//
//===----------------------------------------------------------------------===//
-#define DEBUG_TYPE "codegenprepare"
#include "llvm/CodeGen/Passes.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/Statistic.h"
-#include "llvm/ADT/ValueMap.h"
#include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/IR/CallSite.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
+#include "llvm/IR/GetElementPtrTypeIterator.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InlineAsm.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/MDBuilder.h"
+#include "llvm/IR/PatternMatch.h"
+#include "llvm/IR/Statepoint.h"
+#include "llvm/IR/ValueHandle.h"
+#include "llvm/IR/ValueMap.h"
#include "llvm/Pass.h"
-#include "llvm/Support/CallSite.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
-#include "llvm/Support/GetElementPtrTypeIterator.h"
-#include "llvm/Support/PatternMatch.h"
-#include "llvm/Support/ValueHandle.h"
#include "llvm/Support/raw_ostream.h"
-#include "llvm/Target/TargetLibraryInfo.h"
#include "llvm/Target/TargetLowering.h"
+#include "llvm/Target/TargetSubtargetInfo.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/BuildLibCalls.h"
#include "llvm/Transforms/Utils/BypassSlowDivision.h"
#include "llvm/Transforms/Utils/Local.h"
+#include "llvm/Transforms/Utils/SimplifyLibCalls.h"
using namespace llvm;
using namespace llvm::PatternMatch;
+#define DEBUG_TYPE "codegenprepare"
+
STATISTIC(NumBlocksElim, "Number of blocks eliminated");
STATISTIC(NumPHIsElim, "Number of trivial PHIs eliminated");
STATISTIC(NumGEPsElim, "Number of GEPs converted to casts");
STATISTIC(NumRetsDup, "Number of return instructions duplicated");
STATISTIC(NumDbgValueMoved, "Number of debug value instructions moved");
STATISTIC(NumSelectsExpanded, "Number of selects turned into branches");
+STATISTIC(NumAndCmpsMoved, "Number of and/cmp's pushed into branches");
+STATISTIC(NumStoreExtractExposed, "Number of store(extractelement) exposed");
static cl::opt<bool> DisableBranchOpts(
"disable-cgp-branch-opts", cl::Hidden, cl::init(false),
cl::desc("Disable branch optimizations in CodeGenPrepare"));
+static cl::opt<bool>
+ DisableGCOpts("disable-cgp-gc-opts", cl::Hidden, cl::init(false),
+ cl::desc("Disable GC optimizations in CodeGenPrepare"));
+
static cl::opt<bool> DisableSelectToBranch(
"disable-cgp-select2branch", cl::Hidden, cl::init(false),
cl::desc("Disable select to branch conversion."));
+static cl::opt<bool> AddrSinkUsingGEPs(
+ "addr-sink-using-gep", cl::Hidden, cl::init(false),
+ cl::desc("Address sinking in CGP using GEPs."));
+
+static cl::opt<bool> EnableAndCmpSinking(
+ "enable-andcmp-sinking", cl::Hidden, cl::init(true),
+ cl::desc("Enable sinkinig and/cmp into branches."));
+
+static cl::opt<bool> DisableStoreExtract(
+ "disable-cgp-store-extract", cl::Hidden, cl::init(false),
+ cl::desc("Disable store(extract) optimizations in CodeGenPrepare"));
+
+static cl::opt<bool> StressStoreExtract(
+ "stress-cgp-store-extract", cl::Hidden, cl::init(false),
+ cl::desc("Stress test store(extract) optimizations in CodeGenPrepare"));
+
+static cl::opt<bool> DisableExtLdPromotion(
+ "disable-cgp-ext-ld-promotion", cl::Hidden, cl::init(false),
+ cl::desc("Disable ext(promotable(ld)) -> promoted(ext(ld)) optimization in "
+ "CodeGenPrepare"));
+
+static cl::opt<bool> StressExtLdPromotion(
+ "stress-cgp-ext-ld-promotion", cl::Hidden, cl::init(false),
+ cl::desc("Stress test ext(promotable(ld)) -> promoted(ext(ld)) "
+ "optimization in CodeGenPrepare"));
+
namespace {
typedef SmallPtrSet<Instruction *, 16> SetOfInstrs;
-typedef DenseMap<Instruction *, Type *> InstrToOrigTy;
+struct TypeIsSExt {
+ Type *Ty;
+ bool IsSExt;
+ TypeIsSExt(Type *Ty, bool IsSExt) : Ty(Ty), IsSExt(IsSExt) {}
+};
+typedef DenseMap<Instruction *, TypeIsSExt> InstrToOrigTy;
+class TypePromotionTransaction;
class CodeGenPrepare : public FunctionPass {
/// TLI - Keep a pointer of a TargetLowering to consult for determining
/// transformation profitability.
const TargetMachine *TM;
const TargetLowering *TLI;
+ const TargetTransformInfo *TTI;
const TargetLibraryInfo *TLInfo;
DominatorTree *DT;
public:
static char ID; // Pass identification, replacement for typeid
- explicit CodeGenPrepare(const TargetMachine *TM = 0)
- : FunctionPass(ID), TM(TM), TLI(0) {
+ explicit CodeGenPrepare(const TargetMachine *TM = nullptr)
+ : FunctionPass(ID), TM(TM), TLI(nullptr), TTI(nullptr) {
initializeCodeGenPreparePass(*PassRegistry::getPassRegistry());
}
- bool runOnFunction(Function &F);
+ bool runOnFunction(Function &F) override;
- const char *getPassName() const { return "CodeGen Prepare"; }
+ const char *getPassName() const override { return "CodeGen Prepare"; }
- virtual void getAnalysisUsage(AnalysisUsage &AU) const {
+ void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addPreserved<DominatorTreeWrapperPass>();
- AU.addRequired<TargetLibraryInfo>();
+ AU.addRequired<TargetLibraryInfoWrapperPass>();
+ AU.addRequired<TargetTransformInfoWrapperPass>();
}
private:
bool EliminateMostlyEmptyBlocks(Function &F);
bool CanMergeBlocks(const BasicBlock *BB, const BasicBlock *DestBB) const;
void EliminateMostlyEmptyBlock(BasicBlock *BB);
- bool OptimizeBlock(BasicBlock &BB);
- bool OptimizeInst(Instruction *I);
+ bool OptimizeBlock(BasicBlock &BB, bool& ModifiedDT);
+ bool OptimizeInst(Instruction *I, bool& ModifiedDT);
bool OptimizeMemoryInst(Instruction *I, Value *Addr, Type *AccessTy);
bool OptimizeInlineAsmInst(CallInst *CS);
- bool OptimizeCallInst(CallInst *CI);
- bool MoveExtToFormExtLoad(Instruction *I);
+ bool OptimizeCallInst(CallInst *CI, bool& ModifiedDT);
+ bool MoveExtToFormExtLoad(Instruction *&I);
bool OptimizeExtUses(Instruction *I);
bool OptimizeSelectInst(SelectInst *SI);
bool OptimizeShuffleVectorInst(ShuffleVectorInst *SI);
+ bool OptimizeExtractElementInst(Instruction *Inst);
bool DupRetToEnableTailCallOpts(BasicBlock *BB);
bool PlaceDbgValues(Function &F);
+ bool sinkAndCmp(Function &F);
+ bool ExtLdPromotion(TypePromotionTransaction &TPT, LoadInst *&LI,
+ Instruction *&Inst,
+ const SmallVectorImpl<Instruction *> &Exts,
+ unsigned CreatedInst);
+ bool splitBranchCondition(Function &F);
+ bool simplifyOffsetableRelocate(Instruction &I);
};
}
char CodeGenPrepare::ID = 0;
-static void *initializeCodeGenPreparePassOnce(PassRegistry &Registry) {
- initializeTargetLibraryInfoPass(Registry);
- PassInfo *PI = new PassInfo(
- "Optimize for code generation", "codegenprepare", &CodeGenPrepare::ID,
- PassInfo::NormalCtor_t(callDefaultCtor<CodeGenPrepare>), false, false,
- PassInfo::TargetMachineCtor_t(callTargetMachineCtor<CodeGenPrepare>));
- Registry.registerPass(*PI, true);
- return PI;
-}
-
-void llvm::initializeCodeGenPreparePass(PassRegistry &Registry) {
- CALL_ONCE_INITIALIZATION(initializeCodeGenPreparePassOnce)
-}
+INITIALIZE_TM_PASS(CodeGenPrepare, "codegenprepare",
+ "Optimize for code generation", false, false)
FunctionPass *llvm::createCodeGenPreparePass(const TargetMachine *TM) {
return new CodeGenPrepare(TM);
}
bool CodeGenPrepare::runOnFunction(Function &F) {
+ if (skipOptnoneFunction(F))
+ return false;
+
bool EverMadeChange = false;
// Clear per function information.
InsertedTruncsSet.clear();
PromotedInsts.clear();
ModifiedDT = false;
- if (TM) TLI = TM->getTargetLowering();
- TLInfo = &getAnalysis<TargetLibraryInfo>();
+ if (TM)
+ TLI = TM->getSubtargetImpl(F)->getTargetLowering();
+ TLInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
+ TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
DominatorTreeWrapperPass *DTWP =
getAnalysisIfAvailable<DominatorTreeWrapperPass>();
- DT = DTWP ? &DTWP->getDomTree() : 0;
- OptSize = F.getAttributes().hasAttribute(AttributeSet::FunctionIndex,
- Attribute::OptimizeForSize);
+ DT = DTWP ? &DTWP->getDomTree() : nullptr;
+ OptSize = F.hasFnAttribute(Attribute::OptimizeForSize);
/// This optimization identifies DIV instructions that can be
/// profitably bypassed and carried out with a shorter, faster divide.
// find a node corresponding to the value.
EverMadeChange |= PlaceDbgValues(F);
+ // If there is a mask, compare against zero, and branch that can be combined
+ // into a single target instruction, push the mask and compare into branch
+ // users. Do this before OptimizeBlock -> OptimizeInst ->
+ // OptimizeCmpExpression, which perturbs the pattern being searched for.
+ if (!DisableBranchOpts) {
+ EverMadeChange |= sinkAndCmp(F);
+ EverMadeChange |= splitBranchCondition(F);
+ }
+
bool MadeChange = true;
while (MadeChange) {
MadeChange = false;
for (Function::iterator I = F.begin(); I != F.end(); ) {
BasicBlock *BB = I++;
- MadeChange |= OptimizeBlock(*BB);
+ bool ModifiedDTOnIteration = false;
+ MadeChange |= OptimizeBlock(*BB, ModifiedDTOnIteration);
+
+ // Restart BB iteration if the dominator tree of the Function was changed
+ ModifiedDT |= ModifiedDTOnIteration;
+ if (ModifiedDTOnIteration)
+ break;
}
EverMadeChange |= MadeChange;
}
if (!DisableBranchOpts) {
MadeChange = false;
SmallPtrSet<BasicBlock*, 8> WorkList;
- for (Function::iterator BB = F.begin(), E = F.end(); BB != E; ++BB) {
- SmallVector<BasicBlock*, 2> Successors(succ_begin(BB), succ_end(BB));
- MadeChange |= ConstantFoldTerminator(BB, true);
+ 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
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);
+ }
+
if (ModifiedDT && DT)
DT->recalculate(F);
bool CodeGenPrepare::EliminateFallThrough(Function &F) {
bool Changed = false;
// Scan all of the blocks in the function, except for the entry block.
- for (Function::iterator I = llvm::next(F.begin()), E = F.end(); I != E; ) {
+ 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.
// 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, this);
+ MergeBasicBlockIntoOnlyPred(BB, DT);
if (isEntry && BB != &BB->getParent()->getEntryBlock())
BB->moveBefore(&BB->getParent()->getEntryBlock());
bool CodeGenPrepare::EliminateMostlyEmptyBlocks(Function &F) {
bool MadeChange = false;
// Note that this intentionally skips the entry block.
- for (Function::iterator I = llvm::next(F.begin()), E = F.end(); I != E; ) {
+ for (Function::iterator I = std::next(F.begin()), E = F.end(); I != E;) {
BasicBlock *BB = I++;
// If this block doesn't end with an uncond branch, ignore it.
// don't mess around with them.
BasicBlock::const_iterator BBI = BB->begin();
while (const PHINode *PN = dyn_cast<PHINode>(BBI++)) {
- for (Value::const_use_iterator UI = PN->use_begin(), E = PN->use_end();
- UI != E; ++UI) {
- const Instruction *User = cast<Instruction>(*UI);
- if (User->getParent() != DestBB || !isa<PHINode>(User))
+ 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 (User->getParent() == DestBB) {
- if (const PHINode *UPN = dyn_cast<PHINode>(User))
+ 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 &&
// 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, this);
+ MergeBasicBlockIntoOnlyPred(DestBB, DT);
if (isEntry && BB != &BB->getParent()->getEntryBlock())
BB->moveBefore(&BB->getParent()->getEntryBlock());
DEBUG(dbgs() << "AFTER:\n" << *DestBB << "\n\n\n");
}
-/// OptimizeNoopCopyExpression - If the specified cast instruction is a noop
-/// copy (e.g. it's casting from one pointer type to another, i32->i8 on PPC),
-/// sink it into user blocks to reduce the number of virtual
-/// registers that must be created and coalesced.
-///
-/// Return true if any changes are made.
-///
-static bool OptimizeNoopCopyExpression(CastInst *CI, const TargetLowering &TLI){
- // If this is a noop copy,
- EVT SrcVT = TLI.getValueType(CI->getOperand(0)->getType());
- EVT DstVT = TLI.getValueType(CI->getType());
+// Computes a map of base pointer relocation instructions to corresponding
+// derived pointer relocation instructions given a vector of all relocate calls
+static void computeBaseDerivedRelocateMap(
+ const SmallVectorImpl<User *> &AllRelocateCalls,
+ DenseMap<IntrinsicInst *, SmallVector<IntrinsicInst *, 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>, IntrinsicInst *> RelocateIdxMap;
+ for (auto &U : AllRelocateCalls) {
+ GCRelocateOperands ThisRelocate(U);
+ IntrinsicInst *I = cast<IntrinsicInst>(U);
+ auto K = std::make_pair(ThisRelocate.basePtrIndex(),
+ ThisRelocate.derivedPtrIndex());
+ RelocateIdxMap.insert(std::make_pair(K, I));
+ }
+ for (auto &Item : RelocateIdxMap) {
+ std::pair<unsigned, unsigned> Key = Item.first;
+ if (Key.first == Key.second)
+ // Base relocation: nothing to insert
+ continue;
- // This is an fp<->int conversion?
- if (SrcVT.isInteger() != DstVT.isInteger())
- return false;
+ IntrinsicInst *I = Item.second;
+ auto BaseKey = std::make_pair(Key.first, Key.first);
+ IntrinsicInst *Base = RelocateIdxMap[BaseKey];
+ if (!Base)
+ // TODO: We might want to insert a new base object relocate and gep off
+ // that, if there are enough derived object relocates.
+ continue;
+ RelocateInstMap[Base].push_back(I);
+ }
+}
- // If this is an extension, it will be a zero or sign extension, which
- // isn't a noop.
- if (SrcVT.bitsLT(DstVT)) return false;
+// Accepts a GEP and extracts the operands into a vector provided they're all
+// small integer constants
+static bool getGEPSmallConstantIntOffsetV(GetElementPtrInst *GEP,
+ SmallVectorImpl<Value *> &OffsetV) {
+ for (unsigned i = 1; i < GEP->getNumOperands(); i++) {
+ // Only accept small constant integer operands
+ auto Op = dyn_cast<ConstantInt>(GEP->getOperand(i));
+ if (!Op || Op->getZExtValue() > 20)
+ return false;
+ }
- // 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);
+ for (unsigned i = 1; i < GEP->getNumOperands(); i++)
+ OffsetV.push_back(GEP->getOperand(i));
+ return true;
+}
- // If, after promotion, these are the same types, this is a noop copy.
