diff options
Diffstat (limited to 'llvm/lib/Transforms')
-rw-r--r-- | llvm/lib/Transforms/Scalar/LoopInterchange.cpp | 2 | ||||
-rw-r--r-- | llvm/lib/Transforms/Utils/LoopUtils.cpp | 118 | ||||
-rw-r--r-- | llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 135 |
3 files changed, 210 insertions, 45 deletions
diff --git a/llvm/lib/Transforms/Scalar/LoopInterchange.cpp b/llvm/lib/Transforms/Scalar/LoopInterchange.cpp index 9241ec36527..70d014f5797 100644 --- a/llvm/lib/Transforms/Scalar/LoopInterchange.cpp +++ b/llvm/lib/Transforms/Scalar/LoopInterchange.cpp @@ -703,7 +703,7 @@ bool LoopInterchangeLegality::findInductionAndReductions( RecurrenceDescriptor RD; InductionDescriptor ID; PHINode *PHI = cast<PHINode>(I); - if (InductionDescriptor::isInductionPHI(PHI, SE, ID)) + if (InductionDescriptor::isInductionPHI(PHI, L, SE, ID)) Inductions.push_back(PHI); else if (RecurrenceDescriptor::isReductionPHI(PHI, L, RD)) Reductions.push_back(PHI); diff --git a/llvm/lib/Transforms/Utils/LoopUtils.cpp b/llvm/lib/Transforms/Utils/LoopUtils.cpp index 3902c67c6a0..882f68ffac9 100644 --- a/llvm/lib/Transforms/Utils/LoopUtils.cpp +++ b/llvm/lib/Transforms/Utils/LoopUtils.cpp @@ -654,8 +654,8 @@ Value *RecurrenceDescriptor::createMinMaxOp(IRBuilder<> &Builder, } InductionDescriptor::InductionDescriptor(Value *Start, InductionKind K, - const SCEV *Step) - : StartValue(Start), IK(K), Step(Step) { + const SCEV *Step, BinaryOperator *BOp) + : StartValue(Start), IK(K), Step(Step), InductionBinOp(BOp) { assert(IK != IK_NoInduction && "Not an induction"); // Start value type should match the induction kind and the value @@ -672,7 +672,15 @@ InductionDescriptor::InductionDescriptor(Value *Start, InductionKind K, assert((IK != IK_PtrInduction || getConstIntStepValue()) && "Step value should be constant for pointer induction"); - assert(Step->getType()->isIntegerTy() && "StepValue is not an integer"); + assert((IK == IK_FpInduction || Step->getType()->isIntegerTy()) && + "StepValue is not an integer"); + + assert((IK != IK_FpInduction || Step->getType()->isFloatingPointTy()) && + "StepValue is not FP for FpInduction"); + assert((IK != IK_FpInduction || (InductionBinOp && + (InductionBinOp->getOpcode() == Instruction::FAdd || + InductionBinOp->getOpcode() == Instruction::FSub))) && + "Binary opcode should be specified for FP induction"); } int InductionDescriptor::getConsecutiveDirection() const { @@ -693,6 +701,8 @@ Value *InductionDescriptor::transform(IRBuilder<> &B, Value *Index, const DataLayout& DL) const { SCEVExpander Exp(*SE, DL, "induction"); + assert(Index->getType() == Step->getType() && + "Index type does not match StepValue type"); switch (IK) { case IK_IntInduction: { assert(Index->getType() == StartValue->getType() && @@ -717,29 +727,113 @@ Value *InductionDescriptor::transform(IRBuilder<> &B, Value *Index, return Exp.expandCodeFor(S, StartValue->getType(), &*B.GetInsertPoint()); } case IK_PtrInduction: { - assert(Index->getType() == Step->getType() && - "Index type does not match StepValue type"); assert(isa<SCEVConstant>(Step) && "Expected constant step for pointer induction"); const SCEV *S = SE->getMulExpr(SE->getSCEV(Index), Step); Index = Exp.expandCodeFor(S, Index->getType(), &*B.GetInsertPoint()); return B.CreateGEP(nullptr, StartValue, Index); } + case IK_FpInduction: { + assert(Step->getType()->isFloatingPointTy() && "Expected