#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/PatternMatch.h"
+#include "llvm/IR/Statepoint.h"
#include "llvm/IR/ValueHandle.h"
#include "llvm/IR/ValueMap.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
-#include "llvm/Target/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;
"computations were sunk");
STATISTIC(NumExtsMoved, "Number of [s|z]ext instructions combined with loads");
STATISTIC(NumExtUses, "Number of uses of [s|z]ext instructions optimized");
+STATISTIC(NumAndsAdded,
+ "Number of and mask instructions added to form ext loads");
+STATISTIC(NumAndUses, "Number of uses of and mask instructions optimized");
STATISTIC(NumRetsDup, "Number of return instructions duplicated");
STATISTIC(NumDbgValueMoved, "Number of debug value instructions moved");
STATISTIC(NumSelectsExpanded, "Number of selects turned into branches");
"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."));
"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;
-struct TypeIsSExt {
- Type *Ty;
- bool IsSExt;
- TypeIsSExt(Type *Ty, bool IsSExt) : Ty(Ty), IsSExt(IsSExt) {}
-};
+typedef PointerIntPair<Type *, 1, bool> TypeIsSExt;
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;
- /// CurInstIterator - As we scan instructions optimizing them, this is the
- /// next instruction to optimize. Xforms that can invalidate this should
- /// update it.
+ /// As we scan instructions optimizing them, this is the next instruction
+ /// to optimize. Transforms that can invalidate this should update it.
BasicBlock::iterator CurInstIterator;
/// Keeps track of non-local addresses that have been sunk into a block.
/// multiple load/stores of the same address.
ValueMap<Value*, Value*> SunkAddrs;
- /// Keeps track of all truncates inserted for the current function.
- SetOfInstrs InsertedTruncsSet;
+ /// Keeps track of all instructions inserted for the current function.
+ SetOfInstrs InsertedInsts;
/// Keeps track of the type of the related instruction before their
/// promotion for the current function.
InstrToOrigTy PromotedInsts;
- /// ModifiedDT - If CFG is modified in anyway, dominator tree may need to
- /// be updated.
+ /// True if CFG is modified in any way.
bool ModifiedDT;
- /// OptSize - True if optimizing for size.
+ /// True if optimizing for size.
bool OptSize;
+ /// DataLayout for the Function being processed.
+ const DataLayout *DL;
+
public:
static char ID; // Pass identification, replacement for typeid
explicit CodeGenPrepare(const TargetMachine *TM = nullptr)
- : FunctionPass(ID), TM(TM), TLI(nullptr), TTI(nullptr) {
+ : FunctionPass(ID), TM(TM), TLI(nullptr), TTI(nullptr), DL(nullptr) {
initializeCodeGenPreparePass(*PassRegistry::getPassRegistry());
}
bool runOnFunction(Function &F) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addPreserved<DominatorTreeWrapperPass>();
- AU.addRequired<TargetLibraryInfo>();
- AU.addRequired<TargetTransformInfo>();
+ AU.addRequired<TargetLibraryInfoWrapperPass>();
+ AU.addRequired<TargetTransformInfoWrapperPass>();
}
private:
- bool EliminateFallThrough(Function &F);
- bool EliminateMostlyEmptyBlocks(Function &F);
- bool CanMergeBlocks(const BasicBlock *BB, const BasicBlock *DestBB) const;
- void EliminateMostlyEmptyBlock(BasicBlock *BB);
- bool OptimizeBlock(BasicBlock &BB);
- bool OptimizeInst(Instruction *I);
- bool OptimizeMemoryInst(Instruction *I, Value *Addr, Type *AccessTy);
- bool OptimizeInlineAsmInst(CallInst *CS);
- bool OptimizeCallInst(CallInst *CI);
- 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 eliminateFallThrough(Function &F);
+ bool eliminateMostlyEmptyBlocks(Function &F);
+ bool canMergeBlocks(const BasicBlock *BB, const BasicBlock *DestBB) const;
+ void eliminateMostlyEmptyBlock(BasicBlock *BB);
+ bool optimizeBlock(BasicBlock &BB, bool& ModifiedDT);
+ bool optimizeInst(Instruction *I, bool& ModifiedDT);
+ bool optimizeMemoryInst(Instruction *I, Value *Addr,
+ Type *AccessTy, unsigned AS);
+ bool optimizeInlineAsmInst(CallInst *CS);
+ bool optimizeCallInst(CallInst *CI, bool& ModifiedDT);
+ bool moveExtToFormExtLoad(Instruction *&I);
+ bool optimizeExtUses(Instruction *I);
+ bool optimizeLoadExt(LoadInst *I);
+ bool optimizeSelectInst(SelectInst *SI);
+ bool optimizeShuffleVectorInst(ShuffleVectorInst *SI);
+ bool optimizeSwitchInst(SwitchInst *CI);
+ bool optimizeExtractElementInst(Instruction *Inst);
+ bool dupRetToEnableTailCallOpts(BasicBlock *BB);
+ bool placeDbgValues(Function &F);
bool sinkAndCmp(Function &F);
+ bool extLdPromotion(TypePromotionTransaction &TPT, LoadInst *&LI,
+ Instruction *&Inst,
+ const SmallVectorImpl<Instruction *> &Exts,
+ unsigned CreatedInstCost);
bool splitBranchCondition(Function &F);
+ bool simplifyOffsetableRelocate(Instruction &I);
+ void stripInvariantGroupMetadata(Instruction &I);
};
}
if (skipOptnoneFunction(F))
return false;
+ DL = &F.getParent()->getDataLayout();
+
bool EverMadeChange = false;
// Clear per function information.
- InsertedTruncsSet.clear();
+ InsertedInsts.clear();
PromotedInsts.clear();
ModifiedDT = false;
if (TM)
- TLI = TM->getSubtargetImpl()->getTargetLowering();
- TLInfo = &getAnalysis<TargetLibraryInfo>();
- TTI = &getAnalysis<TargetTransformInfo>();
- DominatorTreeWrapperPass *DTWP =
- getAnalysisIfAvailable<DominatorTreeWrapperPass>();
- DT = DTWP ? &DTWP->getDomTree() : nullptr;
- OptSize = F.getAttributes().hasAttribute(AttributeSet::FunctionIndex,
- Attribute::OptimizeForSize);
+ TLI = TM->getSubtargetImpl(F)->getTargetLowering();
+ TLInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
+ TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
+ OptSize = F.optForSize();
/// This optimization identifies DIV instructions that can be
/// profitably bypassed and carried out with a shorter, faster divide.
if (!OptSize && TLI && TLI->isSlowDivBypassed()) {
const DenseMap<unsigned int, unsigned int> &BypassWidths =
TLI->getBypassSlowDivWidths();
- for (Function::iterator I = F.begin(); I != F.end(); I++)
- EverMadeChange |= bypassSlowDivision(F, I, BypassWidths);
+ BasicBlock* BB = &*F.begin();
+ while (BB != nullptr) {
+ // bypassSlowDivision may create new BBs, but we don't want to reapply the
+ // optimization to those blocks.
+ BasicBlock* Next = BB->getNextNode();
+ EverMadeChange |= bypassSlowDivision(BB, BypassWidths);
+ BB = Next;
+ }
}
// Eliminate blocks that contain only PHI nodes and an
// unconditional branch.
- EverMadeChange |= EliminateMostlyEmptyBlocks(F);
+ EverMadeChange |= eliminateMostlyEmptyBlocks(F);
// llvm.dbg.value is far away from the value then iSel may not be able
// handle it properly. iSel will drop llvm.dbg.value if it can not
// find a node corresponding to the value.
- EverMadeChange |= PlaceDbgValues(F);
+ 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
while (MadeChange) {
MadeChange = false;
for (Function::iterator I = F.begin(); I != F.end(); ) {
- BasicBlock *BB = I++;
- MadeChange |= OptimizeBlock(*BB);
+ BasicBlock *BB = &*I++;
+ bool ModifiedDTOnIteration = false;
+ MadeChange |= optimizeBlock(*BB, ModifiedDTOnIteration);
+
+ // Restart BB iteration if the dominator tree of the Function was changed
+ if (ModifiedDTOnIteration)
+ break;
}
EverMadeChange |= MadeChange;
}
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
// Merge pairs of basic blocks with unconditional branches, connected by
// a single edge.
if (EverMadeChange || MadeChange)
- MadeChange |= EliminateFallThrough(F);
+ MadeChange |= eliminateFallThrough(F);
- if (MadeChange)
- ModifiedDT = true;
EverMadeChange |= MadeChange;
}
- if (ModifiedDT && DT)
- DT->recalculate(F);
+ if (!DisableGCOpts) {
+ SmallVector<Instruction *, 2> Statepoints;
+ for (BasicBlock &BB : F)
+ for (Instruction &I : BB)
+ if (isStatepoint(I))
+ Statepoints.push_back(&I);
+ for (auto &I : Statepoints)
+ EverMadeChange |= simplifyOffsetableRelocate(*I);
+ }
return EverMadeChange;
}
-/// EliminateFallThrough - Merge basic blocks which are connected
-/// by a single edge, where one of the basic blocks has a single successor
-/// pointing to the other basic block, which has a single predecessor.
-bool CodeGenPrepare::EliminateFallThrough(Function &F) {
+/// Merge basic blocks which are connected by a single edge, where one of the
+/// basic blocks has a single successor pointing to the other basic block,
+/// which has a single predecessor.
+bool CodeGenPrepare::eliminateFallThrough(Function &F) {
bool Changed = false;
// Scan all of the blocks in the function, except for the entry block.
for (Function::iterator I = std::next(F.begin()), E = F.end(); I != E;) {
- BasicBlock *BB = I++;
+ BasicBlock *BB = &*I++;
// If the destination block has a single pred, then this is a trivial
// edge, just collapse it.
BasicBlock *SinglePred = BB->getSinglePredecessor();
// 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, nullptr);
if (isEntry && BB != &BB->getParent()->getEntryBlock())
BB->moveBefore(&BB->getParent()->getEntryBlock());
// We have erased a block. Update the iterator.
- I = BB;
+ I = BB->getIterator();
}
}
return Changed;
}
-/// EliminateMostlyEmptyBlocks - eliminate blocks that contain only PHI nodes,
-/// debug info directives, and an unconditional branch. Passes before isel
-/// (e.g. LSR/loopsimplify) often split edges in ways that are non-optimal for
-/// isel. Start by eliminating these blocks so we can split them the way we
-/// want them.
-bool CodeGenPrepare::EliminateMostlyEmptyBlocks(Function &F) {
+/// Eliminate blocks that contain only PHI nodes, debug info directives, and an
+/// unconditional branch. Passes before isel (e.g. LSR/loopsimplify) often split
+/// edges in ways that are non-optimal for isel. Start by eliminating these
+/// blocks so we can split them the way we want them.
+bool CodeGenPrepare::eliminateMostlyEmptyBlocks(Function &F) {
bool MadeChange = false;
// Note that this intentionally skips the entry block.
for (Function::iterator I = std::next(F.begin()), E = F.end(); I != E;) {
- BasicBlock *BB = I++;
+ BasicBlock *BB = &*I++;
// If this block doesn't end with an uncond branch, ignore it.
BranchInst *BI = dyn_cast<BranchInst>(BB->getTerminator());
// If the instruction before the branch (skipping debug info) isn't a phi
// node, then other stuff is happening here.
- BasicBlock::iterator BBI = BI;
+ BasicBlock::iterator BBI = BI->getIterator();
if (BBI != BB->begin()) {
--BBI;
while (isa<DbgInfoIntrinsic>(BBI)) {
if (DestBB == BB)
continue;
- if (!CanMergeBlocks(BB, DestBB))
+ if (!canMergeBlocks(BB, DestBB))
continue;
- EliminateMostlyEmptyBlock(BB);
+ eliminateMostlyEmptyBlock(BB);
MadeChange = true;
}
return MadeChange;
}
-/// CanMergeBlocks - Return true if we can merge BB into DestBB if there is a
-/// single uncond branch between them, and BB contains no other non-phi
+/// Return true if we can merge BB into DestBB if there is a single
+/// unconditional branch between them, and BB contains no other non-phi
/// instructions.
-bool CodeGenPrepare::CanMergeBlocks(const BasicBlock *BB,
+bool CodeGenPrepare::canMergeBlocks(const BasicBlock *BB,
const BasicBlock *DestBB) const {
// We only want to eliminate blocks whose phi nodes are used by phi nodes in
// the successor. If there are more complex condition (e.g. preheaders),
}
-/// EliminateMostlyEmptyBlock - Eliminate a basic block that have only phi's and
-/// an unconditional branch in it.
-void CodeGenPrepare::EliminateMostlyEmptyBlock(BasicBlock *BB) {
+/// Eliminate a basic block that has only phi's and an unconditional branch in
+/// it.
+void CodeGenPrepare::eliminateMostlyEmptyBlock(BasicBlock *BB) {
BranchInst *BI = cast<BranchInst>(BB->getTerminator());
BasicBlock *DestBB = BI->getSuccessor(0);
// 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, nullptr);
if (isEntry && BB != &BB->getParent()->getEntryBlock())
BB->moveBefore(&BB->getParent()->getEntryBlock());
// The PHIs are now updated, change everything that refers to BB to use
// DestBB and remove BB.
BB->replaceAllUsesWith(DestBB);
- if (DT && !ModifiedDT) {
- BasicBlock *BBIDom = DT->getNode(BB)->getIDom()->getBlock();
- BasicBlock *DestBBIDom = DT->getNode(DestBB)->getIDom()->getBlock();
- BasicBlock *NewIDom = DT->findNearestCommonDominator(BBIDom, DestBBIDom);
- DT->changeImmediateDominator(DestBB, NewIDom);
- DT->eraseNode(BB);
- }
BB->eraseFromParent();
++NumBlocksElim;
DEBUG(dbgs() << "AFTER:\n" << *DestBB << "\n\n\n");
}
+// Computes a map of base pointer relocation instructions to corresponding
+// derived pointer relocation instructions given a vector of all relocate calls
+static void computeBaseDerivedRelocateMap(
+ const SmallVectorImpl<GCRelocateInst *> &AllRelocateCalls,
+ DenseMap<GCRelocateInst *, SmallVector<GCRelocateInst *, 2>>
+ &RelocateInstMap) {
+ // Collect information in two maps: one primarily for locating the base object
+ // while filling the second map; the second map is the final structure holding
+ // a mapping between Base and corresponding Derived relocate calls
+ DenseMap<std::pair<unsigned, unsigned>, GCRelocateInst *> RelocateIdxMap;
+ for (auto *ThisRelocate : AllRelocateCalls) {
+ auto K = std::make_pair(ThisRelocate->getBasePtrIndex(),
+ ThisRelocate->getDerivedPtrIndex());
+ RelocateIdxMap.insert(std::make_pair(K, ThisRelocate));
+ }
+ for (auto &Item : RelocateIdxMap) {
+ std::pair<unsigned, unsigned> Key = Item.first;
+ if (Key.first == Key.second)
+ // Base relocation: nothing to insert
+ continue;
+
+ GCRelocateInst *I = Item.second;
+ auto BaseKey = std::make_pair(Key.first, Key.first);
+
+ // We're iterating over RelocateIdxMap so we cannot modify it.
+ auto MaybeBase = RelocateIdxMap.find(BaseKey);
+ if (MaybeBase == RelocateIdxMap.end())
+ // TODO: We might want to insert a new base object relocate and gep off
+ // that, if there are enough derived object relocates.
+ continue;
+
+ RelocateInstMap[MaybeBase->second].push_back(I);
+ }
+}
+
+// Accepts a GEP and extracts the operands into a vector provided they're all
+// small integer constants
+static bool getGEPSmallConstantIntOffsetV(GetElementPtrInst *GEP,
+ SmallVectorImpl<Value *> &OffsetV) {
+ for (unsigned i = 1; i < GEP->getNumOperands(); i++) {
+ // Only accept small constant integer operands
+ auto Op = dyn_cast<ConstantInt>(GEP->getOperand(i));
+ if (!Op || Op->getZExtValue() > 20)
+ return false;
+ }
+
+ for (unsigned i = 1; i < GEP->getNumOperands(); i++)
+ OffsetV.push_back(GEP->getOperand(i));
+ return true;
+}
+
+// Takes a RelocatedBase (base pointer relocation instruction) and Targets to
+// replace, computes a replacement, and affects it.
+static bool
+simplifyRelocatesOffABase(GCRelocateInst *RelocatedBase,
+ const SmallVectorImpl<GCRelocateInst *> &Targets) {
+ bool MadeChange = false;
+ for (GCRelocateInst *ToReplace : Targets) {
+ assert(ToReplace->getBasePtrIndex() == RelocatedBase->getBasePtrIndex() &&
+ "Not relocating a derived object of the original base object");
+ if (ToReplace->getBasePtrIndex() == ToReplace->getDerivedPtrIndex()) {
+ // A duplicate relocate call. TODO: coalesce duplicates.
+ continue;
+ }
+
+ if (RelocatedBase->getParent() != ToReplace->getParent()) {
+ // Base and derived relocates are in different basic blocks.
+ // In this case transform is only valid when base dominates derived
+ // relocate. However it would be too expensive to check dominance
+ // for each such relocate, so we skip the whole transformation.
+ continue;
+ }
+
+ Value *Base = ToReplace->getBasePtr();
+ auto Derived = dyn_cast<GetElementPtrInst>(ToReplace->getDerivedPtr());
+ if (!Derived || Derived->getPointerOperand() != Base)
+ continue;
+
+ SmallVector<Value *, 2> OffsetV;
+ if (!getGEPSmallConstantIntOffsetV(Derived, OffsetV))
+ continue;
+
+ // Create a Builder and replace the target callsite with a gep
+ assert(RelocatedBase->getNextNode() && "Should always have one since it's not a terminator");
+
+ // Insert after RelocatedBase
+ IRBuilder<> Builder(RelocatedBase->getNextNode());
+ Builder.SetCurrentDebugLocation(ToReplace->getDebugLoc());
+
+ // If gc_relocate does not match the actual type, cast it to the right type.
+ // In theory, there must be a bitcast after gc_relocate if the type does not
+ // match, and we should reuse it to get the derived pointer. But it could be
+ // cases like this:
+ // bb1:
+ // ...