- if (SrcVT != DstVT)
+// Takes a RelocatedBase (base pointer relocation instruction) and Targets to
+// replace, computes a replacement, and affects it.
+static bool
+simplifyRelocatesOffABase(IntrinsicInst *RelocatedBase,
+ const SmallVectorImpl<IntrinsicInst *> &Targets) {
+ bool MadeChange = false;
+ for (auto &ToReplace : Targets) {
+ GCRelocateOperands MasterRelocate(RelocatedBase);
+ GCRelocateOperands ThisRelocate(ToReplace);
+
+ assert(ThisRelocate.basePtrIndex() == MasterRelocate.basePtrIndex() &&
+ "Not relocating a derived object of the original base object");
+ if (ThisRelocate.basePtrIndex() == ThisRelocate.derivedPtrIndex()) {
+ // A duplicate relocate call. TODO: coalesce duplicates.
+ continue;
+ }
+
+ Value *Base = ThisRelocate.basePtr();
+ auto Derived = dyn_cast<GetElementPtrInst>(ThisRelocate.derivedPtr());
+ 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
+ IRBuilder<> Builder(ToReplace);
+ Builder.SetCurrentDebugLocation(ToReplace->getDebugLoc());
+ Value *Replacement =
+ Builder.CreateGEP(RelocatedBase, makeArrayRef(OffsetV));
+ Instruction *ReplacementInst = cast<Instruction>(Replacement);
+ ReplacementInst->removeFromParent();
+ ReplacementInst->insertAfter(RelocatedBase);
+ Replacement->takeName(ToReplace);
+ ToReplace->replaceAllUsesWith(Replacement);
+ ToReplace->eraseFromParent();
+
+ MadeChange = true;
+ }
+ return MadeChange;
+}
+
+// Turns this:
+//
+// %base = ...
+// %ptr = gep %base + 15
+// %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
+// %base' = relocate(%tok, i32 4, i32 4)
+// %ptr' = relocate(%tok, i32 4, i32 5)
+// %val = load %ptr'
+//
+// into this:
+//
+// %base = ...
+// %ptr = gep %base + 15
+// %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
+// %base' = gc.relocate(%tok, i32 4, i32 4)
+// %ptr' = gep %base' + 15
+// %val = load %ptr'
+bool CodeGenPrepare::simplifyOffsetableRelocate(Instruction &I) {
+ bool MadeChange = false;
+ SmallVector<User *, 2> AllRelocateCalls;
+
+ for (auto *U : I.users())
+ if (isGCRelocate(dyn_cast<Instruction>(U)))
+ // Collect all the relocate calls associated with a statepoint
+ AllRelocateCalls.push_back(U);
+
+ // 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<IntrinsicInst *, SmallVector<IntrinsicInst *, 2>> RelocateInstMap;
+ computeBaseDerivedRelocateMap(AllRelocateCalls, RelocateInstMap);
+ if (RelocateInstMap.empty())
return false;
+ for (auto &Item : RelocateInstMap)
+ // Item.first is the RelocatedBase to offset against
+ // Item.second is the vector of Targets to replace
+ MadeChange = simplifyRelocatesOffABase(Item.first, Item.second);
+ return MadeChange;
+}
+
+/// SinkCast - Sink the specified cast instruction into its user blocks
+static bool SinkCast(CastInst *CI) {
BasicBlock *DefBB = CI->getParent();
/// InsertedCasts - Only insert a cast in each block once.
DenseMap<BasicBlock*, CastInst*> InsertedCasts;
bool MadeChange = false;
- for (Value::use_iterator UI = CI->use_begin(), E = CI->use_end();
+ for (Value::user_iterator UI = CI->user_begin(), E = CI->user_end();
UI != E; ) {
Use &TheUse = UI.getUse();
Instruction *User = cast<Instruction>(*UI);
// appropriate predecessor block.
BasicBlock *UserBB = User->getParent();
if (PHINode *PN = dyn_cast<PHINode>(User)) {
- UserBB = PN->getIncomingBlock(UI);
+ UserBB = PN->getIncomingBlock(TheUse);
}
// Preincrement use iterator so we don't invalidate it.
return MadeChange;
}
+/// OptimizeNoopCopyExpression - If the specified cast instruction is a noop
+/// copy (e.g. it's casting from one pointer type to another, i32->i8 on PPC),
+/// sink it into user blocks to reduce the number of virtual
+/// registers that must be created and coalesced.
+///
+/// Return true if any changes are made.
+///
+static bool OptimizeNoopCopyExpression(CastInst *CI, const TargetLowering &TLI){
+ // If this is a noop copy,
+ EVT SrcVT = TLI.getValueType(CI->getOperand(0)->getType());
+ EVT DstVT = TLI.getValueType(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);
+}
+
/// OptimizeCmpExpression - sink the given CmpInst into user blocks to reduce
/// the number of virtual registers that must be created and coalesced. This is
/// a clear win except on targets with multiple condition code registers
DenseMap<BasicBlock*, CmpInst*> InsertedCmps;
bool MadeChange = false;
- for (Value::use_iterator UI = CI->use_begin(), E = CI->use_end();
+ for (Value::user_iterator UI = CI->user_begin(), E = CI->user_end();
UI != E; ) {
Use &TheUse = UI.getUse();
Instruction *User = cast<Instruction>(*UI);
return MadeChange;
}
-namespace {
-class CodeGenPrepareFortifiedLibCalls : public SimplifyFortifiedLibCalls {
-protected:
- void replaceCall(Value *With) {
- CI->replaceAllUsesWith(With);
- CI->eraseFromParent();
+/// isExtractBitsCandidateUse - Check if the candidates could
+/// be combined with shift instruction, which includes:
+/// 1. Truncate instruction
+/// 2. And instruction and the imm is a mask of the low bits:
+/// imm & (imm+1) == 0
+static bool isExtractBitsCandidateUse(Instruction *User) {
+ if (!isa<TruncInst>(User)) {
+ if (User->getOpcode() != Instruction::And ||
+ !isa<ConstantInt>(User->getOperand(1)))
+ return false;
+
+ const APInt &Cimm = cast<ConstantInt>(User->getOperand(1))->getValue();
+
+ if ((Cimm & (Cimm + 1)).getBoolValue())
+ return false;
}
- bool isFoldable(unsigned SizeCIOp, unsigned, bool) const {
- if (ConstantInt *SizeCI =
- dyn_cast<ConstantInt>(CI->getArgOperand(SizeCIOp)))
- return SizeCI->isAllOnesValue();
- return false;
+ return true;
+}
+
+/// SinkShiftAndTruncate - sink both shift and truncate instruction
+/// to the use of truncate's BB.
+static bool
+SinkShiftAndTruncate(BinaryOperator *ShiftI, Instruction *User, ConstantInt *CI,
+ DenseMap<BasicBlock *, BinaryOperator *> &InsertedShifts,
+ const TargetLowering &TLI) {
+ 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(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();
+ // 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++;
+
+ InsertedTrunc = CastInst::Create(TruncI->getOpcode(), InsertedShift,
+ TruncI->getType(), "", TruncInsertPt);
+
+ MadeChange = true;
+
+ TruncTheUse = InsertedTrunc;
+ }
}
-};
-} // end anonymous namespace
+ return MadeChange;
+}
+
+/// OptimizeExtractBits - sink the shift *right* instruction into user blocks if
+/// the uses could potentially be combined with this shift instruction and
+/// generate BitExtract instruction. It will only be applied if the architecture
+/// supports BitExtract instruction. Here is an example:
+/// BB1:
+/// %x.extract.shift = lshr i64 %arg1, 32
+/// BB2:
+/// %x.extract.trunc = trunc i64 %x.extract.shift to i16
+/// ==>
+///
+/// BB2:
+/// %x.extract.shift.1 = lshr i64 %arg1, 32
+/// %x.extract.trunc = trunc i64 %x.extract.shift.1 to i16
+///
+/// CodeGen will recoginze the pattern in BB2 and generate BitExtract
+/// instruction.
+/// Return true if any changes are made.
+static bool OptimizeExtractBits(BinaryOperator *ShiftI, ConstantInt *CI,
+ const TargetLowering &TLI) {
+ BasicBlock *DefBB = ShiftI->getParent();
+
+ /// Only insert instructions in each block once.
+ DenseMap<BasicBlock *, BinaryOperator *> InsertedShifts;
+
+ bool shiftIsLegal = TLI.isTypeLegal(TLI.getValueType(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(User->getType()))))
+ MadeChange =
+ SinkShiftAndTruncate(ShiftI, User, CI, InsertedShifts, TLI);
+
+ continue;
+ }
+ // If we have already inserted a shift into this block, use it.
+ BinaryOperator *&InsertedShift = InsertedShifts[UserBB];
+
+ if (!InsertedShift) {
+ BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
+
+ 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;
+}
+
+// ScalarizeMaskedLoad() translates masked load intrinsic, like
+// <16 x i32 > @llvm.masked.load( <16 x i32>* %addr, i32 align,
+// <16 x i1> %mask, <16 x i32> %passthru)
+// to a chain of basic blocks, whith loading element one-by-one if
+// the appropriate mask bit is set
+//
+// %1 = bitcast i8* %addr to i32*
+// %2 = extractelement <16 x i1> %mask, i32 0
+// %3 = icmp eq i1 %2, true
+// br i1 %3, label %cond.load, label %else
+//
+//cond.load: ; preds = %0
+// %4 = getelementptr i32* %1, i32 0
+// %5 = load i32* %4
+// %6 = insertelement <16 x i32> undef, i32 %5, i32 0
+// br label %else
+//
+//else: ; preds = %0, %cond.load
+// %res.phi.else = phi <16 x i32> [ %6, %cond.load ], [ undef, %0 ]
+// %7 = extractelement <16 x i1> %mask, i32 1
+// %8 = icmp eq i1 %7, true
+// br i1 %8, label %cond.load1, label %else2
+//
+//cond.load1: ; preds = %else
+// %9 = getelementptr i32* %1, i32 1
+// %10 = load i32* %9
+// %11 = insertelement <16 x i32> %res.phi.else, i32 %10, i32 1
+// br label %else2
+//
+//else2: ; preds = %else, %cond.load1
+// %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
+// %12 = extractelement <16 x i1> %mask, i32 2
+// %13 = icmp eq i1 %12, true
+// br i1 %13, label %cond.load4, label %else5
+//
+static void ScalarizeMaskedLoad(CallInst *CI) {
+ Value *Ptr = CI->getArgOperand(0);
+ Value *Src0 = CI->getArgOperand(3);
+ Value *Mask = CI->getArgOperand(2);
+ VectorType *VecType = dyn_cast<VectorType>(CI->getType());
+ Type *EltTy = VecType->getElementType();
+
+ assert(VecType && "Unexpected return type of masked load intrinsic");
+
+ IRBuilder<> Builder(CI->getContext());
+ Instruction *InsertPt = CI;
+ BasicBlock *IfBlock = CI->getParent();
+ BasicBlock *CondBlock = nullptr;
+ BasicBlock *PrevIfBlock = CI->getParent();
+ Builder.SetInsertPoint(InsertPt);
+
+ Builder.SetCurrentDebugLocation(CI->getDebugLoc());
+
+ // Bitcast %addr fron i8* to EltTy*
+ Type *NewPtrType =
+ EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
+ Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
+ Value *UndefVal = UndefValue::get(VecType);
+
+ // The result vector
+ Value *VResult = UndefVal;
+
+ PHINode *Phi = nullptr;
+ Value *PrevPhi = UndefVal;
+
+ unsigned VectorWidth = VecType->getNumElements();
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+
+ // Fill the "else" block, created in the previous iteration
+ //
+ // %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
+ // %mask_1 = extractelement <16 x i1> %mask, i32 Idx
+ // %to_load = icmp eq i1 %mask_1, true
+ // br i1 %to_load, label %cond.load, label %else
+ //
+ if (Idx > 0) {
+ Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
+ Phi->addIncoming(VResult, CondBlock);
+ Phi->addIncoming(PrevPhi, PrevIfBlock);
+ PrevPhi = Phi;
+ VResult = Phi;
+ }
+
+ Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
+ Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
+ ConstantInt::get(Predicate->getType(), 1));
+
+ // Create "cond" block
+ //
+ // %EltAddr = getelementptr i32* %1, i32 0
+ // %Elt = load i32* %EltAddr
+ // VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
+ //
+ CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.load");
+ Builder.SetInsertPoint(InsertPt);
+
+ Value* Gep = Builder.CreateInBoundsGEP(FirstEltPtr, Builder.getInt32(Idx));
+ LoadInst* Load = Builder.CreateLoad(Gep, false);
+ VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
+
+ // Create "else" block, fill it in the next iteration
+ BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
+ Builder.SetInsertPoint(InsertPt);
+ Instruction *OldBr = IfBlock->getTerminator();
+ BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
+ OldBr->eraseFromParent();
+ PrevIfBlock = IfBlock;
+ IfBlock = NewIfBlock;
+ }
+
+ Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
+ Phi->addIncoming(VResult, CondBlock);
+ Phi->addIncoming(PrevPhi, PrevIfBlock);
+ Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
+ CI->replaceAllUsesWith(NewI);
+ CI->eraseFromParent();
+}
+
+// ScalarizeMaskedStore() translates masked store intrinsic, like
+// void @llvm.masked.store(<16 x i32> %src, <16 x i32>* %addr, i32 align,
+// <16 x i1> %mask)
+// to a chain of basic blocks, that stores element one-by-one if
+// the appropriate mask bit is set
+//
+// %1 = bitcast i8* %addr to i32*
+// %2 = extractelement <16 x i1> %mask, i32 0
+// %3 = icmp eq i1 %2, true
+// br i1 %3, label %cond.store, label %else
+//
+// cond.store: ; preds = %0
+// %4 = extractelement <16 x i32> %val, i32 0
+// %5 = getelementptr i32* %1, i32 0
+// store i32 %4, i32* %5
+// br label %else
+//
+// else: ; preds = %0, %cond.store
+// %6 = extractelement <16 x i1> %mask, i32 1
+// %7 = icmp eq i1 %6, true
+// br i1 %7, label %cond.store1, label %else2
+//
+// cond.store1: ; preds = %else
+// %8 = extractelement <16 x i32> %val, i32 1
+// %9 = getelementptr i32* %1, i32 1
+// store i32 %8, i32* %9
+// br label %else2
+// . . .
+static void ScalarizeMaskedStore(CallInst *CI) {
+ Value *Ptr = CI->getArgOperand(1);
+ Value *Src = CI->getArgOperand(0);
+ Value *Mask = CI->getArgOperand(3);
+
+ VectorType *VecType = dyn_cast<VectorType>(Src->getType());
+ Type *EltTy = VecType->getElementType();
+
+ assert(VecType && "Unexpected data type in masked store intrinsic");
+
+ IRBuilder<> Builder(CI->getContext());
+ Instruction *InsertPt = CI;
+ BasicBlock *IfBlock = CI->getParent();
+ Builder.SetInsertPoint(InsertPt);
+ Builder.SetCurrentDebugLocation(CI->getDebugLoc());
+
+ // Bitcast %addr fron i8* to EltTy*
+ Type *NewPtrType =
+ EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
+ Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
+
+ unsigned VectorWidth = VecType->getNumElements();
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+
+ // Fill the "else" block, created in the previous iteration
+ //
+ // %mask_1 = extractelement <16 x i1> %mask, i32 Idx
+ // %to_store = icmp eq i1 %mask_1, true
+ // br i1 %to_load, label %cond.store, label %else
+ //
+ Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
+ Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
+ ConstantInt::get(Predicate->getType(), 1));
+
+ // Create "cond" block
+ //
+ // %OneElt = extractelement <16 x i32> %Src, i32 Idx
+ // %EltAddr = getelementptr i32* %1, i32 0
+ // %store i32 %OneElt, i32* %EltAddr
+ //
+ BasicBlock *CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
+ Builder.SetInsertPoint(InsertPt);
+
+ Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
+ Value* Gep = Builder.CreateInBoundsGEP(FirstEltPtr, Builder.getInt32(Idx));
+ Builder.CreateStore(OneElt, Gep);
+
+ // Create "else" block, fill it in the next iteration
+ BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
+ Builder.SetInsertPoint(InsertPt);
+ Instruction *OldBr = IfBlock->getTerminator();
+ BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
+ OldBr->eraseFromParent();
+ IfBlock = NewIfBlock;
+ }
+ CI->eraseFromParent();
+}
-bool CodeGenPrepare::OptimizeCallInst(CallInst *CI) {
+bool CodeGenPrepare::OptimizeCallInst(CallInst *CI, bool& ModifiedDT) {
BasicBlock *BB = CI->getParent();
// Lower inline assembly if we can.
return true;
}
- // Lower all uses of llvm.objectsize.*
IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
- if (II && II->getIntrinsicID() == Intrinsic::objectsize) {
- bool Min = (cast<ConstantInt>(II->getArgOperand(1))->getZExtValue() == 1);
- Type *ReturnTy = CI->getType();
- Constant *RetVal = ConstantInt::get(ReturnTy, Min ? 0 : -1ULL);
-
- // Substituting this can cause recursive simplifications, which can
- // invalidate our iterator. Use a WeakVH to hold onto it in case this
- // happens.
