandle = CanHandle && (DifferentField != ExtAddrMode::BaseOffsField ||
                            !NewAddrMode.ScaledReg);

  // We also must reject the case when GV is different and BaseReg installed
  // due to we want to use base reg as a merge of GV values.
  CanHandle = CanHandle && (DifferentField != ExtAddrMode::BaseGVField ||
                            !NewAddrMode.HasBaseReg);

  // Even if NewAddMode is the same we still need to collect it due to
  // original value is different. And later we will need all original values
  // as anchors during finding the common Phi node.
  if (CanHandle)
    AddrModes.emplace_back(NewAddrMode);
  else
    AddrModes.clear();

  return CanHandle;
}

/// \brief Combine the addressing modes we've collected into a single
/// addressing mode.
/// \return True iff we successfully combined them or we only had one so
/// didn't need to combine them anyway.
bool combineAddrModes() {
  // If we have no AddrModes then they can't be combined.
  if (AddrModes.size() == 0)
27
←
Assuming the condition is false→
28
←
Taking false branch→
    return false;

  // A single AddrMode can trivially be combined.
  if (AddrModes.size() == 1 || DifferentField == ExtAddrMode::NoField)
29
←
Assuming the condition is false→
30
←
Assuming the condition is false→
31
←
Taking false branch→
    return true;

  // If the AddrModes we collected are all just equal to the value they are
  // derived from then combining them wouldn't do anything useful.
  if (AllAddrModesTrivial)
32
←
Assuming the condition is false→
33
←
Taking false branch→
    return false;

  if (!addrModeCombiningAllowed())
34
←
Assuming the condition is false→
35
←
Taking false branch→
    return false;

  // Build a map between <original value, basic block where we saw it> to
  // value of base register.
  // Bail out if there is no common type.
  FoldAddrToValueMapping Map;
  if (!initializeMap(Map))
36
←
Taking false branch→
    return false;

  Value *CommonValue = findCommon(Map);
37
←
Calling 'AddressingModeCombiner::findCommon'→
  if (CommonValue)
    AddrModes[0].SetCombinedField(DifferentField, CommonValue, AddrModes);
  return CommonValue != nullptr;
}

2762private:
/// \brief Initialize Map with anchor values. For address seen in some BB
/// we set the value of different field saw in this address.
/// If address is not an instruction than basic block is set to null.
/// At the same time we find a common type for different field we will
/// use to create new Phi/Select nodes. Keep it in CommonType field.
/// Return false if there is no common type found.
bool initializeMap(FoldAddrToValueMapping &Map) {
  // Keep track of keys where the value is null. We will need to replace it
  // with constant null when we know the common type.
  SmallVector<ValueInBB, 2> NullValue;
  Type *IntPtrTy = SQ.DL.getIntPtrType(AddrModes[0].OriginalValue->getType());
  for (auto &AM : AddrModes) {
    BasicBlock *BB = nullptr;
    if (Instruction *I = dyn_cast<Instruction>(AM.OriginalValue))
      BB = I->getParent();

    Value *DV = AM.GetFieldAsValue(DifferentField, IntPtrTy);
    if (DV) {
      auto *Type = DV->getType();
      if (CommonType && CommonType != Type)
        return false;
      CommonType = Type;
      Map[{ AM.OriginalValue, BB }] = DV;
    } else {
      NullValue.push_back({ AM.OriginalValue, BB });
    }
  }
  assert(CommonType && "At least one non-null value must be!")(static_cast <bool> (CommonType && "At least one non-null value must be!"
) ? void (0) : __assert_fail ("CommonType && \"At least one non-null value must be!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 2790, __extension__ __PRETTY_FUNCTION__));
  for (auto VIBB : NullValue)
    Map[VIBB] = Constant::getNullValue(CommonType);
  return true;
}

/// \brief We have mapping between value A and basic block where value A
/// seen to other value B where B was a field in addressing mode represented
/// by A. Also we have an original value C representin an address in some
/// basic block. Traversing from C through phi and selects we ended up with
/// A's in a map. This utility function tries to find a value V which is a
/// field in addressing mode C and traversing through phi nodes and selects
/// we will end up in corresponded values B in a map.
/// The utility will create a new Phi/Selects if needed.
// The simple example looks as follows:
// BB1:
//   p1 = b1 + 40
//   br cond BB2, BB3
// BB2:
//   p2 = b2 + 40
//   br BB3
// BB3:
//   p = phi [p1, BB1], [p2, BB2]
//   v = load p
// Map is
//   <p1, BB1> -> b1
//   <p2, BB2> -> b2
// Request is
//   <p, BB3> -> ?
// The function tries to find or build phi [b1, BB1], [b2, BB2] in BB3
Value *findCommon(FoldAddrToValueMapping &Map) {
  // Tracks newly created Phi nodes.
  SmallPtrSet<PHINode *, 32> NewPhiNodes;
  // Tracks newly created Select nodes.
  SmallPtrSet<SelectInst *, 32> NewSelectNodes;
  // Tracks the simplification of newly created phi nodes. The reason we use
  // this mapping is because we will add new created Phi nodes in AddrToBase.
  // Simplification of Phi nodes is recursive, so some Phi node may
  // be simplified after we added it to AddrToBase.
  // Using this mapping we can find the current value in AddrToBase.
  SimplificationTracker ST(SQ, NewPhiNodes, NewSelectNodes);

  // First step, DFS to create PHI nodes for all intermediate blocks.
  // Also fill traverse order for the second step.
  SmallVector<ValueInBB, 32> TraverseOrder;
  InsertPlaceholders(Map, TraverseOrder, NewPhiNodes, NewSelectNodes);
38
←
Calling 'AddressingModeCombiner::InsertPlaceholders'→

  // Second Step, fill new nodes by merged values and simplify if possible.
  FillPlaceholders(Map, TraverseOrder, ST);

  if (!AddrSinkNewSelects && NewSelectNodes.size() > 0) {
    DestroyNodes(NewPhiNodes);
    DestroyNodes(NewSelectNodes);
    return nullptr;
  }

  // Now we'd like to match New Phi nodes to existed ones.
  unsigned PhiNotMatchedCount = 0;
  if (!MatchPhiSet(NewPhiNodes, ST, AddrSinkNewPhis, PhiNotMatchedCount)) {
    DestroyNodes(NewPhiNodes);
    DestroyNodes(NewSelectNodes);
    return nullptr;
  }

  auto *Result = ST.Get(Map.find(Original)->second);
  if (Result) {
    NumMemoryInstsPhiCreated += NewPhiNodes.size() + PhiNotMatchedCount;
    NumMemoryInstsSelectCreated += NewSelectNodes.size();
  }
  return Result;
}

/// \brief Destroy nodes from a set.
template <typename T> void DestroyNodes(SmallPtrSetImpl<T *> &Instructions) {
  // For safe erasing, replace the Phi with dummy value first.
  auto Dummy = UndefValue::get(CommonType);
  for (auto I : Instructions) {
    I->replaceAllUsesWith(Dummy);
    I->eraseFromParent();
  }
}

/// \brief Try to match PHI node to Candidate.
/// Matcher tracks the matched Phi nodes.
bool MatchPhiNode(PHINode *PHI, PHINode *Candidate,
                  DenseSet<PHIPair> &Matcher,
                  SmallPtrSetImpl<PHINode *> &PhiNodesToMatch) {
  SmallVector<PHIPair, 8> WorkList;
  Matcher.insert({ PHI, Candidate });
  WorkList.push_back({ PHI, Candidate });
  SmallSet<PHIPair, 8> Visited;
  while (!WorkList.empty()) {
    auto Item = WorkList.pop_back_val();
    if (!Visited.insert(Item).second)
      continue;
    // We iterate over all incoming values to Phi to compare them.
    // If values are different and both of them Phi and the first one is a
    // Phi we added (subject to match) and both of them is in the same basic
    // block then we can match our pair if values match. So we state that
    // these values match and add it to work list to verify that.
    for (auto B : Item.first->blocks()) {
      Value *FirstValue = Item.first->getIncomingValueForBlock(B);
      Value *SecondValue = Item.second->getIncomingValueForBlock(B);
      if (FirstValue == SecondValue)
        continue;

      PHINode *FirstPhi = dyn_cast<PHINode>(FirstValue);
      PHINode *SecondPhi = dyn_cast<PHINode>(SecondValue);

      // One of them is not Phi or
      // The first one is not Phi node from the set we'd like to match or
      // Phi nodes from different basic blocks then
      // we will not be able to match.
      if (!FirstPhi || !SecondPhi || !PhiNodesToMatch.count(FirstPhi) ||
          FirstPhi->getParent() != SecondPhi->getParent())
        return false;

      // If we already matched them then continue.
      if (Matcher.count({ FirstPhi, SecondPhi }))
        continue;
      // So the values are different and does not match. So we need them to
      // match.
      Matcher.insert({ FirstPhi, SecondPhi });
      // But me must check it.
      WorkList.push_back({ FirstPhi, SecondPhi });
    }
  }
  return true;
}

/// \brief For the given set of PHI nodes try to find their equivalents.
/// Returns false if this matching fails and creation of new Phi is disabled.
bool MatchPhiSet(SmallPtrSetImpl<PHINode *> &PhiNodesToMatch,
                 SimplificationTracker &ST, bool AllowNewPhiNodes,
                 unsigned &PhiNotMatchedCount) {
  DenseSet<PHIPair> Matched;
  SmallPtrSet<PHINode *, 8> WillNotMatch;
  while (PhiNodesToMatch.size()) {
    PHINode *PHI = *PhiNodesToMatch.begin();

    // Add us, if no Phi nodes in the basic block we do not match.
    WillNotMatch.clear();
    WillNotMatch.insert(PHI);

    // Traverse all Phis until we found equivalent or fail to do that.
    bool IsMatched = false;
    for (auto &P : PHI->getParent()->phis()) {
      if (&P == PHI)
        continue;
      if ((IsMatched = MatchPhiNode(PHI, &P, Matched, PhiNodesToMatch)))
        break;
      // If it does not match, collect all Phi nodes from matcher.
      // if we end up with no match, them all these Phi nodes will not match
      // later.
      for (auto M : Matched)
        WillNotMatch.insert(M.first);
      Matched.clear();
    }
    if (IsMatched) {
      // Replace all matched values and erase them.
      for (auto MV : Matched) {
        MV.first->replaceAllUsesWith(MV.second);
        PhiNodesToMatch.erase(MV.first);
        ST.Put(MV.first, MV.second);
        MV.first->eraseFromParent();
      }
      Matched.clear();
      continue;
    }
    // If we are not allowed to create new nodes then bail out.
    if (!AllowNewPhiNodes)
      return false;
    // Just remove all seen values in matcher. They will not match anything.
    PhiNotMatchedCount += WillNotMatch.size();
    for (auto *P : WillNotMatch)
      PhiNodesToMatch.erase(P);
  }
  return true;
}
/// \brief Fill the placeholder with values from predecessors and simplify it.
void FillPlaceholders(FoldAddrToValueMapping &Map,
                      SmallVectorImpl<ValueInBB> &TraverseOrder,
                      SimplificationTracker &ST) {
  while (!TraverseOrder.empty()) {
    auto Current = TraverseOrder.pop_back_val();
    assert(Map.find(Current) != Map.end() && "No node to fill!!!")(static_cast <bool> (Map.find(Current) != Map.end() &&
 "No node to fill!!!") ? void (0) : __assert_fail ("Map.find(Current) != Map.end() && \"No node to fill!!!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 2975, __extension__ __PRETTY_FUNCTION__));
    Value *CurrentValue = Current.first;
    BasicBlock *CurrentBlock = Current.second;
    Value *V = Map[Current];