+ // %g1 = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(...)
+ // br label %merge
+ //
+ // bb2:
+ // ...
+ // %g2 = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(...)
+ // br label %merge
+ //
+ // merge:
+ // %p1 = phi i8 addrspace(1)* [ %g1, %bb1 ], [ %g2, %bb2 ]
+ // %cast = bitcast i8 addrspace(1)* %p1 in to i32 addrspace(1)*
+ //
+ // In this case, we can not find the bitcast any more. So we insert a new bitcast
+ // no matter there is already one or not. In this way, we can handle all cases, and
+ // the extra bitcast should be optimized away in later passes.
+ Value *ActualRelocatedBase = RelocatedBase;
+ if (RelocatedBase->getType() != Base->getType()) {
+ ActualRelocatedBase =
+ Builder.CreateBitCast(RelocatedBase, Base->getType());
+ }
+ Value *Replacement = Builder.CreateGEP(
+ Derived->getSourceElementType(), ActualRelocatedBase, makeArrayRef(OffsetV));
+ Replacement->takeName(ToReplace);
+ // If the newly generated derived pointer's type does not match the original derived
+ // pointer's type, cast the new derived pointer to match it. Same reasoning as above.
+ Value *ActualReplacement = Replacement;
+ if (Replacement->getType() != ToReplace->getType()) {
+ ActualReplacement =
+ Builder.CreateBitCast(Replacement, ToReplace->getType());
+ }
+ ToReplace->replaceAllUsesWith(ActualReplacement);
+ ToReplace->eraseFromParent();
+
+ MadeChange = true;
+ }
+ return MadeChange;
+}
+
+// Turns this:
+//
+// %base = ...
+// %ptr = gep %base + 15
+// %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
+// %base' = relocate(%tok, i32 4, i32 4)
+// %ptr' = relocate(%tok, i32 4, i32 5)
+// %val = load %ptr'
+//
+// into this:
+//
+// %base = ...
+// %ptr = gep %base + 15
+// %tok = statepoint (%fun, i32 0, i32 0, i32 0, %base, %ptr)
+// %base' = gc.relocate(%tok, i32 4, i32 4)
+// %ptr' = gep %base' + 15
+// %val = load %ptr'
+bool CodeGenPrepare::simplifyOffsetableRelocate(Instruction &I) {
+ bool MadeChange = false;
+ SmallVector<GCRelocateInst *, 2> AllRelocateCalls;
+
+ for (auto *U : I.users())
+ if (GCRelocateInst *Relocate = dyn_cast<GCRelocateInst>(U))
+ // Collect all the relocate calls associated with a statepoint
+ AllRelocateCalls.push_back(Relocate);
+
+ // We need atleast one base pointer relocation + one derived pointer
+ // relocation to mangle
+ if (AllRelocateCalls.size() < 2)
+ return false;
+
+ // RelocateInstMap is a mapping from the base relocate instruction to the
+ // corresponding derived relocate instructions
+ DenseMap<GCRelocateInst *, SmallVector<GCRelocateInst *, 2>> RelocateInstMap;
+ computeBaseDerivedRelocateMap(AllRelocateCalls, RelocateInstMap);
+ if (RelocateInstMap.empty())
+ return false;
+
+ for (auto &Item : RelocateInstMap)
+ // Item.first is the RelocatedBase to offset against
+ // Item.second is the vector of Targets to replace
+ MadeChange = simplifyRelocatesOffABase(Item.first, Item.second);
+ return MadeChange;
+}
+
/// SinkCast - Sink the specified cast instruction into its user blocks
static bool SinkCast(CastInst *CI) {
BasicBlock *DefBB = CI->getParent();
// Preincrement use iterator so we don't invalidate it.
++UI;
+ // If the block selected to receive the cast is an EH pad that does not
+ // allow non-PHI instructions before the terminator, we can't sink the
+ // cast.
+ if (UserBB->getTerminator()->isEHPad())
+ continue;
+
// If this user is in the same block as the cast, don't change the cast.
if (UserBB == DefBB) continue;
if (!InsertedCast) {
BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
- InsertedCast =
- CastInst::Create(CI->getOpcode(), CI->getOperand(0), CI->getType(), "",
- InsertPt);
- MadeChange = true;
+ assert(InsertPt != UserBB->end());
+ InsertedCast = CastInst::Create(CI->getOpcode(), CI->getOperand(0),
+ CI->getType(), "", &*InsertPt);
}
// Replace a use of the cast with a use of the new cast.
TheUse = InsertedCast;
+ MadeChange = true;
++NumCastUses;
}
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.
+/// 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){
+static bool OptimizeNoopCopyExpression(CastInst *CI, const TargetLowering &TLI,
+ const DataLayout &DL) {
// If this is a noop copy,
- EVT SrcVT = TLI.getValueType(CI->getOperand(0)->getType());
- EVT DstVT = TLI.getValueType(CI->getType());
+ EVT SrcVT = TLI.getValueType(DL, CI->getOperand(0)->getType());
+ EVT DstVT = TLI.getValueType(DL, CI->getType());
// This is an fp<->int conversion?
if (SrcVT.isInteger() != DstVT.isInteger())
return 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
-/// (PowerPC), where it might lose; some adjustment may be wanted there.
+/// Try to combine CI into a call to the llvm.uadd.with.overflow intrinsic if
+/// possible.
+///
+/// Return true if any changes were made.
+static bool CombineUAddWithOverflow(CmpInst *CI) {
+ Value *A, *B;
+ Instruction *AddI;
+ if (!match(CI,
+ m_UAddWithOverflow(m_Value(A), m_Value(B), m_Instruction(AddI))))
+ return false;
+
+ Type *Ty = AddI->getType();
+ if (!isa<IntegerType>(Ty))
+ return false;
+
+ // We don't want to move around uses of condition values this late, so we we
+ // check if it is legal to create the call to the intrinsic in the basic
+ // block containing the icmp:
+
+ if (AddI->getParent() != CI->getParent() && !AddI->hasOneUse())
+ return false;
+
+#ifndef NDEBUG
+ // Someday m_UAddWithOverflow may get smarter, but this is a safe assumption
+ // for now:
+ if (AddI->hasOneUse())
+ assert(*AddI->user_begin() == CI && "expected!");
+#endif
+
+ Module *M = CI->getModule();
+ Value *F = Intrinsic::getDeclaration(M, Intrinsic::uadd_with_overflow, Ty);
+
+ auto *InsertPt = AddI->hasOneUse() ? CI : AddI;
+
+ auto *UAddWithOverflow =
+ CallInst::Create(F, {A, B}, "uadd.overflow", InsertPt);
+ auto *UAdd = ExtractValueInst::Create(UAddWithOverflow, 0, "uadd", InsertPt);
+ auto *Overflow =
+ ExtractValueInst::Create(UAddWithOverflow, 1, "overflow", InsertPt);
+
+ CI->replaceAllUsesWith(Overflow);
+ AddI->replaceAllUsesWith(UAdd);
+ CI->eraseFromParent();
+ AddI->eraseFromParent();
+ return true;
+}
+
+/// Sink the given CmpInst into user blocks to reduce the number of virtual
+/// registers that must be created and coalesced. This is a clear win except on
+/// targets with multiple condition code registers (PowerPC), where it might
+/// lose; some adjustment may be wanted there.
///
/// Return true if any changes are made.
-static bool OptimizeCmpExpression(CmpInst *CI) {
+static bool SinkCmpExpression(CmpInst *CI) {
BasicBlock *DefBB = CI->getParent();
- /// InsertedCmp - Only insert a cmp in each block once.
+ /// Only insert a cmp in each block once.
DenseMap<BasicBlock*, CmpInst*> InsertedCmps;
bool MadeChange = false;
if (!InsertedCmp) {
BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
+ assert(InsertPt != UserBB->end());
InsertedCmp =
- CmpInst::Create(CI->getOpcode(),
- CI->getPredicate(), CI->getOperand(0),
- CI->getOperand(1), "", InsertPt);
- MadeChange = true;
+ CmpInst::Create(CI->getOpcode(), CI->getPredicate(),
+ CI->getOperand(0), CI->getOperand(1), "", &*InsertPt);
}
// Replace a use of the cmp with a use of the new cmp.
TheUse = InsertedCmp;
+ MadeChange = true;
++NumCmpUses;
}
// If we removed all uses, nuke the cmp.
- if (CI->use_empty())
+ if (CI->use_empty()) {
CI->eraseFromParent();
+ MadeChange = true;
+ }
return MadeChange;
}
-/// isExtractBitsCandidateUse - Check if the candidates could
-/// be combined with shift instruction, which includes:
+static bool OptimizeCmpExpression(CmpInst *CI) {
+ if (SinkCmpExpression(CI))
+ return true;
+
+ if (CombineUAddWithOverflow(CI))
+ return true;
+
+ return false;
+}
+
+/// Check if the candidates could be combined with a shift instruction, which
+/// includes:
/// 1. Truncate instruction
/// 2. And instruction and the imm is a mask of the low bits:
/// imm & (imm+1) == 0
return true;
}
-/// SinkShiftAndTruncate - sink both shift and truncate instruction
-/// to the use of truncate's BB.
+/// Sink both shift and truncate instruction to the use of truncate's BB.
static bool
SinkShiftAndTruncate(BinaryOperator *ShiftI, Instruction *User, ConstantInt *CI,
DenseMap<BasicBlock *, BinaryOperator *> &InsertedShifts,
- const TargetLowering &TLI) {
+ const TargetLowering &TLI, const DataLayout &DL) {
BasicBlock *UserBB = User->getParent();
DenseMap<BasicBlock *, CastInst *> InsertedTruncs;
TruncInst *TruncI = dyn_cast<TruncInst>(User);
// 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)))
+ ISDOpcode, TLI.getValueType(DL, TruncUser->getType(), true)))
continue;
// Don't bother for PHI nodes.
if (!InsertedShift && !InsertedTrunc) {
BasicBlock::iterator InsertPt = TruncUserBB->getFirstInsertionPt();
+ assert(InsertPt != TruncUserBB->end());
// Sink the shift
if (ShiftI->getOpcode() == Instruction::AShr)
- InsertedShift =
- BinaryOperator::CreateAShr(ShiftI->getOperand(0), CI, "", InsertPt);
+ InsertedShift = BinaryOperator::CreateAShr(ShiftI->getOperand(0), CI,
+ "", &*InsertPt);
else
- InsertedShift =
- BinaryOperator::CreateLShr(ShiftI->getOperand(0), CI, "", InsertPt);
+ InsertedShift = BinaryOperator::CreateLShr(ShiftI->getOperand(0), CI,
+ "", &*InsertPt);
// Sink the trunc
BasicBlock::iterator TruncInsertPt = TruncUserBB->getFirstInsertionPt();
TruncInsertPt++;
+ assert(TruncInsertPt != TruncUserBB->end());
InsertedTrunc = CastInst::Create(TruncI->getOpcode(), InsertedShift,
- TruncI->getType(), "", TruncInsertPt);
+ TruncI->getType(), "", &*TruncInsertPt);
MadeChange = true;
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:
+/// 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:
/// instruction.
/// Return true if any changes are made.
static bool OptimizeExtractBits(BinaryOperator *ShiftI, ConstantInt *CI,
- const TargetLowering &TLI) {
+ const TargetLowering &TLI,
+ const DataLayout &DL) {
BasicBlock *DefBB = ShiftI->getParent();
/// Only insert instructions in each block once.
DenseMap<BasicBlock *, BinaryOperator *> InsertedShifts;
- bool shiftIsLegal = TLI.isTypeLegal(TLI.getValueType(ShiftI->getType()));
+ bool shiftIsLegal = TLI.isTypeLegal(TLI.getValueType(DL, ShiftI->getType()));
bool MadeChange = false;
for (Value::user_iterator UI = ShiftI->user_begin(), E = ShiftI->user_end();
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()))))
+ &&
+ (!TLI.isTypeLegal(TLI.getValueType(DL, User->getType()))))
MadeChange =
- SinkShiftAndTruncate(ShiftI, User, CI, InsertedShifts, TLI);
+ SinkShiftAndTruncate(ShiftI, User, CI, InsertedShifts, TLI, DL);
continue;
}
if (!InsertedShift) {
BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
+ assert(InsertPt != UserBB->end());
if (ShiftI->getOpcode() == Instruction::AShr)
- InsertedShift =
- BinaryOperator::CreateAShr(ShiftI->getOperand(0), CI, "", InsertPt);
+ InsertedShift = BinaryOperator::CreateAShr(ShiftI->getOperand(0), CI,
+ "", &*InsertPt);
else
- InsertedShift =
- BinaryOperator::CreateLShr(ShiftI->getOperand(0), CI, "", InsertPt);
+ InsertedShift = BinaryOperator::CreateLShr(ShiftI->getOperand(0), CI,
+ "", &*InsertPt);
MadeChange = true;
}
return MadeChange;
}
-namespace {
-class CodeGenPrepareFortifiedLibCalls : public SimplifyFortifiedLibCalls {
-protected:
- void replaceCall(Value *With) override {
- CI->replaceAllUsesWith(With);
+// Translate a masked load intrinsic like
+// <16 x i32 > @llvm.masked.load( <16 x i32>* %addr, i32 align,
+// <16 x i1> %mask, <16 x i32> %passthru)
+// to a chain of basic blocks, with loading element one-by-one if
+// the appropriate mask bit is set
+//
+// %1 = bitcast i8* %addr to i32*
+// %2 = extractelement <16 x i1> %mask, i32 0
+// %3 = icmp eq i1 %2, true
+// br i1 %3, label %cond.load, label %else
+//
+//cond.load: ; preds = %0
+// %4 = getelementptr i32* %1, i32 0
+// %5 = load i32* %4
+// %6 = insertelement <16 x i32> undef, i32 %5, i32 0
+// br label %else
+//
+//else: ; preds = %0, %cond.load
+// %res.phi.else = phi <16 x i32> [ %6, %cond.load ], [ undef, %0 ]
+// %7 = extractelement <16 x i1> %mask, i32 1
+// %8 = icmp eq i1 %7, true
+// br i1 %8, label %cond.load1, label %else2
+//
+//cond.load1: ; preds = %else
+// %9 = getelementptr i32* %1, i32 1
+// %10 = load i32* %9
+// %11 = insertelement <16 x i32> %res.phi.else, i32 %10, i32 1
+// br label %else2
+//
+//else2: ; preds = %else, %cond.load1
+// %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
+// %12 = extractelement <16 x i1> %mask, i32 2
+// %13 = icmp eq i1 %12, true
+// br i1 %13, label %cond.load4, label %else5
+//
+static void ScalarizeMaskedLoad(CallInst *CI) {
+ Value *Ptr = CI->getArgOperand(0);
+ Value *Alignment = CI->getArgOperand(1);
+ Value *Mask = CI->getArgOperand(2);
+ Value *Src0 = CI->getArgOperand(3);
+
+ unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
+ VectorType *VecType = dyn_cast<VectorType>(CI->getType());
+ assert(VecType && "Unexpected return type of masked load intrinsic");
+
+ Type *EltTy = CI->getType()->getVectorElementType();
+
+ IRBuilder<> Builder(CI->getContext());
+ Instruction *InsertPt = CI;
+ BasicBlock *IfBlock = CI->getParent();
+ BasicBlock *CondBlock = nullptr;
+ BasicBlock *PrevIfBlock = CI->getParent();
+
+ Builder.SetInsertPoint(InsertPt);
+ Builder.SetCurrentDebugLocation(CI->getDebugLoc());
+
+ // Short-cut if the mask is all-true.
+ bool IsAllOnesMask = isa<Constant>(Mask) &&
+ cast<Constant>(Mask)->isAllOnesValue();
+
+ if (IsAllOnesMask) {
+ Value *NewI = Builder.CreateAlignedLoad(Ptr, AlignVal);
+ CI->replaceAllUsesWith(NewI);
CI->eraseFromParent();
+ return;
}
- bool isFoldable(unsigned SizeCIOp, unsigned, bool) const override {
- if (ConstantInt *SizeCI =
- dyn_cast<ConstantInt>(CI->getArgOperand(SizeCIOp)))
- return SizeCI->isAllOnesValue();
- return false;
+
+ // Adjust alignment for the scalar instruction.