- WeakVH IterHandle(CurInstIterator);
+ if (II) {
+ switch (II->getIntrinsicID()) {
+ default: break;
+ case Intrinsic::objectsize: {
+ // Lower all uses of llvm.objectsize.*
+ bool Min = (cast<ConstantInt>(II->getArgOperand(1))->getZExtValue() == 1);
+ Type *ReturnTy = CI->getType();
+ Constant *RetVal = ConstantInt::get(ReturnTy, Min ? 0 : -1ULL);
+
+ // Substituting this can cause recursive simplifications, which can
+ // invalidate our iterator. Use a WeakVH to hold onto it in case this
+ // happens.
+ WeakVH IterHandle(CurInstIterator);
+
+ replaceAndRecursivelySimplify(CI, RetVal,
+ TLI ? TLI->getDataLayout() : nullptr,
+ TLInfo, ModifiedDT ? nullptr : DT);
- replaceAndRecursivelySimplify(CI, RetVal, TLI ? TLI->getDataLayout() : 0,
- TLInfo, ModifiedDT ? 0 : DT);
-
- // If the iterator instruction was recursively deleted, start over at the
- // start of the block.
- if (IterHandle != CurInstIterator) {
- CurInstIterator = BB->begin();
- SunkAddrs.clear();
+ // If the iterator instruction was recursively deleted, start over at the
+ // start of the block.
+ if (IterHandle != CurInstIterator) {
+ CurInstIterator = BB->begin();
+ SunkAddrs.clear();
+ }
+ return true;
+ }
+ case Intrinsic::masked_load: {
+ // Scalarize unsupported vector masked load
+ if (!TTI->isLegalMaskedLoad(CI->getType(), 1)) {
+ ScalarizeMaskedLoad(CI);
+ ModifiedDT = true;
+ return true;
+ }
+ return false;
+ }
+ case Intrinsic::masked_store: {
+ if (!TTI->isLegalMaskedStore(CI->getArgOperand(0)->getType(), 1)) {
+ ScalarizeMaskedStore(CI);
+ ModifiedDT = true;
+ return true;
+ }
+ return false;
+ }
}
- return true;
- }
- if (II && TLI) {
- SmallVector<Value*, 2> PtrOps;
- Type *AccessTy;
- if (TLI->GetAddrModeArguments(II, PtrOps, AccessTy))
- while (!PtrOps.empty())
- if (OptimizeMemoryInst(II, PtrOps.pop_back_val(), AccessTy))
- return true;
+ if (TLI) {
+ SmallVector<Value*, 2> PtrOps;
+ Type *AccessTy;
+ if (TLI->GetAddrModeArguments(II, PtrOps, AccessTy))
+ while (!PtrOps.empty())
+ if (OptimizeMemoryInst(II, PtrOps.pop_back_val(), AccessTy))
+ return true;
+ }
}
// From here on out we're working with named functions.
- if (CI->getCalledFunction() == 0) return false;
+ if (!CI->getCalledFunction()) return false;
// We'll need DataLayout from here on out.
- const DataLayout *TD = TLI ? TLI->getDataLayout() : 0;
+ const DataLayout *TD = TLI ? TLI->getDataLayout() : nullptr;
if (!TD) return false;
// Lower all default uses of _chk calls. This is very similar
// to what InstCombineCalls does, but here we are only lowering calls
- // that have the default "don't know" as the objectsize. Anything else
- // should be left alone.
- CodeGenPrepareFortifiedLibCalls Simplifier;
- return Simplifier.fold(CI, TD, TLInfo);
+ // 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(TD, TLInfo, true);
+ if (Value *V = Simplifier.optimizeCall(CI)) {
+ CI->replaceAllUsesWith(V);
+ CI->eraseFromParent();
+ return true;
+ }
+ return false;
}
/// DupRetToEnableTailCallOpts - Look for opportunities to duplicate return
if (!RI)
return false;
- PHINode *PN = 0;
- BitCastInst *BCI = 0;
+ PHINode *PN = nullptr;
+ BitCastInst *BCI = nullptr;
Value *V = RI->getReturnValue();
if (V) {
BCI = dyn_cast<BitCastInst>(V);
} else {
SmallPtrSet<BasicBlock*, 4> VisitedBBs;
for (pred_iterator PI = pred_begin(BB), PE = pred_end(BB); PI != PE; ++PI) {
- if (!VisitedBBs.insert(*PI))
+ if (!VisitedBBs.insert(*PI).second)
continue;
BasicBlock::InstListType &InstList = (*PI)->getInstList();
struct ExtAddrMode : public TargetLowering::AddrMode {
Value *BaseReg;
Value *ScaledReg;
- ExtAddrMode() : BaseReg(0), ScaledReg(0) {}
+ ExtAddrMode() : BaseReg(nullptr), ScaledReg(nullptr) {}
void print(raw_ostream &OS) const;
void dump() const;
NeedPlus = true;
}
- if (BaseOffs)
- OS << (NeedPlus ? " + " : "") << BaseOffs, NeedPlus = true;
+ if (BaseOffs) {
+ OS << (NeedPlus ? " + " : "")
+ << BaseOffs;
+ NeedPlus = true;
+ }
if (BaseReg) {
OS << (NeedPlus ? " + " : "")
}
/// \brief Move the instruction back to its original position.
- void undo() {
+ void undo() override {
DEBUG(dbgs() << "Undo: moveBefore: " << *Inst << "\n");
Position.insert(Inst);
}
}
/// \brief Restore the original value of the instruction.
- void undo() {
+ void undo() override {
DEBUG(dbgs() << "Undo: setOperand:" << Idx << "\n"
<< "for: " << *Inst << "\n"
<< "with: " << *Origin << "\n");
}
/// \brief Restore the original list of uses.
- void undo() {
+ void undo() override {
DEBUG(dbgs() << "Undo: OperandsHider: " << *Inst << "\n");
for (unsigned It = 0, EndIt = OriginalValues.size(); It != EndIt; ++It)
Inst->setOperand(It, OriginalValues[It]);
/// \brief Build a truncate instruction.
class TruncBuilder : public TypePromotionAction {
+ Value *Val;
public:
/// \brief Build a truncate instruction of \p Opnd producing a \p Ty
/// result.
/// trunc Opnd to Ty.
TruncBuilder(Instruction *Opnd, Type *Ty) : TypePromotionAction(Opnd) {
IRBuilder<> Builder(Opnd);
- Inst = cast<Instruction>(Builder.CreateTrunc(Opnd, Ty, "promoted"));
- DEBUG(dbgs() << "Do: TruncBuilder: " << *Inst << "\n");
+ Val = Builder.CreateTrunc(Opnd, Ty, "promoted");
+ DEBUG(dbgs() << "Do: TruncBuilder: " << *Val << "\n");
}
- /// \brief Get the built instruction.
- Instruction *getBuiltInstruction() { return Inst; }
+ /// \brief Get the built value.
+ Value *getBuiltValue() { return Val; }
/// \brief Remove the built instruction.
- void undo() {
- DEBUG(dbgs() << "Undo: TruncBuilder: " << *Inst << "\n");
- Inst->eraseFromParent();
+ void undo() override {
+ DEBUG(dbgs() << "Undo: TruncBuilder: " << *Val << "\n");
+ if (Instruction *IVal = dyn_cast<Instruction>(Val))
+ IVal->eraseFromParent();
}
};
/// \brief Build a sign extension instruction.
class SExtBuilder : public TypePromotionAction {
+ Value *Val;
public:
/// \brief Build a sign extension instruction of \p Opnd producing a \p Ty
/// result.
/// sext Opnd to Ty.
SExtBuilder(Instruction *InsertPt, Value *Opnd, Type *Ty)
- : TypePromotionAction(Inst) {
+ : TypePromotionAction(InsertPt) {
IRBuilder<> Builder(InsertPt);
- Inst = cast<Instruction>(Builder.CreateSExt(Opnd, Ty, "promoted"));
- DEBUG(dbgs() << "Do: SExtBuilder: " << *Inst << "\n");
+ Val = Builder.CreateSExt(Opnd, Ty, "promoted");
+ DEBUG(dbgs() << "Do: SExtBuilder: " << *Val << "\n");
}
- /// \brief Get the built instruction.
- Instruction *getBuiltInstruction() { return Inst; }
+ /// \brief Get the built value.
+ Value *getBuiltValue() { return Val; }
/// \brief Remove the built instruction.
- void undo() {
- DEBUG(dbgs() << "Undo: SExtBuilder: " << *Inst << "\n");
- Inst->eraseFromParent();
+ void undo() override {
+ DEBUG(dbgs() << "Undo: SExtBuilder: " << *Val << "\n");
+ if (Instruction *IVal = dyn_cast<Instruction>(Val))
+ IVal->eraseFromParent();
+ }
+ };
+
+ /// \brief Build a zero extension instruction.
+ class ZExtBuilder : public TypePromotionAction {
+ Value *Val;
+ public:
+ /// \brief Build a zero extension instruction of \p Opnd producing a \p Ty
+ /// result.
+ /// zext Opnd to Ty.
+ ZExtBuilder(Instruction *InsertPt, Value *Opnd, Type *Ty)
+ : TypePromotionAction(InsertPt) {
+ IRBuilder<> Builder(InsertPt);
+ Val = Builder.CreateZExt(Opnd, Ty, "promoted");
+ DEBUG(dbgs() << "Do: ZExtBuilder: " << *Val << "\n");
+ }
+
+ /// \brief Get the built value.
+ Value *getBuiltValue() { return Val; }
+
+ /// \brief Remove the built instruction.
+ void undo() override {
+ DEBUG(dbgs() << "Undo: ZExtBuilder: " << *Val << "\n");
+ if (Instruction *IVal = dyn_cast<Instruction>(Val))
+ IVal->eraseFromParent();
}
};
}
/// \brief Mutate the instruction back to its original type.
- void undo() {
+ void undo() override {
DEBUG(dbgs() << "Undo: MutateType: " << *Inst << " with " << *OrigTy
<< "\n");
Inst->mutateType(OrigTy);
DEBUG(dbgs() << "Do: UsersReplacer: " << *Inst << " with " << *New
<< "\n");
// Record the original uses.
- for (Value::use_iterator UseIt = Inst->use_begin(),
- EndIt = Inst->use_end();
- UseIt != EndIt; ++UseIt) {
- Instruction *Use = cast<Instruction>(*UseIt);
- OriginalUses.push_back(InstructionAndIdx(Use, UseIt.getOperandNo()));
+ 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() {
+ void undo() override {
DEBUG(dbgs() << "Undo: UsersReplacer: " << *Inst << "\n");
for (use_iterator UseIt = OriginalUses.begin(),
EndIt = OriginalUses.end();
public:
/// \brief Remove all reference of \p Inst and optinally replace all its
/// uses with New.
- /// \pre If !Inst->use_empty(), then New != NULL
- InstructionRemover(Instruction *Inst, Value *New = NULL)
+ /// \pre If !Inst->use_empty(), then New != nullptr
+ InstructionRemover(Instruction *Inst, Value *New = nullptr)
: TypePromotionAction(Inst), Inserter(Inst), Hider(Inst),
- Replacer(NULL) {
+ Replacer(nullptr) {
if (New)
Replacer = new UsesReplacer(Inst, New);
DEBUG(dbgs() << "Do: InstructionRemover: " << *Inst << "\n");
~InstructionRemover() { delete Replacer; }
/// \brief Really remove the instruction.
- void commit() { delete Inst; }
+ void commit() override { delete Inst; }
/// \brief Resurrect the instruction and reassign it to the proper uses if
/// new value was provided when build this action.
- void undo() {
+ void undo() override {
DEBUG(dbgs() << "Undo: InstructionRemover: " << *Inst << "\n");
Inserter.insert(Inst);
if (Replacer)
/// Same as Instruction::setOperand.
void setOperand(Instruction *Inst, unsigned Idx, Value *NewVal);
/// Same as Instruction::eraseFromParent.
- void eraseInstruction(Instruction *Inst, Value *NewVal = NULL);
+ 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.
- Instruction *createTrunc(Instruction *Opnd, Type *Ty);
+ Value *createTrunc(Instruction *Opnd, Type *Ty);
/// Same as IRBuilder::createSExt.
- Instruction *createSExt(Instruction *Inst, Value *Opnd, Type *Ty);
+ 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);
/// @}
- ~TypePromotionTransaction();
-
private:
/// The ordered list of actions made so far.
