#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"
"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");
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);
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 = ThisRelocate.getBasePtr();
auto Derived = dyn_cast<GetElementPtrInst>(ThisRelocate.getDerivedPtr());
if (!Derived || Derived->getPointerOperand() != Base)
//
static void ScalarizeMaskedLoad(CallInst *CI) {
Value *Ptr = CI->getArgOperand(0);
- Value *Src0 = CI->getArgOperand(3);
+ Value *Alignment = CI->getArgOperand(1);
Value *Mask = CI->getArgOperand(2);
- VectorType *VecType = dyn_cast<VectorType>(CI->getType());
- Type *EltTy = VecType->getElementType();
+ 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.SetInsertPoint(InsertPt);
Builder.SetCurrentDebugLocation(CI->getDebugLoc());
+ // Short-cut if the mask is all-true.
+ bool IsAllOnesMask = isa<Constant>(Mask) &&
+ cast<Constant>(Mask)->isAllOnesValue();
+
+ if (IsAllOnesMask) {
+ Value *NewI = Builder.CreateAlignedLoad(Ptr, AlignVal);
+ CI->replaceAllUsesWith(NewI);
+ CI->eraseFromParent();
+ return;
+ }
+
+ // Adjust alignment for the scalar instruction.
+ AlignVal = std::min(AlignVal, VecType->getScalarSizeInBits()/8);
// Bitcast %addr fron i8* to EltTy*
Type *NewPtrType =
EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
+ unsigned VectorWidth = VecType->getNumElements();
+
Value *UndefVal = UndefValue::get(VecType);
// The result vector
Value *VResult = UndefVal;
+ if (isa<ConstantVector>(Mask)) {
+ for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+ if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
+ continue;
+ Value *Gep =
+ Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
+ LoadInst* Load = Builder.CreateAlignedLoad(Gep, AlignVal);
+ VResult = Builder.CreateInsertElement(VResult, Load,
+ Builder.getInt32(Idx));
+ }
+ Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
+ CI->replaceAllUsesWith(NewI);
+ CI->eraseFromParent();
+ return;
+ }
+
PHINode *Phi = nullptr;
Value *PrevPhi = UndefVal;
- unsigned VectorWidth = VecType->getNumElements();
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
// Fill the "else" block, created in the previous iteration
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
- LoadInst* Load = Builder.CreateLoad(Gep, false);
+ LoadInst *Load = Builder.CreateAlignedLoad(Gep, AlignVal);
VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
// Create "else" block, fill it in the next iteration
// br label %else2
// . . .
static void ScalarizeMaskedStore(CallInst *CI) {
- Value *Ptr = CI->getArgOperand(1);
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());
- Type *EltTy = VecType->getElementType();
-
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_load, label %cond.store, label %else
+ // 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,
Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
Value *Gep =
Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
- Builder.CreateStore(OneElt, Gep);
+ Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
// Create "else" block, fill it in the next iteration
BasicBlock *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();
}
case Intrinsic::masked_load: {
// Scalarize unsupported vector masked load
- if (!TTI->isLegalMaskedLoad(CI->getType(), 1)) {
+ if (!TTI->isLegalMaskedLoad(CI->getType())) {
ScalarizeMaskedLoad(CI);
ModifiedDT = true;
return true;
return false;
}
case Intrinsic::masked_store: {
- if (!TTI->isLegalMaskedStore(CI->getArgOperand(0)->getType(), 1)) {
+ 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));
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) {
/// \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
return false;
// #2 check that the truncate just drops extended bits.
- if (Inst->getType()->getIntegerBitWidth() >= OpndType->getIntegerBitWidth())
- return true;
-
- return false;
+ return Inst->getType()->getIntegerBitWidth() >=
+ OpndType->getIntegerBitWidth();
}
TypePromotionHelper::Action TypePromotionHelper::getAction(
return MadeChange;
}
+// Find loads whose uses only use some of the loaded value's bits. Add an "and"
+// just after the load if the target can fold this into one extload instruction,
+// with the hope of eliminating some of the other later "and" instructions using
+// the loaded value. "and"s that are made trivially redundant by the insertion
+// of the new "and" are removed by this function, while others (e.g. those whose
+// path from the load goes through a phi) are left for isel to potentially
+// remove.