+ AlignVal = std::min(AlignVal, VecType->getScalarSizeInBits()/8);
+ // Bitcast %addr fron i8* to EltTy*
+ Type *NewPtrType =
+ EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
+ Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
+ unsigned VectorWidth = VecType->getNumElements();
+
+ Value *UndefVal = UndefValue::get(VecType);
+
+ // The result vector
+ Value *VResult = UndefVal;
+
+ if (isa<ConstantVector>(Mask)) {
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+ if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
+ continue;
+ Value *Gep =
+ Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
+ LoadInst* Load = Builder.CreateAlignedLoad(Gep, AlignVal);
+ VResult = Builder.CreateInsertElement(VResult, Load,
+ Builder.getInt32(Idx));
+ }
+ Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
+ CI->replaceAllUsesWith(NewI);
+ CI->eraseFromParent();
+ return;
}
-};
-} // end anonymous namespace
-bool CodeGenPrepare::OptimizeCallInst(CallInst *CI) {
+ PHINode *Phi = nullptr;
+ Value *PrevPhi = UndefVal;
+
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+
+ // Fill the "else" block, created in the previous iteration
+ //
+ // %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
+ // %mask_1 = extractelement <16 x i1> %mask, i32 Idx
+ // %to_load = icmp eq i1 %mask_1, true
+ // br i1 %to_load, label %cond.load, label %else
+ //
+ if (Idx > 0) {
+ Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
+ Phi->addIncoming(VResult, CondBlock);
+ Phi->addIncoming(PrevPhi, PrevIfBlock);
+ PrevPhi = Phi;
+ VResult = Phi;
+ }
+
+ Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
+ Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
+ ConstantInt::get(Predicate->getType(), 1));
+
+ // Create "cond" block
+ //
+ // %EltAddr = getelementptr i32* %1, i32 0
+ // %Elt = load i32* %EltAddr
+ // VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
+ //
+ CondBlock = IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.load");
+ Builder.SetInsertPoint(InsertPt);
+
+ Value *Gep =
+ Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
+ LoadInst *Load = Builder.CreateAlignedLoad(Gep, AlignVal);
+ VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
+
+ // Create "else" block, fill it in the next iteration
+ BasicBlock *NewIfBlock =
+ CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
+ Builder.SetInsertPoint(InsertPt);
+ Instruction *OldBr = IfBlock->getTerminator();
+ BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
+ OldBr->eraseFromParent();
+ PrevIfBlock = IfBlock;
+ IfBlock = NewIfBlock;
+ }
+
+ Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
+ Phi->addIncoming(VResult, CondBlock);
+ Phi->addIncoming(PrevPhi, PrevIfBlock);
+ Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
+ CI->replaceAllUsesWith(NewI);
+ CI->eraseFromParent();
+}
+
+// Translate a masked store intrinsic, like
+// void @llvm.masked.store(<16 x i32> %src, <16 x i32>* %addr, i32 align,
+// <16 x i1> %mask)
+// to a chain of basic blocks, that stores element one-by-one if
+// the appropriate mask bit is set
+//
+// %1 = bitcast i8* %addr to i32*
+// %2 = extractelement <16 x i1> %mask, i32 0
+// %3 = icmp eq i1 %2, true
+// br i1 %3, label %cond.store, label %else
+//
+// cond.store: ; preds = %0
+// %4 = extractelement <16 x i32> %val, i32 0
+// %5 = getelementptr i32* %1, i32 0
+// store i32 %4, i32* %5
+// br label %else
+//
+// else: ; preds = %0, %cond.store
+// %6 = extractelement <16 x i1> %mask, i32 1
+// %7 = icmp eq i1 %6, true
+// br i1 %7, label %cond.store1, label %else2
+//
+// cond.store1: ; preds = %else
+// %8 = extractelement <16 x i32> %val, i32 1
+// %9 = getelementptr i32* %1, i32 1
+// store i32 %8, i32* %9
+// br label %else2
+// . . .
+static void ScalarizeMaskedStore(CallInst *CI) {
+ Value *Src = CI->getArgOperand(0);
+ Value *Ptr = CI->getArgOperand(1);
+ Value *Alignment = CI->getArgOperand(2);
+ Value *Mask = CI->getArgOperand(3);
+
+ unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
+ VectorType *VecType = dyn_cast<VectorType>(Src->getType());
+ assert(VecType && "Unexpected data type in masked store intrinsic");
+
+ Type *EltTy = VecType->getElementType();
+
+ IRBuilder<> Builder(CI->getContext());
+ Instruction *InsertPt = CI;
+ BasicBlock *IfBlock = CI->getParent();
+ Builder.SetInsertPoint(InsertPt);
+ Builder.SetCurrentDebugLocation(CI->getDebugLoc());
+
+ // Short-cut if the mask is all-true.
+ bool IsAllOnesMask = isa<Constant>(Mask) &&
+ cast<Constant>(Mask)->isAllOnesValue();
+
+ if (IsAllOnesMask) {
+ Builder.CreateAlignedStore(Src, Ptr, AlignVal);
+ CI->eraseFromParent();
+ return;
+ }
+
+ // Adjust alignment for the scalar instruction.
+ AlignVal = std::max(AlignVal, VecType->getScalarSizeInBits()/8);
+ // Bitcast %addr fron i8* to EltTy*
+ Type *NewPtrType =
+ EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
+ Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
+ unsigned VectorWidth = VecType->getNumElements();
+
+ if (isa<ConstantVector>(Mask)) {
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+ if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
+ continue;
+ Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
+ Value *Gep =
+ Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
+ Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
+ }
+ CI->eraseFromParent();
+ return;
+ }
+
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+
+ // Fill the "else" block, created in the previous iteration
+ //
+ // %mask_1 = extractelement <16 x i1> %mask, i32 Idx
+ // %to_store = icmp eq i1 %mask_1, true
+ // br i1 %to_store, label %cond.store, label %else
+ //
+ Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
+ Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
+ ConstantInt::get(Predicate->getType(), 1));
+
+ // Create "cond" block
+ //
+ // %OneElt = extractelement <16 x i32> %Src, i32 Idx
+ // %EltAddr = getelementptr i32* %1, i32 0
+ // %store i32 %OneElt, i32* %EltAddr
+ //
+ BasicBlock *CondBlock =
+ IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.store");
+ Builder.SetInsertPoint(InsertPt);
+
+ Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
+ Value *Gep =
+ Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
+ Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
+
+ // Create "else" block, fill it in the next iteration
+ BasicBlock *NewIfBlock =
+ CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
+ Builder.SetInsertPoint(InsertPt);
+ Instruction *OldBr = IfBlock->getTerminator();
+ BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
+ OldBr->eraseFromParent();
+ IfBlock = NewIfBlock;
+ }
+ CI->eraseFromParent();
+}
+
+// Translate a masked gather intrinsic like
+// <16 x i32 > @llvm.masked.gather.v16i32( <16 x i32*> %Ptrs, i32 4,
+// <16 x i1> %Mask, <16 x i32> %Src)
+// to a chain of basic blocks, with loading element one-by-one if
+// the appropriate mask bit is set
+//
+// % Ptrs = getelementptr i32, i32* %base, <16 x i64> %ind
+// % Mask0 = extractelement <16 x i1> %Mask, i32 0
+// % ToLoad0 = icmp eq i1 % Mask0, true
+// br i1 % ToLoad0, label %cond.load, label %else
+//
+// cond.load:
+// % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
+// % Load0 = load i32, i32* % Ptr0, align 4
+// % Res0 = insertelement <16 x i32> undef, i32 % Load0, i32 0
+// br label %else
+//
+// else:
+// %res.phi.else = phi <16 x i32>[% Res0, %cond.load], [undef, % 0]
+// % Mask1 = extractelement <16 x i1> %Mask, i32 1
+// % ToLoad1 = icmp eq i1 % Mask1, true
+// br i1 % ToLoad1, label %cond.load1, label %else2
+//
+// cond.load1:
+// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
+// % Load1 = load i32, i32* % Ptr1, align 4
+// % Res1 = insertelement <16 x i32> %res.phi.else, i32 % Load1, i32 1
+// br label %else2
+// . . .
+// % Result = select <16 x i1> %Mask, <16 x i32> %res.phi.select, <16 x i32> %Src
+// ret <16 x i32> %Result
+static void ScalarizeMaskedGather(CallInst *CI) {
+ Value *Ptrs = CI->getArgOperand(0);
+ Value *Alignment = CI->getArgOperand(1);
+ Value *Mask = CI->getArgOperand(2);
+ Value *Src0 = CI->getArgOperand(3);
+
+ VectorType *VecType = dyn_cast<VectorType>(CI->getType());
+
+ assert(VecType && "Unexpected return type of masked load intrinsic");
+
+ IRBuilder<> Builder(CI->getContext());
+ Instruction *InsertPt = CI;
+ BasicBlock *IfBlock = CI->getParent();
+ BasicBlock *CondBlock = nullptr;
+ BasicBlock *PrevIfBlock = CI->getParent();
+ Builder.SetInsertPoint(InsertPt);
+ unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
+
+ Builder.SetCurrentDebugLocation(CI->getDebugLoc());
+
+ Value *UndefVal = UndefValue::get(VecType);
+
+ // The result vector
+ Value *VResult = UndefVal;
+ unsigned VectorWidth = VecType->getNumElements();
+
+ // Shorten the way if the mask is a vector of constants.
+ bool IsConstMask = isa<ConstantVector>(Mask);
+
+ if (IsConstMask) {
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+ if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
+ continue;
+ Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
+ "Ptr" + Twine(Idx));
+ LoadInst *Load = Builder.CreateAlignedLoad(Ptr, AlignVal,
+ "Load" + Twine(Idx));
+ VResult = Builder.CreateInsertElement(VResult, Load,
+ Builder.getInt32(Idx),
+ "Res" + Twine(Idx));
+ }
+ Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
+ CI->replaceAllUsesWith(NewI);
+ CI->eraseFromParent();
+ return;
+ }
+
+ PHINode *Phi = nullptr;
+ Value *PrevPhi = UndefVal;
+
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+
+ // Fill the "else" block, created in the previous iteration
+ //
+ // %Mask1 = extractelement <16 x i1> %Mask, i32 1
+ // %ToLoad1 = icmp eq i1 %Mask1, true
+ // br i1 %ToLoad1, label %cond.load, label %else
+ //
+ if (Idx > 0) {
+ Phi = Builder.CreatePHI(VecType, 2, "res.phi.else");
+ Phi->addIncoming(VResult, CondBlock);
+ Phi->addIncoming(PrevPhi, PrevIfBlock);
+ PrevPhi = Phi;
+ VResult = Phi;
+ }
+
+ Value *Predicate = Builder.CreateExtractElement(Mask,
+ Builder.getInt32(Idx),
+ "Mask" + Twine(Idx));
+ Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
+ ConstantInt::get(Predicate->getType(), 1),
+ "ToLoad" + Twine(Idx));
+
+ // Create "cond" block
+ //
+ // %EltAddr = getelementptr i32* %1, i32 0
+ // %Elt = load i32* %EltAddr
+ // VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
+ //
+ CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.load");
+ Builder.SetInsertPoint(InsertPt);
+
+ Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
+ "Ptr" + Twine(Idx));
+ LoadInst *Load = Builder.CreateAlignedLoad(Ptr, AlignVal,
+ "Load" + Twine(Idx));
+ VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx),
+ "Res" + Twine(Idx));
+
+ // Create "else" block, fill it in the next iteration
+ BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
+ Builder.SetInsertPoint(InsertPt);
+ Instruction *OldBr = IfBlock->getTerminator();
+ BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
+ OldBr->eraseFromParent();
+ PrevIfBlock = IfBlock;
+ IfBlock = NewIfBlock;
+ }
+
+ Phi = Builder.CreatePHI(VecType, 2, "res.phi.select");
+ Phi->addIncoming(VResult, CondBlock);
+ Phi->addIncoming(PrevPhi, PrevIfBlock);
+ Value *NewI = Builder.CreateSelect(Mask, Phi, Src0);
+ CI->replaceAllUsesWith(NewI);
+ CI->eraseFromParent();
+}
+
+// Translate a masked scatter intrinsic, like
+// void @llvm.masked.scatter.v16i32(<16 x i32> %Src, <16 x i32*>* %Ptrs, i32 4,
+// <16 x i1> %Mask)
+// to a chain of basic blocks, that stores element one-by-one if
+// the appropriate mask bit is set.
+//
+// % Ptrs = getelementptr i32, i32* %ptr, <16 x i64> %ind
+// % Mask0 = extractelement <16 x i1> % Mask, i32 0
+// % ToStore0 = icmp eq i1 % Mask0, true
+// br i1 %ToStore0, label %cond.store, label %else
+//
+// cond.store:
+// % Elt0 = extractelement <16 x i32> %Src, i32 0
+// % Ptr0 = extractelement <16 x i32*> %Ptrs, i32 0
+// store i32 %Elt0, i32* % Ptr0, align 4
+// br label %else
+//
+// else:
+// % Mask1 = extractelement <16 x i1> % Mask, i32 1
+// % ToStore1 = icmp eq i1 % Mask1, true
+// br i1 % ToStore1, label %cond.store1, label %else2
+//
+// cond.store1:
+// % Elt1 = extractelement <16 x i32> %Src, i32 1
+// % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
+// store i32 % Elt1, i32* % Ptr1, align 4
+// br label %else2
+// . . .
+static void ScalarizeMaskedScatter(CallInst *CI) {
+ Value *Src = CI->getArgOperand(0);
+ Value *Ptrs = CI->getArgOperand(1);
+ Value *Alignment = CI->getArgOperand(2);
+ Value *Mask = CI->getArgOperand(3);
+
+ assert(isa<VectorType>(Src->getType()) &&
+ "Unexpected data type in masked scatter intrinsic");
+ assert(isa<VectorType>(Ptrs->getType()) &&
+ isa<PointerType>(Ptrs->getType()->getVectorElementType()) &&
+ "Vector of pointers is expected in masked scatter intrinsic");
+
+ IRBuilder<> Builder(CI->getContext());
+ Instruction *InsertPt = CI;
+ BasicBlock *IfBlock = CI->getParent();
+ Builder.SetInsertPoint(InsertPt);
+ Builder.SetCurrentDebugLocation(CI->getDebugLoc());
+
+ unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
+ unsigned VectorWidth = Src->getType()->getVectorNumElements();
+
+ // Shorten the way if the mask is a vector of constants.
+ bool IsConstMask = isa<ConstantVector>(Mask);
+
+ if (IsConstMask) {
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+ if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
+ continue;
+ Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
+ "Elt" + Twine(Idx));
+ Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
+ "Ptr" + Twine(Idx));
+ Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
+ }
+ CI->eraseFromParent();
+ return;
+ }
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+ // Fill the "else" block, created in the previous iteration
+ //
+ // % Mask1 = extractelement <16 x i1> % Mask, i32 Idx
+ // % ToStore = icmp eq i1 % Mask1, true
+ // br i1 % ToStore, label %cond.store, label %else
+ //
+ Value *Predicate = Builder.CreateExtractElement(Mask,
+ Builder.getInt32(Idx),
+ "Mask" + Twine(Idx));
+ Value *Cmp =
+ Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
+ ConstantInt::get(Predicate->getType(), 1),
+ "ToStore" + Twine(Idx));
+
+ // Create "cond" block
+ //
+ // % Elt1 = extractelement <16 x i32> %Src, i32 1
+ // % Ptr1 = extractelement <16 x i32*> %Ptrs, i32 1
+ // %store i32 % Elt1, i32* % Ptr1
+ //
+ BasicBlock *CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
+ Builder.SetInsertPoint(InsertPt);
+
+ Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx),
+ "Elt" + Twine(Idx));
+ Value *Ptr = Builder.CreateExtractElement(Ptrs, Builder.getInt32(Idx),
+ "Ptr" + Twine(Idx));
+ Builder.CreateAlignedStore(OneElt, Ptr, AlignVal);
+
+ // Create "else" block, fill it in the next iteration
+ BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
+ Builder.SetInsertPoint(InsertPt);
+ Instruction *OldBr = IfBlock->getTerminator();
+ BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
+ OldBr->eraseFromParent();
+ IfBlock = NewIfBlock;
+ }
+ CI->eraseFromParent();
+}
+
+/// If counting leading or trailing zeros is an expensive operation and a zero
+/// input is defined, add a check for zero to avoid calling the intrinsic.
+///
+/// We want to transform:
+/// %z = call i64 @llvm.cttz.i64(i64 %A, i1 false)
+///
+/// into:
+/// entry:
+/// %cmpz = icmp eq i64 %A, 0
+/// br i1 %cmpz, label %cond.end, label %cond.false
+/// cond.false:
+/// %z = call i64 @llvm.cttz.i64(i64 %A, i1 true)
+/// br label %cond.end
+/// cond.end:
+/// %ctz = phi i64 [ 64, %entry ], [ %z, %cond.false ]
+///
+/// If the transform is performed, return true and set ModifiedDT to true.
+static bool despeculateCountZeros(IntrinsicInst *CountZeros,
+ const TargetLowering *TLI,
+ const DataLayout *DL,
+ bool &ModifiedDT) {
+ if (!TLI || !DL)
+ return false;
+
+ // If a zero input is undefined, it doesn't make sense to despeculate that.
+ if (match(CountZeros->getOperand(1), m_One()))
+ return false;
+
+ // If it's cheap to speculate, there's nothing to do.
+ auto IntrinsicID = CountZeros->getIntrinsicID();
+ if ((IntrinsicID == Intrinsic::cttz && TLI->isCheapToSpeculateCttz()) ||
+ (IntrinsicID == Intrinsic::ctlz && TLI->isCheapToSpeculateCtlz()))
+ return false;
+
+ // Only handle legal scalar cases. Anything else requires too much work.
+ Type *Ty = CountZeros->getType();
+ unsigned SizeInBits = Ty->getPrimitiveSizeInBits();
+ if (Ty->isVectorTy() || SizeInBits > DL->getLargestLegalIntTypeSize())
+ return false;
+
+ // The intrinsic will be sunk behind a compare against zero and branch.
+ BasicBlock *StartBlock = CountZeros->getParent();
+ BasicBlock *CallBlock = StartBlock->splitBasicBlock(CountZeros, "cond.false");
+
+ // Create another block after the count zero intrinsic. A PHI will be added
+ // in this block to select the result of the intrinsic or the bit-width
+ // constant if the input to the intrinsic is zero.
+ BasicBlock::iterator SplitPt = ++(BasicBlock::iterator(CountZeros));
+ BasicBlock *EndBlock = CallBlock->splitBasicBlock(SplitPt, "cond.end");
+
+ // Set up a builder to create a compare, conditional branch, and PHI.
+ IRBuilder<> Builder(CountZeros->getContext());
+ Builder.SetInsertPoint(StartBlock->getTerminator());
+ Builder.SetCurrentDebugLocation(CountZeros->getDebugLoc());
+
+ // Replace the unconditional branch that was created by the first split with
+ // a compare against zero and a conditional branch.
+ Value *Zero = Constant::getNullValue(Ty);
+ Value *Cmp = Builder.CreateICmpEQ(CountZeros->getOperand(0), Zero, "cmpz");
+ Builder.CreateCondBr(Cmp, EndBlock, CallBlock);
+ StartBlock->getTerminator()->eraseFromParent();
+
+ // Create a PHI in the end block to select either the output of the intrinsic
+ // or the bit width of the operand.
+ Builder.SetInsertPoint(&EndBlock->front());
+ PHINode *PN = Builder.CreatePHI(Ty, 2, "ctz");
+ CountZeros->replaceAllUsesWith(PN);
+ Value *BitWidth = Builder.getInt(APInt(SizeInBits, SizeInBits));
+ PN->addIncoming(BitWidth, StartBlock);
+ PN->addIncoming(CountZeros, CallBlock);
+
+ // We are explicitly handling the zero case, so we can set the intrinsic's
+ // undefined zero argument to 'true'. This will also prevent reprocessing the
+ // intrinsic; we only despeculate when a zero input is defined.