- SmallVector<TypePromotionAction *, 16> Actions;
- typedef SmallVectorImpl<TypePromotionAction *>::iterator CommitPt;
+ SmallVector<std::unique_ptr<TypePromotionAction>, 16> Actions;
+ typedef SmallVectorImpl<std::unique_ptr<TypePromotionAction>>::iterator CommitPt;
};
void TypePromotionTransaction::setOperand(Instruction *Inst, unsigned Idx,
Value *NewVal) {
Actions.push_back(
- new TypePromotionTransaction::OperandSetter(Inst, Idx, NewVal));
+ make_unique<TypePromotionTransaction::OperandSetter>(Inst, Idx, NewVal));
}
void TypePromotionTransaction::eraseInstruction(Instruction *Inst,
Value *NewVal) {
Actions.push_back(
- new TypePromotionTransaction::InstructionRemover(Inst, NewVal));
+ make_unique<TypePromotionTransaction::InstructionRemover>(Inst, NewVal));
}
void TypePromotionTransaction::replaceAllUsesWith(Instruction *Inst,
Value *New) {
- Actions.push_back(new TypePromotionTransaction::UsesReplacer(Inst, New));
+ Actions.push_back(make_unique<TypePromotionTransaction::UsesReplacer>(Inst, New));
}
void TypePromotionTransaction::mutateType(Instruction *Inst, Type *NewTy) {
- Actions.push_back(new TypePromotionTransaction::TypeMutator(Inst, NewTy));
+ Actions.push_back(make_unique<TypePromotionTransaction::TypeMutator>(Inst, NewTy));
+}
+
+Value *TypePromotionTransaction::createTrunc(Instruction *Opnd,
+ Type *Ty) {
+ std::unique_ptr<TruncBuilder> Ptr(new TruncBuilder(Opnd, Ty));
+ Value *Val = Ptr->getBuiltValue();
+ Actions.push_back(std::move(Ptr));
+ return Val;
}
-Instruction *TypePromotionTransaction::createTrunc(Instruction *Opnd,
- Type *Ty) {
- TruncBuilder *TB = new TruncBuilder(Opnd, Ty);
- Actions.push_back(TB);
- return TB->getBuiltInstruction();
+Value *TypePromotionTransaction::createSExt(Instruction *Inst,
+ Value *Opnd, Type *Ty) {
+ std::unique_ptr<SExtBuilder> Ptr(new SExtBuilder(Inst, Opnd, Ty));
+ Value *Val = Ptr->getBuiltValue();
+ Actions.push_back(std::move(Ptr));
+ return Val;
}
-Instruction *TypePromotionTransaction::createSExt(Instruction *Inst,
- Value *Opnd, Type *Ty) {
- SExtBuilder *SB = new SExtBuilder(Inst, Opnd, Ty);
- Actions.push_back(SB);
- return SB->getBuiltInstruction();
+Value *TypePromotionTransaction::createZExt(Instruction *Inst,
+ Value *Opnd, Type *Ty) {
+ std::unique_ptr<ZExtBuilder> Ptr(new ZExtBuilder(Inst, Opnd, Ty));
+ Value *Val = Ptr->getBuiltValue();
+ Actions.push_back(std::move(Ptr));
+ return Val;
}
void TypePromotionTransaction::moveBefore(Instruction *Inst,
Instruction *Before) {
Actions.push_back(
- new TypePromotionTransaction::InstructionMoveBefore(Inst, Before));
+ make_unique<TypePromotionTransaction::InstructionMoveBefore>(Inst, Before));
}
TypePromotionTransaction::ConstRestorationPt
TypePromotionTransaction::getRestorationPoint() const {
- return Actions.rbegin() != Actions.rend() ? *Actions.rbegin() : NULL;
+ return !Actions.empty() ? Actions.back().get() : nullptr;
}
void TypePromotionTransaction::commit() {
for (CommitPt It = Actions.begin(), EndIt = Actions.end(); It != EndIt;
- ++It) {
+ ++It)
(*It)->commit();
- delete *It;
- }
Actions.clear();
}
void TypePromotionTransaction::rollback(
TypePromotionTransaction::ConstRestorationPt Point) {
- while (!Actions.empty() && Point != (*Actions.rbegin())) {
- TypePromotionAction *Curr = Actions.pop_back_val();
+ while (!Actions.empty() && Point != Actions.back().get()) {
+ std::unique_ptr<TypePromotionAction> Curr = Actions.pop_back_val();
Curr->undo();
- delete Curr;
}
}
-TypePromotionTransaction::~TypePromotionTransaction() {
- for (CommitPt It = Actions.begin(), EndIt = Actions.end(); It != EndIt; ++It)
- delete *It;
- Actions.clear();
-}
-
/// \brief A helper class for matching addressing modes.
///
/// This encapsulates the logic for matching the target-legal addressing modes.
class AddressingModeMatcher {
SmallVectorImpl<Instruction*> &AddrModeInsts;
+ const TargetMachine &TM;
const TargetLowering &TLI;
/// AccessTy/MemoryInst - This is the type for the access (e.g. double) and
/// always returns true.
bool IgnoreProfitability;
- AddressingModeMatcher(SmallVectorImpl<Instruction*> &AMI,
- const TargetLowering &T, Type *AT,
- Instruction *MI, ExtAddrMode &AM,
- const SetOfInstrs &InsertedTruncs,
+ AddressingModeMatcher(SmallVectorImpl<Instruction *> &AMI,
+ const TargetMachine &TM, Type *AT, Instruction *MI,
+ ExtAddrMode &AM, const SetOfInstrs &InsertedTruncs,
InstrToOrigTy &PromotedInsts,
TypePromotionTransaction &TPT)
- : AddrModeInsts(AMI), TLI(T), AccessTy(AT), MemoryInst(MI), AddrMode(AM),
+ : AddrModeInsts(AMI), TM(TM),
+ TLI(*TM.getSubtargetImpl(*MI->getParent()->getParent())
+ ->getTargetLowering()),
+ AccessTy(AT), MemoryInst(MI), AddrMode(AM),
InsertedTruncs(InsertedTruncs), PromotedInsts(PromotedInsts), TPT(TPT) {
IgnoreProfitability = false;
}
static ExtAddrMode Match(Value *V, Type *AccessTy,
Instruction *MemoryInst,
SmallVectorImpl<Instruction*> &AddrModeInsts,
- const TargetLowering &TLI,
+ const TargetMachine &TM,
const SetOfInstrs &InsertedTruncs,
InstrToOrigTy &PromotedInsts,
TypePromotionTransaction &TPT) {
ExtAddrMode Result;
- bool Success = AddressingModeMatcher(AddrModeInsts, TLI, AccessTy,
+ bool Success = AddressingModeMatcher(AddrModeInsts, TM, AccessTy,
MemoryInst, Result, InsertedTruncs,
PromotedInsts, TPT).MatchAddr(V, 0);
(void)Success; assert(Success && "Couldn't select *anything*?");
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 = NULL);
+ bool *MovedAway = nullptr);
bool IsProfitableToFoldIntoAddressingMode(Instruction *I,
ExtAddrMode &AMBefore,
ExtAddrMode &AMAfter);
// 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 = 0; Value *AddLHS = 0;
+ 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;
static bool MightBeFoldableInst(Instruction *I) {
switch (I->getOpcode()) {
case Instruction::BitCast:
+ case Instruction::AddrSpaceCast:
// Don't touch identity bitcasts.
if (I->getType() == I->getOperand(0)->getType())
return false;
}
}
+/// \brief Check whether or not \p Val is a legal instruction for \p TLI.
+/// \note \p Val is assumed to be the product of some type promotion.
+/// Therefore if \p Val has an undefined state in \p TLI, this is assumed
+/// to be legal, as the non-promoted value would have had the same state.
+static bool isPromotedInstructionLegal(const TargetLowering &TLI, 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(PromotedInst->getType()));
+}
+
/// \brief Hepler class to perform type promotion.
class TypePromotionHelper {
- /// \brief Utility function to check whether or not a sign extension of
- /// \p Inst with \p ConsideredSExtType can be moved through \p Inst by either
- /// using the operands of \p Inst or promoting \p Inst.
+ /// \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:
- /// sext (Ty Inst opnd1 opnd2 ... opndN) to ConsideredSExtType.
+ /// ext (Ty Inst opnd1 opnd2 ... opndN) to ConsideredExtType.
/// #1 Promotion applies:
- /// ConsideredSExtType Inst (sext opnd1 to ConsideredSExtType, ...).
+ /// ConsideredExtType Inst (ext opnd1 to ConsideredExtType, ...).
/// #2 Operand reuses:
- /// sext opnd1 to ConsideredSExtType.
+ /// ext opnd1 to ConsideredExtType.
/// \p PromotedInsts maps the instructions to their type before promotion.
- static bool canGetThrough(const Instruction *Inst, Type *ConsideredSExtType,
- const InstrToOrigTy &PromotedInsts);
+ 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 shouldSExtOperand(const Instruction *Inst, int OpIdx) {
+ static bool shouldExtOperand(const Instruction *Inst, int OpIdx) {
if (isa<SelectInst>(Inst) && OpIdx == 0)
return false;
return true;
}
- /// \brief Utility function to promote the operand of \p SExt when this
- /// operand is a promotable trunc or sext.
+ /// \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 CreatedInsts[out] contains how many non-free instructions have been
- /// created to promote the operand of SExt.
+ /// 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 SExt.
- static Value *promoteOperandForTruncAndSExt(Instruction *SExt,
- TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts);
-
- /// \brief Utility function to promote the operand of \p SExt when this
+ /// \return The promoted value which is used instead of Ext.
+ static Value *promoteOperandForTruncAndAnyExt(
+ Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs);
+
+ /// \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 CreatedInsts[out] contains how many non-free instructions have been
- /// created to promote the operand of SExt.
+ /// 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 SExt.
- static Value *promoteOperandForOther(Instruction *SExt,
- TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts);
+ /// \return The promoted value which is used instead of Ext.
+ static Value *
+ promoteOperandForOther(Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs, bool IsSExt);
+
+ /// \see promoteOperandForOther.
+ static Value *
+ signExtendOperandForOther(Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts,
+ unsigned &CreatedInsts,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs) {
+ return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInsts, Exts,
+ Truncs, true);
+ }
+
+ /// \see promoteOperandForOther.
+ static Value *
+ zeroExtendOperandForOther(Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts,
+ unsigned &CreatedInsts,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs) {
+ return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInsts, Exts,
+ Truncs, false);
+ }
public:
- /// Type for the utility function that promotes the operand of SExt.
- typedef Value *(*Action)(Instruction *SExt, TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts);
- /// \brief Given a sign extend instruction \p SExt, return the approriate
- /// action to promote the operand of \p SExt instead of using SExt.
+ /// Type for the utility function that promotes the operand of Ext.
+ typedef Value *(*Action)(Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs);
+ /// \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 InsertedTruncs keeps track of all the truncate instructions inserted by
/// 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 *SExt, const SetOfInstrs &InsertedTruncs,
+ static Action getAction(Instruction *Ext, const SetOfInstrs &InsertedTruncs,
const TargetLowering &TLI,
const InstrToOrigTy &PromotedInsts);
};
bool TypePromotionHelper::canGetThrough(const Instruction *Inst,
- Type *ConsideredSExtType,
- const InstrToOrigTy &PromotedInsts) {
- // We can always get through sext.
- if (isa<SExtInst>(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) &&
- (BinOp->hasNoUnsignedWrap() || BinOp->hasNoSignedWrap()))
+ ((!IsSExt && BinOp->hasNoUnsignedWrap()) ||
+ (IsSExt && BinOp->hasNoSignedWrap())))
return true;
// Check if we can do the following simplification.
- // sext(trunc(sext)) --> sext
+ // 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 sext.
- // If the type is larger than the result type of the sign extension,
+ // 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()->getIntegerBitWidth() >
- ConsideredSExtType->getIntegerBitWidth())
+ 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
return false;
// Check if the source of the type is narrow enough.
- // I.e., check that trunc just drops sign extended bits.
- // #1 get the type of the operand.
+ // 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())
- OpndType = It->second;
- else if (isa<SExtInst>(Opnd))
- OpndType = cast<Instruction>(Opnd)->getOperand(0)->getType();
+ if (It != PromotedInsts.end() && It->second.IsSExt == IsSExt)
+ OpndType = It->second.Ty;
+ else if ((IsSExt && isa<SExtInst>(Opnd)) || (!IsSExt && isa<ZExtInst>(Opnd)))
+ OpndType = Opnd->getOperand(0)->getType();
else
return false;
- // #2 check that the truncate just drop sign extended bits.
+ // #2 check that the truncate just drop extended bits.
if (Inst->getType()->getIntegerBitWidth() >= OpndType->getIntegerBitWidth())
return true;
}
TypePromotionHelper::Action TypePromotionHelper::getAction(
- Instruction *SExt, const SetOfInstrs &InsertedTruncs,
+ Instruction *Ext, const SetOfInstrs &InsertedTruncs,
const TargetLowering &TLI, const InstrToOrigTy &PromotedInsts) {
- Instruction *SExtOpnd = dyn_cast<Instruction>(SExt->getOperand(0));
- Type *SExtTy = SExt->getType();
- // If the operand of the sign extension is not an instruction, we cannot
+ assert((isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) &&
+ "Unexpected instruction type");
+ Instruction *ExtOpnd = dyn_cast<Instruction>(Ext->getOperand(0));
+ Type *ExtTy = Ext->getType();
+ bool IsSExt = isa<SExtInst>(Ext);
+ // If the operand of the extension is not an instruction, we cannot
// get through.
// If it, check we can get through.
- if (!SExtOpnd || !canGetThrough(SExtOpnd, SExtTy, PromotedInsts))
- return NULL;
+ 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>(SExtOpnd) && InsertedTruncs.count(SExtOpnd))
- return NULL;
+ if (isa<TruncInst>(ExtOpnd) && InsertedTruncs.count(ExtOpnd))
+ return nullptr;
// SExt or Trunc instructions.
// Return the related handler.
- if (isa<SExtInst>(SExtOpnd) || isa<TruncInst>(SExtOpnd))
- return promoteOperandForTruncAndSExt;
+ 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 (!SExtOpnd->hasOneUse() &&
- !TLI.isTruncateFree(SExtTy, SExtOpnd->getType()))
- return NULL;
- return promoteOperandForOther;
+ if (!ExtOpnd->hasOneUse() && !TLI.isTruncateFree(ExtTy, ExtOpnd->getType()))
+ return nullptr;
+ return IsSExt ? signExtendOperandForOther : zeroExtendOperandForOther;
}
-Value *TypePromotionHelper::promoteOperandForTruncAndSExt(
+Value *TypePromotionHelper::promoteOperandForTruncAndAnyExt(
llvm::Instruction *SExt, TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts) {
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs) {
// 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));
- // Replace sext(trunc(opnd)) or sext(sext(opnd))
- // => sext(opnd).
- TPT.setOperand(SExt, 0, SExtOpnd->getOperand(0));
+ Value *ExtVal = SExt;
+ if (isa<ZExtInst>(SExtOpnd)) {
+ // Replace s|zext(zext(opnd))
+ // => zext(opnd).
+ 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));
+ }
CreatedInsts = 0;
// Remove dead code.
if (SExtOpnd->use_empty())
TPT.eraseInstruction(SExtOpnd);
- // Check if the sext is still needed.
- if (SExt->getType() != SExt->getOperand(0)->getType())
- return SExt;
+ // Check if the extension is still needed.
+ Instruction *ExtInst = dyn_cast<Instruction>(ExtVal);
+ if (!ExtInst || ExtInst->getType() != ExtInst->getOperand(0)->getType()) {
+ if (ExtInst && Exts)
+ Exts->push_back(ExtInst);
+ return ExtVal;
+ }
- // At this point we have: sext ty opnd to ty.
- // Reassign the uses of SExt to the opnd and remove SExt.
- Value *NextVal = SExt->getOperand(0);
- TPT.eraseInstruction(SExt, NextVal);
+ // At this point we have: ext ty opnd to ty.
+ // Reassign the uses of ExtInst to the opnd and remove ExtInst.
+ Value *NextVal = ExtInst->getOperand(0);
+ TPT.eraseInstruction(ExtInst, NextVal);
return NextVal;
}
-Value *
-TypePromotionHelper::promoteOperandForOther(Instruction *SExt,
- TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts) {
- // By construction, the operand of SExt is an instruction. Otherwise we cannot
+Value *TypePromotionHelper::promoteOperandForOther(
+ Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs, 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 *SExtOpnd = cast<Instruction>(SExt->getOperand(0));
+ Instruction *ExtOpnd = cast<Instruction>(Ext->getOperand(0));
CreatedInsts = 0;
- if (!SExtOpnd->hasOneUse()) {
- // SExtOpnd will be promoted.
- // All its uses, but SExt, will need to use a truncated value of the
+ 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.
- Instruction *Trunc = TPT.createTrunc(SExt, SExtOpnd->getType());
- Trunc->removeFromParent();
- // Insert it just after the definition.
- Trunc->insertAfter(SExtOpnd);
+ Value *Trunc = TPT.createTrunc(Ext, ExtOpnd->getType());
+ if (Instruction *ITrunc = dyn_cast<Instruction>(Trunc)) {
+ ITrunc->removeFromParent();
+ // Insert it just after the definition.
+ ITrunc->insertAfter(ExtOpnd);
+ if (Truncs)
+ Truncs->push_back(ITrunc);
+ }
- TPT.replaceAllUsesWith(SExtOpnd, Trunc);
- // Restore the operand of SExt (which has been replace by the previous call
+ TPT.replaceAllUsesWith(ExtOpnd, Trunc);
+ // Restore the operand of Ext (which has been replace by the previous call
// to replaceAllUsesWith) to avoid creating a cycle trunc <-> sext.