+//
+// For example:
+//
+// b0:
+// x = load i32
+// ...
+// b1:
+// y = and x, 0xff
+// z = use y
+//
+// becomes:
+//
+// b0:
+// x = load i32
+// x' = and x, 0xff
+// ...
+// b1:
+// z = use x'
+//
+// whereas:
+//
+// b0:
+// x1 = load i32
+// ...
+// b1:
+// x2 = load i32
+// ...
+// b2:
+// x = phi x1, x2
+// y = and x, 0xff
+//
+// becomes (after a call to optimizeLoadExt for each load):
+//
+// b0:
+// x1 = load i32
+// x1' = and x1, 0xff
+// ...
+// b1:
+// x2 = load i32
+// x2' = and x2, 0xff
+// ...
+// b2:
+// x = phi x1', x2'
+// y = and x, 0xff
+//
+
+bool CodeGenPrepare::optimizeLoadExt(LoadInst *Load) {
+
+ if (!Load->isSimple() ||
+ !(Load->getType()->isIntegerTy() || Load->getType()->isPointerTy()))
+ return false;
+
+ // Skip loads we've already transformed or have no reason to transform.
+ if (Load->hasOneUse()) {
+ User *LoadUser = *Load->user_begin();
+ if (cast<Instruction>(LoadUser)->getParent() == Load->getParent() &&
+ !dyn_cast<PHINode>(LoadUser))
+ return false;
+ }
+
+ // Look at all uses of Load, looking through phis, to determine how many bits
+ // of the loaded value are needed.
+ SmallVector<Instruction *, 8> WorkList;
+ SmallPtrSet<Instruction *, 16> Visited;
+ SmallVector<Instruction *, 8> AndsToMaybeRemove;
+ for (auto *U : Load->users())
+ WorkList.push_back(cast<Instruction>(U));
+
+ EVT LoadResultVT = TLI->getValueType(*DL, Load->getType());
+ unsigned BitWidth = LoadResultVT.getSizeInBits();
+ APInt DemandBits(BitWidth, 0);
+ APInt WidestAndBits(BitWidth, 0);
+
+ while (!WorkList.empty()) {
+ Instruction *I = WorkList.back();
+ WorkList.pop_back();
+
+ // Break use-def graph loops.
+ if (!Visited.insert(I).second)
+ continue;
+
+ // For a PHI node, push all of its users.
+ if (auto *Phi = dyn_cast<PHINode>(I)) {
+ for (auto *U : Phi->users())
+ WorkList.push_back(cast<Instruction>(U));
+ continue;
+ }
+
+ switch (I->getOpcode()) {
+ case llvm::Instruction::And: {
+ auto *AndC = dyn_cast<ConstantInt>(I->getOperand(1));
+ if (!AndC)
+ return false;
+ APInt AndBits = AndC->getValue();
+ DemandBits |= AndBits;
+ // Keep track of the widest and mask we see.
+ if (AndBits.ugt(WidestAndBits))
+ WidestAndBits = AndBits;
+ if (AndBits == WidestAndBits && I->getOperand(0) == Load)
+ AndsToMaybeRemove.push_back(I);
+ break;
+ }
+
+ case llvm::Instruction::Shl: {
+ auto *ShlC = dyn_cast<ConstantInt>(I->getOperand(1));
+ if (!ShlC)
+ return false;
+ uint64_t ShiftAmt = ShlC->getLimitedValue(BitWidth - 1);
+ auto ShlDemandBits = APInt::getAllOnesValue(BitWidth).lshr(ShiftAmt);
+ DemandBits |= ShlDemandBits;
+ break;
+ }
+
+ case llvm::Instruction::Trunc: {
+ EVT TruncVT = TLI->getValueType(*DL, I->getType());
+ unsigned TruncBitWidth = TruncVT.getSizeInBits();
+ auto TruncBits = APInt::getAllOnesValue(TruncBitWidth).zext(BitWidth);
+ DemandBits |= TruncBits;
+ break;
+ }
+
+ default:
+ return false;
+ }
+ }
+
+ uint32_t ActiveBits = DemandBits.getActiveBits();
+ // Avoid hoisting (and (load x) 1) since it is unlikely to be folded by the
+ // target even if isLoadExtLegal says an i1 EXTLOAD is valid. For example,
+ // for the AArch64 target isLoadExtLegal(ZEXTLOAD, i32, i1) returns true, but
+ // (and (load x) 1) is not matched as a single instruction, rather as a LDR
+ // followed by an AND.