+ CountZeros->setArgOperand(1, Builder.getTrue());
+ ModifiedDT = true;
+ return true;
+}
+
+bool CodeGenPrepare::optimizeCallInst(CallInst *CI, bool& ModifiedDT) {
BasicBlock *BB = CI->getParent();
// Lower inline assembly if we can.
return true;
}
// Sink address computing for memory operands into the block.
- if (OptimizeInlineAsmInst(CI))
+ if (optimizeInlineAsmInst(CI))
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);
-
- replaceAndRecursivelySimplify(CI, RetVal,
- TLI ? TLI->getDataLayout() : nullptr,
- TLInfo, ModifiedDT ? nullptr : DT);
-
- // If the iterator instruction was recursively deleted, start over at the
- // start of the block.
- if (IterHandle != CurInstIterator) {
- CurInstIterator = BB->begin();
- SunkAddrs.clear();
+ // Align the pointer arguments to this call if the target thinks it's a good
+ // idea
+ unsigned MinSize, PrefAlign;
+ if (TLI && TLI->shouldAlignPointerArgs(CI, MinSize, PrefAlign)) {
+ for (auto &Arg : CI->arg_operands()) {
+ // We want to align both objects whose address is used directly and
+ // objects whose address is used in casts and GEPs, though it only makes
+ // sense for GEPs if the offset is a multiple of the desired alignment and
+ // if size - offset meets the size threshold.
+ if (!Arg->getType()->isPointerTy())
+ continue;
+ APInt Offset(DL->getPointerSizeInBits(
+ cast<PointerType>(Arg->getType())->getAddressSpace()),
+ 0);
+ Value *Val = Arg->stripAndAccumulateInBoundsConstantOffsets(*DL, Offset);
+ uint64_t Offset2 = Offset.getLimitedValue();
+ if ((Offset2 & (PrefAlign-1)) != 0)
+ continue;
+ AllocaInst *AI;
+ if ((AI = dyn_cast<AllocaInst>(Val)) && AI->getAlignment() < PrefAlign &&
+ DL->getTypeAllocSize(AI->getAllocatedType()) >= MinSize + Offset2)
+ AI->setAlignment(PrefAlign);
+ // Global variables can only be aligned if they are defined in this
+ // object (i.e. they are uniquely initialized in this object), and
+ // over-aligning global variables that have an explicit section is
+ // forbidden.
+ GlobalVariable *GV;
+ if ((GV = dyn_cast<GlobalVariable>(Val)) && GV->hasUniqueInitializer() &&
+ !GV->hasSection() && GV->getAlignment() < PrefAlign &&
+ DL->getTypeAllocSize(GV->getType()->getElementType()) >=
+ MinSize + Offset2)
+ GV->setAlignment(PrefAlign);
+ }
+ // If this is a memcpy (or similar) then we may be able to improve the
+ // alignment
+ if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(CI)) {
+ unsigned Align = getKnownAlignment(MI->getDest(), *DL);
+ if (MemTransferInst *MTI = dyn_cast<MemTransferInst>(MI))
+ Align = std::min(Align, getKnownAlignment(MTI->getSource(), *DL));
+ if (Align > MI->getAlignment())
+ MI->setAlignment(ConstantInt::get(MI->getAlignmentType(), Align));
}
- 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;
+ IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
+ if (II) {
+ switch (II->getIntrinsicID()) {
+ default: break;
+ case Intrinsic::objectsize: {
+ // Lower all uses of llvm.objectsize.*
+ bool Min = (cast<ConstantInt>(II->getArgOperand(1))->getZExtValue() == 1);
+ Type *ReturnTy = CI->getType();
+ Constant *RetVal = ConstantInt::get(ReturnTy, Min ? 0 : -1ULL);
+
+ // Substituting this can cause recursive simplifications, which can
+ // invalidate our iterator. Use a WeakVH to hold onto it in case this
+ // happens.
+ WeakVH IterHandle(&*CurInstIterator);
+
+ replaceAndRecursivelySimplify(CI, RetVal,
+ TLInfo, nullptr);
+
+ // If the iterator instruction was recursively deleted, start over at the
+ // start of the block.
+ if (IterHandle != CurInstIterator.getNodePtrUnchecked()) {
+ CurInstIterator = BB->begin();
+ SunkAddrs.clear();
+ }
+ return true;
+ }
+ case Intrinsic::masked_load: {
+ // Scalarize unsupported vector masked load
+ if (!TTI->isLegalMaskedLoad(CI->getType())) {
+ ScalarizeMaskedLoad(CI);
+ ModifiedDT = true;
+ return true;
+ }
+ return false;
+ }
+ case Intrinsic::masked_store: {
+ if (!TTI->isLegalMaskedStore(CI->getArgOperand(0)->getType())) {
+ ScalarizeMaskedStore(CI);
+ ModifiedDT = true;
+ return true;
+ }
+ return false;
+ }
+ case Intrinsic::masked_gather: {
+ if (!TTI->isLegalMaskedGather(CI->getType())) {
+ ScalarizeMaskedGather(CI);
+ ModifiedDT = true;
+ return true;
+ }
+ return false;
+ }
+ case Intrinsic::masked_scatter: {
+ if (!TTI->isLegalMaskedScatter(CI->getArgOperand(0)->getType())) {
+ ScalarizeMaskedScatter(CI);
+ ModifiedDT = true;
+ return true;
+ }
+ return false;
+ }
+ case Intrinsic::aarch64_stlxr:
+ case Intrinsic::aarch64_stxr: {
+ ZExtInst *ExtVal = dyn_cast<ZExtInst>(CI->getArgOperand(0));
+ if (!ExtVal || !ExtVal->hasOneUse() ||
+ ExtVal->getParent() == CI->getParent())
+ return false;
+ // Sink a zext feeding stlxr/stxr before it, so it can be folded into it.
+ ExtVal->moveBefore(CI);
+ // Mark this instruction as "inserted by CGP", so that other
+ // optimizations don't touch it.
+ InsertedInsts.insert(ExtVal);
+ return true;
+ }
+ case Intrinsic::invariant_group_barrier:
+ II->replaceAllUsesWith(II->getArgOperand(0));
+ II->eraseFromParent();
+ return true;
+
+ case Intrinsic::cttz:
+ case Intrinsic::ctlz:
+ // If counting zeros is expensive, try to avoid it.
+ return despeculateCountZeros(II, TLI, DL, ModifiedDT);
+ }
+
+ if (TLI) {
+ // Unknown address space.
+ // TODO: Target hook to pick which address space the intrinsic cares
+ // about?
+ unsigned AddrSpace = ~0u;
+ SmallVector<Value*, 2> PtrOps;
+ Type *AccessTy;
+ if (TLI->GetAddrModeArguments(II, PtrOps, AccessTy, AddrSpace))
+ while (!PtrOps.empty())
+ if (optimizeMemoryInst(II, PtrOps.pop_back_val(), AccessTy, AddrSpace))
+ return true;
+ }
}
// From here on out we're working with named functions.
if (!CI->getCalledFunction()) return false;
- // We'll need DataLayout from here on out.
- 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(TLInfo, true);
+ if (Value *V = Simplifier.optimizeCall(CI)) {
+ CI->replaceAllUsesWith(V);
+ CI->eraseFromParent();
+ return true;
+ }
+ return false;
}
-/// DupRetToEnableTailCallOpts - Look for opportunities to duplicate return
-/// instructions to the predecessor to enable tail call optimizations. The
-/// case it is currently looking for is:
+/// Look for opportunities to duplicate return instructions to the predecessor
+/// to enable tail call optimizations. The case it is currently looking for is:
/// @code
/// bb0:
/// %tmp0 = tail call i32 @f0()
/// %tmp2 = tail call i32 @f2()
/// ret i32 %tmp2
/// @endcode
-bool CodeGenPrepare::DupRetToEnableTailCallOpts(BasicBlock *BB) {
+bool CodeGenPrepare::dupRetToEnableTailCallOpts(BasicBlock *BB) {
if (!TLI)
return false;
namespace {
-/// ExtAddrMode - This is an extended version of TargetLowering::AddrMode
+/// This is an extended version of TargetLowering::AddrMode
/// which holds actual Value*'s for register values.
struct ExtAddrMode : public TargetLowering::AddrMode {
Value *BaseReg;
public:
/// \brief Record the position of \p Inst.
InsertionHandler(Instruction *Inst) {
- BasicBlock::iterator It = Inst;
+ BasicBlock::iterator It = Inst->getIterator();
HasPrevInstruction = (It != (Inst->getParent()->begin()));
if (HasPrevInstruction)
- Point.PrevInst = --It;
+ Point.PrevInst = &*--It;
else
Point.BB = Inst->getParent();
}
Inst->removeFromParent();
Inst->insertAfter(Point.PrevInst);
} else {
- Instruction *Position = Point.BB->getFirstInsertionPt();
+ Instruction *Position = &*Point.BB->getFirstInsertionPt();
if (Inst->getParent())
Inst->moveBefore(Position);
else
Value *Val = Inst->getOperand(It);
OriginalValues.push_back(Val);
// Set a dummy one.
- // We could use OperandSetter here, but that would implied an overhead
+ // We could use OperandSetter here, but that would imply an overhead
// that we are not willing to pay.
Inst->setOperand(It, UndefValue::get(Val->getType()));
}
Inst->removeFromParent();
}
- ~InstructionRemover() { delete Replacer; }
+ ~InstructionRemover() override { delete Replacer; }
/// \brief Really remove the instruction.
void commit() override { delete Inst; }
/// This encapsulates the logic for matching the target-legal addressing modes.
class AddressingModeMatcher {
SmallVectorImpl<Instruction*> &AddrModeInsts;
+ const TargetMachine &TM;
const TargetLowering &TLI;
+ const DataLayout &DL;
/// AccessTy/MemoryInst - This is the type for the access (e.g. double) and
/// the memory instruction that we're computing this address for.
Type *AccessTy;
+ unsigned AddrSpace;
Instruction *MemoryInst;
- /// AddrMode - This is the addressing mode that we're building up. This is
+ /// This is the addressing mode that we're building up. This is
/// part of the return value of this addressing mode matching stuff.
ExtAddrMode &AddrMode;
- /// The truncate instruction inserted by other CodeGenPrepare optimizations.
- const SetOfInstrs &InsertedTruncs;
+ /// The instructions inserted by other CodeGenPrepare optimizations.
+ const SetOfInstrs &InsertedInsts;
/// A map from the instructions to their type before promotion.
InstrToOrigTy &PromotedInsts;
/// The ongoing transaction where every action should be registered.
TypePromotionTransaction &TPT;
- /// IgnoreProfitability - This is set to true when we should not do
- /// profitability checks. When true, IsProfitableToFoldIntoAddressingMode
- /// always returns true.
+ /// This is set to true when we should not do profitability checks.
+ /// When true, IsProfitableToFoldIntoAddressingMode always returns true.
bool IgnoreProfitability;
- AddressingModeMatcher(SmallVectorImpl<Instruction*> &AMI,
- const TargetLowering &T, Type *AT,
+ AddressingModeMatcher(SmallVectorImpl<Instruction *> &AMI,
+ const TargetMachine &TM, Type *AT, unsigned AS,
Instruction *MI, ExtAddrMode &AM,
- const SetOfInstrs &InsertedTruncs,
+ const SetOfInstrs &InsertedInsts,
InstrToOrigTy &PromotedInsts,
TypePromotionTransaction &TPT)
- : AddrModeInsts(AMI), TLI(T), AccessTy(AT), MemoryInst(MI), AddrMode(AM),
- InsertedTruncs(InsertedTruncs), PromotedInsts(PromotedInsts), TPT(TPT) {
+ : AddrModeInsts(AMI), TM(TM),
+ TLI(*TM.getSubtargetImpl(*MI->getParent()->getParent())
+ ->getTargetLowering()),
+ DL(MI->getModule()->getDataLayout()), AccessTy(AT), AddrSpace(AS),
+ MemoryInst(MI), AddrMode(AM), InsertedInsts(InsertedInsts),
+ PromotedInsts(PromotedInsts), TPT(TPT) {
IgnoreProfitability = false;
}
public:
- /// Match - Find the maximal addressing mode that a load/store of V can fold,
+ /// Find the maximal addressing mode that a load/store of V can fold,
/// give an access type of AccessTy. This returns a list of involved
/// instructions in AddrModeInsts.
- /// \p InsertedTruncs The truncate instruction inserted by other
- /// CodeGenPrepare
+ /// \p InsertedInsts The instructions inserted by other CodeGenPrepare
/// optimizations.
/// \p PromotedInsts maps the instructions to their type before promotion.
/// \p The ongoing transaction where every action should be registered.
- static ExtAddrMode Match(Value *V, Type *AccessTy,
+ static ExtAddrMode Match(Value *V, Type *AccessTy, unsigned AS,
Instruction *MemoryInst,
SmallVectorImpl<Instruction*> &AddrModeInsts,
- const TargetLowering &TLI,
- const SetOfInstrs &InsertedTruncs,
+ const TargetMachine &TM,
+ const SetOfInstrs &InsertedInsts,
InstrToOrigTy &PromotedInsts,
TypePromotionTransaction &TPT) {
ExtAddrMode Result;
- bool Success = AddressingModeMatcher(AddrModeInsts, TLI, AccessTy,
- MemoryInst, Result, InsertedTruncs,
- PromotedInsts, TPT).MatchAddr(V, 0);
+ bool Success = AddressingModeMatcher(AddrModeInsts, TM, AccessTy, AS,
+ MemoryInst, Result, InsertedInsts,
+ PromotedInsts, TPT).matchAddr(V, 0);
(void)Success; assert(Success && "Couldn't select *anything*?");
return Result;
}
private:
- bool MatchScaledValue(Value *ScaleReg, int64_t Scale, unsigned Depth);
- bool MatchAddr(Value *V, unsigned Depth);
- bool MatchOperationAddr(User *Operation, unsigned Opcode, unsigned Depth,
+ bool matchScaledValue(Value *ScaleReg, int64_t Scale, unsigned Depth);
+ bool matchAddr(Value *V, unsigned Depth);
+ bool matchOperationAddr(User *Operation, unsigned Opcode, unsigned Depth,
bool *MovedAway = nullptr);
- bool IsProfitableToFoldIntoAddressingMode(Instruction *I,
+ bool isProfitableToFoldIntoAddressingMode(Instruction *I,
ExtAddrMode &AMBefore,
ExtAddrMode &AMAfter);
- bool ValueAlreadyLiveAtInst(Value *Val, Value *KnownLive1, Value *KnownLive2);
- bool IsPromotionProfitable(unsigned MatchedSize, unsigned SizeWithPromotion,
+ bool valueAlreadyLiveAtInst(Value *Val, Value *KnownLive1, Value *KnownLive2);
+ bool isPromotionProfitable(unsigned NewCost, unsigned OldCost,
Value *PromotedOperand) const;
};
-/// MatchScaledValue - Try adding ScaleReg*Scale to the current addressing mode.
+/// Try adding ScaleReg*Scale to the current addressing mode.
/// Return true and update AddrMode if this addr mode is legal for the target,
/// false if not.
-bool AddressingModeMatcher::MatchScaledValue(Value *ScaleReg, int64_t Scale,
+bool AddressingModeMatcher::matchScaledValue(Value *ScaleReg, int64_t Scale,
unsigned Depth) {
// If Scale is 1, then this is the same as adding ScaleReg to the addressing
// mode. Just process that directly.
if (Scale == 1)
- return MatchAddr(ScaleReg, Depth);
+ return matchAddr(ScaleReg, Depth);
// If the scale is 0, it takes nothing to add this.
if (Scale == 0)
TestAddrMode.ScaledReg = ScaleReg;
// If the new address isn't legal, bail out.
- if (!TLI.isLegalAddressingMode(TestAddrMode, AccessTy))
+ if (!TLI.isLegalAddressingMode(DL, TestAddrMode, AccessTy, AddrSpace))
return false;
// It was legal, so commit it.
// If this addressing mode is legal, commit it and remember that we folded
// this instruction.
- if (TLI.isLegalAddressingMode(TestAddrMode, AccessTy)) {
+ if (TLI.isLegalAddressingMode(DL, TestAddrMode, AccessTy, AddrSpace)) {
AddrModeInsts.push_back(cast<Instruction>(ScaleReg));
AddrMode = TestAddrMode;
return true;
return true;
}
-/// MightBeFoldableInst - This is a little filter, which returns true if an
-/// addressing computation involving I might be folded into a load/store
-/// accessing it. This doesn't need to be perfect, but needs to accept at least
+/// This is a little filter, which returns true if an addressing computation
+/// involving I might be folded into a load/store accessing it.
+/// This doesn't need to be perfect, but needs to accept at least
/// the set of instructions that MatchOperationAddr can.
static bool MightBeFoldableInst(Instruction *I) {
switch (I->getOpcode()) {
}
}
+/// \brief Check whether or not \p Val is a legal instruction for \p TLI.
+/// \note \p Val is assumed to be the product of some type promotion.
+/// Therefore if \p Val has an undefined state in \p TLI, this is assumed
+/// to be legal, as the non-promoted value would have had the same state.
+static bool isPromotedInstructionLegal(const TargetLowering &TLI,
+ const DataLayout &DL, Value *Val) {
+ Instruction *PromotedInst = dyn_cast<Instruction>(Val);
+ if (!PromotedInst)
+ return false;
+ int ISDOpcode = TLI.InstructionOpcodeToISD(PromotedInst->getOpcode());
+ // If the ISDOpcode is undefined, it was undefined before the promotion.
+ if (!ISDOpcode)
+ return true;
+ // Otherwise, check if the promoted instruction is legal or not.
+ return TLI.isOperationLegalOrCustom(
+ ISDOpcode, TLI.getValueType(DL, PromotedInst->getType()));
+}
+
/// \brief Hepler class to perform type promotion.
class TypePromotionHelper {
/// \brief Utility function to check whether or not a sign or zero extension
/// \brief Utility function to determine if \p OpIdx should be promoted when
/// promoting \p Inst.
static bool shouldExtOperand(const Instruction *Inst, int OpIdx) {
- if (isa<SelectInst>(Inst) && OpIdx == 0)
- return false;
- return true;
+ return !(isa<SelectInst>(Inst) && OpIdx == 0);
}
/// \brief Utility function to promote the operand of \p Ext when this
/// operand is a promotable trunc or sext or zext.