- TPT.setOperand(SExt, 0, SExtOpnd);
+ TPT.setOperand(Ext, 0, ExtOpnd);
}
// Get through the Instruction:
// 1. Update its type.
- // 2. Replace the uses of SExt by Inst.
- // 3. Sign extend each operand that needs to be sign extended.
+ // 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 *, Type *>(SExtOpnd, SExtOpnd->getType()));
+ PromotedInsts.insert(std::pair<Instruction *, TypeIsSExt>(
+ ExtOpnd, TypeIsSExt(ExtOpnd->getType(), IsSExt)));
// Step #1.
- TPT.mutateType(SExtOpnd, SExt->getType());
+ TPT.mutateType(ExtOpnd, Ext->getType());
// Step #2.
- TPT.replaceAllUsesWith(SExt, SExtOpnd);
+ TPT.replaceAllUsesWith(Ext, ExtOpnd);
// Step #3.
- Instruction *SExtForOpnd = SExt;
+ Instruction *ExtForOpnd = Ext;
- DEBUG(dbgs() << "Propagate SExt to operands\n");
- for (int OpIdx = 0, EndOpIdx = SExtOpnd->getNumOperands(); OpIdx != EndOpIdx;
+ DEBUG(dbgs() << "Propagate Ext to operands\n");
+ for (int OpIdx = 0, EndOpIdx = ExtOpnd->getNumOperands(); OpIdx != EndOpIdx;
++OpIdx) {
- DEBUG(dbgs() << "Operand:\n" << *(SExtOpnd->getOperand(OpIdx)) << '\n');
- if (SExtOpnd->getOperand(OpIdx)->getType() == SExt->getType() ||
- !shouldSExtOperand(SExtOpnd, OpIdx)) {
+ DEBUG(dbgs() << "Operand:\n" << *(ExtOpnd->getOperand(OpIdx)) << '\n');
+ if (ExtOpnd->getOperand(OpIdx)->getType() == Ext->getType() ||
+ !shouldExtOperand(ExtOpnd, OpIdx)) {
DEBUG(dbgs() << "No need to propagate\n");
continue;
}
- // Check if we can statically sign extend the operand.
- Value *Opnd = SExtOpnd->getOperand(OpIdx);
+ // Check if we can statically extend the operand.
+ Value *Opnd = ExtOpnd->getOperand(OpIdx);
if (const ConstantInt *Cst = dyn_cast<ConstantInt>(Opnd)) {
- DEBUG(dbgs() << "Statically sign extend\n");
- TPT.setOperand(
- SExtOpnd, OpIdx,
- ConstantInt::getSigned(SExt->getType(), Cst->getSExtValue()));
+ DEBUG(dbgs() << "Statically extend\n");
+ unsigned BitWidth = Ext->getType()->getIntegerBitWidth();
+ APInt CstVal = IsSExt ? Cst->getValue().sext(BitWidth)
+ : Cst->getValue().zext(BitWidth);
+ TPT.setOperand(ExtOpnd, OpIdx, ConstantInt::get(Ext->getType(), CstVal));
continue;
}
// UndefValue are typed, so we have to statically sign extend them.
if (isa<UndefValue>(Opnd)) {
- DEBUG(dbgs() << "Statically sign extend\n");
- TPT.setOperand(SExtOpnd, OpIdx, UndefValue::get(SExt->getType()));
+ DEBUG(dbgs() << "Statically extend\n");
+ TPT.setOperand(ExtOpnd, OpIdx, UndefValue::get(Ext->getType()));
continue;
}
// Otherwise we have to explicity sign extend the operand.
- // Check if SExt was reused to sign extend an operand.
- if (!SExtForOpnd) {
+ // Check if Ext was reused to extend an operand.
+ if (!ExtForOpnd) {
// If yes, create a new one.
- DEBUG(dbgs() << "More operands to sext\n");
- SExtForOpnd = TPT.createSExt(SExt, Opnd, SExt->getType());
+ DEBUG(dbgs() << "More operands to ext\n");
+ Value *ValForExtOpnd = IsSExt ? TPT.createSExt(Ext, Opnd, Ext->getType())
+ : TPT.createZExt(Ext, Opnd, Ext->getType());
+ if (!isa<Instruction>(ValForExtOpnd)) {
+ TPT.setOperand(ExtOpnd, OpIdx, ValForExtOpnd);
+ continue;
+ }
+ ExtForOpnd = cast<Instruction>(ValForExtOpnd);
++CreatedInsts;
}
-
- TPT.setOperand(SExtForOpnd, 0, Opnd);
+ if (Exts)
+ Exts->push_back(ExtForOpnd);
+ TPT.setOperand(ExtForOpnd, 0, Opnd);
// Move the sign extension before the insertion point.
- TPT.moveBefore(SExtForOpnd, SExtOpnd);
- TPT.setOperand(SExtOpnd, OpIdx, SExtForOpnd);
+ TPT.moveBefore(ExtForOpnd, ExtOpnd);
+ TPT.setOperand(ExtOpnd, OpIdx, ExtForOpnd);
// If more sext are required, new instructions will have to be created.
- SExtForOpnd = NULL;
+ ExtForOpnd = nullptr;
}
- if (SExtForOpnd == SExt) {
- DEBUG(dbgs() << "Sign extension is useless now\n");
- TPT.eraseInstruction(SExt);
+ if (ExtForOpnd == Ext) {
+ DEBUG(dbgs() << "Extension is useless now\n");
+ TPT.eraseInstruction(Ext);
}
- return SExtOpnd;
+ return ExtOpnd;
}
/// IsPromotionProfitable - Check whether or not promoting an instruction
// 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.
- Instruction *PromotedInst = dyn_cast<Instruction>(PromotedOperand);
- 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,
- EVT::getEVT(PromotedInst->getType()));
+ return isPromotedInstructionLegal(TLI, PromotedOperand);
}
/// MatchOperationAddr - Given an instruction or constant expr, see if we can
return MatchAddr(AddrInst->getOperand(0), Depth);
return false;
case Instruction::BitCast:
+ case Instruction::AddrSpaceCast:
// 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() ||
case Instruction::Shl: {
// Can only handle X*C and X << C.
ConstantInt *RHS = dyn_cast<ConstantInt>(AddrInst->getOperand(1));
- if (!RHS) return false;
+ if (!RHS)
+ return false;
int64_t Scale = RHS->getSExtValue();
if (Opcode == Instruction::Shl)
Scale = 1LL << Scale;
return true;
}
- case Instruction::SExt: {
- // Try to move this sext out of the way of the addressing mode.
- Instruction *SExt = cast<Instruction>(AddrInst);
+ 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(
- SExt, InsertedTruncs, TLI, PromotedInsts);
+ TypePromotionHelper::Action TPH =
+ TypePromotionHelper::getAction(Ext, InsertedTruncs, TLI, PromotedInsts);
if (!TPH)
return false;
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
TPT.getRestorationPoint();
unsigned CreatedInsts = 0;
- Value *PromotedOperand = TPH(SExt, TPT, PromotedInsts, CreatedInsts);
+ Value *PromotedOperand =
+ TPH(Ext, TPT, PromotedInsts, CreatedInsts, nullptr, nullptr);
// 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 = sext op
+ // idx = ext op
// addr = gep base, idx
// is now:
- // promotedOpnd = sext opnd <- no match here
+ // promotedOpnd = ext opnd <- no match here
// op = promoted_add promotedOpnd, 1 <- match (later in recursive calls)
// addr = gep base, op <- match
if (MovedAway)
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 == 0) {
+ if (!AddrMode.BaseGV) {
AddrMode.BaseGV = GV;
if (TLI.isLegalAddressingMode(AddrMode, AccessTy))
return true;
- AddrMode.BaseGV = 0;
+ AddrMode.BaseGV = nullptr;
}
} else if (Instruction *I = dyn_cast<Instruction>(Addr)) {
ExtAddrMode BackupAddrMode = AddrMode;
if (TLI.isLegalAddressingMode(AddrMode, AccessTy))
return true;
AddrMode.HasBaseReg = false;
- AddrMode.BaseReg = 0;
+ AddrMode.BaseReg = nullptr;
}
// If the base register is already taken, see if we can do [r+r].
if (TLI.isLegalAddressingMode(AddrMode, AccessTy))
return true;
AddrMode.Scale = 0;
- AddrMode.ScaledReg = 0;
+ AddrMode.ScaledReg = nullptr;
}
// Couldn't match.
TPT.rollback(LastKnownGood);
/// return false.
static bool IsOperandAMemoryOperand(CallInst *CI, InlineAsm *IA, Value *OpVal,
const TargetLowering &TLI) {
- TargetLowering::AsmOperandInfoVector TargetConstraints = TLI.ParseConstraints(ImmutableCallSite(CI));
+ TargetLowering::AsmOperandInfoVector TargetConstraints =
+ TLI.ParseConstraints(ImmutableCallSite(CI));
for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];
/// Add the ultimately found memory instructions to MemoryUses.
static bool FindAllMemoryUses(Instruction *I,
SmallVectorImpl<std::pair<Instruction*,unsigned> > &MemoryUses,
- SmallPtrSet<Instruction*, 16> &ConsideredInsts,
+ SmallPtrSetImpl<Instruction*> &ConsideredInsts,
const TargetLowering &TLI) {
// If we already considered this instruction, we're done.
- if (!ConsideredInsts.insert(I))
+ if (!ConsideredInsts.insert(I).second)
return false;
// If this is an obviously unfoldable instruction, bail out.
return true;
// Loop over all the uses, recursively processing them.
- for (Value::use_iterator UI = I->use_begin(), E = I->use_end();
- UI != E; ++UI) {
- User *U = *UI;
+ for (Use &U : I->uses()) {
+ Instruction *UserI = cast<Instruction>(U.getUser());
- if (LoadInst *LI = dyn_cast<LoadInst>(U)) {
- MemoryUses.push_back(std::make_pair(LI, UI.getOperandNo()));
+ if (LoadInst *LI = dyn_cast<LoadInst>(UserI)) {
+ MemoryUses.push_back(std::make_pair(LI, U.getOperandNo()));
continue;
}
- if (StoreInst *SI = dyn_cast<StoreInst>(U)) {
- unsigned opNo = UI.getOperandNo();
+ if (StoreInst *SI = dyn_cast<StoreInst>(UserI)) {
+ unsigned opNo = U.getOperandNo();
if (opNo == 0) return true; // Storing addr, not into addr.
MemoryUses.push_back(std::make_pair(SI, opNo));
continue;
}
- if (CallInst *CI = dyn_cast<CallInst>(U)) {
+ if (CallInst *CI = dyn_cast<CallInst>(UserI)) {
InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue());
if (!IA) return true;
continue;
}
- if (FindAllMemoryUses(cast<Instruction>(U), MemoryUses, ConsideredInsts,
- TLI))
+ if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI))
return true;
}
bool AddressingModeMatcher::ValueAlreadyLiveAtInst(Value *Val,Value *KnownLive1,
Value *KnownLive2) {
// If Val is either of the known-live values, we know it is live!
- if (Val == 0 || Val == KnownLive1 || Val == KnownLive2)
+ if (Val == nullptr || Val == KnownLive1 || Val == KnownLive2)
return true;
// All values other than instructions and arguments (e.g. constants) are live.
// 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 = 0;
+ BaseReg = nullptr;
if (ValueAlreadyLiveAtInst(ScaledReg, AMBefore.BaseReg, AMBefore.ScaledReg))
- ScaledReg = 0;
+ ScaledReg = nullptr;
// If folding this instruction (and it's subexprs) didn't extend any live
// ranges, we're ok with it.
- if (BaseReg == 0 && ScaledReg == 0)
+ if (!BaseReg && !ScaledReg)
return true;
// If all uses of this instruction are ultimately load/store/inlineasm's,
ExtAddrMode Result;
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
TPT.getRestorationPoint();
- AddressingModeMatcher Matcher(MatchedAddrModeInsts, TLI, AddressAccessTy,
+ AddressingModeMatcher Matcher(MatchedAddrModeInsts, TM, AddressAccessTy,
MemoryInst, Result, InsertedTruncs,
PromotedInsts, TPT);
Matcher.IgnoreProfitability = true;
// Use a worklist to iteratively look through PHI nodes, and ensure that
// the addressing mode obtained from the non-PHI roots of the graph
// are equivalent.
- Value *Consensus = 0;
+ Value *Consensus = nullptr;
unsigned NumUsesConsensus = 0;
bool IsNumUsesConsensusValid = false;
SmallVector<Instruction*, 16> AddrModeInsts;
worklist.pop_back();
// Break use-def graph loops.
- if (!Visited.insert(V)) {
- Consensus = 0;
+ if (!Visited.insert(V).second) {
+ Consensus = nullptr;
break;
}
// For non-PHIs, determine the addressing mode being computed.
SmallVector<Instruction*, 16> NewAddrModeInsts;
ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
- V, AccessTy, MemoryInst, NewAddrModeInsts, *TLI, InsertedTruncsSet,
+ V, AccessTy, MemoryInst, NewAddrModeInsts, *TM, InsertedTruncsSet,
PromotedInsts, TPT);
// This check is broken into two cases with very similar code to avoid using
continue;
}
- Consensus = 0;
+ Consensus = nullptr;
break;
}
Value *&SunkAddr = SunkAddrs[Addr];
if (SunkAddr) {
DEBUG(dbgs() << "CGP: Reusing nonlocal addrmode: " << AddrMode << " for "
- << *MemoryInst);
+ << *MemoryInst << "\n");
if (SunkAddr->getType() != Addr->getType())
SunkAddr = Builder.CreateBitCast(SunkAddr, Addr->getType());
+ } else if (AddrSinkUsingGEPs ||
+ (!AddrSinkUsingGEPs.getNumOccurrences() && TM &&
+ TM->getSubtargetImpl(*MemoryInst->getParent()->getParent())
+ ->useAA())) {
+ // By default, we use the GEP-based method when AA is used later. This
+ // prevents new inttoptr/ptrtoint pairs from degrading AA capabilities.
+ DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "
+ << *MemoryInst << "\n");
+ Type *IntPtrTy = TLI->getDataLayout()->getIntPtrType(Addr->getType());
+ Value *ResultPtr = nullptr, *ResultIndex = nullptr;
+
+ // First, find the pointer.
+ if (AddrMode.BaseReg && AddrMode.BaseReg->getType()->isPointerTy()) {
+ ResultPtr = AddrMode.BaseReg;
+ AddrMode.BaseReg = nullptr;
+ }
+
+ if (AddrMode.Scale && AddrMode.ScaledReg->getType()->isPointerTy()) {
+ // We can't add more than one pointer together, nor can we scale a
+ // pointer (both of which seem meaningless).
+ if (ResultPtr || AddrMode.Scale != 1)
+ return false;
+
+ ResultPtr = AddrMode.ScaledReg;
+ AddrMode.Scale = 0;
+ }
+
+ if (AddrMode.BaseGV) {
+ if (ResultPtr)
+ return false;
+
+ ResultPtr = AddrMode.BaseGV;
+ }
+
+ // If the real base value actually came from an inttoptr, then the matcher
+ // will look through it and provide only the integer value. In that case,
+ // use it here.
+ if (!ResultPtr && AddrMode.BaseReg) {
+ ResultPtr =
+ Builder.CreateIntToPtr(AddrMode.BaseReg, Addr->getType(), "sunkaddr");
+ AddrMode.BaseReg = nullptr;
+ } else if (!ResultPtr && AddrMode.Scale == 1) {
+ ResultPtr =
+ Builder.CreateIntToPtr(AddrMode.ScaledReg, Addr->getType(), "sunkaddr");
+ AddrMode.Scale = 0;
+ }
+
+ if (!ResultPtr &&
+ !AddrMode.BaseReg && !AddrMode.Scale && !AddrMode.BaseOffs) {
+ SunkAddr = Constant::getNullValue(Addr->getType());
+ } else if (!ResultPtr) {
+ return false;
+ } else {
+ Type *I8PtrTy =
+ Builder.getInt8PtrTy(Addr->getType()->getPointerAddressSpace());
+
+ // Start with the base register. Do this first so that subsequent address
+ // matching finds it last, which will prevent it from trying to match it
+ // as the scaled value in case it happens to be a mul. That would be
+ // problematic if we've sunk a different mul for the scale, because then
+ // we'd end up sinking both muls.