    if (SelectInst *Select = dyn_cast<SelectInst>(V)) {
      // CurrentValue also must be Select.
      auto *CurrentSelect = cast<SelectInst>(CurrentValue);
      auto *TrueValue = CurrentSelect->getTrueValue();
      ValueInBB TrueItem = { TrueValue, isa<Instruction>(TrueValue)
                                            ? CurrentBlock
                                            : nullptr };
      assert(Map.find(TrueItem) != Map.end() && "No True Value!")(static_cast <bool> (Map.find(TrueItem) != Map.end() &&
 "No True Value!") ? void (0) : __assert_fail ("Map.find(TrueItem) != Map.end() && \"No True Value!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 2987, __extension__ __PRETTY_FUNCTION__));
      Select->setTrueValue(ST.Get(Map[TrueItem]));
      auto *FalseValue = CurrentSelect->getFalseValue();
      ValueInBB FalseItem = { FalseValue, isa<Instruction>(FalseValue)
                                              ? CurrentBlock
                                              : nullptr };
      assert(Map.find(FalseItem) != Map.end() && "No False Value!")(static_cast <bool> (Map.find(FalseItem) != Map.end() &&
 "No False Value!") ? void (0) : __assert_fail ("Map.find(FalseItem) != Map.end() && \"No False Value!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 2993, __extension__ __PRETTY_FUNCTION__));
      Select->setFalseValue(ST.Get(Map[FalseItem]));
    } else {
      // Must be a Phi node then.
      PHINode *PHI = cast<PHINode>(V);
      // Fill the Phi node with values from predecessors.
      bool IsDefinedInThisBB =
          cast<Instruction>(CurrentValue)->getParent() == CurrentBlock;
      auto *CurrentPhi = dyn_cast<PHINode>(CurrentValue);
      for (auto B : predecessors(CurrentBlock)) {
        Value *PV = IsDefinedInThisBB
                        ? CurrentPhi->getIncomingValueForBlock(B)
                        : CurrentValue;
        ValueInBB item = { PV, isa<Instruction>(PV) ? B : nullptr };
        assert(Map.find(item) != Map.end() && "No predecessor Value!")(static_cast <bool> (Map.find(item) != Map.end() &&
 "No predecessor Value!") ? void (0) : __assert_fail ("Map.find(item) != Map.end() && \"No predecessor Value!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3007, __extension__ __PRETTY_FUNCTION__));
        PHI->addIncoming(ST.Get(Map[item]), B);
      }
    }
    // Simplify if possible.
    Map[Current] = ST.Simplify(V);
  }
}

/// Starting from value recursively iterates over predecessors up to known
/// ending values represented in a map. For each traversed block inserts
/// a placeholder Phi or Select.
/// Reports all new created Phi/Select nodes by adding them to set.
/// Also reports and order in what basic blocks have been traversed.
void InsertPlaceholders(FoldAddrToValueMapping &Map,
                        SmallVectorImpl<ValueInBB> &TraverseOrder,
                        SmallPtrSetImpl<PHINode *> &NewPhiNodes,
                        SmallPtrSetImpl<SelectInst *> &NewSelectNodes) {
  SmallVector<ValueInBB, 32> Worklist;
  assert((isa<PHINode>(Original.first) || isa<SelectInst>(Original.first)) &&(static_cast <bool> ((isa<PHINode>(Original.first
) || isa<SelectInst>(Original.first)) && "Address must be a Phi or Select node"
) ? void (0) : __assert_fail ("(isa<PHINode>(Original.first) || isa<SelectInst>(Original.first)) && \"Address must be a Phi or Select node\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3027, __extension__ __PRETTY_FUNCTION__))
         "Address must be a Phi or Select node")(static_cast <bool> ((isa<PHINode>(Original.first
) || isa<SelectInst>(Original.first)) && "Address must be a Phi or Select node"
) ? void (0) : __assert_fail ("(isa<PHINode>(Original.first) || isa<SelectInst>(Original.first)) && \"Address must be a Phi or Select node\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3027, __extension__ __PRETTY_FUNCTION__));
  auto *Dummy = UndefValue::get(CommonType);
  Worklist.push_back(Original);
  while (!Worklist.empty()) {
39
←
Loop condition is true.  Entering loop body→
    auto Current = Worklist.pop_back_val();
    // If value is not an instruction it is something global, constant,
    // parameter and we can say that this value is observable in any block.
    // Set block to null to denote it.
    // Also please take into account that it is how we build anchors.
    if (!isa<Instruction>(Current.first))
40
←
Taking true branch→
      Current.second = nullptr;
41
←
Null pointer value stored to 'Current.second'→
    // if it is already visited or it is an ending value then skip it.
    if (Map.find(Current) != Map.end())
42
←
Assuming the condition is false→
43
←
Taking false branch→
      continue;
    TraverseOrder.push_back(Current);

    Value *CurrentValue = Current.first;
    BasicBlock *CurrentBlock = Current.second;
44
←
'CurrentBlock' initialized to a null pointer value→
    // CurrentValue must be a Phi node or select. All others must be covered
    // by anchors.
    Instruction *CurrentI = cast<Instruction>(CurrentValue);
    bool IsDefinedInThisBB = CurrentI->getParent() == CurrentBlock;
45
←
Assuming the condition is true→

    unsigned PredCount =
        std::distance(pred_begin(CurrentBlock), pred_end(CurrentBlock));
    // if Current Value is not defined in this basic block we are interested
    // in values in predecessors.
    if (!IsDefinedInThisBB) {
46
←
Taking false branch→
      assert(PredCount && "Unreachable block?!")(static_cast <bool> (PredCount && "Unreachable block?!"
) ? void (0) : __assert_fail ("PredCount && \"Unreachable block?!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3055, __extension__ __PRETTY_FUNCTION__));
      PHINode *PHI = PHINode::Create(CommonType, PredCount, "sunk_phi",
                                     &CurrentBlock->front());
      Map[Current] = PHI;
      NewPhiNodes.insert(PHI);
      // Add all predecessors in work list.
      for (auto B : predecessors(CurrentBlock))
        Worklist.push_back({ CurrentValue, B });
      continue;
    }
    // Value is defined in this basic block.
    if (SelectInst *OrigSelect = dyn_cast<SelectInst>(CurrentI)) {
47
←
Taking false branch→
      // Is it OK to get metadata from OrigSelect?!
      // Create a Select placeholder with dummy value.
      SelectInst *Select =
          SelectInst::Create(OrigSelect->getCondition(), Dummy, Dummy,
                             OrigSelect->getName(), OrigSelect, OrigSelect);
      Map[Current] = Select;
      NewSelectNodes.insert(Select);
      // We are interested in True and False value in this basic block.
      Worklist.push_back({ OrigSelect->getTrueValue(), CurrentBlock });
      Worklist.push_back({ OrigSelect->getFalseValue(), CurrentBlock });
    } else {
      // It must be a Phi node then.
      auto *CurrentPhi = cast<PHINode>(CurrentI);
      // Create new Phi node for merge of bases.
      assert(PredCount && "Unreachable block?!")(static_cast <bool> (PredCount && "Unreachable block?!"
) ? void (0) : __assert_fail ("PredCount && \"Unreachable block?!\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3081, __extension__ __PRETTY_FUNCTION__));
      PHINode *PHI = PHINode::Create(CommonType, PredCount, "sunk_phi",
                                     &CurrentBlock->front());
48
←
Called C++ object pointer is null
      Map[Current] = PHI;
      NewPhiNodes.insert(PHI);

      // Add all predecessors in work list.
      for (auto B : predecessors(CurrentBlock))
        Worklist.push_back({ CurrentPhi->getIncomingValueForBlock(B), B });
    }
  }
}

bool addrModeCombiningAllowed() {
  if (DisableComplexAddrModes)
    return false;
  switch (DifferentField) {
  default:
    return false;
  case ExtAddrMode::BaseRegField:
    return AddrSinkCombineBaseReg;
  case ExtAddrMode::BaseGVField:
    return AddrSinkCombineBaseGV;
  case ExtAddrMode::BaseOffsField:
    return AddrSinkCombineBaseOffs;
  case ExtAddrMode::ScaledRegField:
    return AddrSinkCombineScaledReg;
  }
}
3110};
3111} // end anonymous namespace

3113/// Try adding ScaleReg*Scale to the current addressing mode.
3114/// Return true and update AddrMode if this addr mode is legal for the target,
3115/// false if not.
3116bool 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;
3166}

3168/// This is a little filter, which returns true if an addressing computation
3169/// involving I might be folded into a load/store accessing it.
3170/// This doesn't need to be perfect, but needs to accept at least
3171/// the set of instructions that MatchOperationAddr can.
3172static 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;
}
3197}

3199/// \brief Check whether or not \p Val is a legal instruction for \p TLI.
3200/// \note \p Val is assumed to be the product of some type promotion.
3201/// Therefore if \p Val has an undefined state in \p TLI, this is assumed
3202/// to be legal, as the non-promoted value would have had the same state.
3203static 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()));
3215}

3217namespace {

3219/// \brief Hepler class to perform type promotion.
3220class 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);
}

3293public:
/// Type for the utility function that promotes the operand of Ext.
using Action = Value *(*)(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);
3314};

3316} // end anonymous namespace

3318bool 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();
3380}

3382TypePromotionHelper::Action TypePromotionHelper::getAction(
  Instruction *Ext, const SetOfInstrs &InsertedInsts,
  const TargetLowering &TLI, const InstrToOrigTy &PromotedInsts) {
assert((isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) &&(static_cast <bool> ((isa<SExtInst>(Ext) || isa<
ZExtInst>(Ext)) && "Unexpected instruction type") ?
 void (0) : __assert_fail ("(isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) && \"Unexpected instruction type\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3386, __extension__ __PRETTY_FUNCTION__))
       "Unexpected instruction type")(static_cast <bool> ((isa<SExtInst>(Ext) || isa<
ZExtInst>(Ext)) && "Unexpected instruction type") ?
 void (0) : __assert_fail ("(isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) && \"Unexpected instruction type\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3386, __extension__ __PRETTY_FUNCTION__));
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;
3413}

3415Value *TypePromotionHelper::promoteOperandForTruncAndAnyExt(
  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;
3461}

3463Value *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)) {
    // Insert it just after the definition.
    ITrunc->moveAfter(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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Propagate Ext to operands\n"
; } } while (false);
for (int OpIdx = 0, EndOpIdx = ExtOpnd->getNumOperands(); OpIdx != EndOpIdx;
     ++OpIdx) {
  DEBUG(dbgs() << "Operand:\n" << *(ExtOpnd->getOperand(OpIdx)) << '\n')do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Operand:\n" << *
(ExtOpnd->getOperand(OpIdx)) << '\n'; } } while (false
);
  if (ExtOpnd->getOperand(OpIdx)->getType() == Ext->getType() ||
      !shouldExtOperand(ExtOpnd, OpIdx)) {
    DEBUG(dbgs() << "No need to propagate\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "No need to propagate\n"
; } } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Statically extend\n"; }
 } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Statically extend\n"; }
 } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "More operands to ext\n"
; } } while (false);
    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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Extension is useless now\n"
; } } while (false);
  TPT.eraseInstruction(Ext);
}
return ExtOpnd;
3563}

3565/// Check whether or not promoting an instruction to a wider type is profitable.
3566/// \p NewCost gives the cost of extension instructions created by the
3567/// promotion.
3568/// \p OldCost gives the cost of extension instructions before the promotion
3569/// plus the number of instructions that have been
3570/// matched in the addressing mode the promotion.
3571/// \p PromotedOperand is the value that has been promoted.
3572/// \return True if the promotion is profitable, false otherwise.
3573bool AddressingModeMatcher::isPromotionProfitable(
  unsigned NewCost, unsigned OldCost, Value *PromotedOperand) const {
DEBUG(dbgs() << "OldCost: " << OldCost << "\tNewCost: " << NewCost << '\n')do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "OldCost: " << OldCost
 << "\tNewCost: " << NewCost << '\n'; } } while
 (false);
// 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);
3587}