/// \p PromotedInsts maps the instructions to their type before promotion.
- /// \p CreatedInsts[out] contains how many non-free instructions have been
+ /// \p CreatedInstsCost[out] contains the cost of all instructions
/// created to promote the operand of Ext.
+ /// Newly added extensions are inserted in \p Exts.
+ /// Newly added truncates are inserted in \p Truncs.
/// Should never be called directly.
/// \return The promoted value which is used instead of Ext.
- static Value *promoteOperandForTruncAndAnyExt(Instruction *Ext,
- TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts);
+ static Value *promoteOperandForTruncAndAnyExt(
+ Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI);
/// \brief Utility function to promote the operand of \p Ext when this
/// operand is promotable and is not a supported trunc or sext.
/// \p PromotedInsts maps the instructions to their type before promotion.
- /// \p CreatedInsts[out] contains how many non-free instructions have been
+ /// \p CreatedInstsCost[out] contains the cost of all the instructions
/// created to promote the operand of Ext.
+ /// Newly added extensions are inserted in \p Exts.
+ /// Newly added truncates are inserted in \p Truncs.
/// Should never be called directly.
/// \return The promoted value which is used instead of Ext.
static Value *promoteOperandForOther(Instruction *Ext,
TypePromotionTransaction &TPT,
InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts, bool IsSExt);
+ unsigned &CreatedInstsCost,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs,
+ const TargetLowering &TLI, bool IsSExt);
/// \see promoteOperandForOther.
- static Value *signExtendOperandForOther(Instruction *Ext,
- TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts) {
- return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInsts, true);
+ static Value *signExtendOperandForOther(
+ Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI) {
+ return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInstsCost,
+ Exts, Truncs, TLI, true);
}
/// \see promoteOperandForOther.
- static Value *zeroExtendOperandForOther(Instruction *Ext,
- TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts) {
- return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInsts, false);
+ static Value *zeroExtendOperandForOther(
+ Instruction *Ext, TypePromotionTransaction &TPT,
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI) {
+ return promoteOperandForOther(Ext, TPT, PromotedInsts, CreatedInstsCost,
+ Exts, Truncs, TLI, false);
}
public:
/// Type for the utility function that promotes the operand of Ext.
typedef Value *(*Action)(Instruction *Ext, TypePromotionTransaction &TPT,
InstrToOrigTy &PromotedInsts,
- unsigned &CreatedInsts);
+ unsigned &CreatedInstsCost,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs,
+ const TargetLowering &TLI);
/// \brief Given a sign/zero extend instruction \p Ext, return the approriate
/// action to promote the operand of \p Ext instead of using Ext.
/// \return NULL if no promotable action is possible with the current
/// sign extension.
- /// \p InsertedTruncs keeps track of all the truncate instructions inserted by
- /// the others CodeGenPrepare optimizations. This information is important
+ /// \p InsertedInsts keeps track of all the instructions inserted by the
+ /// other CodeGenPrepare optimizations. This information is important
/// because we do not want to promote these instructions as CodeGenPrepare
/// will reinsert them later. Thus creating an infinite loop: create/remove.
/// \p PromotedInsts maps the instructions to their type before promotion.
- static Action getAction(Instruction *Ext, const SetOfInstrs &InsertedTruncs,
+ static Action getAction(Instruction *Ext, const SetOfInstrs &InsertedInsts,
const TargetLowering &TLI,
const InstrToOrigTy &PromotedInsts);
};
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;
Value *OpndVal = Inst->getOperand(0);
// Check if we can use this operand in the extension.
- // If the type is larger than the result type of the extension,
- // we cannot.
- if (OpndVal->getType()->getIntegerBitWidth() >
- ConsideredExtType->getIntegerBitWidth())
+ // If the type is larger than the result type of the extension, we cannot.
+ if (!OpndVal->getType()->isIntegerTy() ||
+ OpndVal->getType()->getIntegerBitWidth() >
+ ConsideredExtType->getIntegerBitWidth())
return false;
// If the operand of the truncate is not an instruction, we will not have
// #1 get the type of the operand and check the kind of the extended bits.
const Type *OpndType;
InstrToOrigTy::const_iterator It = PromotedInsts.find(Opnd);
- if (It != PromotedInsts.end() && It->second.IsSExt == IsSExt)
- OpndType = It->second.Ty;
+ if (It != PromotedInsts.end() && It->second.getInt() == IsSExt)
+ OpndType = It->second.getPointer();
else if ((IsSExt && isa<SExtInst>(Opnd)) || (!IsSExt && isa<ZExtInst>(Opnd)))
OpndType = Opnd->getOperand(0)->getType();
else
return false;
- // #2 check that the truncate just drop extended bits.
- if (Inst->getType()->getIntegerBitWidth() >= OpndType->getIntegerBitWidth())
- return true;
-
- return false;
+ // #2 check that the truncate just drops extended bits.
+ return Inst->getType()->getIntegerBitWidth() >=
+ OpndType->getIntegerBitWidth();
}
TypePromotionHelper::Action TypePromotionHelper::getAction(
- Instruction *Ext, const SetOfInstrs &InsertedTruncs,
+ Instruction *Ext, const SetOfInstrs &InsertedInsts,
const TargetLowering &TLI, const InstrToOrigTy &PromotedInsts) {
assert((isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) &&
"Unexpected instruction type");
// Do not promote if the operand has been added by codegenprepare.
// Otherwise, it means we are undoing an optimization that is likely to be
// redone, thus causing potential infinite loop.
- if (isa<TruncInst>(ExtOpnd) && InsertedTruncs.count(ExtOpnd))
+ if (isa<TruncInst>(ExtOpnd) && InsertedInsts.count(ExtOpnd))
return nullptr;
// SExt or Trunc instructions.
Value *TypePromotionHelper::promoteOperandForTruncAndAnyExt(
llvm::Instruction *SExt, TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts) {
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI) {
// By construction, the operand of SExt is an instruction. Otherwise we cannot
// get through it and this method should not be called.
Instruction *SExtOpnd = cast<Instruction>(SExt->getOperand(0));
Value *ExtVal = SExt;
+ bool HasMergedNonFreeExt = false;
if (isa<ZExtInst>(SExtOpnd)) {
// Replace s|zext(zext(opnd))
// => zext(opnd).
+ HasMergedNonFreeExt = !TLI.isExtFree(SExtOpnd);
Value *ZExt =
TPT.createZExt(SExt, SExtOpnd->getOperand(0), SExt->getType());
TPT.replaceAllUsesWith(SExt, ZExt);
// => z|sext(opnd).
TPT.setOperand(SExt, 0, SExtOpnd->getOperand(0));
}
- CreatedInsts = 0;
+ CreatedInstsCost = 0;
// Remove dead code.
if (SExtOpnd->use_empty())
// Check if the extension is still needed.
Instruction *ExtInst = dyn_cast<Instruction>(ExtVal);
- if (!ExtInst || ExtInst->getType() != ExtInst->getOperand(0)->getType())
+ if (!ExtInst || ExtInst->getType() != ExtInst->getOperand(0)->getType()) {
+ if (ExtInst) {
+ if (Exts)
+ Exts->push_back(ExtInst);
+ CreatedInstsCost = !TLI.isExtFree(ExtInst) && !HasMergedNonFreeExt;
+ }
return ExtVal;
+ }
// At this point we have: ext ty opnd to ty.
// Reassign the uses of ExtInst to the opnd and remove ExtInst.
Value *TypePromotionHelper::promoteOperandForOther(
Instruction *Ext, TypePromotionTransaction &TPT,
- InstrToOrigTy &PromotedInsts, unsigned &CreatedInsts, bool IsSExt) {
+ InstrToOrigTy &PromotedInsts, unsigned &CreatedInstsCost,
+ SmallVectorImpl<Instruction *> *Exts,
+ SmallVectorImpl<Instruction *> *Truncs, const TargetLowering &TLI,
+ bool IsSExt) {
// By construction, the operand of Ext is an instruction. Otherwise we cannot
// get through it and this method should not be called.
Instruction *ExtOpnd = cast<Instruction>(Ext->getOperand(0));
- CreatedInsts = 0;
+ CreatedInstsCost = 0;
if (!ExtOpnd->hasOneUse()) {
// ExtOpnd will be promoted.
// All its uses, but Ext, will need to use a truncated value of the
ITrunc->removeFromParent();
// Insert it just after the definition.
ITrunc->insertAfter(ExtOpnd);
+ if (Truncs)
+ Truncs->push_back(ITrunc);
}
TPT.replaceAllUsesWith(ExtOpnd, Trunc);
- // Restore the operand of Ext (which has been replace by the previous call
+ // Restore the operand of Ext (which has been replaced by the previous call
// to replaceAllUsesWith) to avoid creating a cycle trunc <-> sext.
TPT.setOperand(Ext, 0, ExtOpnd);
}
if (!ExtForOpnd) {
// If yes, create a new one.
DEBUG(dbgs() << "More operands to ext\n");
- ExtForOpnd =
- cast<Instruction>(IsSExt ? TPT.createSExt(Ext, Opnd, Ext->getType())
- : TPT.createZExt(Ext, Opnd, Ext->getType()));
- ++CreatedInsts;
+ Value *ValForExtOpnd = IsSExt ? TPT.createSExt(Ext, Opnd, Ext->getType())
+ : TPT.createZExt(Ext, Opnd, Ext->getType());
+ if (!isa<Instruction>(ValForExtOpnd)) {
+ TPT.setOperand(ExtOpnd, OpIdx, ValForExtOpnd);
+ continue;
+ }
+ ExtForOpnd = cast<Instruction>(ValForExtOpnd);
}
-
+ if (Exts)
+ Exts->push_back(ExtForOpnd);
TPT.setOperand(ExtForOpnd, 0, Opnd);
// Move the sign extension before the insertion point.
TPT.moveBefore(ExtForOpnd, ExtOpnd);
TPT.setOperand(ExtOpnd, OpIdx, ExtForOpnd);
+ CreatedInstsCost += !TLI.isExtFree(ExtForOpnd);
// If more sext are required, new instructions will have to be created.
ExtForOpnd = nullptr;
}
return ExtOpnd;
}
-/// IsPromotionProfitable - Check whether or not promoting an instruction
-/// to a wider type was profitable.
-/// \p MatchedSize gives the number of instructions that have been matched
-/// in the addressing mode after the promotion was applied.
-/// \p SizeWithPromotion gives the number of created instructions for
-/// the promotion plus the number of instructions that have been
-/// matched in the addressing mode before the promotion.
+/// Check whether or not promoting an instruction to a wider type is profitable.
+/// \p NewCost gives the cost of extension instructions created by the
+/// promotion.
+/// \p OldCost gives the cost of extension instructions before the promotion
+/// plus the number of instructions that have been
+/// matched in the addressing mode the promotion.
/// \p PromotedOperand is the value that has been promoted.
/// \return True if the promotion is profitable, false otherwise.
-bool
-AddressingModeMatcher::IsPromotionProfitable(unsigned MatchedSize,
- unsigned SizeWithPromotion,
- Value *PromotedOperand) const {
- // We folded less instructions than what we created to promote the operand.
+bool AddressingModeMatcher::isPromotionProfitable(
+ unsigned NewCost, unsigned OldCost, Value *PromotedOperand) const {
+ DEBUG(dbgs() << "OldCost: " << OldCost << "\tNewCost: " << NewCost << '\n');
+ // The cost of the new extensions is greater than the cost of the
+ // old extension plus what we folded.
// This is not profitable.
- if (MatchedSize < SizeWithPromotion)
+ if (NewCost > OldCost)
return false;
- if (MatchedSize > SizeWithPromotion)
+ if (NewCost < OldCost)
return true;
// The promotion is neutral but it may help folding the sign extension in
// loads for instance.
// Check that we did not create an illegal instruction.
- 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, TLI.getValueType(PromotedInst->getType()));
+ return isPromotedInstructionLegal(TLI, DL, PromotedOperand);
}
-/// MatchOperationAddr - Given an instruction or constant expr, see if we can
-/// fold the operation into the addressing mode. If so, update the addressing
-/// mode and return true, otherwise return false without modifying AddrMode.
+/// Given an instruction or constant expr, see if we can fold the operation
+/// into the addressing mode. If so, update the addressing mode and return
+/// true, otherwise return false without modifying AddrMode.
/// If \p MovedAway is not NULL, it contains the information of whether or
/// not AddrInst has to be folded into the addressing mode on success.
/// If \p MovedAway == true, \p AddrInst will not be part of the addressing
/// This state can happen when AddrInst is a sext, since it may be moved away.
/// Therefore, AddrInst may not be valid when MovedAway is true and it must
/// not be referenced anymore.
-bool AddressingModeMatcher::MatchOperationAddr(User *AddrInst, unsigned Opcode,
+bool AddressingModeMatcher::matchOperationAddr(User *AddrInst, unsigned Opcode,
unsigned Depth,
bool *MovedAway) {
// Avoid exponential behavior on extremely deep expression trees.
switch (Opcode) {
case Instruction::PtrToInt:
// PtrToInt is always a noop, as we know that the int type is pointer sized.
- return MatchAddr(AddrInst->getOperand(0), Depth);
- case Instruction::IntToPtr:
+ return matchAddr(AddrInst->getOperand(0), Depth);
+ case Instruction::IntToPtr: {
+ auto AS = AddrInst->getType()->getPointerAddressSpace();
+ auto PtrTy = MVT::getIntegerVT(DL.getPointerSizeInBits(AS));
// This inttoptr is a no-op if the integer type is pointer sized.
- if (TLI.getValueType(AddrInst->getOperand(0)->getType()) ==
- TLI.getPointerTy(AddrInst->getType()->getPointerAddressSpace()))
- return MatchAddr(AddrInst->getOperand(0), Depth);
+ if (TLI.getValueType(DL, AddrInst->getOperand(0)->getType()) == PtrTy)
+ 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() ||
// and we don't want to mess around with them. Assume it knows what it
// is doing.
AddrInst->getOperand(0)->getType() != AddrInst->getType())
- return MatchAddr(AddrInst->getOperand(0), Depth);
+ return matchAddr(AddrInst->getOperand(0), Depth);
return false;
+ case Instruction::AddrSpaceCast: {
+ unsigned SrcAS
+ = AddrInst->getOperand(0)->getType()->getPointerAddressSpace();
+ unsigned DestAS = AddrInst->getType()->getPointerAddressSpace();
+ if (TLI.isNoopAddrSpaceCast(SrcAS, DestAS))
+ return matchAddr(AddrInst->getOperand(0), Depth);
+ return false;
+ }
case Instruction::Add: {
// Check to see if we can merge in the RHS then the LHS. If so, we win.
ExtAddrMode BackupAddrMode = AddrMode;
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
TPT.getRestorationPoint();
- if (MatchAddr(AddrInst->getOperand(1), Depth+1) &&
- MatchAddr(AddrInst->getOperand(0), Depth+1))
+ if (matchAddr(AddrInst->getOperand(1), Depth+1) &&
+ matchAddr(AddrInst->getOperand(0), Depth+1))
return true;
// Restore the old addr mode info.
TPT.rollback(LastKnownGood);
// Otherwise this was over-aggressive. Try merging in the LHS then the RHS.
- if (MatchAddr(AddrInst->getOperand(0), Depth+1) &&
- MatchAddr(AddrInst->getOperand(1), Depth+1))
+ if (matchAddr(AddrInst->getOperand(0), Depth+1) &&
+ matchAddr(AddrInst->getOperand(1), Depth+1))
return true;
// Otherwise we definitely can't merge the ADD in.
if (Opcode == Instruction::Shl)
Scale = 1LL << Scale;
- return MatchScaledValue(AddrInst->getOperand(0), Scale, Depth);
+ return matchScaledValue(AddrInst->getOperand(0), Scale, Depth);
}
case Instruction::GetElementPtr: {
// Scan the GEP. We check it if it contains constant offsets and at most
unsigned VariableScale = 0;
int64_t ConstantOffset = 0;
- const DataLayout *TD = TLI.getDataLayout();
gep_type_iterator GTI = gep_type_begin(AddrInst);
for (unsigned i = 1, e = AddrInst->getNumOperands(); i != e; ++i, ++GTI) {
if (StructType *STy = dyn_cast<StructType>(*GTI)) {
- const StructLayout *SL = TD->getStructLayout(STy);
+ const StructLayout *SL = DL.getStructLayout(STy);
unsigned Idx =
cast<ConstantInt>(AddrInst->getOperand(i))->getZExtValue();
ConstantOffset += SL->getElementOffset(Idx);
} else {
- uint64_t TypeSize = TD->getTypeAllocSize(GTI.getIndexedType());
+ uint64_t TypeSize = DL.getTypeAllocSize(GTI.getIndexedType());
if (ConstantInt *CI = dyn_cast<ConstantInt>(AddrInst->getOperand(i))) {
ConstantOffset += CI->getSExtValue()*TypeSize;
} else if (TypeSize) { // Scales of zero don't do anything.
// just add it to the disp field and check validity.
if (VariableOperand == -1) {
AddrMode.BaseOffs += ConstantOffset;
- if (ConstantOffset == 0 || TLI.isLegalAddressingMode(AddrMode, AccessTy)){
+ if (ConstantOffset == 0 ||
+ TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace)) {
// Check to see if we can fold the base pointer in too.
- if (MatchAddr(AddrInst->getOperand(0), Depth+1))
+ if (matchAddr(AddrInst->getOperand(0), Depth+1))
return true;
}
AddrMode.BaseOffs -= ConstantOffset;
AddrMode.BaseOffs += ConstantOffset;
// Match the base operand of the GEP.
- if (!MatchAddr(AddrInst->getOperand(0), Depth+1)) {
+ if (!matchAddr(AddrInst->getOperand(0), Depth+1)) {
// If it couldn't be matched, just stuff the value in a register.
if (AddrMode.HasBaseReg) {
AddrMode = BackupAddrMode;
}
// Match the remaining variable portion of the GEP.