+ if (AddrMode.BaseReg) {
+ Value *V = AddrMode.BaseReg;
+ if (V->getType() != IntPtrTy)
+ V = Builder.CreateIntCast(V, IntPtrTy, /*isSigned=*/true, "sunkaddr");
+
+ ResultIndex = V;
+ }
+
+ // Add the scale value.
+ if (AddrMode.Scale) {
+ Value *V = AddrMode.ScaledReg;
+ if (V->getType() == IntPtrTy) {
+ // done.
+ } else if (cast<IntegerType>(IntPtrTy)->getBitWidth() <
+ cast<IntegerType>(V->getType())->getBitWidth()) {
+ V = Builder.CreateTrunc(V, IntPtrTy, "sunkaddr");
+ } else {
+ // It is only safe to sign extend the BaseReg if we know that the math
+ // required to create it did not overflow before we extend it. Since
+ // the original IR value was tossed in favor of a constant back when
+ // the AddrMode was created we need to bail out gracefully if widths
+ // do not match instead of extending it.
+ Instruction *I = dyn_cast_or_null<Instruction>(ResultIndex);
+ if (I && (ResultIndex != AddrMode.BaseReg))
+ I->eraseFromParent();
+ return false;
+ }
+
+ if (AddrMode.Scale != 1)
+ V = Builder.CreateMul(V, ConstantInt::get(IntPtrTy, AddrMode.Scale),
+ "sunkaddr");
+ if (ResultIndex)
+ ResultIndex = Builder.CreateAdd(ResultIndex, V, "sunkaddr");
+ else
+ ResultIndex = V;
+ }
+
+ // Add in the Base Offset if present.
+ if (AddrMode.BaseOffs) {
+ Value *V = ConstantInt::get(IntPtrTy, AddrMode.BaseOffs);
+ if (ResultIndex) {
+ // We need to add this separately from the scale above to help with
+ // SDAG consecutive load/store merging.
+ if (ResultPtr->getType() != I8PtrTy)
+ ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
+ ResultPtr = Builder.CreateGEP(ResultPtr, ResultIndex, "sunkaddr");
+ }
+
+ ResultIndex = V;
+ }
+
+ if (!ResultIndex) {
+ SunkAddr = ResultPtr;
+ } else {
+ if (ResultPtr->getType() != I8PtrTy)
+ ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
+ SunkAddr = Builder.CreateGEP(ResultPtr, ResultIndex, "sunkaddr");
+ }
+
+ if (SunkAddr->getType() != Addr->getType())
+ SunkAddr = Builder.CreateBitCast(SunkAddr, Addr->getType());
+ }
} else {
DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "
- << *MemoryInst);
+ << *MemoryInst << "\n");
Type *IntPtrTy = TLI->getDataLayout()->getIntPtrType(Addr->getType());
- Value *Result = 0;
+ 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
cast<IntegerType>(V->getType())->getBitWidth()) {
V = Builder.CreateTrunc(V, IntPtrTy, "sunkaddr");
} else {
- V = Builder.CreateSExt(V, IntPtrTy, "sunkaddr");
+ // 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),
Result = V;
}
- if (Result == 0)
+ if (!Result)
SunkAddr = Constant::getNullValue(Addr->getType());
else
SunkAddr = Builder.CreateIntToPtr(Result, Addr->getType(), "sunkaddr");
return MadeChange;
}
+/// \brief Check if all the uses of \p Inst are equivalent (or free) zero or
+/// sign extensions.
+static bool hasSameExtUse(Instruction *Inst, const TargetLowering &TLI) {
+ assert(!Inst->use_empty() && "Input must have at least one use");
+ const Instruction *FirstUser = cast<Instruction>(*Inst->user_begin());
+ bool IsSExt = isa<SExtInst>(FirstUser);
+ Type *ExtTy = FirstUser->getType();
+ for (const User *U : Inst->users()) {
+ const Instruction *UI = cast<Instruction>(U);
+ if ((IsSExt && !isa<SExtInst>(UI)) || (!IsSExt && !isa<ZExtInst>(UI)))
+ return false;
+ Type *CurTy = UI->getType();
+ // Same input and output types: Same instruction after CSE.
+ if (CurTy == ExtTy)
+ continue;
+
+ // If IsSExt is true, we are in this situation:
+ // a = Inst
+ // b = sext ty1 a to ty2
+ // c = sext ty1 a to ty3
+ // Assuming ty2 is shorter than ty3, this could be turned into:
+ // a = Inst
+ // b = sext ty1 a to ty2
+ // c = sext ty2 b to ty3
+ // However, the last sext is not free.
+ if (IsSExt)
+ return false;
+
+ // This is a ZExt, maybe this is free to extend from one type to another.
+ // In that case, we would not account for a different use.
+ Type *NarrowTy;
+ Type *LargeTy;
+ if (ExtTy->getScalarType()->getIntegerBitWidth() >
+ CurTy->getScalarType()->getIntegerBitWidth()) {
+ NarrowTy = CurTy;
+ LargeTy = ExtTy;
+ } else {
+ NarrowTy = ExtTy;
+ LargeTy = CurTy;
+ }
+
+ if (!TLI.isZExtFree(NarrowTy, LargeTy))
+ return false;
+ }
+ // All uses are the same or can be derived from one another for free.
+ return true;
+}
+
+/// \brief Try to form ExtLd by promoting \p Exts until they reach a
+/// load instruction.
+/// If an ext(load) can be formed, it is returned via \p LI for the load
+/// and \p Inst for the extension.
+/// Otherwise LI == nullptr and Inst == nullptr.
+/// When some promotion happened, \p TPT contains the proper state to
+/// revert them.
+///
+/// \return true when promoting was necessary to expose the ext(load)
+/// opportunity, false otherwise.
+///
+/// Example:
+/// \code
+/// %ld = load i32* %addr
+/// %add = add nuw i32 %ld, 4
+/// %zext = zext i32 %add to i64
+/// \endcode
+/// =>
+/// \code
+/// %ld = load i32* %addr
+/// %zext = zext i32 %ld to i64
+/// %add = add nuw i64 %zext, 4
+/// \encode
+/// Thanks to the promotion, we can match zext(load i32*) to i64.
+bool CodeGenPrepare::ExtLdPromotion(TypePromotionTransaction &TPT,
+ LoadInst *&LI, Instruction *&Inst,
+ const SmallVectorImpl<Instruction *> &Exts,
+ unsigned CreatedInsts = 0) {
+ // Iterate over all the extensions to see if one form an ext(load).
+ for (auto I : Exts) {
+ // Check if we directly have ext(load).
+ if ((LI = dyn_cast<LoadInst>(I->getOperand(0)))) {
+ Inst = I;
+ // No promotion happened here.
+ return false;
+ }
+ // Check whether or not we want to do any promotion.
+ if (!TLI || !TLI->enableExtLdPromotion() || DisableExtLdPromotion)
+ continue;
+ // Get the action to perform the promotion.
+ TypePromotionHelper::Action TPH = TypePromotionHelper::getAction(
+ I, InsertedTruncsSet, *TLI, PromotedInsts);
+ // Check if we can promote.
+ if (!TPH)
+ continue;
+ // Save the current state.
+ TypePromotionTransaction::ConstRestorationPt LastKnownGood =
+ TPT.getRestorationPoint();
+ SmallVector<Instruction *, 4> NewExts;
+ unsigned NewCreatedInsts = 0;
+ // Promote.
+ Value *PromotedVal =
+ TPH(I, TPT, PromotedInsts, NewCreatedInsts, &NewExts, nullptr);
+ assert(PromotedVal &&
+ "TypePromotionHelper should have filtered out those cases");
+
+ // We would be able to merge only one extension in a load.
+ // Therefore, if we have more than 1 new extension we heuristically
+ // cut this search path, because it means we degrade the code quality.
+ // With exactly 2, the transformation is neutral, because we will merge
+ // one extension but leave one. However, we optimistically keep going,
+ // because the new extension may be removed too.
+ unsigned TotalCreatedInsts = CreatedInsts + NewCreatedInsts;
+ if (!StressExtLdPromotion &&
+ (TotalCreatedInsts > 1 ||
+ !isPromotedInstructionLegal(*TLI, PromotedVal))) {
+ // The promotion is not profitable, rollback to the previous state.
+ TPT.rollback(LastKnownGood);
+ continue;
+ }
+ // The promotion is profitable.
+ // Check if it exposes an ext(load).
+ (void)ExtLdPromotion(TPT, LI, Inst, NewExts, TotalCreatedInsts);
+ if (LI && (StressExtLdPromotion || NewCreatedInsts == 0 ||
+ // If we have created a new extension, i.e., now we have two
+ // extensions. We must make sure one of them is merged with
+ // the load, otherwise we may degrade the code quality.
+ (LI->hasOneUse() || hasSameExtUse(LI, *TLI))))
+ // Promotion happened.
+ return true;
+ // If this does not help to expose an ext(load) then, rollback.
+ TPT.rollback(LastKnownGood);
+ }
+ // None of the extension can form an ext(load).
+ LI = nullptr;
+ Inst = nullptr;
+ return false;
+}
+
/// MoveExtToFormExtLoad - Move a zext or sext fed by a load into the same
/// basic block as the load, unless conditions are unfavorable. This allows
/// SelectionDAG to fold the extend into the load.
+/// \p I[in/out] the extension may be modified during the process if some
+/// promotions apply.
///
-bool CodeGenPrepare::MoveExtToFormExtLoad(Instruction *I) {
+bool CodeGenPrepare::MoveExtToFormExtLoad(Instruction *&I) {
+ // Try to promote a chain of computation if it allows to form
+ // an extended load.
+ TypePromotionTransaction TPT;
+ TypePromotionTransaction::ConstRestorationPt LastKnownGood =
+ TPT.getRestorationPoint();
+ SmallVector<Instruction *, 1> Exts;
+ Exts.push_back(I);
// Look for a load being extended.
- LoadInst *LI = dyn_cast<LoadInst>(I->getOperand(0));
- if (!LI) return false;
+ LoadInst *LI = nullptr;
+ Instruction *OldExt = I;
+ bool HasPromoted = ExtLdPromotion(TPT, LI, I, Exts);
+ if (!LI || !I) {
+ assert(!HasPromoted && !LI && "If we did not match any load instruction "
+ "the code must remain the same");
+ I = OldExt;
+ return false;
+ }
// If they're already in the same block, there's nothing to do.
- if (LI->getParent() == I->getParent())
+ // Make the cheap checks first if we did not promote.
+ // If we promoted, we need to check if it is indeed profitable.
+ if (!HasPromoted && LI->getParent() == I->getParent())
return false;
+ EVT VT = TLI->getValueType(I->getType());
+ EVT LoadVT = TLI->getValueType(LI->getType());
+
// If the load has other users and the truncate is not free, this probably
// isn't worthwhile.
- if (!LI->hasOneUse() &&
- TLI && (TLI->isTypeLegal(TLI->getValueType(LI->getType())) ||
- !TLI->isTypeLegal(TLI->getValueType(I->getType()))) &&
- !TLI->isTruncateFree(I->getType(), LI->getType()))
+ if (!LI->hasOneUse() && TLI &&
+ (TLI->isTypeLegal(LoadVT) || !TLI->isTypeLegal(VT)) &&
+ !TLI->isTruncateFree(I->getType(), LI->getType())) {
+ I = OldExt;
+ TPT.rollback(LastKnownGood);
return false;
+ }
// Check whether the target supports casts folded into loads.
unsigned LType;
assert(isa<SExtInst>(I) && "Unexpected ext type!");
LType = ISD::SEXTLOAD;
}
- if (TLI && !TLI->isLoadExtLegal(LType, TLI->getValueType(LI->getType())))
+ if (TLI && !TLI->isLoadExtLegal(LType, VT, LoadVT)) {
+ I = OldExt;
+ TPT.rollback(LastKnownGood);
return false;
+ }
// Move the extend into the same block as the load, so that SelectionDAG
// can fold it.
+ TPT.commit();
I->removeFromParent();
I->insertAfter(LI);
++NumExtsMoved;
return false;
bool DefIsLiveOut = false;
- for (Value::use_iterator UI = I->use_begin(), E = I->use_end();
- UI != E; ++UI) {
- Instruction *User = cast<Instruction>(*UI);
+ for (User *U : I->users()) {
+ Instruction *UI = cast<Instruction>(U);
// Figure out which BB this ext is used in.
- BasicBlock *UserBB = User->getParent();
+ BasicBlock *UserBB = UI->getParent();
if (UserBB == DefBB) continue;
DefIsLiveOut = true;
break;
return false;
// Make sure none of the uses are PHI nodes.
- for (Value::use_iterator UI = Src->use_begin(), E = Src->use_end();
- UI != E; ++UI) {
- Instruction *User = cast<Instruction>(*UI);
- BasicBlock *UserBB = User->getParent();
+ 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>(User) || isa<LoadInst>(User) || isa<StoreInst>(User))
+ if (isa<PHINode>(UI) || isa<LoadInst>(UI) || isa<StoreInst>(UI))
return false;
}
DenseMap<BasicBlock*, Instruction*> InsertedTruncs;
bool MadeChange = false;
- for (Value::use_iterator UI = Src->use_begin(), E = Src->use_end();
- UI != E; ++UI) {
- Use &TheUse = UI.getUse();
- Instruction *User = cast<Instruction>(*UI);
+ for (Use &U : Src->uses()) {
+ Instruction *User = cast<Instruction>(U.getUser());
// Figure out which BB this ext is used in.
BasicBlock *UserBB = User->getParent();
}
// Replace a use of the {s|z}ext source with a use of the result.
- TheUse = InsertedTrunc;
+ U = InsertedTrunc;
++NumExtUses;
MadeChange = true;
}
return true;
}
-
-bool isBroadcastShuffle(ShuffleVectorInst *SVI) {
+static bool isBroadcastShuffle(ShuffleVectorInst *SVI) {
SmallVector<int, 16> Mask(SVI->getShuffleMask());
int SplatElem = -1;
for (unsigned i = 0; i < Mask.size(); ++i) {
DenseMap<BasicBlock*, Instruction*> InsertedShuffles;
bool MadeChange = false;
- for (Value::use_iterator UI = SVI->use_begin(), E = SVI->use_end();
- UI != E; ++UI) {
- Instruction *User = cast<Instruction>(*UI);
+ for (User *U : SVI->users()) {
+ Instruction *UI = cast<Instruction>(U);
// Figure out which BB this ext is used in.
- BasicBlock *UserBB = User->getParent();
+ BasicBlock *UserBB = UI->getParent();
if (UserBB == DefBB) continue;
// For now only apply this when the splat is used by a shift instruction.
- if (!User->isShift()) continue;
+ if (!UI->isShift()) continue;
// Everything checks out, sink the shuffle if the user's block doesn't
// already have a copy.
SVI->getOperand(2), "", InsertPt);
}
- User->replaceUsesOfWith(SVI, InsertedShuffle);
+ UI->replaceUsesOfWith(SVI, InsertedShuffle);
MadeChange = true;
}
return MadeChange;
}
-bool CodeGenPrepare::OptimizeInst(Instruction *I) {
+namespace {
+/// \brief Helper class to promote a scalar operation to a vector one.
+/// This class is used to move downward extractelement transition.