3589/// Given an instruction or constant expr, see if we can fold the operation
3590/// into the addressing mode. If so, update the addressing mode and return
3591/// true, otherwise return false without modifying AddrMode.
3592/// If \p MovedAway is not NULL, it contains the information of whether or
3593/// not AddrInst has to be folded into the addressing mode on success.
3594/// If \p MovedAway == true, \p AddrInst will not be part of the addressing
3595/// because it has been moved away.
3596/// Thus AddrInst must not be added in the matched instructions.
3597/// This state can happen when AddrInst is a sext, since it may be moved away.
3598/// Therefore, AddrInst may not be valid when MovedAway is true and it must
3599/// not be referenced anymore.
3600bool 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 || RHS->getBitWidth() > 64)
    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 = GTI.getStructTypeOrNull()) {
      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 &&(static_cast <bool> (PromotedOperand && "TypePromotionHelper should have filtered out those cases"
) ? void (0) : __assert_fail ("PromotedOperand && \"TypePromotionHelper should have filtered out those cases\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3807, __extension__ __PRETTY_FUNCTION__))
         "TypePromotionHelper should have filtered out those cases")(static_cast <bool> (PromotedOperand && "TypePromotionHelper should have filtered out those cases"
) ? void (0) : __assert_fail ("PromotedOperand && \"TypePromotionHelper should have filtered out those cases\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 3807, __extension__ __PRETTY_FUNCTION__));

  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")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Sign extension does not pay off: rollback\n"
; } } while (false);
    TPT.rollback(LastKnownGood);
    return false;
  }
  return true;
}
}
return false;
3830}

3832/// If we can, try to add the value of 'Addr' into the current addressing mode.
3833/// If Addr can't be added to AddrMode this returns false and leaves AddrMode
3834/// unmodified. This assumes that Addr is either a pointer type or intptr_t
3835/// for the target.
3836///
3837bool 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;
3914}

3916/// Check to see if all uses of OpVal by the specified inline asm call are due
3917/// to memory operands. If so, return true, otherwise return false.
3918static bool IsOperandAMemoryOperand(CallInst *CI, InlineAsm *IA, Value *OpVal,
                                  const TargetLowering &TLI,
                                  const TargetRegisterInfo &TRI) {
const Function *F = CI->getFunction();
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;
3941}

3943// Max number of memory uses to look at before aborting the search to conserve
3944// compile time.
3945static constexpr int MaxMemoryUsesToScan = 20;

3947/// Recursively walk all the uses of I until we find a memory use.
3948/// If we find an obviously non-foldable instruction, return true.
3949/// Add the ultimately found memory instructions to MemoryUses.
3950static bool FindAllMemoryUses(
  Instruction *I,
  SmallVectorImpl<std::pair<Instruction *, unsigned>> &MemoryUses,
  SmallPtrSetImpl<Instruction *> &ConsideredInsts, const TargetLowering &TLI,
  const TargetRegisterInfo &TRI, int SeenInsts = 0) {
// 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;

const bool OptSize = I->getFunction()->optForSize();

// Loop over all the uses, recursively processing them.
for (Use &U : I->uses()) {
  // Conservatively return true if we're seeing a large number or a deep chain
  // of users. This avoids excessive compilation times in pathological cases.
  if (SeenInsts++ >= MaxMemoryUsesToScan)
    return true;

  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 != StoreInst::getPointerOperandIndex())
      return true; // Storing addr, not into addr.
    MemoryUses.push_back(std::make_pair(SI, opNo));
    continue;
  }

  if (AtomicRMWInst *RMW = dyn_cast<AtomicRMWInst>(UserI)) {
    unsigned opNo = U.getOperandNo();
    if (opNo != AtomicRMWInst::getPointerOperandIndex())
      return true; // Storing addr, not into addr.
    MemoryUses.push_back(std::make_pair(RMW, opNo));
    continue;
  }

  if (AtomicCmpXchgInst *CmpX = dyn_cast<AtomicCmpXchgInst>(UserI)) {
    unsigned opNo = U.getOperandNo();
    if (opNo != AtomicCmpXchgInst::getPointerOperandIndex())
      return true; // Storing addr, not into addr.
    MemoryUses.push_back(std::make_pair(CmpX, opNo));
    continue;
  }

  if (CallInst *CI = dyn_cast<CallInst>(UserI)) {
    // If this is a cold call, we can sink the addressing calculation into
    // the cold path.  See optimizeCallInst
    if (!OptSize && CI->hasFnAttr(Attribute::Cold))
      continue;

    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, TLI, TRI))
      return true;
    continue;
  }

  if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI, TRI,
                        SeenInsts))
    return true;
}

return false;
4023}

4025/// Return true if Val is already known to be live at the use site that we're
4026/// folding it into. If so, there is no cost to include it in the addressing
4027/// mode. KnownLive1 and KnownLive2 are two values that we know are live at the
4028/// instruction already.
4029bool 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());
4049}

4051/// It is possible for the addressing mode of the machine to fold the specified
4052/// instruction into a load or store that ultimately uses it.
4053/// However, the specified instruction has multiple uses.
4054/// Given this, it may actually increase register pressure to fold it
4055/// into the load. For example, consider this code:
4056///
4057///     X = ...
4058///     Y = X+1
4059///     use(Y)   -> nonload/store
4060///     Z = Y+1
4061///     load Z
4062///
4063/// In this case, Y has multiple uses, and can be folded into the load of Z
4064/// (yielding load [X+2]).  However, doing this will cause both "X" and "X+1" to
4065/// be live at the use(Y) line.  If we don't fold Y into load Z, we use one
4066/// fewer register.  Since Y can't be folded into "use(Y)" we don't increase the
4067/// number of computations either.
4068///
4069/// Note that this (like most of CodeGenPrepare) is just a rough heuristic.  If
4070/// X was live across 'load Z' for other reasons, we actually *would* want to
4071/// fold the addressing mode in the Z case.  This would make Y die earlier.
4072bool AddressingModeMatcher::
4073isProfitableToFoldIntoAddressingMode(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 can have the address mode sunk into them,
// we can remove the addressing mode and effectively trade one live register
// for another (at worst.)  In this context, folding an addressing mode into
// the use is just a particularly nice way of sinking it.
SmallVector<std::pair<Instruction*,unsigned>, 16> MemoryUses;
SmallPtrSet<Instruction*, 16> ConsideredInsts;
if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TLI, TRI))
  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 memory operation uses and see
// if they could  *actually* fold the instruction.  The assumption is that
// addressing modes are cheap and that duplicating the computation involved
// many times is worthwhile, even on a fastpath. For sinking candidates
// (i.e. cold call sites), this serves as a way to prevent excessive code
// growth since most architectures have some reasonable small and fast way to
// compute an effective address.  (i.e LEA on x86)
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, TLI, TRI,
                                AddressAccessTy, AS,
                                MemoryInst, Result, InsertedInsts,
                                PromotedInsts, TPT);
  Matcher.IgnoreProfitability = true;
  bool Success = Matcher.matchAddr(Address, 0);
  (void)Success; assert(Success && "Couldn't select *anything*?")(static_cast <bool> (Success && "Couldn't select *anything*?"
) ? void (0) : __assert_fail ("Success && \"Couldn't select *anything*?\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4144, __extension__ __PRETTY_FUNCTION__));

  // 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 (!is_contained(MatchedAddrModeInsts, I))
    return false;

  MatchedAddrModeInsts.clear();
}

return true;
4159}

4161/// Return true if the specified values are defined in a
4162/// different basic block than BB.
4163static bool IsNonLocalValue(Value *V, BasicBlock *BB) {
if (Instruction *I = dyn_cast<Instruction>(V))
  return I->getParent() != BB;
return false;
4167}

4169/// Sink addressing mode computation immediate before MemoryInst if doing so
4170/// can be done without increasing register pressure.  The need for the
4171/// register pressure constraint means this can end up being an all or nothing
4172/// decision for all uses of the same addressing computation.
4173///
4174/// Load and Store Instructions often have addressing modes that can do
4175/// significant amounts of computation. As such, instruction selection will try
4176/// to get the load or store to do as much computation as possible for the
4177/// program. The problem is that isel can only see within a single block. As
4178/// such, we sink as much legal addressing mode work into the block as possible.
4179///
4180/// This method is used to optimize both load/store and inline asms with memory
4181/// operands.  It's also used to sink addressing computations feeding into cold
4182/// call sites into their (cold) basic block.
4183///
4184/// The motivation for handling sinking into cold blocks is that doing so can
4185/// both enable other address mode sinking (by satisfying the register pressure
4186/// constraint above), and reduce register pressure globally (by removing the
4187/// addressing mode computation from the fast path entirely.).
4188bool 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 and select nodes, and
// ensure that the addressing mode obtained from the non-PHI/select roots of
// the graph are compatible.
bool PhiOrSelectSeen = false;
SmallVector<Instruction*, 16> AddrModeInsts;
const SimplifyQuery SQ(*DL, TLInfo);
AddressingModeCombiner AddrModes(SQ, { Addr, MemoryInst->getParent() });
TypePromotionTransaction TPT(RemovedInsts);
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
    TPT.getRestorationPoint();
while (!worklist.empty()) {
1
Loop condition is true.  Entering loop body→
7
←
Loop condition is true.  Entering loop body→
13
←
Loop condition is true.  Entering loop body→
19
←
Loop condition is true.  Entering loop body→
  Value *V = worklist.back();
  worklist.pop_back();

  // We allow traversing cyclic Phi nodes.
  // In case of success after this loop we ensure that traversing through
  // Phi nodes ends up with all cases to compute address of the form
  //    BaseGV + Base + Scale * Index + Offset
  // where Scale and Offset are constans and BaseGV, Base and Index
  // are exactly the same Values in all cases.
  // It means that BaseGV, Scale and Offset dominate our memory instruction
  // and have the same value as they had in address computation represented
  // as Phi. So we can safely sink address computation to memory instruction.
  if (!Visited.insert(V).second)
2
←
Assuming the condition is false→
3
←
Taking false branch→
8
←
Assuming the condition is false→
9
←
Taking false branch→
14
←
Assuming the condition is false→
15
←
Taking false branch→
20
←
Assuming the condition is false→
21
←
Taking false branch→
    continue;

  // For a PHI node, push all of its incoming values.
  if (PHINode *P = dyn_cast<PHINode>(V)) {
4
←
Taking false branch→
10
←
Taking false branch→
16
←
Taking false branch→
22
←
Taking false branch→
    for (Value *IncValue : P->incoming_values())
      worklist.push_back(IncValue);
    PhiOrSelectSeen = true;
    continue;
  }
  // Similar for select.
  if (SelectInst *SI = dyn_cast<SelectInst>(V)) {
5
←
Taking false branch→
11
←
Taking false branch→
17
←
Taking false branch→
23
←
Taking false branch→
    worklist.push_back(SI->getFalseValue());
    worklist.push_back(SI->getTrueValue());
    PhiOrSelectSeen = true;
    continue;
  }

  // For non-PHIs, determine the addressing mode being computed.  Note that
  // the result may differ depending on what other uses our candidate
  // addressing instructions might have.
  AddrModeInsts.clear();
  ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
      V, AccessTy, AddrSpace, MemoryInst, AddrModeInsts, *TLI, *TRI,
      InsertedInsts, PromotedInsts, TPT);
  NewAddrMode.OriginalValue = V;

  if (!AddrModes.addNewAddrMode(NewAddrMode))
6
←
Taking false branch→
12
←
Taking false branch→
18
←
Taking false branch→
24
←
Taking true branch→
    break;
25
←
 Execution continues on line 4255→
}

// Try to combine the AddrModes we've collected. If we couldn't collect any,
// or we have multiple but either couldn't combine them or combining them
// wouldn't do anything useful, bail out now.
if (!AddrModes.combineAddrModes()) {
26
←
Calling 'AddressingModeCombiner::combineAddrModes'→
  TPT.rollback(LastKnownGood);
  return false;
}
TPT.commit();

// Get the combined AddrMode (or the only AddrMode, if we only had one).
ExtAddrMode AddrMode = AddrModes.getAddrMode();

// If all the instructions matched are already in this BB, don't do anything.
// If we saw a Phi node then it is not local definitely, and if we saw a select
// then we want to push the address calculation past it even if it's already
// in this BB.
if (!PhiOrSelectSeen && none_of(AddrModeInsts, [&](Value *V) {
      return IsNonLocalValue(V, MemoryInst->getParent());
                })) {
  DEBUG(dbgs() << "CGP: Found      local addrmode: " << AddrMode << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "CGP: Found      local addrmode: "
 << AddrMode << "\n"; } } while (false);
  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.  Before attempting reuse, check if the address is valid
// as it may have been erased.