FP Step value"); + assert(InductionBinOp && + (InductionBinOp->getOpcode() == Instruction::FAdd || + InductionBinOp->getOpcode() == Instruction::FSub) && + "Original bin op should be defined for FP induction"); + + Value *StepValue = cast<SCEVUnknown>(Step)->getValue(); + + // Floating point operations had to be 'fast' to enable the induction. + FastMathFlags Flags; + Flags.setUnsafeAlgebra(); + + Value *MulExp = B.CreateFMul(StepValue, Index); + if (isa<Instruction>(MulExp)) + // We have to check, the MulExp may be a constant. + cast<Instruction>(MulExp)->setFastMathFlags(Flags); + + Value *BOp = B.CreateBinOp(InductionBinOp->getOpcode() , StartValue, + MulExp, "induction"); + if (isa<Instruction>(BOp)) + cast<Instruction>(BOp)->setFastMathFlags(Flags); + + return BOp; + } case IK_NoInduction: return nullptr; } llvm_unreachable("invalid enum"); } -bool InductionDescriptor::isInductionPHI(PHINode *Phi, +bool InductionDescriptor::isFPInductionPHI(PHINode *Phi, const Loop *TheLoop, + ScalarEvolution *SE, + InductionDescriptor &D) { + + // Here we only handle FP induction variables. + assert(Phi->getType()->isFloatingPointTy() && "Unexpected Phi type"); + + if (TheLoop->getHeader() != Phi->getParent()) + return false; + + // The loop may have multiple entrances or multiple exits; we can analyze + // this phi if it has a unique entry value and a unique backedge value. + if (Phi->getNumIncomingValues() != 2) + return false; + Value *BEValue = nullptr, *StartValue = nullptr; + if (TheLoop->contains(Phi->getIncomingBlock(0))) { + BEValue = Phi->getIncomingValue(0); + StartValue = Phi->getIncomingValue(1); + } else { + assert(TheLoop->contains(Phi->getIncomingBlock(1)) && + "Unexpected Phi node in the loop"); + BEValue = Phi->getIncomingValue(1); + StartValue = Phi->getIncomingValue(0); + } + + BinaryOperator *BOp = dyn_cast<BinaryOperator>(BEValue); + if (!BOp) + return false; + + Value *Addend = nullptr; + if (BOp->getOpcode() == Instruction::FAdd) { + if (BOp->getOperand(0) == Phi) + Addend = BOp->getOperand(1); + else if (BOp->getOperand(1) == Phi) + Addend = BOp->getOperand(0); + } else if (BOp->getOpcode() == Instruction::FSub) + if (BOp->getOperand(0) == Phi) + Addend = BOp->getOperand(1); + + if (!Addend) + return false; + + // The addend should be loop invariant + if (auto *I = dyn_cast<Instruction>(Addend)) + if (TheLoop->contains(I)) + return false; + + // FP Step has unknown SCEV + const SCEV *Step = SE->getUnknown(Addend); + D = InductionDescriptor(StartValue, IK_FpInduction, Step, BOp); + return true; +} + +bool InductionDescriptor::isInductionPHI(PHINode *Phi, const Loop *TheLoop, PredicatedScalarEvolution &PSE, InductionDescriptor &D, bool Assume) { Type *PhiTy = Phi->getType(); - // We only handle integer and pointer inductions variables. - if (!PhiTy->isIntegerTy() && !PhiTy->isPointerTy()) + + // Handle integer and pointer inductions variables. + // Now we handle also FP induction but not trying to make a + // recurrent expression from the PHI node in-place. + + if (!PhiTy->isIntegerTy() && !PhiTy->isPointerTy() && + !PhiTy->isFloatTy() && !PhiTy->isDoubleTy() && !PhiTy->isHalfTy()) return false; + if (PhiTy->isFloatingPointTy()) + return isFPInductionPHI(Phi, TheLoop, PSE.getSE(), D); + const SCEV *PhiScev = PSE.getSCEV(Phi); const auto *AR = dyn_cast<SCEVAddRecExpr>(PhiScev); @@ -752,10 +846,10 @@ bool InductionDescriptor::isInductionPHI(PHINode *Phi, return false; } - return isInductionPHI(Phi, PSE.getSE(), D, AR); + return isInductionPHI(Phi, TheLoop, PSE.getSE(), D, AR); } -bool InductionDescriptor::isInductionPHI(PHINode *Phi, +bool InductionDescriptor::isInductionPHI(PHINode *Phi, const Loop *TheLoop, ScalarEvolution *SE, InductionDescriptor &D, const SCEV *Expr) { @@ -773,7 +867,7 @@ bool InductionDescriptor::isInductionPHI(PHINode *Phi, return false; } - assert(AR->getLoop()->getHeader() == Phi->getParent() && + assert(TheLoop->getHeader() == Phi->getParent() && "PHI is an AddRec for a different loop?!"); Value *StartValue = Phi->getIncomingValueForBlock(AR->getLoop()->getLoopPreheader()); @@ -781,7 +875,7 @@ bool InductionDescriptor::isInductionPHI(PHINode *Phi, // Calculate the pointer stride and check if it is consecutive. // The stride may be a constant or a loop invariant integer value. const SCEVConstant *ConstStep = dyn_cast<SCEVConstant>(Step); - if (!ConstStep && !SE->isLoopInvariant(Step, AR->getLoop())) + if (!ConstStep && !SE->isLoopInvariant(Step, TheLoop)) return false; if (PhiTy->isIntegerTy()) { diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index b5a751e7361..1f473775c41 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -402,7 +402,10 @@ protected: /// This function adds (StartIdx, StartIdx + Step, StartIdx + 2*Step, ...) /// to each vector element of Val. The sequence starts at StartIndex. - virtual Value *getStepVector(Value *Val, int StartIdx, Value *Step); + /// \p Opcode is relevant for FP induction variable. + virtual Value *getStepVector(Value *Val, int StartIdx, Value *Step, + Instruction::BinaryOps Opcode = + Instruction::BinaryOpsEnd); /// Compute scalar induction steps. \p ScalarIV is the scalar induction /// variable on which to base the steps, \p Step is the size of the step, and @@ -625,7 +628,9 @@ private: bool IfPredicateStore = false) override; void vectorizeMemoryInstruction(Instruction *Instr) override; Value *getBroadcastInstrs(Value *V) override; - Value *getStepVector(Value *Val, int StartIdx, Value *Step) override; + Value *getStepVector(Value *Val, int StartIdx, Value *Step, + Instruction::BinaryOps Opcode = + Instruction::BinaryOpsEnd) override; Value *reverseVector(Value *Vec) override; }; @@ -2000,32 +2005,60 @@ void InnerLoopVectorizer::widenIntInduction(PHINode *IV, VectorParts &Entry, } } -Value *InnerLoopVectorizer::getStepVector(Value *Val, int StartIdx, - Value *Step) { +Value *InnerLoopVectorizer::getStepVector(Value *Val, int StartIdx, Value *Step, + Instruction::BinaryOps BinOp) { + // Create and check the types. assert(Val->getType()->isVectorTy() && "Must be a vector"); - assert(Val->getType()->getScalarType()->isIntegerTy() && - "Elem must be an integer"); - assert(Step->getType() == Val->getType()->getScalarType() && - "Step has wrong type"); - // Create the types. - Type *ITy = Val->getType()->getScalarType(); - VectorType *Ty = cast<VectorType>(Val->getType()); - int VLen = Ty->getNumElements(); + int VLen = Val->getType()->getVectorNumElements(); + + Type *STy = Val->getType()->getScalarType(); + assert((STy->isIntegerTy() || STy->isFloatingPointTy()) && + "Induction Step must be an integer or FP"); + assert(Step->getType() == STy && "Step has wrong type"); + SmallVector<Constant *, 8> Indices; + if (STy->isIntegerTy()) { + // Create a vector of consecutive numbers from zero to VF. + for (int i = 0; i < VLen; ++i) + Indices.push_back(ConstantInt::get(STy, StartIdx + i)); + + // Add the consecutive indices to the vector value. + Constant *Cv = ConstantVector::get(Indices); + assert(Cv->getType() == Val->getType() && "Invalid consecutive vec"); + Step = Builder.CreateVectorSplat(VLen, Step); + assert(Step->getType() == Val->getType() && "Invalid step vec"); + // FIXME: The newly created binary instructions should contain nsw/nuw flags, + // which can be found from the original scalar operations. + Step = Builder.CreateMul(Cv, Step); + return Builder.CreateAdd(Val, Step, "induction"); + } + + // Floating point induction. + assert((BinOp == Instruction::FAdd || BinOp == Instruction::FSub) && + "Binary Opcode should be specified for FP induction"); // Create a vector of consecutive numbers from zero to VF. for (int i = 0; i < VLen; ++i) - Indices.push_back(ConstantInt::get(ITy, StartIdx + i)); + Indices.push_back(ConstantFP::get(STy, (double)(StartIdx + i))); // Add the consecutive indices to the vector value. Constant *Cv = ConstantVector::get(Indices); - assert(Cv->getType() == Val->getType() && "Invalid consecutive vec"); + Step = Builder.CreateVectorSplat(VLen, Step); - assert(Step->getType() == Val->getType() && "Invalid step vec"); - // FIXME: The newly created binary instructions should contain nsw/nuw flags, - // which can be found from the original scalar operations. - Step = Builder.CreateMul(Cv, Step); - return Builder.CreateAdd(Val, Step, "induction"); + + // Floating point operations had to be 'fast' to enable the induction. + FastMathFlags Flags; + Flags.setUnsafeAlgebra(); + + Value *MulOp = Builder.CreateFMul(Cv, Step); + if (isa<Instruction>(MulOp)) + // Have to check, MulOp may be a constant + cast<Instruction>(MulOp)->setFastMathFlags(Flags); + + Value *BOp = Builder.CreateBinOp(BinOp, Val, MulOp, "induction"); + if (isa<Instruction>(BOp)) + cast<Instruction>(BOp)->setFastMathFlags(Flags); + return BOp; } void InnerLoopVectorizer::buildScalarSteps(Value *ScalarIV, Value *Step, @@ -3099,8 +3132,10 @@ void InnerLoopVectorizer::createEmptyLoop() { EndValue = CountRoundDown; } else { IRBuilder<> B(LoopBypassBlocks.back()->getTerminator()); - Value *CRD = B.CreateSExtOrTrunc(CountRoundDown, - II.getStep()->getType(), "cast.crd"); + Type *StepType = II.getStep()->getType(); + Instruction::CastOps CastOp = + CastInst::getCastOpcode(CountRoundDown, true, StepType, true); + Value *CRD = B.CreateCast(CastOp, CountRoundDown, StepType, "cast.crd"); const DataLayout &DL = OrigLoop->getHeader()->getModule()->getDataLayout(); EndValue = II.transform(B, CRD, PSE.getSE(), DL); EndValue->setName("ind.end"); @@ -4047,7 +4082,7 @@ void InnerLoopVectorizer::widenPHIInstruction( llvm_unreachable("Unknown induction"); case InductionDescriptor::IK_IntInduction: return widenIntInduction(P, Entry); - case InductionDescriptor::IK_PtrInduction: + case InductionDescriptor::IK_PtrInduction: { // Handle the pointer induction variable case. assert(P->getType()->isPointerTy() && "Unexpected type."); // This is the normalized GEP that starts counting at zero. @@ -4080,6 +4115,29 @@ void InnerLoopVectorizer::widenPHIInstruction( } return; } + case InductionDescriptor::IK_FpInduction: { + assert(P->getType() == II.getStartValue()->getType() && + "Types must match"); + // Handle other induction variables that are now based on the + // canonical one. + assert(P != OldInduction && "Primary induction can be integer only"); + + Value *V = Builder.CreateCast(Instruction::SIToFP, Induction, P->getType()); + V = II.transform(Builder, V, PSE.getSE(), DL); + V->setName("fp.offset.idx"); + + // Now we have scalar op: %fp.offset.idx = StartVal +/- Induction*StepVal + + Value *Broadcasted = getBroadcastInstrs(V); + // After broadcasting the induction variable we need to make the vector + // consecutive by adding StepVal*0, StepVal*1, StepVal*2, etc. + Value *StepVal = cast<SCEVUnknown>(II.getStep())->getValue(); + for (unsigned part = 0; part < UF; ++part) + Entry[part] = getStepVector(Broadcasted, VF * part, StepVal, + II.getInductionOpcode()); + return; + } + } } void InnerLoopVectorizer::vectorizeBlockInLoop(BasicBlock *BB, PhiVector *PV) { @@ -4565,10 +4623,12 @@ void LoopVectorizationLegality::addInductionPhi( const DataLayout &DL = Phi->getModule()->getDataLayout(); // Get the widest type. - if (!WidestIndTy) - WidestIndTy = convertPointerToIntegerType(DL, PhiTy); - else - WidestIndTy = getWiderType(DL, PhiTy, WidestIndTy); + if (!PhiTy->isFloatingPointTy()) { + if (!WidestIndTy) + WidestIndTy = convertPointerToIntegerType(DL, PhiTy); + else + WidestIndTy = getWiderType(DL, PhiTy, WidestIndTy); + } // Int inductions are special because we only allow one IV. if (ID.getKind() == InductionDescriptor::IK_IntInduction && @@ -4649,8 +4709,10 @@ bool LoopVectorizationLegality::canVectorizeInstrs() { } InductionDescriptor ID; - if (InductionDescriptor::isInductionPHI(Phi, PSE, ID)) { + if (InductionDescriptor::isInductionPHI(Phi, TheLoop, PSE, ID)) { addInductionPhi(Phi, ID, AllowedExit); + if (ID.hasUnsafeAlgebra() && !HasFunNoNaNAttr) + Requirements->addUnsafeAlgebraInst(ID.getUnsafeAlgebraInst()); continue; } @@ -4661,7 +4723,7 @@ bool LoopVectorizationLegality::canVectorizeInstrs() { // As a last resort, coerce the PHI to a AddRec expression // and re-try classifying it a an induction PHI. - if (InductionDescriptor::isInductionPHI(Phi, PSE, ID, true)) { + if (InductionDescriptor::isInductionPHI(Phi, TheLoop, PSE, ID, true)) { addInductionPhi(Phi, ID, AllowedExit); continue; } @@ -6348,11 +6410,20 @@ Value *InnerLoopUnroller::reverseVector(Value *Vec) { return Vec; } Value *InnerLoopUnroller::getBroadcastInstrs(Value *V) { return V; } -Value *InnerLoopUnroller::getStepVector(Value *Val, int StartIdx, Value *Step) { +Value *InnerLoopUnroller::getStepVector(Value *Val, int StartIdx, Value *Step, + Instruction::BinaryOps BinOp) { // When unrolling and the VF is 1, we only need to add a simple scalar. - Type *ITy = Val->getType(); - assert(!ITy->isVectorTy() && "Val must be a scalar"); - Constant *C = ConstantInt::get(ITy, StartIdx); + Type *Ty = Val->getType(); + assert(!Ty->isVectorTy() && "Val must be a scalar"); + + if (Ty->isFloatingPointTy()) { + Constant *C = ConstantFP::get(Ty, (double)StartIdx); + + // Floating point operations had to be 'fast' to enable the unrolling. + Value *MulOp = addFastMathFlag(Builder.CreateFMul(C, Step)); + return addFastMathFlag(Builder.CreateBinOp(BinOp, Val, MulOp)); + } + Constant *C = ConstantInt::get(Ty, StartIdx); return Builder.CreateAdd(Val, Builder.CreateMul(C, Step), "induction"); } |