+/// E.g.,
+/// a = vector_op <2 x i32>
+/// b = extractelement <2 x i32> a, i32 0
+/// c = scalar_op b
+/// store c
+///
+/// =>
+/// a = vector_op <2 x i32>
+/// c = vector_op a (equivalent to scalar_op on the related lane)
+/// * d = extractelement <2 x i32> c, i32 0
+/// * store d
+/// Assuming both extractelement and store can be combine, we get rid of the
+/// transition.
+class VectorPromoteHelper {
+ /// Used to perform some checks on the legality of vector operations.
+ const TargetLowering &TLI;
+
+ /// Used to estimated the cost of the promoted chain.
+ const TargetTransformInfo &TTI;
+
+ /// The transition being moved downwards.
+ Instruction *Transition;
+ /// The sequence of instructions to be promoted.
+ SmallVector<Instruction *, 4> InstsToBePromoted;
+ /// Cost of combining a store and an extract.
+ unsigned StoreExtractCombineCost;
+ /// Instruction that will be combined with the transition.
+ Instruction *CombineInst;
+
+ /// \brief The instruction that represents the current end of the transition.
+ /// Since we are faking the promotion until we reach the end of the chain
+ /// of computation, we need a way to get the current end of the transition.
+ Instruction *getEndOfTransition() const {
+ if (InstsToBePromoted.empty())
+ return Transition;
+ return InstsToBePromoted.back();
+ }
+
+ /// \brief Return the index of the original value in the transition.
+ /// E.g., for "extractelement <2 x i32> c, i32 1" the original value,
+ /// c, is at index 0.
+ unsigned getTransitionOriginalValueIdx() const {
+ assert(isa<ExtractElementInst>(Transition) &&
+ "Other kind of transitions are not supported yet");
+ return 0;
+ }
+
+ /// \brief Return the index of the index in the transition.
+ /// E.g., for "extractelement <2 x i32> c, i32 0" the index
+ /// is at index 1.
+ unsigned getTransitionIdx() const {
+ assert(isa<ExtractElementInst>(Transition) &&
+ "Other kind of transitions are not supported yet");
+ return 1;
+ }
+
+ /// \brief Get the type of the transition.
+ /// This is the type of the original value.
+ /// E.g., for "extractelement <2 x i32> c, i32 1" the type of the
+ /// transition is <2 x i32>.
+ Type *getTransitionType() const {
+ return Transition->getOperand(getTransitionOriginalValueIdx())->getType();
+ }
+
+ /// \brief Promote \p ToBePromoted by moving \p Def downward through.
+ /// I.e., we have the following sequence:
+ /// Def = Transition <ty1> a to <ty2>
+ /// b = ToBePromoted <ty2> Def, ...
+ /// =>
+ /// b = ToBePromoted <ty1> a, ...
+ /// Def = Transition <ty1> ToBePromoted to <ty2>
+ void promoteImpl(Instruction *ToBePromoted);
+
+ /// \brief Check whether or not it is profitable to promote all the
+ /// instructions enqueued to be promoted.
+ bool isProfitableToPromote() {
+ Value *ValIdx = Transition->getOperand(getTransitionOriginalValueIdx());
+ unsigned Index = isa<ConstantInt>(ValIdx)
+ ? cast<ConstantInt>(ValIdx)->getZExtValue()
+ : -1;
+ Type *PromotedType = getTransitionType();
+
+ StoreInst *ST = cast<StoreInst>(CombineInst);
+ unsigned AS = ST->getPointerAddressSpace();
+ unsigned Align = ST->getAlignment();
+ // Check if this store is supported.
+ if (!TLI.allowsMisalignedMemoryAccesses(
+ TLI.getValueType(ST->getValueOperand()->getType()), AS, Align)) {
+ // If this is not supported, there is no way we can combine
+ // the extract with the store.
+ return false;
+ }
+
+ // The scalar chain of computation has to pay for the transition
+ // scalar to vector.
+ // The vector chain has to account for the combining cost.
+ uint64_t ScalarCost =
+ TTI.getVectorInstrCost(Transition->getOpcode(), PromotedType, Index);
+ uint64_t VectorCost = StoreExtractCombineCost;
+ for (const auto &Inst : InstsToBePromoted) {
+ // Compute the cost.
+ // By construction, all instructions being promoted are arithmetic ones.
+ // Moreover, one argument is a constant that can be viewed as a splat
+ // constant.
+ Value *Arg0 = Inst->getOperand(0);
+ bool IsArg0Constant = isa<UndefValue>(Arg0) || isa<ConstantInt>(Arg0) ||
+ isa<ConstantFP>(Arg0);
+ TargetTransformInfo::OperandValueKind Arg0OVK =
+ IsArg0Constant ? TargetTransformInfo::OK_UniformConstantValue
+ : TargetTransformInfo::OK_AnyValue;
+ TargetTransformInfo::OperandValueKind Arg1OVK =
+ !IsArg0Constant ? TargetTransformInfo::OK_UniformConstantValue
+ : TargetTransformInfo::OK_AnyValue;
+ ScalarCost += TTI.getArithmeticInstrCost(
+ Inst->getOpcode(), Inst->getType(), Arg0OVK, Arg1OVK);
+ VectorCost += TTI.getArithmeticInstrCost(Inst->getOpcode(), PromotedType,
+ Arg0OVK, Arg1OVK);
+ }
+ DEBUG(dbgs() << "Estimated cost of computation to be promoted:\nScalar: "
+ << ScalarCost << "\nVector: " << VectorCost << '\n');
+ return ScalarCost > VectorCost;
+ }
+
+ /// \brief Generate a constant vector with \p Val with the same
+ /// number of elements as the transition.
+ /// \p UseSplat defines whether or not \p Val should be replicated
+ /// accross the whole vector.
+ /// In other words, if UseSplat == true, we generate <Val, Val, ..., Val>,
+ /// otherwise we generate a vector with as many undef as possible:
+ /// <undef, ..., undef, Val, undef, ..., undef> where \p Val is only
+ /// used at the index of the extract.
+ Value *getConstantVector(Constant *Val, bool UseSplat) const {
+ unsigned ExtractIdx = UINT_MAX;
+ if (!UseSplat) {
+ // If we cannot determine where the constant must be, we have to
+ // use a splat constant.
+ Value *ValExtractIdx = Transition->getOperand(getTransitionIdx());
+ if (ConstantInt *CstVal = dyn_cast<ConstantInt>(ValExtractIdx))
+ ExtractIdx = CstVal->getSExtValue();
+ else
+ UseSplat = true;
+ }
+
+ unsigned End = getTransitionType()->getVectorNumElements();
+ if (UseSplat)
+ return ConstantVector::getSplat(End, Val);
+
+ SmallVector<Constant *, 4> ConstVec;
+ UndefValue *UndefVal = UndefValue::get(Val->getType());
+ for (unsigned Idx = 0; Idx != End; ++Idx) {
+ if (Idx == ExtractIdx)
+ ConstVec.push_back(Val);
+ else
+ ConstVec.push_back(UndefVal);
+ }
+ return ConstantVector::get(ConstVec);
+ }
+
+ /// \brief Check if promoting to a vector type an operand at \p OperandIdx
+ /// in \p Use can trigger undefined behavior.
+ static bool canCauseUndefinedBehavior(const Instruction *Use,
+ unsigned OperandIdx) {
+ // This is not safe to introduce undef when the operand is on
+ // the right hand side of a division-like instruction.
+ if (OperandIdx != 1)
+ return false;
+ switch (Use->getOpcode()) {
+ default:
+ return false;
+ case Instruction::SDiv:
+ case Instruction::UDiv:
+ case Instruction::SRem:
+ case Instruction::URem:
+ return true;
+ case Instruction::FDiv:
+ case Instruction::FRem:
+ return !Use->hasNoNaNs();
+ }
+ llvm_unreachable(nullptr);
+ }
+
+public:
+ VectorPromoteHelper(const TargetLowering &TLI, const TargetTransformInfo &TTI,
+ Instruction *Transition, unsigned CombineCost)
+ : TLI(TLI), TTI(TTI), Transition(Transition),
+ StoreExtractCombineCost(CombineCost), CombineInst(nullptr) {
+ assert(Transition && "Do not know how to promote null");
+ }
+
+ /// \brief Check if we can promote \p ToBePromoted to \p Type.
+ bool canPromote(const Instruction *ToBePromoted) const {
+ // We could support CastInst too.
+ return isa<BinaryOperator>(ToBePromoted);
+ }
+
+ /// \brief Check if it is profitable to promote \p ToBePromoted
+ /// by moving downward the transition through.
+ bool shouldPromote(const Instruction *ToBePromoted) const {
+ // Promote only if all the operands can be statically expanded.
+ // Indeed, we do not want to introduce any new kind of transitions.
+ for (const Use &U : ToBePromoted->operands()) {
+ const Value *Val = U.get();
+ if (Val == getEndOfTransition()) {
+ // If the use is a division and the transition is on the rhs,
+ // we cannot promote the operation, otherwise we may create a
+ // division by zero.
+ if (canCauseUndefinedBehavior(ToBePromoted, U.getOperandNo()))
+ return false;
+ continue;
+ }
+ if (!isa<ConstantInt>(Val) && !isa<UndefValue>(Val) &&
+ !isa<ConstantFP>(Val))
+ return false;
+ }
+ // Check that the resulting operation is legal.
+ int ISDOpcode = TLI.InstructionOpcodeToISD(ToBePromoted->getOpcode());
+ if (!ISDOpcode)
+ return false;
+ return StressStoreExtract ||
+ TLI.isOperationLegalOrCustom(
+ ISDOpcode, TLI.getValueType(getTransitionType(), true));
+ }
+
+ /// \brief Check whether or not \p Use can be combined
+ /// with the transition.
+ /// I.e., is it possible to do Use(Transition) => AnotherUse?
+ bool canCombine(const Instruction *Use) { return isa<StoreInst>(Use); }
+
+ /// \brief Record \p ToBePromoted as part of the chain to be promoted.
+ void enqueueForPromotion(Instruction *ToBePromoted) {
+ InstsToBePromoted.push_back(ToBePromoted);
+ }
+
+ /// \brief Set the instruction that will be combined with the transition.
+ void recordCombineInstruction(Instruction *ToBeCombined) {
+ assert(canCombine(ToBeCombined) && "Unsupported instruction to combine");
+ CombineInst = ToBeCombined;
+ }
+
+ /// \brief Promote all the instructions enqueued for promotion if it is
+ /// is profitable.
+ /// \return True if the promotion happened, false otherwise.
+ bool promote() {
+ // Check if there is something to promote.
+ // Right now, if we do not have anything to combine with,
+ // we assume the promotion is not profitable.
+ if (InstsToBePromoted.empty() || !CombineInst)
+ return false;
+
+ // Check cost.
+ if (!StressStoreExtract && !isProfitableToPromote())
+ return false;
+
+ // Promote.
+ for (auto &ToBePromoted : InstsToBePromoted)
+ promoteImpl(ToBePromoted);
+ InstsToBePromoted.clear();
+ return true;
+ }
+};
+} // End of anonymous namespace.
+
+void VectorPromoteHelper::promoteImpl(Instruction *ToBePromoted) {
+ // At this point, we know that all the operands of ToBePromoted but Def
+ // can be statically promoted.
+ // For Def, we need to use its parameter in ToBePromoted:
+ // b = ToBePromoted ty1 a
+ // Def = Transition ty1 b to ty2
+ // Move the transition down.
+ // 1. Replace all uses of the promoted operation by the transition.
+ // = ... b => = ... Def.
+ assert(ToBePromoted->getType() == Transition->getType() &&
+ "The type of the result of the transition does not match "
+ "the final type");
+ ToBePromoted->replaceAllUsesWith(Transition);
+ // 2. Update the type of the uses.
+ // b = ToBePromoted ty2 Def => b = ToBePromoted ty1 Def.
+ Type *TransitionTy = getTransitionType();
+ ToBePromoted->mutateType(TransitionTy);
+ // 3. Update all the operands of the promoted operation with promoted
+ // operands.
+ // b = ToBePromoted ty1 Def => b = ToBePromoted ty1 a.
+ for (Use &U : ToBePromoted->operands()) {
+ Value *Val = U.get();
+ Value *NewVal = nullptr;
+ if (Val == Transition)
+ NewVal = Transition->getOperand(getTransitionOriginalValueIdx());
+ else if (isa<UndefValue>(Val) || isa<ConstantInt>(Val) ||
+ isa<ConstantFP>(Val)) {
+ // Use a splat constant if it is not safe to use undef.
+ NewVal = getConstantVector(
+ cast<Constant>(Val),
+ isa<UndefValue>(Val) ||
+ canCauseUndefinedBehavior(ToBePromoted, U.getOperandNo()));
+ } else
+ llvm_unreachable("Did you modified shouldPromote and forgot to update "
+ "this?");
+ ToBePromoted->setOperand(U.getOperandNo(), NewVal);
+ }
+ Transition->removeFromParent();
+ Transition->insertAfter(ToBePromoted);
+ Transition->setOperand(getTransitionOriginalValueIdx(), ToBePromoted);
+}
+
+/// Some targets can do store(extractelement) with one instruction.
+/// Try to push the extractelement towards the stores when the target
+/// has this feature and this is profitable.
+bool CodeGenPrepare::OptimizeExtractElementInst(Instruction *Inst) {
+ unsigned CombineCost = UINT_MAX;
+ if (DisableStoreExtract || !TLI ||
+ (!StressStoreExtract &&
+ !TLI->canCombineStoreAndExtract(Inst->getOperand(0)->getType(),
+ Inst->getOperand(1), CombineCost)))
+ return false;
+
+ // At this point we know that Inst is a vector to scalar transition.
+ // Try to move it down the def-use chain, until:
+ // - We can combine the transition with its single use
+ // => we got rid of the transition.
+ // - We escape the current basic block
+ // => we would need to check that we are moving it at a cheaper place and
+ // we do not do that for now.
+ BasicBlock *Parent = Inst->getParent();
+ DEBUG(dbgs() << "Found an interesting transition: " << *Inst << '\n');
+ VectorPromoteHelper VPH(*TLI, *TTI, Inst, CombineCost);
+ // If the transition has more than one use, assume this is not going to be
+ // beneficial.
+ while (Inst->hasOneUse()) {
+ Instruction *ToBePromoted = cast<Instruction>(*Inst->user_begin());
+ DEBUG(dbgs() << "Use: " << *ToBePromoted << '\n');
+
+ if (ToBePromoted->getParent() != Parent) {
+ DEBUG(dbgs() << "Instruction to promote is in a different block ("
+ << ToBePromoted->getParent()->getName()
+ << ") than the transition (" << Parent->getName() << ").\n");
+ return false;
+ }
+
+ if (VPH.canCombine(ToBePromoted)) {
+ DEBUG(dbgs() << "Assume " << *Inst << '\n'
+ << "will be combined with: " << *ToBePromoted << '\n');
+ VPH.recordCombineInstruction(ToBePromoted);
+ bool Changed = VPH.promote();
+ NumStoreExtractExposed += Changed;
+ return Changed;
+ }
+
+ DEBUG(dbgs() << "Try promoting.\n");
+ if (!VPH.canPromote(ToBePromoted) || !VPH.shouldPromote(ToBePromoted))
+ return false;
+
+ DEBUG(dbgs() << "Promoting is possible... Enqueue for promotion!\n");
+
+ VPH.enqueueForPromotion(ToBePromoted);
+ Inst = ToBePromoted;
+ }
+ return false;
+}
+
+bool CodeGenPrepare::OptimizeInst(Instruction *I, bool& ModifiedDT) {
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, TLI ? TLI->getDataLayout() : 0,
+ if (Value *V = SimplifyInstruction(P, TLI ? TLI->getDataLayout() : nullptr,
TLInfo, DT)) {
P->replaceAllUsesWith(V);
P->eraseFromParent();
return true;
if (isa<ZExtInst>(I) || isa<SExtInst>(I)) {
- bool MadeChange = MoveExtToFormExtLoad(I);
- return MadeChange | OptimizeExtUses(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(CI->getType())) ==
+ TargetLowering::TypeExpandInteger) {
+ return SinkCast(CI);
+ } else {
+ bool MadeChange = MoveExtToFormExtLoad(I);
+ return MadeChange | OptimizeExtUses(I);
+ }
}
return false;
}
return false;
}
+ BinaryOperator *BinOp = dyn_cast<BinaryOperator>(I);
+
+ if (BinOp && (BinOp->getOpcode() == Instruction::AShr ||
+ BinOp->getOpcode() == Instruction::LShr)) {
+ ConstantInt *CI = dyn_cast<ConstantInt>(BinOp->getOperand(1));
+ if (TLI && CI && TLI->hasExtractBitsInsn())
+ return OptimizeExtractBits(BinOp, CI, *TLI);
+
+ return false;
+ }
+
if (GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(I)) {
if (GEPI->hasAllZeroIndices()) {
/// The GEP operand must be a pointer, so must its result -> BitCast
GEPI->replaceAllUsesWith(NC);
GEPI->eraseFromParent();
++NumGEPsElim;
- OptimizeInst(NC);
+ OptimizeInst(NC, ModifiedDT);
return true;
}
return false;
}
if (CallInst *CI = dyn_cast<CallInst>(I))
- return OptimizeCallInst(CI);
+ 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 (isa<ExtractElementInst>(I))
+ return OptimizeExtractElementInst(I);
+
return false;
}
// In this pass we look for GEP and cast instructions that are used
// across basic blocks and rewrite them to improve basic-block-at-a-time
// selection.