WeakTrackingVH SunkAddrVH = SunkAddrs[Addr];

Value * SunkAddr = SunkAddrVH.pointsToAliveValue() ? SunkAddrVH : nullptr;
if (SunkAddr) {
  DEBUG(dbgs() << "CGP: Reusing nonlocal addrmode: " << AddrMode << " for "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "CGP: Reusing nonlocal addrmode: "
 << AddrMode << " for " << *MemoryInst <<
 "\n"; } } while (false)
               << *MemoryInst << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "CGP: Reusing nonlocal addrmode: "
 << AddrMode << " for " << *MemoryInst <<
 "\n"; } } while (false);
  if (SunkAddr->getType() != Addr->getType())
    SunkAddr = Builder.CreatePointerCast(SunkAddr, Addr->getType());
} else if (AddrSinkUsingGEPs ||
           (!AddrSinkUsingGEPs.getNumOccurrences() && TM &&
            SubtargetInfo->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 "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "CGP: SINKING nonlocal addrmode: "
 << AddrMode << " for " << *MemoryInst <<
 "\n"; } } while (false)
               << *MemoryInst << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "CGP: SINKING nonlocal addrmode: "
 << AddrMode << " for " << *MemoryInst <<
 "\n"; } } while (false);
  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;
  }

  // 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.
  //
  // (See below for code to add the scale.)
  if (AddrMode.Scale) {
    Type *ScaledRegTy = AddrMode.ScaledReg->getType();
    if (cast<IntegerType>(IntPtrTy)->getBitWidth() >
        cast<IntegerType>(ScaledRegTy)->getBitWidth())
      return false;
  }

  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 (!DL->isNonIntegralPointerType(Addr->getType())) {
    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 {
        assert(cast<IntegerType>(IntPtrTy)->getBitWidth() <(static_cast <bool> (cast<IntegerType>(IntPtrTy)->
getBitWidth() < cast<IntegerType>(V->getType())->
getBitWidth() && "We can't transform if ScaledReg is too narrow"
) ? void (0) : __assert_fail ("cast<IntegerType>(IntPtrTy)->getBitWidth() < cast<IntegerType>(V->getType())->getBitWidth() && \"We can't transform if ScaledReg is too narrow\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4387, __extension__ __PRETTY_FUNCTION__))
               cast<IntegerType>(V->getType())->getBitWidth() &&(static_cast <bool> (cast<IntegerType>(IntPtrTy)->
getBitWidth() < cast<IntegerType>(V->getType())->
getBitWidth() && "We can't transform if ScaledReg is too narrow"
) ? void (0) : __assert_fail ("cast<IntegerType>(IntPtrTy)->getBitWidth() < cast<IntegerType>(V->getType())->getBitWidth() && \"We can't transform if ScaledReg is too narrow\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4387, __extension__ __PRETTY_FUNCTION__))
               "We can't transform if ScaledReg is too narrow")(static_cast <bool> (cast<IntegerType>(IntPtrTy)->
getBitWidth() < cast<IntegerType>(V->getType())->
getBitWidth() && "We can't transform if ScaledReg is too narrow"
) ? void (0) : __assert_fail ("cast<IntegerType>(IntPtrTy)->getBitWidth() < cast<IntegerType>(V->getType())->getBitWidth() && \"We can't transform if ScaledReg is too narrow\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4387, __extension__ __PRETTY_FUNCTION__));
        V = Builder.CreateTrunc(V, IntPtrTy, "sunkaddr");
      }

      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.CreatePointerCast(ResultPtr, I8PtrTy);
        ResultPtr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
      }

      ResultIndex = V;
    }

    if (!ResultIndex) {
      SunkAddr = ResultPtr;
    } else {
      if (ResultPtr->getType() != I8PtrTy)
        ResultPtr = Builder.CreatePointerCast(ResultPtr, I8PtrTy);
      SunkAddr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
    }

    if (SunkAddr->getType() != Addr->getType())
      SunkAddr = Builder.CreatePointerCast(SunkAddr, Addr->getType());
  }
} else {
  // We'd require a ptrtoint/inttoptr down the line, which we can't do for
  // non-integral pointers, so in that case bail out now.
  Type *BaseTy = AddrMode.BaseReg ? AddrMode.BaseReg->getType() : nullptr;
  Type *ScaleTy = AddrMode.Scale ? AddrMode.ScaledReg->getType() : nullptr;
  PointerType *BasePtrTy = dyn_cast_or_null<PointerType>(BaseTy);
  PointerType *ScalePtrTy = dyn_cast_or_null<PointerType>(ScaleTy);
  if (DL->isNonIntegralPointerType(Addr->getType()) ||
      (BasePtrTy && DL->isNonIntegralPointerType(BasePtrTy)) ||
      (ScalePtrTy && DL->isNonIntegralPointerType(ScalePtrTy)) ||
      (AddrMode.BaseGV &&
       DL->isNonIntegralPointerType(AddrMode.BaseGV->getType())))
    return false;

  DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "CGP: SINKING nonlocal addrmode: "
 << AddrMode << " for " << *MemoryInst <<
 "\n"; } } while (false)
               << *MemoryInst << "\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "CGP: SINKING nonlocal addrmode: "
 << AddrMode << " for " << *MemoryInst <<
 "\n"; } } while (false);
  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);
// Store the newly computed address into the cache. In the case we reused a
// value, this should be idempotent.
SunkAddrs[Addr] = WeakTrackingVH(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 WeakTrackingVH to hold onto it in case this happens.
  Value *CurValue = &*CurInstIterator;
  WeakTrackingVH IterHandle(CurValue);
  BasicBlock *BB = CurInstIterator->getParent();

  RecursivelyDeleteTriviallyDeadInstructions(Repl, TLInfo);

  if (IterHandle != CurValue) {
    // If the iterator instruction was recursively deleted, start over at the
    // start of the block.
    CurInstIterator = BB->begin();
    SunkAddrs.clear();
  }
}
++NumMemoryInsts;
return true;
4537}

4539/// If there are any memory operands, use OptimizeMemoryInst to sink their
4540/// address computing into the block when possible / profitable.
4541bool CodeGenPrepare::optimizeInlineAsmInst(CallInst *CS) {
bool MadeChange = false;

const TargetRegisterInfo *TRI =
    TM->getSubtargetImpl(*CS->getFunction())->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;
4564}

4566/// \brief Check if all the uses of \p Val are equivalent (or free) zero or
4567/// sign extensions.
4568static bool hasSameExtUse(Value *Val, const TargetLowering &TLI) {
assert(!Val->use_empty() && "Input must have at least one use")(static_cast <bool> (!Val->use_empty() && "Input must have at least one use"
) ? void (0) : __assert_fail ("!Val->use_empty() && \"Input must have at least one use\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4569, __extension__ __PRETTY_FUNCTION__));
const Instruction *FirstUser = cast<Instruction>(*Val->user_begin());
bool IsSExt = isa<SExtInst>(FirstUser);
Type *ExtTy = FirstUser->getType();
for (const User *U : Val->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 = Val
  // b = sext ty1 a to ty2
  // c = sext ty1 a to ty3
  // Assuming ty2 is shorter than ty3, this could be turned into:
  // a = Val
  // 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;
4612}

4614/// \brief Try to speculatively promote extensions in \p Exts and continue
4615/// promoting through newly promoted operands recursively as far as doing so is
4616/// profitable. Save extensions profitably moved up, in \p ProfitablyMovedExts.
4617/// When some promotion happened, \p TPT contains the proper state to revert
4618/// them.
4619///
4620/// \return true if some promotion happened, false otherwise.
4621bool CodeGenPrepare::tryToPromoteExts(
  TypePromotionTransaction &TPT, const SmallVectorImpl<Instruction *> &Exts,
  SmallVectorImpl<Instruction *> &ProfitablyMovedExts,
  unsigned CreatedInstsCost) {
bool Promoted = false;

// Iterate over all the extensions to try to promote them.
for (auto I : Exts) {
  // Early check if we directly have ext(load).
  if (isa<LoadInst>(I->getOperand(0))) {
    ProfitablyMovedExts.push_back(I);
    continue;
  }

  // Check whether or not we want to do any promotion.  The reason we have
  // this check inside the for loop is to catch the case where an extension
  // is directly fed by a load because in such case the extension can be moved
  // up without any promotion on its operands.
  if (!TLI || !TLI->enableExtLdPromotion() || DisableExtLdPromotion)
    return false;

  // Get the action to perform the promotion.
  TypePromotionHelper::Action TPH =
      TypePromotionHelper::getAction(I, InsertedInsts, *TLI, PromotedInsts);
  // Check if we can promote.
  if (!TPH) {
    // Save the current extension as we cannot move up through its operand.
    ProfitablyMovedExts.push_back(I);
    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 &&(static_cast <bool> (PromotedVal && "TypePromotionHelper should have filtered out those cases"
) ? void (0) : __assert_fail ("PromotedVal && \"TypePromotionHelper should have filtered out those cases\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4662, __extension__ __PRETTY_FUNCTION__))
         "TypePromotionHelper should have filtered out those cases")(static_cast <bool> (PromotedVal && "TypePromotionHelper should have filtered out those cases"
) ? void (0) : __assert_fail ("PromotedVal && \"TypePromotionHelper should have filtered out those cases\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4662, __extension__ __PRETTY_FUNCTION__));

  // 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;
  // FIXME: It would be possible to propagate a negative value instead of
  // conservatively ceiling it to 0.
  TotalCreatedInstsCost =
      std::max((long long)0, (TotalCreatedInstsCost - ExtCost));
  if (!StressExtLdPromotion &&
      (TotalCreatedInstsCost > 1 ||
       !isPromotedInstructionLegal(*TLI, *DL, PromotedVal))) {
    // This promotion is not profitable, rollback to the previous state, and
    // save the current extension in ProfitablyMovedExts as the latest
    // speculative promotion turned out to be unprofitable.
    TPT.rollback(LastKnownGood);
    ProfitablyMovedExts.push_back(I);
    continue;
  }
  // Continue promoting NewExts as far as doing so is profitable.
  SmallVector<Instruction *, 2> NewlyMovedExts;
  (void)tryToPromoteExts(TPT, NewExts, NewlyMovedExts, TotalCreatedInstsCost);
  bool NewPromoted = false;
  for (auto ExtInst : NewlyMovedExts) {
    Instruction *MovedExt = cast<Instruction>(ExtInst);
    Value *ExtOperand = MovedExt->getOperand(0);
    // If we have reached to a load, we need this extra profitability check
    // as it could potentially be merged into an ext(load).
    if (isa<LoadInst>(ExtOperand) &&
        !(StressExtLdPromotion || NewCreatedInstsCost <= ExtCost ||
          (ExtOperand->hasOneUse() || hasSameExtUse(ExtOperand, *TLI))))
      continue;