+ // TODO: Look into removing this restriction by fixing backends to either
+ // return false for isLoadExtLegal for i1 or have them select this pattern to
+ // a single instruction.
+ //
+ // Also avoid hoisting if we didn't see any ands with the exact DemandBits
+ // mask, since these are the only ands that will be removed by isel.
+ if (ActiveBits <= 1 || !APIntOps::isMask(ActiveBits, DemandBits) ||
+ WidestAndBits != DemandBits)
+ return false;
+
+ LLVMContext &Ctx = Load->getType()->getContext();
+ Type *TruncTy = Type::getIntNTy(Ctx, ActiveBits);
+ EVT TruncVT = TLI->getValueType(*DL, TruncTy);
+
+ // Reject cases that won't be matched as extloads.
+ if (!LoadResultVT.bitsGT(TruncVT) || !TruncVT.isRound() ||
+ !TLI->isLoadExtLegal(ISD::ZEXTLOAD, LoadResultVT, TruncVT))
+ return false;
+
+ IRBuilder<> Builder(Load->getNextNode());
+ auto *NewAnd = dyn_cast<Instruction>(
+ Builder.CreateAnd(Load, ConstantInt::get(Ctx, DemandBits)));
+
+ // Replace all uses of load with new and (except for the use of load in the
+ // new and itself).
+ Load->replaceAllUsesWith(NewAnd);
+ NewAnd->setOperand(0, Load);
+
+ // Remove any and instructions that are now redundant.
+ for (auto *And : AndsToMaybeRemove)
+ // Check that the and mask is the same as the one we decided to put on the
+ // new and.
+ if (cast<ConstantInt>(And->getOperand(1))->getValue() == DemandBits) {
+ And->replaceAllUsesWith(NewAnd);
+ if (&*CurInstIterator == And)
+ CurInstIterator = std::next(And->getIterator());
+ And->eraseFromParent();
+ ++NumAndUses;
+ }
+
+ ++NumAndsAdded;
+ return true;
+}
+
/// Check if V (an operand of a select instruction) is an expensive instruction
/// that is only used once.
static bool sinkSelectOperand(const TargetTransformInfo *TTI, Value *V) {
auto *I = dyn_cast<Instruction>(V);
- if (I && I->hasOneUse() &&
- TTI->getUserCost(I) == TargetTransformInfo::TCC_Expensive)
- return true;
-
- return false;
+ // 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.
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.
if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
stripInvariantGroupMetadata(*LI);
if (TLI) {
+ bool Modified = optimizeLoadExt(LI);
unsigned AS = LI->getPointerAddressSpace();
- return optimizeMemoryInst(I, I->getOperand(0), LI->getType(), AS);
+ Modified |= optimizeMemoryInst(I, I->getOperand(0), LI->getType(), AS);
+ return Modified;
}
return false;
}
if (ShuffleVectorInst *SVI = dyn_cast<ShuffleVectorInst>(I))
return optimizeShuffleVectorInst(SVI);
+ if (auto *Switch = dyn_cast<SwitchInst>(I))
+ return optimizeSwitchInst(Switch);
+
if (isa<ExtractElementInst>(I))
return optimizeExtractElementInst(I);
projects / oota-llvm.git / blobdiff