- if (!MatchScaledValue(AddrInst->getOperand(VariableOperand), VariableScale,
+ if (!matchScaledValue(AddrInst->getOperand(VariableOperand), VariableScale,
Depth)) {
// If it couldn't be matched, try stuffing the base into a register
// instead of matching it, and retrying the match of the scale.
AddrMode.HasBaseReg = true;
AddrMode.BaseReg = AddrInst->getOperand(0);
AddrMode.BaseOffs += ConstantOffset;
- if (!MatchScaledValue(AddrInst->getOperand(VariableOperand),
+ if (!matchScaledValue(AddrInst->getOperand(VariableOperand),
VariableScale, Depth)) {
// If even that didn't work, bail.
AddrMode = BackupAddrMode;
// Try to move this ext out of the way of the addressing mode.
// Ask for a method for doing so.
TypePromotionHelper::Action TPH =
- TypePromotionHelper::getAction(Ext, InsertedTruncs, TLI, PromotedInsts);
+ TypePromotionHelper::getAction(Ext, InsertedInsts, TLI, PromotedInsts);
if (!TPH)
return false;
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
TPT.getRestorationPoint();
- unsigned CreatedInsts = 0;
- Value *PromotedOperand = TPH(Ext, TPT, PromotedInsts, CreatedInsts);
+ unsigned CreatedInstsCost = 0;
+ unsigned ExtCost = !TLI.isExtFree(Ext);
+ Value *PromotedOperand =
+ TPH(Ext, TPT, PromotedInsts, CreatedInstsCost, nullptr, nullptr, TLI);
// SExt has been moved away.
// Thus either it will be rematched later in the recursive calls or it is
// gone. Anyway, we must not fold it into the addressing mode at this point.
ExtAddrMode BackupAddrMode = AddrMode;
unsigned OldSize = AddrModeInsts.size();
- if (!MatchAddr(PromotedOperand, Depth) ||
- !IsPromotionProfitable(AddrModeInsts.size(), OldSize + CreatedInsts,
+ if (!matchAddr(PromotedOperand, Depth) ||
+ // The total of the new cost is equal to the cost of the created
+ // instructions.
+ // The total of the old cost is equal to the cost of the extension plus
+ // what we have saved in the addressing mode.
+ !isPromotionProfitable(CreatedInstsCost,
+ ExtCost + (AddrModeInsts.size() - OldSize),
PromotedOperand)) {
AddrMode = BackupAddrMode;
AddrModeInsts.resize(OldSize);
return false;
}
-/// MatchAddr - If we can, try to add the value of 'Addr' into the current
-/// addressing mode. If Addr can't be added to AddrMode this returns false and
-/// leaves AddrMode unmodified. This assumes that Addr is either a pointer type
-/// or intptr_t for the target.
+/// If we can, try to add the value of 'Addr' into the current addressing mode.
+/// If Addr can't be added to AddrMode this returns false and leaves AddrMode
+/// unmodified. This assumes that Addr is either a pointer type or intptr_t
+/// for the target.
///
-bool AddressingModeMatcher::MatchAddr(Value *Addr, unsigned Depth) {
+bool AddressingModeMatcher::matchAddr(Value *Addr, unsigned Depth) {
// Start a transaction at this point that we will rollback if the matching
// fails.
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
if (ConstantInt *CI = dyn_cast<ConstantInt>(Addr)) {
// Fold in immediates if legal for the target.
AddrMode.BaseOffs += CI->getSExtValue();
- if (TLI.isLegalAddressingMode(AddrMode, AccessTy))
+ if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
return true;
AddrMode.BaseOffs -= CI->getSExtValue();
} else if (GlobalValue *GV = dyn_cast<GlobalValue>(Addr)) {
// If this is a global variable, try to fold it into the addressing mode.
if (!AddrMode.BaseGV) {
AddrMode.BaseGV = GV;
- if (TLI.isLegalAddressingMode(AddrMode, AccessTy))
+ if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
return true;
AddrMode.BaseGV = nullptr;
}
// Check to see if it is possible to fold this operation.
bool MovedAway = false;
- if (MatchOperationAddr(I, I->getOpcode(), Depth, &MovedAway)) {
- // This instruction may have been move away. If so, there is nothing
+ if (matchOperationAddr(I, I->getOpcode(), Depth, &MovedAway)) {
+ // This instruction may have been moved away. If so, there is nothing
// to check here.
if (MovedAway)
return true;
// *profitable* to do so. We use a simple cost model to avoid increasing
// register pressure too much.
if (I->hasOneUse() ||
- IsProfitableToFoldIntoAddressingMode(I, BackupAddrMode, AddrMode)) {
+ isProfitableToFoldIntoAddressingMode(I, BackupAddrMode, AddrMode)) {
AddrModeInsts.push_back(I);
return true;
}
TPT.rollback(LastKnownGood);
}
} else if (ConstantExpr *CE = dyn_cast<ConstantExpr>(Addr)) {
- if (MatchOperationAddr(CE, CE->getOpcode(), Depth))
+ if (matchOperationAddr(CE, CE->getOpcode(), Depth))
return true;
TPT.rollback(LastKnownGood);
} else if (isa<ConstantPointerNull>(Addr)) {
AddrMode.HasBaseReg = true;
AddrMode.BaseReg = Addr;
// Still check for legality in case the target supports [imm] but not [i+r].
- if (TLI.isLegalAddressingMode(AddrMode, AccessTy))
+ if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
return true;
AddrMode.HasBaseReg = false;
AddrMode.BaseReg = nullptr;
if (AddrMode.Scale == 0) {
AddrMode.Scale = 1;
AddrMode.ScaledReg = Addr;
- if (TLI.isLegalAddressingMode(AddrMode, AccessTy))
+ if (TLI.isLegalAddressingMode(DL, AddrMode, AccessTy, AddrSpace))
return true;
AddrMode.Scale = 0;
AddrMode.ScaledReg = nullptr;
return false;
}
-/// IsOperandAMemoryOperand - Check to see if all uses of OpVal by the specified
-/// inline asm call are due to memory operands. If so, return true, otherwise
-/// return false.
+/// Check to see if all uses of OpVal by the specified inline asm call are due
+/// to memory operands. If so, return true, otherwise return false.
static bool IsOperandAMemoryOperand(CallInst *CI, InlineAsm *IA, Value *OpVal,
- const TargetLowering &TLI) {
- TargetLowering::AsmOperandInfoVector TargetConstraints = TLI.ParseConstraints(ImmutableCallSite(CI));
+ const TargetMachine &TM) {
+ const Function *F = CI->getParent()->getParent();
+ const TargetLowering *TLI = TM.getSubtargetImpl(*F)->getTargetLowering();
+ const TargetRegisterInfo *TRI = TM.getSubtargetImpl(*F)->getRegisterInfo();
+ TargetLowering::AsmOperandInfoVector TargetConstraints =
+ TLI->ParseConstraints(F->getParent()->getDataLayout(), TRI,
+ ImmutableCallSite(CI));
for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];
// Compute the constraint code and ConstraintType to use.
- TLI.ComputeConstraintToUse(OpInfo, SDValue());
+ TLI->ComputeConstraintToUse(OpInfo, SDValue());
// If this asm operand is our Value*, and if it isn't an indirect memory
// operand, we can't fold it!
return true;
}
-/// FindAllMemoryUses - Recursively walk all the uses of I until we find a
-/// memory use. If we find an obviously non-foldable instruction, return true.
+/// Recursively walk all the uses of I until we find a memory use.
+/// If we find an obviously non-foldable instruction, return true.
/// Add the ultimately found memory instructions to MemoryUses.
-static bool FindAllMemoryUses(Instruction *I,
- SmallVectorImpl<std::pair<Instruction*,unsigned> > &MemoryUses,
- SmallPtrSetImpl<Instruction*> &ConsideredInsts,
- const TargetLowering &TLI) {
+static bool FindAllMemoryUses(
+ Instruction *I,
+ SmallVectorImpl<std::pair<Instruction *, unsigned>> &MemoryUses,
+ SmallPtrSetImpl<Instruction *> &ConsideredInsts, const TargetMachine &TM) {
// If we already considered this instruction, we're done.
if (!ConsideredInsts.insert(I).second)
return false;
if (!IA) return true;
// If this is a memory operand, we're cool, otherwise bail out.
- if (!IsOperandAMemoryOperand(CI, IA, I, TLI))
+ if (!IsOperandAMemoryOperand(CI, IA, I, TM))
return true;
continue;
}
- if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI))
+ if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TM))
return true;
}
return false;
}
-/// ValueAlreadyLiveAtInst - Retrn true if Val is already known to be live at
-/// the use site that we're folding it into. If so, there is no cost to
-/// include it in the addressing mode. KnownLive1 and KnownLive2 are two values
-/// that we know are live at the instruction already.
-bool AddressingModeMatcher::ValueAlreadyLiveAtInst(Value *Val,Value *KnownLive1,
+/// Return true if Val is already known to be live at the use site that we're
+/// folding it into. If so, there is no cost to include it in the addressing
+/// mode. KnownLive1 and KnownLive2 are two values that we know are live at the
+/// instruction already.
+bool AddressingModeMatcher::valueAlreadyLiveAtInst(Value *Val,Value *KnownLive1,
Value *KnownLive2) {
// If Val is either of the known-live values, we know it is live!
if (Val == nullptr || Val == KnownLive1 || Val == KnownLive2)
return Val->isUsedInBasicBlock(MemoryInst->getParent());
}
-/// IsProfitableToFoldIntoAddressingMode - It is possible for the addressing
-/// mode of the machine to fold the specified instruction into a load or store
-/// that ultimately uses it. However, the specified instruction has multiple
-/// uses. Given this, it may actually increase register pressure to fold it
-/// into the load. For example, consider this code:
+/// It is possible for the addressing mode of the machine to fold the specified
+/// instruction into a load or store that ultimately uses it.
+/// However, the specified instruction has multiple uses.
+/// Given this, it may actually increase register pressure to fold it
+/// into the load. For example, consider this code:
///
/// X = ...
/// Y = X+1
/// X was live across 'load Z' for other reasons, we actually *would* want to
/// fold the addressing mode in the Z case. This would make Y die earlier.
bool AddressingModeMatcher::
-IsProfitableToFoldIntoAddressingMode(Instruction *I, ExtAddrMode &AMBefore,
+isProfitableToFoldIntoAddressingMode(Instruction *I, ExtAddrMode &AMBefore,
ExtAddrMode &AMAfter) {
if (IgnoreProfitability) return true;
// 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))
+ if (valueAlreadyLiveAtInst(BaseReg, AMBefore.BaseReg, AMBefore.ScaledReg))
BaseReg = nullptr;
- if (ValueAlreadyLiveAtInst(ScaledReg, AMBefore.BaseReg, AMBefore.ScaledReg))
+ if (valueAlreadyLiveAtInst(ScaledReg, AMBefore.BaseReg, AMBefore.ScaledReg))
ScaledReg = nullptr;
// If folding this instruction (and it's subexprs) didn't extend any live
// uses.
SmallVector<std::pair<Instruction*,unsigned>, 16> MemoryUses;
SmallPtrSet<Instruction*, 16> ConsideredInsts;
- if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TLI))
+ if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TM))
return false; // Has a non-memory, non-foldable use!
// Now that we know that all uses of this instruction are part of a chain of
// Get the access type of this use. If the use isn't a pointer, we don't
// know what it accesses.
Value *Address = User->getOperand(OpNo);
- if (!Address->getType()->isPointerTy())
+ PointerType *AddrTy = dyn_cast<PointerType>(Address->getType());
+ if (!AddrTy)
return false;
- Type *AddressAccessTy = Address->getType()->getPointerElementType();
+ Type *AddressAccessTy = AddrTy->getElementType();
+ unsigned AS = AddrTy->getAddressSpace();
// Do a match against the root of this address, ignoring profitability. This
// will tell us if the addressing mode for the memory operation will
ExtAddrMode Result;
TypePromotionTransaction::ConstRestorationPt LastKnownGood =
TPT.getRestorationPoint();
- AddressingModeMatcher Matcher(MatchedAddrModeInsts, TLI, AddressAccessTy,
- MemoryInst, Result, InsertedTruncs,
+ AddressingModeMatcher Matcher(MatchedAddrModeInsts, TM, AddressAccessTy, AS,
+ MemoryInst, Result, InsertedInsts,
PromotedInsts, TPT);
Matcher.IgnoreProfitability = true;
- bool Success = Matcher.MatchAddr(Address, 0);
+ bool Success = Matcher.matchAddr(Address, 0);
(void)Success; assert(Success && "Couldn't select *anything*?");
// The match was to check the profitability, the changes made are not
} // end anonymous namespace
-/// IsNonLocalValue - Return true if the specified values are defined in a
+/// Return true if the specified values are defined in a
/// different basic block than BB.
static bool IsNonLocalValue(Value *V, BasicBlock *BB) {
if (Instruction *I = dyn_cast<Instruction>(V))
return false;
}
-/// OptimizeMemoryInst - Load and Store Instructions often have
-/// addressing modes that can do significant amounts of computation. As such,
-/// instruction selection will try to get the load or store to do as much
-/// computation as possible for the program. The problem is that isel can only
-/// see within a single block. As such, we sink as much legal addressing mode
-/// stuff into the block as possible.
+/// Load and Store Instructions often have addressing modes that can do
+/// significant amounts of computation. As such, instruction selection will try
+/// to get the load or store to do as much computation as possible for the
+/// program. The problem is that isel can only see within a single block. As
+/// such, we sink as much legal addressing mode work into the block as possible.
///
/// This method is used to optimize both load/store and inline asms with memory
/// operands.
-bool CodeGenPrepare::OptimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
- Type *AccessTy) {
+bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
+ Type *AccessTy, unsigned AddrSpace) {
Value *Repl = Addr;
// Try to collapse single-value PHI nodes. This is necessary to undo
// For a PHI node, push all of its incoming values.
if (PHINode *P = dyn_cast<PHINode>(V)) {
- for (unsigned i = 0, e = P->getNumIncomingValues(); i != e; ++i)
- worklist.push_back(P->getIncomingValue(i));
+ for (Value *IncValue : P->incoming_values())
+ worklist.push_back(IncValue);
continue;
}
// For non-PHIs, determine the addressing mode being computed.
SmallVector<Instruction*, 16> NewAddrModeInsts;
ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
- V, AccessTy, MemoryInst, NewAddrModeInsts, *TLI, InsertedTruncsSet,
- PromotedInsts, TPT);
+ V, AccessTy, AddrSpace, MemoryInst, NewAddrModeInsts, *TM,
+ InsertedInsts, PromotedInsts, TPT);
// This check is broken into two cases with very similar code to avoid using
// getNumUses() as much as possible. Some values have a lot of uses, so
<< *MemoryInst << "\n");
if (SunkAddr->getType() != Addr->getType())
SunkAddr = Builder.CreateBitCast(SunkAddr, Addr->getType());
- } else if (AddrSinkUsingGEPs || (!AddrSinkUsingGEPs.getNumOccurrences() &&
- TM && TM->getSubtarget<TargetSubtargetInfo>().useAA())) {
+ } 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());
+ Type *IntPtrTy = DL->getIntPtrType(Addr->getType());
Value *ResultPtr = nullptr, *ResultIndex = nullptr;
// First, find the pointer.
return false;
} else {
Type *I8PtrTy =
- Builder.getInt8PtrTy(Addr->getType()->getPointerAddressSpace());
+ Builder.getInt8PtrTy(Addr->getType()->getPointerAddressSpace());
+ Type *I8Ty = Builder.getInt8Ty();
// Start with the base register. Do this first so that subsequent address
// matching finds it last, which will prevent it from trying to match it
// SDAG consecutive load/store merging.
if (ResultPtr->getType() != I8PtrTy)
ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
- ResultPtr = Builder.CreateGEP(ResultPtr, ResultIndex, "sunkaddr");
+ ResultPtr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
}
ResultIndex = V;
} else {
if (ResultPtr->getType() != I8PtrTy)
ResultPtr = Builder.CreateBitCast(ResultPtr, I8PtrTy);
- SunkAddr = Builder.CreateGEP(ResultPtr, ResultIndex, "sunkaddr");
+ SunkAddr = Builder.CreateGEP(I8Ty, ResultPtr, ResultIndex, "sunkaddr");
}
if (SunkAddr->getType() != Addr->getType())
} else {
DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "
<< *MemoryInst << "\n");
- Type *IntPtrTy = TLI->getDataLayout()->getIntPtrType(Addr->getType());
+ Type *IntPtrTy = DL->getIntPtrType(Addr->getType());
Value *Result = nullptr;
// Start with the base register. Do this first so that subsequent address
if (Repl->use_empty()) {
// This can cause recursive deletion, which can invalidate our iterator.
// Use a WeakVH to hold onto it in case this happens.
- WeakVH IterHandle(CurInstIterator);
+ WeakVH IterHandle(&*CurInstIterator);
BasicBlock *BB = CurInstIterator->getParent();
RecursivelyDeleteTriviallyDeadInstructions(Repl, TLInfo);
- if (IterHandle != CurInstIterator) {
+ if (IterHandle != CurInstIterator.getNodePtrUnchecked()) {
// If the iterator instruction was recursively deleted, start over at the
// start of the block.
CurInstIterator = BB->begin();
return true;
}
-/// OptimizeInlineAsmInst - If there are any memory operands, use
-/// OptimizeMemoryInst to sink their address computing into the block when
-/// possible / profitable.
-bool CodeGenPrepare::OptimizeInlineAsmInst(CallInst *CS) {
+/// If there are any memory operands, use OptimizeMemoryInst to sink their
+/// address computing into the block when possible / profitable.
+bool CodeGenPrepare::optimizeInlineAsmInst(CallInst *CS) {
bool MadeChange = false;
- TargetLowering::AsmOperandInfoVector
- TargetConstraints = TLI->ParseConstraints(CS);
+ const TargetRegisterInfo *TRI =
+ TM->getSubtargetImpl(*CS->getParent()->getParent())->getRegisterInfo();
+ TargetLowering::AsmOperandInfoVector TargetConstraints =
+ TLI->ParseConstraints(*DL, TRI, CS);
unsigned ArgNo = 0;
for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];
if (OpInfo.ConstraintType == TargetLowering::C_Memory &&
OpInfo.isIndirect) {
Value *OpVal = CS->getArgOperand(ArgNo++);
- MadeChange |= OptimizeMemoryInst(CS, OpVal, OpVal->getType());
+ MadeChange |= optimizeMemoryInst(CS, OpVal, OpVal->getType(), ~0u);
} else if (OpInfo.Type == InlineAsm::isInput)
ArgNo++;
}
return MadeChange;
}
-/// 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.