    ProfitablyMovedExts.push_back(MovedExt);
    NewPromoted = true;
  }

  // If none of speculative promotions for NewExts is profitable, rollback
  // and save the current extension (I) as the last profitable extension.
  if (!NewPromoted) {
    TPT.rollback(LastKnownGood);
    ProfitablyMovedExts.push_back(I);
    continue;
  }
  // The promotion is profitable.
  Promoted = true;
}
return Promoted;
4714}

4716/// Merging redundant sexts when one is dominating the other.
4717bool CodeGenPrepare::mergeSExts(Function &F) {
DominatorTree DT(F);
bool Changed = false;
for (auto &Entry : ValToSExtendedUses) {
  SExts &Insts = Entry.second;
  SExts CurPts;
  for (Instruction *Inst : Insts) {
    if (RemovedInsts.count(Inst) || !isa<SExtInst>(Inst) ||
        Inst->getOperand(0) != Entry.first)
      continue;
    bool inserted = false;
    for (auto &Pt : CurPts) {
      if (DT.dominates(Inst, Pt)) {
        Pt->replaceAllUsesWith(Inst);
        RemovedInsts.insert(Pt);
        Pt->removeFromParent();
        Pt = Inst;
        inserted = true;
        Changed = true;
        break;
      }
      if (!DT.dominates(Pt, Inst))
        // Give up if we need to merge in a common dominator as the
        // expermients show it is not profitable.
        continue;
      Inst->replaceAllUsesWith(Pt);
      RemovedInsts.insert(Inst);
      Inst->removeFromParent();
      inserted = true;
      Changed = true;
      break;
    }
    if (!inserted)
      CurPts.push_back(Inst);
  }
}
return Changed;
4754}

4756/// Return true, if an ext(load) can be formed from an extension in
4757/// \p MovedExts.
4758bool CodeGenPrepare::canFormExtLd(
  const SmallVectorImpl<Instruction *> &MovedExts, LoadInst *&LI,
  Instruction *&Inst, bool HasPromoted) {
for (auto *MovedExtInst : MovedExts) {
  if (isa<LoadInst>(MovedExtInst->getOperand(0))) {
    LI = cast<LoadInst>(MovedExtInst->getOperand(0));
    Inst = MovedExtInst;
    break;
  }
}
if (!LI)
  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() == Inst->getParent())
  return false;

return TLI->isExtLoad(LI, Inst, *DL);
4778}

4780/// Move a zext or sext fed by a load into the same basic block as the load,
4781/// unless conditions are unfavorable. This allows SelectionDAG to fold the
4782/// extend into the load.
4783///
4784/// E.g.,
4785/// \code
4786/// %ld = load i32* %addr
4787/// %add = add nuw i32 %ld, 4
4788/// %zext = zext i32 %add to i64
4789// \endcode
4790/// =>
4791/// \code
4792/// %ld = load i32* %addr
4793/// %zext = zext i32 %ld to i64
4794/// %add = add nuw i64 %zext, 4
4795/// \encode
4796/// Note that the promotion in %add to i64 is done in tryToPromoteExts(), which
4797/// allow us to match zext(load i32*) to i64.
4798///
4799/// Also, try to promote the computations used to obtain a sign extended
4800/// value used into memory accesses.
4801/// E.g.,
4802/// \code
4803/// a = add nsw i32 b, 3
4804/// d = sext i32 a to i64
4805/// e = getelementptr ..., i64 d
4806/// \endcode
4807/// =>
4808/// \code
4809/// f = sext i32 b to i64
4810/// a = add nsw i64 f, 3
4811/// e = getelementptr ..., i64 a
4812/// \endcode
4813///
4814/// \p Inst[in/out] the extension may be modified during the process if some
4815/// promotions apply.
4816bool CodeGenPrepare::optimizeExt(Instruction *&Inst) {
// ExtLoad formation and address type promotion infrastructure requires TLI to
// be effective.
if (!TLI)
  return false;

bool AllowPromotionWithoutCommonHeader = false;
/// See if it is an interesting sext operations for the address type
/// promotion before trying to promote it, e.g., the ones with the right
/// type and used in memory accesses.
bool ATPConsiderable = TTI->shouldConsiderAddressTypePromotion(
    *Inst, AllowPromotionWithoutCommonHeader);
TypePromotionTransaction TPT(RemovedInsts);
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
    TPT.getRestorationPoint();
SmallVector<Instruction *, 1> Exts;
SmallVector<Instruction *, 2> SpeculativelyMovedExts;
Exts.push_back(Inst);

bool HasPromoted = tryToPromoteExts(TPT, Exts, SpeculativelyMovedExts);

// Look for a load being extended.
LoadInst *LI = nullptr;
Instruction *ExtFedByLoad;

// Try to promote a chain of computation if it allows to form an extended
// load.
if (canFormExtLd(SpeculativelyMovedExts, LI, ExtFedByLoad, HasPromoted)) {
  assert(LI && ExtFedByLoad && "Expect a valid load and extension")(static_cast <bool> (LI && ExtFedByLoad &&
 "Expect a valid load and extension") ? void (0) : __assert_fail
 ("LI && ExtFedByLoad && \"Expect a valid load and extension\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4844, __extension__ __PRETTY_FUNCTION__));
  TPT.commit();
  // Move the extend into the same block as the load
  ExtFedByLoad->moveAfter(LI);
  // CGP does not check if the zext would be speculatively executed when moved
  // to the same basic block as the load. Preserving its original location
  // would pessimize the debugging experience, as well as negatively impact
  // the quality of sample pgo. We don't want to use "line 0" as that has a
  // size cost in the line-table section and logically the zext can be seen as
  // part of the load. Therefore we conservatively reuse the same debug
  // location for the load and the zext.
  ExtFedByLoad->setDebugLoc(LI->getDebugLoc());
  ++NumExtsMoved;
  Inst = ExtFedByLoad;
  return true;
}

// Continue promoting SExts if known as considerable depending on targets.
if (ATPConsiderable &&
    performAddressTypePromotion(Inst, AllowPromotionWithoutCommonHeader,
                                HasPromoted, TPT, SpeculativelyMovedExts))
  return true;

TPT.rollback(LastKnownGood);
return false;
4869}

4871// Perform address type promotion if doing so is profitable.
4872// If AllowPromotionWithoutCommonHeader == false, we should find other sext
4873// instructions that sign extended the same initial value. However, if
4874// AllowPromotionWithoutCommonHeader == true, we expect promoting the
4875// extension is just profitable.
4876bool CodeGenPrepare::performAddressTypePromotion(
  Instruction *&Inst, bool AllowPromotionWithoutCommonHeader,
  bool HasPromoted, TypePromotionTransaction &TPT,
  SmallVectorImpl<Instruction *> &SpeculativelyMovedExts) {
bool Promoted = false;
SmallPtrSet<Instruction *, 1> UnhandledExts;
bool AllSeenFirst = true;
for (auto I : SpeculativelyMovedExts) {
  Value *HeadOfChain = I->getOperand(0);
  DenseMap<Value *, Instruction *>::iterator AlreadySeen =
      SeenChainsForSExt.find(HeadOfChain);
  // If there is an unhandled SExt which has the same header, try to promote
  // it as well.
  if (AlreadySeen != SeenChainsForSExt.end()) {
    if (AlreadySeen->second != nullptr)
      UnhandledExts.insert(AlreadySeen->second);
    AllSeenFirst = false;
  }
}

if (!AllSeenFirst || (AllowPromotionWithoutCommonHeader &&
                      SpeculativelyMovedExts.size() == 1)) {
  TPT.commit();
  if (HasPromoted)
    Promoted = true;
  for (auto I : SpeculativelyMovedExts) {
    Value *HeadOfChain = I->getOperand(0);
    SeenChainsForSExt[HeadOfChain] = nullptr;
    ValToSExtendedUses[HeadOfChain].push_back(I);
  }
  // Update Inst as promotion happen.
  Inst = SpeculativelyMovedExts.pop_back_val();
} else {
  // This is the first chain visited from the header, keep the current chain
  // as unhandled. Defer to promote this until we encounter another SExt
  // chain derived from the same header.
  for (auto I : SpeculativelyMovedExts) {
    Value *HeadOfChain = I->getOperand(0);
    SeenChainsForSExt[HeadOfChain] = Inst;
  }
  return false;
}

if (!AllSeenFirst && !UnhandledExts.empty())
  for (auto VisitedSExt : UnhandledExts) {
    if (RemovedInsts.count(VisitedSExt))
      continue;
    TypePromotionTransaction TPT(RemovedInsts);
    SmallVector<Instruction *, 1> Exts;
    SmallVector<Instruction *, 2> Chains;
    Exts.push_back(VisitedSExt);
    bool HasPromoted = tryToPromoteExts(TPT, Exts, Chains);
    TPT.commit();
    if (HasPromoted)
      Promoted = true;
    for (auto I : Chains) {
      Value *HeadOfChain = I->getOperand(0);
      // Mark this as handled.
      SeenChainsForSExt[HeadOfChain] = nullptr;
      ValToSExtendedUses[HeadOfChain].push_back(I);
    }
  }
return Promoted;
4939}

4941bool 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())(static_cast <bool> (InsertPt != UserBB->end()) ? void
 (0) : __assert_fail ("InsertPt != UserBB->end()", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 4999, __extension__ __PRETTY_FUNCTION__));
    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;
5011}

5013// Find loads whose uses only use some of the loaded value's bits.  Add an "and"
5014// just after the load if the target can fold this into one extload instruction,
5015// with the hope of eliminating some of the other later "and" instructions using
5016// the loaded value.  "and"s that are made trivially redundant by the insertion
5017// of the new "and" are removed by this function, while others (e.g. those whose
5018// path from the load goes through a phi) are left for isel to potentially
5019// remove.
5020//
5021// For example:
5022//
5023// b0:
5024//   x = load i32
5025//   ...
5026// b1:
5027//   y = and x, 0xff
5028//   z = use y
5029//
5030// becomes:
5031//
5032// b0:
5033//   x = load i32
5034//   x' = and x, 0xff
5035//   ...
5036// b1:
5037//   z = use x'
5038//
5039// whereas:
5040//
5041// b0:
5042//   x1 = load i32
5043//   ...
5044// b1:
5045//   x2 = load i32
5046//   ...
5047// b2:
5048//   x = phi x1, x2
5049//   y = and x, 0xff
5050//
5051// becomes (after a call to optimizeLoadExt for each load):
5052//
5053// b0:
5054//   x1 = load i32
5055//   x1' = and x1, 0xff
5056//   ...
5057// b1:
5058//   x2 = load i32
5059//   x2' = and x2, 0xff
5060//   ...
5061// b2:
5062//   x = phi x1', x2'
5063//   y = and x, 0xff
5064bool CodeGenPrepare::optimizeLoadExt(LoadInst *Load) {
if (!Load->isSimple() ||
    !(Load->getType()->isIntegerTy() || Load->getType()->isPointerTy()))
  return false;

// Skip loads we've already transformed.
if (Load->hasOneUse() &&
    InsertedInsts.count(cast<Instruction>(*Load->user_begin())))
  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 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 Instruction::Shl: {
    auto *ShlC = dyn_cast<ConstantInt>(I->getOperand(1));
    if (!ShlC)
      return false;
    uint64_t ShiftAmt = ShlC->getLimitedValue(BitWidth - 1);
    DemandBits.setLowBits(BitWidth - ShiftAmt);
    break;
  }

  case Instruction::Trunc: {
    EVT TruncVT = TLI->getValueType(*DL, I->getType());
    unsigned TruncBitWidth = TruncVT.getSizeInBits();
    DemandBits.setLowBits(TruncBitWidth);
    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 || !DemandBits.isMask(ActiveBits) ||
    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)));
// Mark this instruction as "inserted by CGP", so that other
// optimizations don't touch it.
InsertedInsts.insert(NewAnd);

// 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;
5189}

5191/// Check if V (an operand of a select instruction) is an expensive instruction
5192/// that is only used once.
5193static 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;
5199}

5201/// Returns true if a SelectInst should be turned into an explicit branch.
5202static bool isFormingBranchFromSelectProfitable(const TargetTransformInfo *TTI,
                                              const TargetLowering *TLI,
                                              SelectInst *SI) {
// If even a predictable select is cheap, then a branch can't be cheaper.
if (!TLI->isPredictableSelectExpensive())
  return false;

// FIXME: This should use the same heuristics as IfConversion to determine
// whether a select is better represented as a branch.