-bool CodeGenPrepare::OptimizeBlock(BasicBlock &BB) {
+bool CodeGenPrepare::OptimizeBlock(BasicBlock &BB, bool& ModifiedDT) {
SunkAddrs.clear();
bool MadeChange = false;
CurInstIterator = BB.begin();
- while (CurInstIterator != BB.end())
- MadeChange |= OptimizeInst(CurInstIterator++);
-
+ while (CurInstIterator != BB.end()) {
+ MadeChange |= OptimizeInst(CurInstIterator++, ModifiedDT);
+ if (ModifiedDT)
+ return true;
+ }
MadeChange |= DupRetToEnableTailCallOpts(&BB);
return MadeChange;
// find a node corresponding to the value.
bool CodeGenPrepare::PlaceDbgValues(Function &F) {
bool MadeChange = false;
- for (Function::iterator I = F.begin(), E = F.end(); I != E; ++I) {
- Instruction *PrevNonDbgInst = NULL;
- for (BasicBlock::iterator BI = I->begin(), BE = I->end(); BI != BE;) {
- Instruction *Insn = BI; ++BI;
+ 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);
- if (!DVI) {
+ // Leave dbg.values that refer to an alloca alone. These
+ // instrinsics describe the address of a variable (= the alloca)
+ // being taken. They should not be moved next to the alloca
+ // (and to the beginning of the scope), but rather stay close to
+ // where said address is used.
+ if (!DVI || (DVI->getValue() && isa<AllocaInst>(DVI->getValue()))) {
PrevNonDbgInst = Insn;
continue;
}
}
return MadeChange;
}
+
+// If there is a sequence that branches based on comparing a single bit
+// against zero that can be combined into a single instruction, and the
+// target supports folding these into a single instruction, sink the
+// mask and compare into the branch uses. Do this before OptimizeBlock ->
+// OptimizeInst -> OptimizeCmpExpression, which perturbs the pattern being
+// searched for.
+bool CodeGenPrepare::sinkAndCmp(Function &F) {
+ if (!EnableAndCmpSinking)
+ return false;
+ if (!TLI || !TLI->isMaskAndBranchFoldingLegal())
+ return false;
+ bool MadeChange = false;
+ for (Function::iterator I = F.begin(), E = F.end(); I != E; ) {
+ BasicBlock *BB = I++;
+
+ // Does this BB end with the following?
+ // %andVal = and %val, #single-bit-set
+ // %icmpVal = icmp %andResult, 0
+ // br i1 %cmpVal label %dest1, label %dest2"
+ BranchInst *Brcc = dyn_cast<BranchInst>(BB->getTerminator());
+ if (!Brcc || !Brcc->isConditional())
+ continue;
+ ICmpInst *Cmp = dyn_cast<ICmpInst>(Brcc->getOperand(0));
+ if (!Cmp || Cmp->getParent() != BB)
+ continue;
+ ConstantInt *Zero = dyn_cast<ConstantInt>(Cmp->getOperand(1));
+ if (!Zero || !Zero->isZero())
+ continue;
+ Instruction *And = dyn_cast<Instruction>(Cmp->getOperand(0));
+ if (!And || And->getOpcode() != Instruction::And || And->getParent() != BB)
+ continue;
+ ConstantInt* Mask = dyn_cast<ConstantInt>(And->getOperand(1));
+ if (!Mask || !Mask->getUniqueInteger().isPowerOf2())
+ continue;
+ DEBUG(dbgs() << "found and; icmp ?,0; brcc\n"); DEBUG(BB->dump());
+
+ // Push the "and; icmp" for any users that are conditional branches.
+ // Since there can only be one branch use per BB, we don't need to keep
+ // track of which BBs we insert into.
+ for (Value::use_iterator UI = Cmp->use_begin(), E = Cmp->use_end();
+ UI != E; ) {
+ Use &TheUse = *UI;
+ // Find brcc use.
+ BranchInst *BrccUser = dyn_cast<BranchInst>(*UI);
+ ++UI;
+ if (!BrccUser || !BrccUser->isConditional())
+ continue;
+ BasicBlock *UserBB = BrccUser->getParent();
+ if (UserBB == BB) continue;
+ DEBUG(dbgs() << "found Brcc use\n");
+
+ // Sink the "and; icmp" to use.
+ MadeChange = true;
+ BinaryOperator *NewAnd =
+ BinaryOperator::CreateAnd(And->getOperand(0), And->getOperand(1), "",
+ BrccUser);
+ CmpInst *NewCmp =
+ CmpInst::Create(Cmp->getOpcode(), Cmp->getPredicate(), NewAnd, Zero,
+ "", BrccUser);
+ TheUse = NewCmp;
+ ++NumAndCmpsMoved;
+ DEBUG(BrccUser->getParent()->dump());
+ }
+ }
+ return MadeChange;
+}
+
+/// \brief Retrieve the probabilities of a conditional branch. Returns true on
+/// success, or returns false if no or invalid metadata was found.
+static bool extractBranchMetadata(BranchInst *BI,
+ uint64_t &ProbTrue, uint64_t &ProbFalse) {
+ assert(BI->isConditional() &&
+ "Looking for probabilities on unconditional branch?");
+ auto *ProfileData = BI->getMetadata(LLVMContext::MD_prof);
+ if (!ProfileData || ProfileData->getNumOperands() != 3)
+ return false;
+
+ const auto *CITrue =
+ mdconst::dyn_extract<ConstantInt>(ProfileData->getOperand(1));
+ const auto *CIFalse =
+ mdconst::dyn_extract<ConstantInt>(ProfileData->getOperand(2));
+ if (!CITrue || !CIFalse)
+ return false;
+
+ ProbTrue = CITrue->getValue().getZExtValue();
+ ProbFalse = CIFalse->getValue().getZExtValue();
+
+ return true;
+}
+
+/// \brief Scale down both weights to fit into uint32_t.
+static void scaleWeights(uint64_t &NewTrue, uint64_t &NewFalse) {
+ uint64_t NewMax = (NewTrue > NewFalse) ? NewTrue : NewFalse;
+ uint32_t Scale = (NewMax / UINT32_MAX) + 1;
+ NewTrue = NewTrue / Scale;
+ NewFalse = NewFalse / Scale;
+}
+
+/// \brief Some targets prefer to split a conditional branch like:
+/// \code
+/// %0 = icmp ne i32 %a, 0
+/// %1 = icmp ne i32 %b, 0
+/// %or.cond = or i1 %0, %1
+/// br i1 %or.cond, label %TrueBB, label %FalseBB
+/// \endcode
+/// into multiple branch instructions like:
+/// \code
+/// bb1:
+/// %0 = icmp ne i32 %a, 0
+/// br i1 %0, label %TrueBB, label %bb2
+/// bb2:
+/// %1 = icmp ne i32 %b, 0
+/// br i1 %1, label %TrueBB, label %FalseBB
+/// \endcode
+/// This usually allows instruction selection to do even further optimizations
+/// and combine the compare with the branch instruction. Currently this is
+/// applied for targets which have "cheap" jump instructions.
+///
+/// FIXME: Remove the (equivalent?) implementation in SelectionDAG.
+///
+bool CodeGenPrepare::splitBranchCondition(Function &F) {
+ if (!TM || TM->Options.EnableFastISel != true ||
+ !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;
+
+ unsigned Opc;
+ Value *Cond1, *Cond2;
+ if (match(LogicOp, m_And(m_OneUse(m_Value(Cond1)),
+ m_OneUse(m_Value(Cond2)))))
+ Opc = Instruction::And;
+ else if (match(LogicOp, m_Or(m_OneUse(m_Value(Cond1)),
+ m_OneUse(m_Value(Cond2)))))
+ Opc = Instruction::Or;
+ else
+ continue;
+
+ if (!match(Cond1, m_CombineOr(m_Cmp(), m_BinOp())) ||
+ !match(Cond2, m_CombineOr(m_Cmp(), m_BinOp())) )
+ continue;
+
+ DEBUG(dbgs() << "Before branch condition splitting\n"; BB.dump());
+
+ // Create a new BB.
+ auto *InsertBefore = std::next(Function::iterator(BB))
+ .getNodePtrUnchecked();
+ auto TmpBB = BasicBlock::Create(BB.getContext(),
+ BB.getName() + ".cond.split",
+ BB.getParent(), InsertBefore);
+
+ // Update original basic block by using the first condition directly by the
+ // branch instruction and removing the no longer needed and/or instruction.
+ auto *Br1 = cast<BranchInst>(BB.getTerminator());
+ Br1->setCondition(Cond1);
+ LogicOp->eraseFromParent();
+
+ // Depending on the conditon we have to either replace the true or the false
+ // successor of the original branch instruction.
+ if (Opc == Instruction::And)
+ Br1->setSuccessor(0, TmpBB);
+ else
+ Br1->setSuccessor(1, TmpBB);
+
+ // Fill in the new basic block.
+ auto *Br2 = IRBuilder<>(TmpBB).CreateCondBr(Cond2, TBB, FBB);
+ if (auto *I = dyn_cast<Instruction>(Cond2)) {
+ I->removeFromParent();
+ I->insertBefore(Br2);
+ }
+
+ // Update PHI nodes in both successors. The original BB needs to be
+ // replaced in one succesor's PHI nodes, because the branch comes now from
+ // the newly generated BB (NewBB). In the other successor we need to add one
+ // incoming edge to the PHI nodes, because both branch instructions target
+ // now the same successor. Depending on the original branch condition
+ // (and/or) we have to swap the successors (TrueDest, FalseDest), so that
+ // we perfrom the correct update for the PHI nodes.
+ // This doesn't change the successor order of the just created branch
+ // instruction (or any other instruction).
+ if (Opc == Instruction::Or)
+ std::swap(TBB, FBB);
+
+ // Replace the old BB with the new BB.
+ for (auto &I : *TBB) {
+ PHINode *PN = dyn_cast<PHINode>(&I);
+ if (!PN)
+ break;
+ int i;
+ while ((i = PN->getBasicBlockIndex(&BB)) >= 0)
+ PN->setIncomingBlock(i, TmpBB);
+ }
+
+ // Add another incoming edge form the new BB.
+ for (auto &I : *FBB) {
+ PHINode *PN = dyn_cast<PHINode>(&I);
+ if (!PN)
+ break;
+ auto *Val = PN->getIncomingValueForBlock(&BB);
+ PN->addIncoming(Val, TmpBB);
+ }
+
+ // Update the branch weights (from SelectionDAGBuilder::
+ // FindMergedConditions).
+ if (Opc == Instruction::Or) {
+ // Codegen X | Y as:
+ // BB1:
+ // jmp_if_X TBB
+ // jmp TmpBB
+ // TmpBB:
+ // jmp_if_Y TBB
+ // jmp FBB
+ //
+
+ // We have flexibility in setting Prob for BB1 and Prob for NewBB.
+ // The requirement is that
+ // TrueProb for BB1 + (FalseProb for BB1 * TrueProb for TmpBB)
+ // = TrueProb for orignal BB.
+ // Assuming the orignal weights are A and B, one choice is to set BB1's
+ // weights to A and A+2B, and set TmpBB's weights to A and 2B. This choice
+ // assumes that
+ // TrueProb for BB1 == FalseProb for BB1 * TrueProb for TmpBB.
+ // Another choice is to assume TrueProb for BB1 equals to TrueProb for
+ // TmpBB, but the math is more complicated.
+ uint64_t TrueWeight, FalseWeight;
+ if (extractBranchMetadata(Br1, TrueWeight, FalseWeight)) {
+ uint64_t NewTrueWeight = TrueWeight;
+ uint64_t NewFalseWeight = TrueWeight + 2 * FalseWeight;
+ scaleWeights(NewTrueWeight, NewFalseWeight);
+ Br1->setMetadata(LLVMContext::MD_prof, MDBuilder(Br1->getContext())
+ .createBranchWeights(TrueWeight, FalseWeight));
+
+ NewTrueWeight = TrueWeight;
+ NewFalseWeight = 2 * FalseWeight;
+ scaleWeights(NewTrueWeight, NewFalseWeight);
+ Br2->setMetadata(LLVMContext::MD_prof, MDBuilder(Br2->getContext())
+ .createBranchWeights(TrueWeight, FalseWeight));
+ }
+ } else {
+ // Codegen X & Y as:
+ // BB1:
+ // jmp_if_X TmpBB
+ // jmp FBB
+ // TmpBB:
+ // jmp_if_Y TBB
+ // jmp FBB
+ //
+ // This requires creation of TmpBB after CurBB.
+
+ // We have flexibility in setting Prob for BB1 and Prob for TmpBB.
+ // The requirement is that
+ // FalseProb for BB1 + (TrueProb for BB1 * FalseProb for TmpBB)
+ // = FalseProb for orignal BB.
+ // Assuming the orignal weights are A and B, one choice is to set BB1's
+ // weights to 2A+B and B, and set TmpBB's weights to 2A and B. This choice
+ // assumes that
+ // FalseProb for BB1 == TrueProb for BB1 * FalseProb for TmpBB.
+ uint64_t TrueWeight, FalseWeight;
+ if (extractBranchMetadata(Br1, TrueWeight, FalseWeight)) {
+ uint64_t NewTrueWeight = 2 * TrueWeight + FalseWeight;
+ uint64_t NewFalseWeight = FalseWeight;
+ scaleWeights(NewTrueWeight, NewFalseWeight);
+ Br1->setMetadata(LLVMContext::MD_prof, MDBuilder(Br1->getContext())
+ .createBranchWeights(TrueWeight, FalseWeight));
+
+ NewTrueWeight = 2 * TrueWeight;
+ NewFalseWeight = FalseWeight;
+ scaleWeights(NewTrueWeight, NewFalseWeight);
+ Br2->setMetadata(LLVMContext::MD_prof, MDBuilder(Br2->getContext())
+ .createBranchWeights(TrueWeight, FalseWeight));
+ }
+ }
+
+ // Request DOM Tree update.
+ // Note: No point in getting fancy here, since the DT info is never
+ // available to CodeGenPrepare and the existing update code is broken
+ // anyways.
+ ModifiedDT = true;
+
+ MadeChange = true;
+
+ DEBUG(dbgs() << "After branch condition splitting\n"; BB.dump();
+ TmpBB->dump());
+ }
+ return MadeChange;
+}
projects / oota-llvm.git / blobdiff