+/// \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.
///
-bool CodeGenPrepare::MoveExtToFormExtLoad(Instruction *I) {
+/// \return true when promoting was necessary to expose the ext(load)
+/// opportunity, false otherwise.
+///
+/// Example:
+/// \code
+/// %ld = load i32* %addr
+/// %add = add nuw i32 %ld, 4
+/// %zext = zext i32 %add to i64
+/// \endcode
+/// =>
+/// \code
+/// %ld = load i32* %addr
+/// %zext = zext i32 %ld to i64
+/// %add = add nuw i64 %zext, 4
+/// \encode
+/// Thanks to the promotion, we can match zext(load i32*) to i64.
+bool CodeGenPrepare::extLdPromotion(TypePromotionTransaction &TPT,
+ LoadInst *&LI, Instruction *&Inst,
+ const SmallVectorImpl<Instruction *> &Exts,
+ unsigned CreatedInstsCost = 0) {
+ // Iterate over all the extensions to see if one form an ext(load).
+ for (auto I : Exts) {
+ // Check if we directly have ext(load).
+ if ((LI = dyn_cast<LoadInst>(I->getOperand(0)))) {
+ Inst = I;
+ // No promotion happened here.
+ return false;
+ }
+ // Check whether or not we want to do any promotion.
+ if (!TLI || !TLI->enableExtLdPromotion() || DisableExtLdPromotion)
+ continue;
+ // Get the action to perform the promotion.
+ TypePromotionHelper::Action TPH = TypePromotionHelper::getAction(
+ I, InsertedInsts, *TLI, PromotedInsts);
+ // Check if we can promote.
+ if (!TPH)
+ continue;
+ // Save the current state.
+ TypePromotionTransaction::ConstRestorationPt LastKnownGood =
+ TPT.getRestorationPoint();
+ SmallVector<Instruction *, 4> NewExts;
+ unsigned NewCreatedInstsCost = 0;
+ unsigned ExtCost = !TLI->isExtFree(I);
+ // Promote.
+ Value *PromotedVal = TPH(I, TPT, PromotedInsts, NewCreatedInstsCost,
+ &NewExts, nullptr, *TLI);
+ assert(PromotedVal &&
+ "TypePromotionHelper should have filtered out those cases");
+
+ // We would be able to merge only one extension in a load.
+ // Therefore, if we have more than 1 new extension we heuristically
+ // cut this search path, because it means we degrade the code quality.
+ // With exactly 2, the transformation is neutral, because we will merge
+ // one extension but leave one. However, we optimistically keep going,
+ // because the new extension may be removed too.
+ long long TotalCreatedInstsCost = CreatedInstsCost + NewCreatedInstsCost;
+ TotalCreatedInstsCost -= ExtCost;
+ if (!StressExtLdPromotion &&
+ (TotalCreatedInstsCost > 1 ||
+ !isPromotedInstructionLegal(*TLI, *DL, PromotedVal))) {
+ // The promotion is not profitable, rollback to the previous state.
+ TPT.rollback(LastKnownGood);
+ continue;
+ }
+ // The promotion is profitable.
+ // Check if it exposes an ext(load).
+ (void)extLdPromotion(TPT, LI, Inst, NewExts, TotalCreatedInstsCost);
+ if (LI && (StressExtLdPromotion || NewCreatedInstsCost <= ExtCost ||
+ // If we have created a new extension, i.e., now we have two
+ // extensions. We must make sure one of them is merged with
+ // the load, otherwise we may degrade the code quality.
+ (LI->hasOneUse() || hasSameExtUse(LI, *TLI))))
+ // Promotion happened.
+ return true;
+ // If this does not help to expose an ext(load) then, rollback.
+ TPT.rollback(LastKnownGood);
+ }
+ // None of the extension can form an ext(load).
+ LI = nullptr;
+ Inst = nullptr;
+ return false;
+}
+
+/// Move a zext or sext fed by a load into the same basic block as the load,
+/// unless conditions are unfavorable. This allows SelectionDAG to fold the
+/// extend into the load.
+/// \p I[in/out] the extension may be modified during the process if some
+/// promotions apply.
+///
+bool CodeGenPrepare::moveExtToFormExtLoad(Instruction *&I) {
+ // Try to promote a chain of computation if it allows to form
+ // an extended load.
+ TypePromotionTransaction TPT;
+ TypePromotionTransaction::ConstRestorationPt LastKnownGood =
+ TPT.getRestorationPoint();
+ SmallVector<Instruction *, 1> Exts;
+ Exts.push_back(I);
// Look for a load being extended.
- LoadInst *LI = 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());
+ EVT VT = TLI->getValueType(*DL, I->getType());
+ EVT LoadVT = TLI->getValueType(*DL, LI->getType());
// If the load has other users and the truncate is not free, this probably
// isn't worthwhile.
if (!LI->hasOneUse() && TLI &&
(TLI->isTypeLegal(LoadVT) || !TLI->isTypeLegal(VT)) &&
- !TLI->isTruncateFree(I->getType(), LI->getType()))
+ !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, LoadVT))
+ if (TLI && !TLI->isLoadExtLegal(LType, VT, LoadVT)) {
+ I = OldExt;
+ TPT.rollback(LastKnownGood);
return false;
+ }
// Move the extend into the same block as the load, so that SelectionDAG
// can fold it.
+ TPT.commit();
I->removeFromParent();
I->insertAfter(LI);
++NumExtsMoved;
return true;
}
-bool CodeGenPrepare::OptimizeExtUses(Instruction *I) {
+bool CodeGenPrepare::optimizeExtUses(Instruction *I) {
BasicBlock *DefBB = I->getParent();
// If the result of a {s|z}ext and its source are both live out, rewrite all
if (!InsertedTrunc) {
BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
- InsertedTrunc = new TruncInst(I, Src->getType(), "", InsertPt);
- InsertedTruncsSet.insert(InsertedTrunc);
+ assert(InsertPt != UserBB->end());
+ InsertedTrunc = new TruncInst(I, Src->getType(), "", &*InsertPt);
+ InsertedInsts.insert(InsertedTrunc);
}
// Replace a use of the {s|z}ext source with a use of the result.
return MadeChange;
}
-/// isFormingBranchFromSelectProfitable - Returns true if a SelectInst should be
-/// turned into an explicit branch.
-static bool isFormingBranchFromSelectProfitable(SelectInst *SI) {
+// Find loads whose uses only use some of the loaded value's bits. Add an "and"
+// just after the load if the target can fold this into one extload instruction,
+// with the hope of eliminating some of the other later "and" instructions using
+// the loaded value. "and"s that are made trivially redundant by the insertion
+// of the new "and" are removed by this function, while others (e.g. those whose
+// path from the load goes through a phi) are left for isel to potentially
+// remove.
+//
+// For example:
+//
+// b0:
+// x = load i32
+// ...
+// b1:
+// y = and x, 0xff
+// z = use y
+//
+// becomes:
+//
+// b0:
+// x = load i32
+// x' = and x, 0xff
+// ...
+// b1:
+// z = use x'
+//
+// whereas:
+//
+// b0:
+// x1 = load i32
+// ...
+// b1:
+// x2 = load i32
+// ...
+// b2:
+// x = phi x1, x2
+// y = and x, 0xff
+//
+// becomes (after a call to optimizeLoadExt for each load):
+//
+// b0:
+// x1 = load i32
+// x1' = and x1, 0xff
+// ...
+// b1:
+// x2 = load i32
+// x2' = and x2, 0xff
+// ...
+// b2:
+// x = phi x1', x2'
+// y = and x, 0xff
+//
+
+bool CodeGenPrepare::optimizeLoadExt(LoadInst *Load) {
+
+ if (!Load->isSimple() ||
+ !(Load->getType()->isIntegerTy() || Load->getType()->isPointerTy()))
+ return false;
+
+ // Skip loads we've already transformed or have no reason to transform.
+ if (Load->hasOneUse()) {
+ User *LoadUser = *Load->user_begin();
+ if (cast<Instruction>(LoadUser)->getParent() == Load->getParent() &&
+ !dyn_cast<PHINode>(LoadUser))
+ return false;
+ }
+
+ // Look at all uses of Load, looking through phis, to determine how many bits
+ // of the loaded value are needed.
+ SmallVector<Instruction *, 8> WorkList;
+ SmallPtrSet<Instruction *, 16> Visited;
+ SmallVector<Instruction *, 8> AndsToMaybeRemove;
+ for (auto *U : Load->users())
+ WorkList.push_back(cast<Instruction>(U));
+
+ EVT LoadResultVT = TLI->getValueType(*DL, Load->getType());
+ unsigned BitWidth = LoadResultVT.getSizeInBits();
+ APInt DemandBits(BitWidth, 0);
+ APInt WidestAndBits(BitWidth, 0);
+
+ while (!WorkList.empty()) {
+ Instruction *I = WorkList.back();
+ WorkList.pop_back();
+
+ // Break use-def graph loops.
+ if (!Visited.insert(I).second)
+ continue;
+
+ // For a PHI node, push all of its users.
+ if (auto *Phi = dyn_cast<PHINode>(I)) {
+ for (auto *U : Phi->users())
+ WorkList.push_back(cast<Instruction>(U));
+ continue;
+ }
+
+ switch (I->getOpcode()) {
+ case llvm::Instruction::And: {
+ auto *AndC = dyn_cast<ConstantInt>(I->getOperand(1));
+ if (!AndC)
+ return false;
+ APInt AndBits = AndC->getValue();
+ DemandBits |= AndBits;
+ // Keep track of the widest and mask we see.
+ if (AndBits.ugt(WidestAndBits))
+ WidestAndBits = AndBits;
+ if (AndBits == WidestAndBits && I->getOperand(0) == Load)
+ AndsToMaybeRemove.push_back(I);
+ break;
+ }
+
+ case llvm::Instruction::Shl: {
+ auto *ShlC = dyn_cast<ConstantInt>(I->getOperand(1));
+ if (!ShlC)
+ return false;
+ uint64_t ShiftAmt = ShlC->getLimitedValue(BitWidth - 1);
+ auto ShlDemandBits = APInt::getAllOnesValue(BitWidth).lshr(ShiftAmt);
+ DemandBits |= ShlDemandBits;
+ break;
+ }
+
+ case llvm::Instruction::Trunc: {
+ EVT TruncVT = TLI->getValueType(*DL, I->getType());
+ unsigned TruncBitWidth = TruncVT.getSizeInBits();
+ auto TruncBits = APInt::getAllOnesValue(TruncBitWidth).zext(BitWidth);
+ DemandBits |= TruncBits;
+ break;
+ }
+
+ default:
+ return false;
+ }
+ }
+
+ uint32_t ActiveBits = DemandBits.getActiveBits();
+ // Avoid hoisting (and (load x) 1) since it is unlikely to be folded by the
+ // target even if isLoadExtLegal says an i1 EXTLOAD is valid. For example,
+ // for the AArch64 target isLoadExtLegal(ZEXTLOAD, i32, i1) returns true, but
+ // (and (load x) 1) is not matched as a single instruction, rather as a LDR
+ // followed by an AND.
+ // TODO: Look into removing this restriction by fixing backends to either
+ // return false for isLoadExtLegal for i1 or have them select this pattern to
+ // a single instruction.
+ //
+ // Also avoid hoisting if we didn't see any ands with the exact DemandBits
+ // mask, since these are the only ands that will be removed by isel.
+ if (ActiveBits <= 1 || !APIntOps::isMask(ActiveBits, DemandBits) ||
+ WidestAndBits != DemandBits)
+ return false;
+
+ LLVMContext &Ctx = Load->getType()->getContext();
+ Type *TruncTy = Type::getIntNTy(Ctx, ActiveBits);
+ EVT TruncVT = TLI->getValueType(*DL, TruncTy);
+
+ // Reject cases that won't be matched as extloads.
+ if (!LoadResultVT.bitsGT(TruncVT) || !TruncVT.isRound() ||
+ !TLI->isLoadExtLegal(ISD::ZEXTLOAD, LoadResultVT, TruncVT))
+ return false;
+
+ IRBuilder<> Builder(Load->getNextNode());
+ auto *NewAnd = dyn_cast<Instruction>(
+ Builder.CreateAnd(Load, ConstantInt::get(Ctx, DemandBits)));
+
+ // Replace all uses of load with new and (except for the use of load in the
+ // new and itself).
+ Load->replaceAllUsesWith(NewAnd);
+ NewAnd->setOperand(0, Load);
+
+ // Remove any and instructions that are now redundant.
+ for (auto *And : AndsToMaybeRemove)
+ // Check that the and mask is the same as the one we decided to put on the
+ // new and.
+ if (cast<ConstantInt>(And->getOperand(1))->getValue() == DemandBits) {
+ And->replaceAllUsesWith(NewAnd);
+ if (&*CurInstIterator == And)
+ CurInstIterator = std::next(And->getIterator());
+ And->eraseFromParent();
+ ++NumAndUses;
+ }
+
+ ++NumAndsAdded;
+ return true;
+}
+
+/// Check if V (an operand of a select instruction) is an expensive instruction
+/// that is only used once.
+static bool sinkSelectOperand(const TargetTransformInfo *TTI, Value *V) {
+ auto *I = dyn_cast<Instruction>(V);
+ // If it's safe to speculatively execute, then it should not have side
+ // effects; therefore, it's safe to sink and possibly *not* execute.
+ return I && I->hasOneUse() && isSafeToSpeculativelyExecute(I) &&
+ TTI->getUserCost(I) >= TargetTransformInfo::TCC_Expensive;
+}
+
+/// Returns true if a SelectInst should be turned into an explicit branch.
+static bool isFormingBranchFromSelectProfitable(const TargetTransformInfo *TTI,
+ SelectInst *SI) {
// FIXME: This should use the same heuristics as IfConversion to determine
// whether a select is better represented as a branch. This requires that
// branch probability metadata is preserved for the select, which is not the
CmpInst *Cmp = dyn_cast<CmpInst>(SI->getCondition());
- // If the branch is predicted right, an out of order CPU can avoid blocking on
- // the compare. Emit cmovs on compares with a memory operand as branches to
- // avoid stalls on the load from memory. If the compare has more than one use
- // there's probably another cmov or setcc around so it's not worth emitting a
- // branch.
- if (!Cmp)
+ // If a branch is predictable, an out-of-order CPU can avoid blocking on its
+ // comparison condition. If the compare has more than one use, there's
+ // probably another cmov or setcc around, so it's not worth emitting a branch.
+ if (!Cmp || !Cmp->hasOneUse())
return false;
Value *CmpOp0 = Cmp->getOperand(0);
Value *CmpOp1 = Cmp->getOperand(1);
- // We check that the memory operand has one use to avoid uses of the loaded
- // value directly after the compare, making branches unprofitable.
- return Cmp->hasOneUse() &&
- ((isa<LoadInst>(CmpOp0) && CmpOp0->hasOneUse()) ||
- (isa<LoadInst>(CmpOp1) && CmpOp1->hasOneUse()));
+ // Emit "cmov on compare with a memory operand" as a branch to avoid stalls
+ // on a load from memory. But if the load is used more than once, do not
+ // change the select to a branch because the load is probably needed
+ // regardless of whether the branch is taken or not.
+ if ((isa<LoadInst>(CmpOp0) && CmpOp0->hasOneUse()) ||
+ (isa<LoadInst>(CmpOp1) && CmpOp1->hasOneUse()))
+ return true;
+
+ // If either operand of the select is expensive and only needed on one side
+ // of the select, we should form a branch.
+ if (sinkSelectOperand(TTI, SI->getTrueValue()) ||
+ sinkSelectOperand(TTI, SI->getFalseValue()))
+ return true;
+
+ return false;
}
/// If we have a SelectInst that will likely profit from branch prediction,
/// turn it into a branch.
-bool CodeGenPrepare::OptimizeSelectInst(SelectInst *SI) {
+bool CodeGenPrepare::optimizeSelectInst(SelectInst *SI) {
bool VectorCond = !SI->getCondition()->getType()->isIntegerTy(1);
// Can we convert the 'select' to CF ?
// We have efficient codegen support for the select instruction.
// Check if it is profitable to keep this 'select'.
if (!TLI->isPredictableSelectExpensive() ||
- !isFormingBranchFromSelectProfitable(SI))
+ !isFormingBranchFromSelectProfitable(TTI, SI))
return false;
}
ModifiedDT = true;
+ // Transform a sequence like this:
+ // start:
+ // %cmp = cmp uge i32 %a, %b
+ // %sel = select i1 %cmp, i32 %c, i32 %d
+ //
+ // Into:
+ // start:
+ // %cmp = cmp uge i32 %a, %b
+ // br i1 %cmp, label %select.true, label %select.false
+ // select.true:
+ // br label %select.end
+ // select.false:
+ // br label %select.end
+ // select.end:
+ // %sel = phi i32 [ %c, %select.true ], [ %d, %select.false ]
+ //
+ // In addition, we may sink instructions that produce %c or %d from
+ // the entry block into the destination(s) of the new branch.
+ // If the true or false blocks do not contain a sunken instruction, that
+ // block and its branch may be optimized away. In that case, one side of the
+ // first branch will point directly to select.end, and the corresponding PHI
+ // predecessor block will be the start block.
+
// First, we split the block containing the select into 2 blocks.
BasicBlock *StartBlock = SI->getParent();
BasicBlock::iterator SplitPt = ++(BasicBlock::iterator(SI));
- BasicBlock *NextBlock = StartBlock->splitBasicBlock(SplitPt, "select.end");
+ BasicBlock *EndBlock = StartBlock->splitBasicBlock(SplitPt, "select.end");
- // Create a new block serving as the landing pad for the branch.
- BasicBlock *SmallBlock = BasicBlock::Create(SI->getContext(), "select.mid",
- NextBlock->getParent(), NextBlock);
-
- // Move the unconditional branch from the block with the select in it into our
- // landing pad block.