// If metadata tells us that the select condition is obviously predictable,
// then we want to replace the select with a branch.
uint64_t TrueWeight, FalseWeight;
if (SI->extractProfMetadata(TrueWeight, FalseWeight)) {
  uint64_t Max = std::max(TrueWeight, FalseWeight);
  uint64_t Sum = TrueWeight + FalseWeight;
  if (Sum != 0) {
    auto Probability = BranchProbability::getBranchProbability(Max, Sum);
    if (Probability > TLI->getPredictableBranchThreshold())
      return true;
  }
}

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;

// 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;
5240}

5242/// If \p isTrue is true, return the true value of \p SI, otherwise return
5243/// false value of \p SI. If the true/false value of \p SI is defined by any
5244/// select instructions in \p Selects, look through the defining select
5245/// instruction until the true/false value is not defined in \p Selects.
5246static Value *getTrueOrFalseValue(
  SelectInst *SI, bool isTrue,
  const SmallPtrSet<const Instruction *, 2> &Selects) {
Value *V;

for (SelectInst *DefSI = SI; DefSI != nullptr && Selects.count(DefSI);
     DefSI = dyn_cast<SelectInst>(V)) {
  assert(DefSI->getCondition() == SI->getCondition() &&(static_cast <bool> (DefSI->getCondition() == SI->
getCondition() && "The condition of DefSI does not match with SI"
) ? void (0) : __assert_fail ("DefSI->getCondition() == SI->getCondition() && \"The condition of DefSI does not match with SI\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5254, __extension__ __PRETTY_FUNCTION__))
         "The condition of DefSI does not match with SI")(static_cast <bool> (DefSI->getCondition() == SI->
getCondition() && "The condition of DefSI does not match with SI"
) ? void (0) : __assert_fail ("DefSI->getCondition() == SI->getCondition() && \"The condition of DefSI does not match with SI\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5254, __extension__ __PRETTY_FUNCTION__));
  V = (isTrue ? DefSI->getTrueValue() : DefSI->getFalseValue());
}
return V;
5258}

5260/// If we have a SelectInst that will likely profit from branch prediction,
5261/// turn it into a branch.
5262bool CodeGenPrepare::optimizeSelectInst(SelectInst *SI) {
// Find all consecutive select instructions that share the same condition.
SmallVector<SelectInst *, 2> ASI;
ASI.push_back(SI);
for (BasicBlock::iterator It = ++BasicBlock::iterator(SI);
     It != SI->getParent()->end(); ++It) {
  SelectInst *I = dyn_cast<SelectInst>(&*It);
  if (I && SI->getCondition() == I->getCondition()) {
    ASI.push_back(I);
  } else {
    break;
  }
}

SelectInst *LastSI = ASI.back();
// Increment the current iterator to skip all the rest of select instructions
// because they will be either "not lowered" or "all lowered" to branch.
CurInstIterator = std::next(LastSI->getIterator());

bool VectorCond = !SI->getCondition()->getType()->isIntegerTy(1);

// Can we convert the 'select' to CF ?
if (DisableSelectToBranch || OptSize || !TLI || VectorCond ||
    SI->getMetadata(LLVMContext::MD_unpredictable))
  return false;

TargetLowering::SelectSupportKind SelectKind;
if (VectorCond)
  SelectKind = TargetLowering::VectorMaskSelect;
else if (SI->getType()->isVectorTy())
  SelectKind = TargetLowering::ScalarCondVectorVal;
else
  SelectKind = TargetLowering::ScalarValSelect;

if (TLI->isSelectSupported(SelectKind) &&
    !isFormingBranchFromSelectProfitable(TTI, TLI, 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(LastSI));
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;
BranchInst *TrueBranch = nullptr;
BranchInst *FalseBranch = nullptr;

// Sink expensive instructions into the conditional blocks to avoid executing
// them speculatively.
for (SelectInst *SI : ASI) {
  if (sinkSelectOperand(TTI, SI->getTrueValue())) {
    if (TrueBlock == nullptr) {
      TrueBlock = BasicBlock::Create(SI->getContext(), "select.true.sink",
                                     EndBlock->getParent(), EndBlock);
      TrueBranch = BranchInst::Create(EndBlock, TrueBlock);
    }
    auto *TrueInst = cast<Instruction>(SI->getTrueValue());
    TrueInst->moveBefore(TrueBranch);
  }
  if (sinkSelectOperand(TTI, SI->getFalseValue())) {
    if (FalseBlock == nullptr) {
      FalseBlock = BasicBlock::Create(SI->getContext(), "select.false.sink",
                                      EndBlock->getParent(), EndBlock);
      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 &&(static_cast <bool> (TrueBlock == nullptr && "Unexpected basic block transform while optimizing select"
) ? void (0) : __assert_fail ("TrueBlock == nullptr && \"Unexpected basic block transform while optimizing select\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5367, __extension__ __PRETTY_FUNCTION__))
         "Unexpected basic block transform while optimizing select")(static_cast <bool> (TrueBlock == nullptr && "Unexpected basic block transform while optimizing select"
) ? void (0) : __assert_fail ("TrueBlock == nullptr && \"Unexpected basic block transform while optimizing select\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5367, __extension__ __PRETTY_FUNCTION__));

  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.
BasicBlock *TT, *FT;
if (TrueBlock == nullptr) {
  TT = EndBlock;
  FT = FalseBlock;
  TrueBlock = StartBlock;
} else if (FalseBlock == nullptr) {
  TT = TrueBlock;
  FT = EndBlock;
  FalseBlock = StartBlock;
} else {
  TT = TrueBlock;
  FT = FalseBlock;
}
IRBuilder<>(SI).CreateCondBr(SI->getCondition(), TT, FT, SI);

SmallPtrSet<const Instruction *, 2> INS;
INS.insert(ASI.begin(), ASI.end());
// Use reverse iterator because later select may use the value of the
// earlier select, and we need to propagate value through earlier select
// to get the PHI operand.
for (auto It = ASI.rbegin(); It != ASI.rend(); ++It) {
  SelectInst *SI = *It;
  // The select itself is replaced with a PHI Node.
  PHINode *PN = PHINode::Create(SI->getType(), 2, "", &EndBlock->front());
  PN->takeName(SI);
  PN->addIncoming(getTrueOrFalseValue(SI, true, INS), TrueBlock);
  PN->addIncoming(getTrueOrFalseValue(SI, false, INS), FalseBlock);

  SI->replaceAllUsesWith(PN);
  SI->eraseFromParent();
  INS.erase(SI);
  ++NumSelectsExpanded;
}

// Instruct OptimizeBlock to skip to the next block.
CurInstIterator = StartBlock->end();
return true;
5416}

5418static 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;
5428}

5430/// Some targets have expensive vector shifts if the lanes aren't all the same
5431/// (e.g. x86 only introduced "vpsllvd" and friends with AVX2). In these cases
5432/// it's often worth sinking a shufflevector splat down to its use so that
5433/// codegen can spot all lanes are identical.
5434bool 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())(static_cast <bool> (InsertPt != UserBB->end()) ? void
 (0) : __assert_fail ("InsertPt != UserBB->end()", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5466, __extension__ __PRETTY_FUNCTION__));
    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;
5483}

5485bool 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 (auto 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;
5526}


5529namespace {

5531/// \brief Helper class to promote a scalar operation to a vector one.
5532/// This class is used to move downward extractelement transition.
5533/// E.g.,
5534/// a = vector_op <2 x i32>
5535/// b = extractelement <2 x i32> a, i32 0
5536/// c = scalar_op b
5537/// store c
5538///
5539/// =>
5540/// a = vector_op <2 x i32>
5541/// c = vector_op a (equivalent to scalar_op on the related lane)
5542/// * d = extractelement <2 x i32> c, i32 0
5543/// * store d
5544/// Assuming both extractelement and store can be combine, we get rid of the
5545/// transition.
5546class 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 = nullptr;

/// \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) &&(static_cast <bool> (isa<ExtractElementInst>(Transition
) && "Other kind of transitions are not supported yet"
) ? void (0) : __assert_fail ("isa<ExtractElementInst>(Transition) && \"Other kind of transitions are not supported yet\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5582, __extension__ __PRETTY_FUNCTION__))
         "Other kind of transitions are not supported yet")(static_cast <bool> (isa<ExtractElementInst>(Transition
) && "Other kind of transitions are not supported yet"
) ? void (0) : __assert_fail ("isa<ExtractElementInst>(Transition) && \"Other kind of transitions are not supported yet\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5582, __extension__ __PRETTY_FUNCTION__));
  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) &&(static_cast <bool> (isa<ExtractElementInst>(Transition
) && "Other kind of transitions are not supported yet"
) ? void (0) : __assert_fail ("isa<ExtractElementInst>(Transition) && \"Other kind of transitions are not supported yet\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5591, __extension__ __PRETTY_FUNCTION__))
         "Other kind of transitions are not supported yet")(static_cast <bool> (isa<ExtractElementInst>(Transition
) && "Other kind of transitions are not supported yet"
) ? void (0) : __assert_fail ("isa<ExtractElementInst>(Transition) && \"Other kind of transitions are not supported yet\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5591, __extension__ __PRETTY_FUNCTION__));
  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: "do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Estimated cost of computation to be promoted:\nScalar: "
 << ScalarCost << "\nVector: " << VectorCost
 << '\n'; } } while (false)
               << ScalarCost << "\nVector: " << VectorCost << '\n')do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Estimated cost of computation to be promoted:\nScalar: "
 << ScalarCost << "\nVector: " << VectorCost
 << '\n'; } } while (false);
  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 = std::numeric_limits<unsigned>::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)::llvm::llvm_unreachable_internal(nullptr, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5718);
}

5721public:
VectorPromoteHelper(const DataLayout &DL, const TargetLowering &TLI,
                    const TargetTransformInfo &TTI, Instruction *Transition,
                    unsigned CombineCost)
    : DL(DL), TLI(TLI), TTI(TTI), Transition(Transition),
      StoreExtractCombineCost(CombineCost) {
  assert(Transition && "Do not know how to promote null")(static_cast <bool> (Transition && "Do not know how to promote null"
) ? void (0) : __assert_fail ("Transition && \"Do not know how to promote null\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5727, __extension__ __PRETTY_FUNCTION__));
}

/// \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")(static_cast <bool> (canCombine(ToBeCombined) &&
 "Unsupported instruction to combine") ? void (0) : __assert_fail
 ("canCombine(ToBeCombined) && \"Unsupported instruction to combine\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5776, __extension__ __PRETTY_FUNCTION__));
  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;
}
5800};

5802} // end anonymous namespace

5804void 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() &&(static_cast <bool> (ToBePromoted->getType() == Transition
->getType() && "The type of the result of the transition does not match "
 "the final type") ? void (0) : __assert_fail ("ToBePromoted->getType() == Transition->getType() && \"The type of the result of the transition does not match \" \"the final type\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5815, __extension__ __PRETTY_FUNCTION__))
       "The type of the result of the transition does not match "(static_cast <bool> (ToBePromoted->getType() == Transition
->getType() && "The type of the result of the transition does not match "
 "the final type") ? void (0) : __assert_fail ("ToBePromoted->getType() == Transition->getType() && \"The type of the result of the transition does not match \" \"the final type\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5815, __extension__ __PRETTY_FUNCTION__))
       "the final type")(static_cast <bool> (ToBePromoted->getType() == Transition
->getType() && "The type of the result of the transition does not match "
 "the final type") ? void (0) : __assert_fail ("ToBePromoted->getType() == Transition->getType() && \"The type of the result of the transition does not match \" \"the final type\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5815, __extension__ __PRETTY_FUNCTION__));
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 "::llvm::llvm_unreachable_internal("Did you modified shouldPromote and forgot to update "
 "this?", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5838)
                     "this?")::llvm::llvm_unreachable_internal("Did you modified shouldPromote and forgot to update "
 "this?", "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 5838);
  ToBePromoted->setOperand(U.getOperandNo(), NewVal);
}
Transition->moveAfter(ToBePromoted);
Transition->setOperand(getTransitionOriginalValueIdx(), ToBePromoted);
5843}

5845/// Some targets can do store(extractelement) with one instruction.
5846/// Try to push the extractelement towards the stores when the target
5847/// has this feature and this is profitable.
5848bool CodeGenPrepare::optimizeExtractElementInst(Instruction *Inst) {
unsigned CombineCost = std::numeric_limits<unsigned>::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')do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Found an interesting transition: "
 << *Inst << '\n'; } } while (false);
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')do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Use: " << *ToBePromoted
 << '\n'; } } while (false);

  if (ToBePromoted->getParent() != Parent) {
    DEBUG(dbgs() << "Instruction to promote is in a different block ("do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Instruction to promote is in a different block ("
 << ToBePromoted->getParent()->getName() <<
 ") than the transition (" << Parent->getName() <<
 ").\n"; } } while (false)
                 << ToBePromoted->getParent()->getName()do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Instruction to promote is in a different block ("
 << ToBePromoted->getParent()->getName() <<
 ") than the transition (" << Parent->getName() <<
 ").\n"; } } while (false)
                 << ") than the transition (" << Parent->getName() << ").\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Instruction to promote is in a different block ("
 << ToBePromoted->getParent()->getName() <<
 ") than the transition (" << Parent->getName() <<
 ").\n"; } } while (false);
    return false;
  }

  if (VPH.canCombine(ToBePromoted)) {
    DEBUG(dbgs() << "Assume " << *Inst << '\n'do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Assume " << *Inst
 << '\n' << "will be combined with: " << *ToBePromoted
 << '\n'; } } while (false)
                 << "will be combined with: " << *ToBePromoted << '\n')do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Assume " << *Inst
 << '\n' << "will be combined with: " << *ToBePromoted
 << '\n'; } } while (false);
    VPH.recordCombineInstruction(ToBePromoted);
    bool Changed = VPH.promote();
    NumStoreExtractExposed += Changed;
    return Changed;
  }

  DEBUG(dbgs() << "Try promoting.\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Try promoting.\n"; } }
 while (false);
  if (!VPH.canPromote(ToBePromoted) || !VPH.shouldPromote(ToBePromoted))
    return false;

  DEBUG(dbgs() << "Promoting is possible... Enqueue for promotion!\n")do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Promoting is possible... Enqueue for promotion!\n"
; } } while (false);

  VPH.enqueueForPromotion(ToBePromoted);
  Inst = ToBePromoted;
}
return false;
5898}

5900/// For the instruction sequence of store below, F and I values
5901/// are bundled together as an i64 value before being stored into memory.
5902/// Sometimes it is more efficent to generate separate stores for F and I,
5903/// which can remove the bitwise instructions or sink them to colder places.
5904///
5905///   (store (or (zext (bitcast F to i32) to i64),
5906///              (shl (zext I to i64), 32)), addr)  -->
5907///   (store F, addr) and (store I, addr+4)
5908///
5909/// Similarly, splitting for other merged store can also be beneficial, like:
5910/// For pair of {i32, i32}, i64 store --> two i32 stores.
5911/// For pair of {i32, i16}, i64 store --> two i32 stores.
5912/// For pair of {i16, i16}, i32 store --> two i16 stores.
5913/// For pair of {i16, i8},  i32 store --> two i16 stores.
5914/// For pair of {i8, i8},   i16 store --> two i8 stores.
5915///
5916/// We allow each target to determine specifically which kind of splitting is
5917/// supported.
5918///
5919/// The store patterns are commonly seen from the simple code snippet below
5920/// if only std::make_pair(...) is sroa transformed before inlined into hoo.
5921///   void goo(const std::pair<int, float> &);
5922///   hoo() {
5923///     ...
5924///     goo(std::make_pair(tmp, ftmp));
5925///     ...
5926///   }
5927///
5928/// Although we already have similar splitting in DAG Combine, we duplicate
5929/// it in CodeGenPrepare to catch the case in which pattern is across
5930/// multiple BBs. The logic in DAG Combine is kept to catch case generated
5931/// during code expansion.
5932static bool splitMergedValStore(StoreInst &SI, const DataLayout &DL,
                              const TargetLowering &TLI) {
// Handle simple but common cases only.
Type *StoreType = SI.getValueOperand()->getType();
if (DL.getTypeStoreSizeInBits(StoreType) != DL.getTypeSizeInBits(StoreType) ||
    DL.getTypeSizeInBits(StoreType) == 0)
  return false;

unsigned HalfValBitSize = DL.getTypeSizeInBits(StoreType) / 2;
Type *SplitStoreType = Type::getIntNTy(SI.getContext(), HalfValBitSize);
if (DL.getTypeStoreSizeInBits(SplitStoreType) !=
    DL.getTypeSizeInBits(SplitStoreType))
  return false;

// Match the following patterns:
// (store (or (zext LValue to i64),
//            (shl (zext HValue to i64), 32)), HalfValBitSize)
//  or
// (store (or (shl (zext HValue to i64), 32)), HalfValBitSize)
//            (zext LValue to i64),
// Expect both operands of OR and the first operand of SHL have only
// one use.
Value *LValue, *HValue;
if (!match(SI.getValueOperand(),
           m_c_Or(m_OneUse(m_ZExt(m_Value(LValue))),
                  m_OneUse(m_Shl(m_OneUse(m_ZExt(m_Value(HValue))),
                                 m_SpecificInt(HalfValBitSize))))))
  return false;

// Check LValue and HValue are int with size less or equal than 32.
if (!LValue->getType()->isIntegerTy() ||
    DL.getTypeSizeInBits(LValue->getType()) > HalfValBitSize ||
    !HValue->getType()->isIntegerTy() ||
    DL.getTypeSizeInBits(HValue->getType()) > HalfValBitSize)
  return false;

// If LValue/HValue is a bitcast instruction, use the EVT before bitcast
// as the input of target query.
auto *LBC = dyn_cast<BitCastInst>(LValue);
auto *HBC = dyn_cast<BitCastInst>(HValue);
EVT LowTy = LBC ? EVT::getEVT(LBC->getOperand(0)->getType())
                : EVT::getEVT(LValue->getType());
EVT HighTy = HBC ? EVT::getEVT(HBC->getOperand(0)->getType())
                 : EVT::getEVT(HValue->getType());
if (!ForceSplitStore && !TLI.isMultiStoresCheaperThanBitsMerge(LowTy, HighTy))
  return false;

// Start to split store.
IRBuilder<> Builder(SI.getContext());
Builder.SetInsertPoint(&SI);

// If LValue/HValue is a bitcast in another BB, create a new one in current
// BB so it may be merged with the splitted stores by dag combiner.
if (LBC && LBC->getParent() != SI.getParent())
  LValue = Builder.CreateBitCast(LBC->getOperand(0), LBC->getType());
if (HBC && HBC->getParent() != SI.getParent())
  HValue = Builder.CreateBitCast(HBC->getOperand(0), HBC->getType());

auto CreateSplitStore = [&](Value *V, bool Upper) {
  V = Builder.CreateZExtOrBitCast(V, SplitStoreType);
  Value *Addr = Builder.CreateBitCast(
      SI.getOperand(1),
      SplitStoreType->getPointerTo(SI.getPointerAddressSpace()));
  if (Upper)
    Addr = Builder.CreateGEP(
        SplitStoreType, Addr,
        ConstantInt::get(Type::getInt32Ty(SI.getContext()), 1));
  Builder.CreateAlignedStore(
      V, Addr, Upper ? SI.getAlignment() / 2 : SI.getAlignment());
};

CreateSplitStore(LValue, false);
CreateSplitStore(HValue, true);

// Delete the old store.
SI.eraseFromParent();
return true;
6009}

6011// Return true if the GEP has two operands, the first operand is of a sequential
6012// type, and the second operand is a constant.
6013static bool GEPSequentialConstIndexed(GetElementPtrInst *GEP) {
gep_type_iterator I = gep_type_begin(*GEP);
return GEP->getNumOperands() == 2 &&
    I.isSequential() &&
    isa<ConstantInt>(GEP->getOperand(1));
6018}