+ // Delete the unconditional branch that was just created by the split.
StartBlock->getTerminator()->eraseFromParent();
- BranchInst::Create(NextBlock, SmallBlock);
+
+ // These are the new basic blocks for the conditional branch.
+ // At least one will become an actual new basic block.
+ BasicBlock *TrueBlock = nullptr;
+ BasicBlock *FalseBlock = nullptr;
+
+ // Sink expensive instructions into the conditional blocks to avoid executing
+ // them speculatively.
+ if (sinkSelectOperand(TTI, SI->getTrueValue())) {
+ TrueBlock = BasicBlock::Create(SI->getContext(), "select.true.sink",
+ EndBlock->getParent(), EndBlock);
+ auto *TrueBranch = BranchInst::Create(EndBlock, TrueBlock);
+ auto *TrueInst = cast<Instruction>(SI->getTrueValue());
+ TrueInst->moveBefore(TrueBranch);
+ }
+ if (sinkSelectOperand(TTI, SI->getFalseValue())) {
+ FalseBlock = BasicBlock::Create(SI->getContext(), "select.false.sink",
+ EndBlock->getParent(), EndBlock);
+ auto *FalseBranch = BranchInst::Create(EndBlock, FalseBlock);
+ auto *FalseInst = cast<Instruction>(SI->getFalseValue());
+ FalseInst->moveBefore(FalseBranch);
+ }
+
+ // If there was nothing to sink, then arbitrarily choose the 'false' side
+ // for a new input value to the PHI.
+ if (TrueBlock == FalseBlock) {
+ assert(TrueBlock == nullptr &&
+ "Unexpected basic block transform while optimizing select");
+
+ FalseBlock = BasicBlock::Create(SI->getContext(), "select.false",
+ EndBlock->getParent(), EndBlock);
+ BranchInst::Create(EndBlock, FalseBlock);
+ }
// Insert the real conditional branch based on the original condition.
- BranchInst::Create(NextBlock, SmallBlock, SI->getCondition(), SI);
+ // If we did not create a new block for one of the 'true' or 'false' paths
+ // of the condition, it means that side of the branch goes to the end block
+ // directly and the path originates from the start block from the point of
+ // view of the new PHI.
+ if (TrueBlock == nullptr) {
+ BranchInst::Create(EndBlock, FalseBlock, SI->getCondition(), SI);
+ TrueBlock = StartBlock;
+ } else if (FalseBlock == nullptr) {
+ BranchInst::Create(TrueBlock, EndBlock, SI->getCondition(), SI);
+ FalseBlock = StartBlock;
+ } else {
+ BranchInst::Create(TrueBlock, FalseBlock, SI->getCondition(), SI);
+ }
// The select itself is replaced with a PHI Node.
- PHINode *PN = PHINode::Create(SI->getType(), 2, "", NextBlock->begin());
+ PHINode *PN = PHINode::Create(SI->getType(), 2, "", &EndBlock->front());
PN->takeName(SI);
- PN->addIncoming(SI->getTrueValue(), StartBlock);
- PN->addIncoming(SI->getFalseValue(), SmallBlock);
+ PN->addIncoming(SI->getTrueValue(), TrueBlock);
+ PN->addIncoming(SI->getFalseValue(), FalseBlock);
+
SI->replaceAllUsesWith(PN);
SI->eraseFromParent();
/// (e.g. x86 only introduced "vpsllvd" and friends with AVX2). In these cases
/// it's often worth sinking a shufflevector splat down to its use so that
/// codegen can spot all lanes are identical.
-bool CodeGenPrepare::OptimizeShuffleVectorInst(ShuffleVectorInst *SVI) {
+bool CodeGenPrepare::optimizeShuffleVectorInst(ShuffleVectorInst *SVI) {
BasicBlock *DefBB = SVI->getParent();
// Only do this xform if variable vector shifts are particularly expensive.
if (!InsertedShuffle) {
BasicBlock::iterator InsertPt = UserBB->getFirstInsertionPt();
- InsertedShuffle = new ShuffleVectorInst(SVI->getOperand(0),
- SVI->getOperand(1),
- SVI->getOperand(2), "", InsertPt);
+ assert(InsertPt != UserBB->end());
+ InsertedShuffle =
+ new ShuffleVectorInst(SVI->getOperand(0), SVI->getOperand(1),
+ SVI->getOperand(2), "", &*InsertPt);
}
UI->replaceUsesOfWith(SVI, InsertedShuffle);
return MadeChange;
}
+bool CodeGenPrepare::optimizeSwitchInst(SwitchInst *SI) {
+ if (!TLI || !DL)
+ return false;
+
+ Value *Cond = SI->getCondition();
+ Type *OldType = Cond->getType();
+ LLVMContext &Context = Cond->getContext();
+ MVT RegType = TLI->getRegisterType(Context, TLI->getValueType(*DL, OldType));
+ unsigned RegWidth = RegType.getSizeInBits();
+
+ if (RegWidth <= cast<IntegerType>(OldType)->getBitWidth())
+ return false;
+
+ // If the register width is greater than the type width, expand the condition
+ // of the switch instruction and each case constant to the width of the
+ // register. By widening the type of the switch condition, subsequent
+ // comparisons (for case comparisons) will not need to be extended to the
+ // preferred register width, so we will potentially eliminate N-1 extends,
+ // where N is the number of cases in the switch.
+ auto *NewType = Type::getIntNTy(Context, RegWidth);
+
+ // Zero-extend the switch condition and case constants unless the switch
+ // condition is a function argument that is already being sign-extended.
+ // In that case, we can avoid an unnecessary mask/extension by sign-extending
+ // everything instead.
+ Instruction::CastOps ExtType = Instruction::ZExt;
+ if (auto *Arg = dyn_cast<Argument>(Cond))
+ if (Arg->hasSExtAttr())
+ ExtType = Instruction::SExt;
+
+ auto *ExtInst = CastInst::Create(ExtType, Cond, NewType);
+ ExtInst->insertBefore(SI);
+ SI->setCondition(ExtInst);
+ for (SwitchInst::CaseIt Case : SI->cases()) {
+ APInt NarrowConst = Case.getCaseValue()->getValue();
+ APInt WideConst = (ExtType == Instruction::ZExt) ?
+ NarrowConst.zext(RegWidth) : NarrowConst.sext(RegWidth);
+ Case.setValue(ConstantInt::get(Context, WideConst));
+ }
+
+ return true;
+}
+
namespace {
/// \brief Helper class to promote a scalar operation to a vector one.
/// This class is used to move downward extractelement transition.
/// Assuming both extractelement and store can be combine, we get rid of the
/// transition.
class VectorPromoteHelper {
+ /// DataLayout associated with the current module.
+ const DataLayout &DL;
+
/// Used to perform some checks on the legality of vector operations.
const TargetLowering &TLI;
unsigned Align = ST->getAlignment();
// Check if this store is supported.
if (!TLI.allowsMisalignedMemoryAccesses(
- TLI.getValueType(ST->getValueOperand()->getType()), AS, Align)) {
+ TLI.getValueType(DL, ST->getValueOperand()->getType()), AS,
+ Align)) {
// If this is not supported, there is no way we can combine
// the extract with the store.
return false;
/// \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.
+ /// across the whole vector.
/// In other words, if UseSplat == true, we generate <Val, Val, ..., Val>,
/// otherwise we generate a vector with as many undef as possible:
/// <undef, ..., undef, Val, undef, ..., undef> where \p Val is only
}
public:
- VectorPromoteHelper(const TargetLowering &TLI, const TargetTransformInfo &TTI,
- Instruction *Transition, unsigned CombineCost)
- : TLI(TLI), TTI(TTI), Transition(Transition),
+ VectorPromoteHelper(const DataLayout &DL, const TargetLowering &TLI,
+ const TargetTransformInfo &TTI, Instruction *Transition,
+ unsigned CombineCost)
+ : DL(DL), TLI(TLI), TTI(TTI), Transition(Transition),
StoreExtractCombineCost(CombineCost), CombineInst(nullptr) {
assert(Transition && "Do not know how to promote null");
}
return false;
return StressStoreExtract ||
TLI.isOperationLegalOrCustom(
- ISDOpcode, TLI.getValueType(getTransitionType(), true));
+ ISDOpcode, TLI.getValueType(DL, getTransitionType(), true));
}
/// \brief Check whether or not \p Use can be combined
isa<UndefValue>(Val) ||
canCauseUndefinedBehavior(ToBePromoted, U.getOperandNo()));
} else
- assert(0 && "Did you modified shouldPromote and forgot to update this?");
+ llvm_unreachable("Did you modified shouldPromote and forgot to update "
+ "this?");
ToBePromoted->setOperand(U.getOperandNo(), NewVal);
}
Transition->removeFromParent();
/// 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) {
+bool CodeGenPrepare::optimizeExtractElementInst(Instruction *Inst) {
unsigned CombineCost = UINT_MAX;
if (DisableStoreExtract || !TLI ||
(!StressStoreExtract &&
// 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);
+ VectorPromoteHelper VPH(*DL, *TLI, *TTI, Inst, CombineCost);
// If the transition has more than one use, assume this is not going to be
// beneficial.
while (Inst->hasOneUse()) {
return false;
}
-bool CodeGenPrepare::OptimizeInst(Instruction *I) {
+bool CodeGenPrepare::optimizeInst(Instruction *I, bool& ModifiedDT) {
+ // Bail out if we inserted the instruction to prevent optimizations from
+ // stepping on each other's toes.
+ if (InsertedInsts.count(I))
+ return false;
+
if (PHINode *P = dyn_cast<PHINode>(I)) {
// It is possible for very late stage optimizations (such as SimplifyCFG)
// to introduce PHI nodes too late to be cleaned up. If we detect such a
// trivial PHI, go ahead and zap it here.
- if (Value *V = SimplifyInstruction(P, TLI ? TLI->getDataLayout() : nullptr,
- TLInfo, DT)) {
+ if (Value *V = SimplifyInstruction(P, *DL, TLInfo, nullptr)) {
P->replaceAllUsesWith(V);
P->eraseFromParent();
++NumPHIsElim;
if (isa<Constant>(CI->getOperand(0)))
return false;
- if (TLI && OptimizeNoopCopyExpression(CI, *TLI))
+ if (TLI && OptimizeNoopCopyExpression(CI, *TLI, *DL))
return true;
if (isa<ZExtInst>(I) || isa<SExtInst>(I)) {
/// Sink a zext or sext into its user blocks if the target type doesn't
/// fit in one register
- if (TLI && TLI->getTypeAction(CI->getContext(),
- TLI->getValueType(CI->getType())) ==
- TargetLowering::TypeExpandInteger) {
+ if (TLI &&
+ TLI->getTypeAction(CI->getContext(),
+ TLI->getValueType(*DL, CI->getType())) ==
+ TargetLowering::TypeExpandInteger) {
return SinkCast(CI);
} else {
- bool MadeChange = MoveExtToFormExtLoad(I);
- return MadeChange | OptimizeExtUses(I);
+ bool MadeChange = moveExtToFormExtLoad(I);
+ return MadeChange | optimizeExtUses(I);
}
}
return false;
return OptimizeCmpExpression(CI);
if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
- if (TLI)
- return OptimizeMemoryInst(I, I->getOperand(0), LI->getType());
+ stripInvariantGroupMetadata(*LI);
+ if (TLI) {
+ bool Modified = optimizeLoadExt(LI);
+ unsigned AS = LI->getPointerAddressSpace();
+ Modified |= optimizeMemoryInst(I, I->getOperand(0), LI->getType(), AS);
+ return Modified;
+ }
return false;
}
if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
- if (TLI)
- return OptimizeMemoryInst(I, SI->getOperand(1),
- SI->getOperand(0)->getType());
+ stripInvariantGroupMetadata(*SI);
+ if (TLI) {
+ unsigned AS = SI->getPointerAddressSpace();
+ return optimizeMemoryInst(I, SI->getOperand(1),
+ SI->getOperand(0)->getType(), AS);
+ }
return false;
}
BinOp->getOpcode() == Instruction::LShr)) {
ConstantInt *CI = dyn_cast<ConstantInt>(BinOp->getOperand(1));
if (TLI && CI && TLI->hasExtractBitsInsn())
- return OptimizeExtractBits(BinOp, CI, *TLI);
+ return OptimizeExtractBits(BinOp, CI, *TLI, *DL);
return false;
}
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);
+ return optimizeSelectInst(SI);
if (ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(I))
- return OptimizeShuffleVectorInst(SVI);
+ return optimizeShuffleVectorInst(SVI);
+
+ if (auto *Switch = dyn_cast<SwitchInst>(I))
+ return optimizeSwitchInst(Switch);
if (isa<ExtractElementInst>(I))
- return OptimizeExtractElementInst(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++);
-
- MadeChange |= DupRetToEnableTailCallOpts(&BB);
+ while (CurInstIterator != BB.end()) {
+ MadeChange |= optimizeInst(&*CurInstIterator++, ModifiedDT);
+ if (ModifiedDT)
+ return true;
+ }
+ MadeChange |= dupRetToEnableTailCallOpts(&BB);
return MadeChange;
}
// llvm.dbg.value is far away from the value then iSel may not be able
// handle it properly. iSel will drop llvm.dbg.value if it can not
// find a node corresponding to the value.
-bool CodeGenPrepare::PlaceDbgValues(Function &F) {
+bool CodeGenPrepare::placeDbgValues(Function &F) {
bool MadeChange = false;
- for (Function::iterator I = F.begin(), E = F.end(); I != E; ++I) {
+ for (BasicBlock &BB : F) {
Instruction *PrevNonDbgInst = nullptr;
- for (BasicBlock::iterator BI = I->begin(), BE = I->end(); BI != BE;) {
- Instruction *Insn = BI; ++BI;
+ for (BasicBlock::iterator BI = BB.begin(), BE = BB.end(); BI != BE;) {
+ Instruction *Insn = &*BI++;
DbgValueInst *DVI = dyn_cast<DbgValueInst>(Insn);
// Leave dbg.values that refer to an alloca alone. These
// instrinsics describe the address of a variable (= the alloca)
Instruction *VI = dyn_cast_or_null<Instruction>(DVI->getValue());
if (VI && VI != PrevNonDbgInst && !VI->isTerminator()) {
+ // If VI is a phi in a block with an EHPad terminator, we can't insert
+ // after it.
+ if (isa<PHINode>(VI) && VI->getParent()->getTerminator()->isEHPad())
+ continue;
DEBUG(dbgs() << "Moving Debug Value before :\n" << *DVI << ' ' << *VI);
DVI->removeFromParent();
if (isa<PHINode>(VI))
- DVI->insertBefore(VI->getParent()->getFirstInsertionPt());
+ DVI->insertBefore(&*VI->getParent()->getFirstInsertionPt());
else
DVI->insertAfter(VI);
MadeChange = true;
return false;
bool MadeChange = false;
for (Function::iterator I = F.begin(), E = F.end(); I != E; ) {
- BasicBlock *BB = I++;
+ BasicBlock *BB = &*I++;
// Does this BB end with the following?
// %andVal = and %val, #single-bit-set
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;
/// FIXME: Remove the (equivalent?) implementation in SelectionDAG.
///
bool CodeGenPrepare::splitBranchCondition(Function &F) {
- if (!TM || TM->Options.EnableFastISel != true ||
- !TLI || TLI->isJumpExpensive())
+ if (!TM || !TM->Options.EnableFastISel || !TLI || TLI->isJumpExpensive())
return false;
bool MadeChange = false;
if (!match(BB.getTerminator(), m_Br(m_OneUse(m_BinOp(LogicOp)), TBB, FBB)))
continue;
+ auto *Br1 = cast<BranchInst>(BB.getTerminator());
+ if (Br1->getMetadata(LLVMContext::MD_unpredictable))
+ continue;
+
unsigned Opc;
- Instruction *Cond1, *Cond2;
- if (match(LogicOp, m_And(m_OneUse(m_Instruction(Cond1)),
- m_OneUse(m_Instruction(Cond2)))))
+ 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_Instruction(Cond1)),
- m_OneUse(m_Instruction(Cond2)))))
+ else if (match(LogicOp, m_Or(m_OneUse(m_Value(Cond1)),
+ m_OneUse(m_Value(Cond2)))))
Opc = Instruction::Or;
else
continue;
// 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();
- Cond2->removeFromParent();
+
// Depending on the conditon we have to either replace the true or the false
// successor of the original branch instruction.
if (Opc == Instruction::And)
// Fill in the new basic block.
auto *Br2 = IRBuilder<>(TmpBB).CreateCondBr(Cond2, TBB, FBB);
- Cond2->insertBefore(Br2);
+ 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
// Another choice is to assume TrueProb for BB1 equals to TrueProb for
// TmpBB, but the math is more complicated.
uint64_t TrueWeight, FalseWeight;
- if (Br1->getBranchWeights(TrueWeight, FalseWeight)) {
+ if (extractBranchMetadata(Br1, TrueWeight, FalseWeight)) {
uint64_t NewTrueWeight = TrueWeight;
uint64_t NewFalseWeight = TrueWeight + 2 * FalseWeight;
scaleWeights(NewTrueWeight, NewFalseWeight);
// assumes that
// FalseProb for BB1 == TrueProb for BB1 * FalseProb for TmpBB.
uint64_t TrueWeight, FalseWeight;
- if (Br1->getBranchWeights(TrueWeight, FalseWeight)) {
+ if (extractBranchMetadata(Br1, TrueWeight, FalseWeight)) {
uint64_t NewTrueWeight = 2 * TrueWeight + FalseWeight;
uint64_t NewFalseWeight = FalseWeight;
scaleWeights(NewTrueWeight, NewFalseWeight);
}
}
- // 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.
+ // available to CodeGenPrepare.
ModifiedDT = true;
MadeChange = true;
}
return MadeChange;
}
+
+void CodeGenPrepare::stripInvariantGroupMetadata(Instruction &I) {
+ if (auto *InvariantMD = I.getMetadata(LLVMContext::MD_invariant_group))
+ I.dropUnknownNonDebugMetadata(InvariantMD->getMetadataID());
+}
projects / oota-llvm.git / blobdiff