6020// Try unmerging GEPs to reduce liveness interference (register pressure) across
6021// IndirectBr edges. Since IndirectBr edges tend to touch on many blocks,
6022// reducing liveness interference across those edges benefits global register
6023// allocation. Currently handles only certain cases.
6024//
6025// For example, unmerge %GEPI and %UGEPI as below.
6026//
6027// ---------- BEFORE ----------
6028// SrcBlock:
6029//   ...
6030//   %GEPIOp = ...
6031//   ...
6032//   %GEPI = gep %GEPIOp, Idx
6033//   ...
6034//   indirectbr ... [ label %DstB0, label %DstB1, ... label %DstBi ... ]
6035//   (* %GEPI is alive on the indirectbr edges due to other uses ahead)
6036//   (* %GEPIOp is alive on the indirectbr edges only because of it's used by
6037//   %UGEPI)
6038//
6039// DstB0: ... (there may be a gep similar to %UGEPI to be unmerged)
6040// DstB1: ... (there may be a gep similar to %UGEPI to be unmerged)
6041// ...
6042//
6043// DstBi:
6044//   ...
6045//   %UGEPI = gep %GEPIOp, UIdx
6046// ...
6047// ---------------------------
6048//
6049// ---------- AFTER ----------
6050// SrcBlock:
6051//   ... (same as above)
6052//    (* %GEPI is still alive on the indirectbr edges)
6053//    (* %GEPIOp is no longer alive on the indirectbr edges as a result of the
6054//    unmerging)
6055// ...
6056//
6057// DstBi:
6058//   ...
6059//   %UGEPI = gep %GEPI, (UIdx-Idx)
6060//   ...
6061// ---------------------------
6062//
6063// The register pressure on the IndirectBr edges is reduced because %GEPIOp is
6064// no longer alive on them.
6065//
6066// We try to unmerge GEPs here in CodGenPrepare, as opposed to limiting merging
6067// of GEPs in the first place in InstCombiner::visitGetElementPtrInst() so as
6068// not to disable further simplications and optimizations as a result of GEP
6069// merging.
6070//
6071// Note this unmerging may increase the length of the data flow critical path
6072// (the path from %GEPIOp to %UGEPI would go through %GEPI), which is a tradeoff
6073// between the register pressure and the length of data-flow critical
6074// path. Restricting this to the uncommon IndirectBr case would minimize the
6075// impact of potentially longer critical path, if any, and the impact on compile
6076// time.
6077static bool tryUnmergingGEPsAcrossIndirectBr(GetElementPtrInst *GEPI,
                                           const TargetTransformInfo *TTI) {
BasicBlock *SrcBlock = GEPI->getParent();
// Check that SrcBlock ends with an IndirectBr. If not, give up. The common
// (non-IndirectBr) cases exit early here.
if (!isa<IndirectBrInst>(SrcBlock->getTerminator()))
  return false;
// Check that GEPI is a simple gep with a single constant index.
if (!GEPSequentialConstIndexed(GEPI))
  return false;
ConstantInt *GEPIIdx = cast<ConstantInt>(GEPI->getOperand(1));
// Check that GEPI is a cheap one.
if (TTI->getIntImmCost(GEPIIdx->getValue(), GEPIIdx->getType())
    > TargetTransformInfo::TCC_Basic)
  return false;
Value *GEPIOp = GEPI->getOperand(0);
// Check that GEPIOp is an instruction that's also defined in SrcBlock.
if (!isa<Instruction>(GEPIOp))
  return false;
auto *GEPIOpI = cast<Instruction>(GEPIOp);
if (GEPIOpI->getParent() != SrcBlock)
  return false;
// Check that GEP is used outside the block, meaning it's alive on the
// IndirectBr edge(s).
if (find_if(GEPI->users(), [&](User *Usr) {
      if (auto *I = dyn_cast<Instruction>(Usr)) {
        if (I->getParent() != SrcBlock) {
          return true;
        }
      }
      return false;
    }) == GEPI->users().end())
  return false;
// The second elements of the GEP chains to be unmerged.
std::vector<GetElementPtrInst *> UGEPIs;
// Check each user of GEPIOp to check if unmerging would make GEPIOp not alive
// on IndirectBr edges.
for (User *Usr : GEPIOp->users()) {
  if (Usr == GEPI) continue;
  // Check if Usr is an Instruction. If not, give up.
  if (!isa<Instruction>(Usr))
    return false;
  auto *UI = cast<Instruction>(Usr);
  // Check if Usr in the same block as GEPIOp, which is fine, skip.
  if (UI->getParent() == SrcBlock)
    continue;
  // Check if Usr is a GEP. If not, give up.
  if (!isa<GetElementPtrInst>(Usr))
    return false;
  auto *UGEPI = cast<GetElementPtrInst>(Usr);
  // Check if UGEPI is a simple gep with a single constant index and GEPIOp is
  // the pointer operand to it. If so, record it in the vector. If not, give
  // up.
  if (!GEPSequentialConstIndexed(UGEPI))
    return false;
  if (UGEPI->getOperand(0) != GEPIOp)
    return false;
  if (GEPIIdx->getType() !=
      cast<ConstantInt>(UGEPI->getOperand(1))->getType())
    return false;
  ConstantInt *UGEPIIdx = cast<ConstantInt>(UGEPI->getOperand(1));
  if (TTI->getIntImmCost(UGEPIIdx->getValue(), UGEPIIdx->getType())
      > TargetTransformInfo::TCC_Basic)
    return false;
  UGEPIs.push_back(UGEPI);
}
if (UGEPIs.size() == 0)
  return false;
// Check the materializing cost of (Uidx-Idx).
for (GetElementPtrInst *UGEPI : UGEPIs) {
  ConstantInt *UGEPIIdx = cast<ConstantInt>(UGEPI->getOperand(1));
  APInt NewIdx = UGEPIIdx->getValue() - GEPIIdx->getValue();
  unsigned ImmCost = TTI->getIntImmCost(NewIdx, GEPIIdx->getType());
  if (ImmCost > TargetTransformInfo::TCC_Basic)
    return false;
}
// Now unmerge between GEPI and UGEPIs.
for (GetElementPtrInst *UGEPI : UGEPIs) {
  UGEPI->setOperand(0, GEPI);
  ConstantInt *UGEPIIdx = cast<ConstantInt>(UGEPI->getOperand(1));
  Constant *NewUGEPIIdx =
      ConstantInt::get(GEPIIdx->getType(),
                       UGEPIIdx->getValue() - GEPIIdx->getValue());
  UGEPI->setOperand(1, NewUGEPIIdx);
  // If GEPI is not inbounds but UGEPI is inbounds, change UGEPI to not
  // inbounds to avoid UB.
  if (!GEPI->isInBounds()) {
    UGEPI->setIsInBounds(false);
  }
}
// After unmerging, verify that GEPIOp is actually only used in SrcBlock (not
// alive on IndirectBr edges).
assert(find_if(GEPIOp->users(), [&](User *Usr) {(static_cast <bool> (find_if(GEPIOp->users(), [&
](User *Usr) { return cast<Instruction>(Usr)->getParent
() != SrcBlock; }) == GEPIOp->users().end() && "GEPIOp is used outside SrcBlock"
) ? void (0) : __assert_fail ("find_if(GEPIOp->users(), [&](User *Usr) { return cast<Instruction>(Usr)->getParent() != SrcBlock; }) == GEPIOp->users().end() && \"GEPIOp is used outside SrcBlock\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 6171, __extension__ __PRETTY_FUNCTION__))
      return cast<Instruction>(Usr)->getParent() != SrcBlock;(static_cast <bool> (find_if(GEPIOp->users(), [&
](User *Usr) { return cast<Instruction>(Usr)->getParent
() != SrcBlock; }) == GEPIOp->users().end() && "GEPIOp is used outside SrcBlock"
) ? void (0) : __assert_fail ("find_if(GEPIOp->users(), [&](User *Usr) { return cast<Instruction>(Usr)->getParent() != SrcBlock; }) == GEPIOp->users().end() && \"GEPIOp is used outside SrcBlock\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 6171, __extension__ __PRETTY_FUNCTION__))
    }) == GEPIOp->users().end() && "GEPIOp is used outside SrcBlock")(static_cast <bool> (find_if(GEPIOp->users(), [&
](User *Usr) { return cast<Instruction>(Usr)->getParent
() != SrcBlock; }) == GEPIOp->users().end() && "GEPIOp is used outside SrcBlock"
) ? void (0) : __assert_fail ("find_if(GEPIOp->users(), [&](User *Usr) { return cast<Instruction>(Usr)->getParent() != SrcBlock; }) == GEPIOp->users().end() && \"GEPIOp is used outside SrcBlock\""
, "/build/llvm-toolchain-snapshot-7~svn326246/lib/CodeGen/CodeGenPrepare.cpp"
, 6171, __extension__ __PRETTY_FUNCTION__));
return true;
6173}

6175bool 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})) {
    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 = optimizeExt(I);
      return MadeChange | optimizeExtUses(I);
    }
  }
  return false;
}

if (CmpInst *CI = dyn_cast<CmpInst>(I))
  if (!TLI || !TLI->hasMultipleConditionRegisters())
    return OptimizeCmpExpression(CI, TLI);

if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
  LI->setMetadata(LLVMContext::MD_invariant_group, nullptr);
  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)) {
  if (TLI && splitMergedValStore(*SI, *DL, *TLI))
    return true;
  SI->setMetadata(LLVMContext::MD_invariant_group, nullptr);
  if (TLI) {
    unsigned AS = SI->getPointerAddressSpace();
    return optimizeMemoryInst(I, SI->getOperand(1),
                              SI->getOperand(0)->getType(), AS);
  }
  return false;
}

if (AtomicRMWInst *RMW = dyn_cast<AtomicRMWInst>(I)) {
    unsigned AS = RMW->getPointerAddressSpace();
    return optimizeMemoryInst(I, RMW->getPointerOperand(),
                              RMW->getType(), AS);
}

if (AtomicCmpXchgInst *CmpX = dyn_cast<AtomicCmpXchgInst>(I)) {
    unsigned AS = CmpX->getPointerAddressSpace();
    return optimizeMemoryInst(I, CmpX->getPointerOperand(),
                              CmpX->getCompareOperand()->getType(), AS);
}

BinaryOperator *BinOp = dyn_cast<BinaryOperator>(I);

if (BinOp && (BinOp->getOpcode() == Instruction::And) &&
    EnableAndCmpSinking && TLI)
  return sinkAndCmp0Expression(BinOp, *TLI, InsertedInsts);

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;
  }
  if (tryUnmergingGEPsAcrossIndirectBr(GEPI, TTI)) {
    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;
6310}

6312/// Given an OR instruction, check to see if this is a bitreverse
6313/// idiom. If so, insert the new intrinsic and return true.
6314static bool makeBitReverse(Instruction &I, const DataLayout &DL,
                         const TargetLowering &TLI) {
if (!I.getType()->isIntegerTy() ||
    !TLI.isOperationLegalOrCustom(ISD::BITREVERSE,
                                  TLI.getValueType(DL, I.getType(), true)))
  return false;

SmallVector<Instruction*, 4> Insts;
if (!recognizeBSwapOrBitReverseIdiom(&I, false, true, Insts))
  return false;
Instruction *LastInst = Insts.back();
I.replaceAllUsesWith(LastInst);
RecursivelyDeleteTriviallyDeadInstructions(&I);
return true;
6328}

6330// In this pass we look for GEP and cast instructions that are used
6331// across basic blocks and rewrite them to improve basic-block-at-a-time
6332// selection.
6333bool 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;
}

bool MadeBitReverse = true;
while (TLI && MadeBitReverse) {
  MadeBitReverse = false;
  for (auto &I : reverse(BB)) {
    if (makeBitReverse(I, *DL, *TLI)) {
      MadeBitReverse = MadeChange = true;
      ModifiedDT = true;
      break;
    }
  }
}
MadeChange |= dupRetToEnableTailCallOpts(&BB);

return MadeChange;
6358}

6360// llvm.dbg.value is far away from the value then iSel may not be able
6361// handle it properly. iSel will drop llvm.dbg.value if it can not
6362// find a node corresponding to the value.
6363bool 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
    // intrinsics 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)do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Moving Debug Value before :\n"
 << *DVI << ' ' << *VI; } } while (false);
      DVI->removeFromParent();
      if (isa<PHINode>(VI))
        DVI->insertBefore(&*VI->getParent()->getFirstInsertionPt());
      else
        DVI->insertAfter(VI);
      MadeChange = true;
      ++NumDbgValueMoved;
    }
  }
}
return MadeChange;
6398}

6400/// \brief Scale down both weights to fit into uint32_t.
6401static void scaleWeights(uint64_t &NewTrue, uint64_t &NewFalse) {
uint64_t NewMax = (NewTrue > NewFalse) ? NewTrue : NewFalse;
uint32_t Scale = (NewMax / std::numeric_limits<uint32_t>::max()) + 1;
NewTrue = NewTrue / Scale;
NewFalse = NewFalse / Scale;
6406}

6408/// \brief Some targets prefer to split a conditional branch like:
6409/// \code
6410///   %0 = icmp ne i32 %a, 0
6411///   %1 = icmp ne i32 %b, 0
6412///   %or.cond = or i1 %0, %1
6413///   br i1 %or.cond, label %TrueBB, label %FalseBB
6414/// \endcode
6415/// into multiple branch instructions like:
6416/// \code
6417///   bb1:
6418///     %0 = icmp ne i32 %a, 0
6419///     br i1 %0, label %TrueBB, label %bb2
6420///   bb2:
6421///     %1 = icmp ne i32 %b, 0
6422///     br i1 %1, label %TrueBB, label %FalseBB
6423/// \endcode
6424/// This usually allows instruction selection to do even further optimizations
6425/// and combine the compare with the branch instruction. Currently this is
6426/// applied for targets which have "cheap" jump instructions.
6427///
6428/// FIXME: Remove the (equivalent?) implementation in SelectionDAG.
6429///
6430bool 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())do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "Before branch condition splitting\n"
; BB.dump(); } } while (false);

  // Create a new BB.
  auto TmpBB =
      BasicBlock::Create(BB.getContext(), BB.getName() + ".cond.split",
                         BB.getParent(), BB.getNextNode());

  // 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 successor'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 perform 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 (PHINode &PN : TBB->phis()) {
    int i;
    while ((i = PN.getBasicBlockIndex(&BB)) >= 0)
      PN.setIncomingBlock(i, TmpBB);
  }

  // Add another incoming edge form the new BB.
  for (PHINode &PN : FBB->phis()) {
    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 (Br1->extractProfMetadata(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 (Br1->extractProfMetadata(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();do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "After branch condition splitting\n"
; BB.dump(); TmpBB->dump(); } } while (false)
        TmpBB->dump())do { if (::llvm::DebugFlag && ::llvm::isCurrentDebugType
("codegenprepare")) { dbgs() << "After branch condition splitting\n"
; BB.dump(); TmpBB->dump(); } } while (false);
}
return MadeChange;
6597}