#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/AliasSetTracker.h"
-#include "llvm/Analysis/AssumptionTracker.h"
+#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/BlockFrequencyInfo.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/LoopInfo.h"
/// element.
virtual Value *getBroadcastInstrs(Value *V);
- /// This function adds 0, 1, 2 ... to each vector element, starting at zero.
- /// If Negate is set then negative numbers are added e.g. (0, -1, -2, ...).
- /// The sequence starts at StartIndex.
- virtual Value *getConsecutiveVector(Value* Val, int StartIdx, bool Negate);
+ /// 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);
/// When we go over instructions in the basic block we rely on previous
/// values within the current basic block or on loop invariant values.
bool IfPredicateStore = false) override;
void vectorizeMemoryInstruction(Instruction *Instr) override;
Value *getBroadcastInstrs(Value *V) override;
- Value *getConsecutiveVector(Value* Val, int StartIdx, bool Negate) override;
+ Value *getStepVector(Value *Val, int StartIdx, Value *Step) override;
Value *reverseVector(Value *Vec) override;
};
/// This enum represents the kinds of inductions that we support.
enum InductionKind {
- IK_NoInduction, ///< Not an induction variable.
- IK_IntInduction, ///< Integer induction variable. Step = 1.
- IK_ReverseIntInduction, ///< Reverse int induction variable. Step = -1.
- IK_PtrInduction, ///< Pointer induction var. Step = sizeof(elem).
- IK_ReversePtrInduction ///< Reverse ptr indvar. Step = - sizeof(elem).
+ IK_NoInduction, ///< Not an induction variable.
+ IK_IntInduction, ///< Integer induction variable. Step = C.
+ IK_PtrInduction ///< Pointer induction var. Step = C / sizeof(elem).
};
// This enum represents the kind of minmax reduction.
/// A struct for saving information about induction variables.
struct InductionInfo {
- InductionInfo(Value *Start, InductionKind K) : StartValue(Start), IK(K) {}
- InductionInfo() : StartValue(nullptr), IK(IK_NoInduction) {}
+ InductionInfo(Value *Start, InductionKind K, ConstantInt *Step)
+ : StartValue(Start), IK(K), StepValue(Step) {
+ assert(IK != IK_NoInduction && "Not an induction");
+ assert(StartValue && "StartValue is null");
+ assert(StepValue && !StepValue->isZero() && "StepValue is zero");
+ assert((IK != IK_PtrInduction || StartValue->getType()->isPointerTy()) &&
+ "StartValue is not a pointer for pointer induction");
+ assert((IK != IK_IntInduction || StartValue->getType()->isIntegerTy()) &&
+ "StartValue is not an integer for integer induction");
+ assert(StepValue->getType()->isIntegerTy() &&
+ "StepValue is not an integer");
+ }
+ InductionInfo()
+ : StartValue(nullptr), IK(IK_NoInduction), StepValue(nullptr) {}
+
+ /// Get the consecutive direction. Returns:
+ /// 0 - unknown or non-consecutive.
+ /// 1 - consecutive and increasing.
+ /// -1 - consecutive and decreasing.
+ int getConsecutiveDirection() const {
+ if (StepValue && (StepValue->isOne() || StepValue->isMinusOne()))
+ return StepValue->getSExtValue();
+ return 0;
+ }
+
+ /// Compute the transformed value of Index at offset StartValue using step
+ /// StepValue.
+ /// For integer induction, returns StartValue + Index * StepValue.
+ /// For pointer induction, returns StartValue[Index * StepValue].
+ /// FIXME: The newly created binary instructions should contain nsw/nuw
+ /// flags, which can be found from the original scalar operations.
+ Value *transform(IRBuilder<> &B, Value *Index) const {
+ switch (IK) {
+ case IK_IntInduction:
+ assert(Index->getType() == StartValue->getType() &&
+ "Index type does not match StartValue type");
+ if (StepValue->isMinusOne())
+ return B.CreateSub(StartValue, Index);
+ if (!StepValue->isOne())
+ Index = B.CreateMul(Index, StepValue);
+ return B.CreateAdd(StartValue, Index);
+
+ case IK_PtrInduction:
+ if (StepValue->isMinusOne())
+ Index = B.CreateNeg(Index);
+ else if (!StepValue->isOne())
+ Index = B.CreateMul(Index, StepValue);
+ return B.CreateGEP(StartValue, Index);
+
+ case IK_NoInduction:
+ return nullptr;
+ }
+ llvm_unreachable("invalid enum");
+ }
+
/// Start value.
TrackingVH<Value> StartValue;
/// Induction kind.
InductionKind IK;
+ /// Step value.
+ ConstantInt *StepValue;
};
/// ReductionList contains the reduction descriptors for all
/// pattern corresponding to a min(X, Y) or max(X, Y).
static ReductionInstDesc isMinMaxSelectCmpPattern(Instruction *I,
ReductionInstDesc &Prev);
- /// Returns the induction kind of Phi. This function may return NoInduction
- /// if the PHI is not an induction variable.
- InductionKind isInductionVariable(PHINode *Phi);
+ /// Returns the induction kind of Phi and record the step. This function may
+ /// return NoInduction if the PHI is not an induction variable.
+ InductionKind isInductionVariable(PHINode *Phi, ConstantInt *&StepValue);
/// \brief Collect memory access with loop invariant strides.
///
/// Looks for accesses like "a[i * StrideA]" where "StrideA" is loop
/// invariant.
- void collectStridedAcccess(Value *LoadOrStoreInst);
+ void collectStridedAccess(Value *LoadOrStoreInst);
/// Report an analysis message to assist the user in diagnosing loops that are
/// not vectorized.
LoopVectorizationLegality *Legal,
const TargetTransformInfo &TTI,
const DataLayout *DL, const TargetLibraryInfo *TLI,
- AssumptionTracker *AT, const Function *F,
+ AssumptionCache *AC, const Function *F,
const LoopVectorizeHints *Hints)
: TheLoop(L), SE(SE), LI(LI), Legal(Legal), TTI(TTI), DL(DL), TLI(TLI),
TheFunction(F), Hints(Hints) {
- CodeMetrics::collectEphemeralValues(L, AT, EphValues);
+ CodeMetrics::collectEphemeralValues(L, AC, EphValues);
}
/// Information about vectorization costs
BlockFrequencyInfo *BFI;
TargetLibraryInfo *TLI;
AliasAnalysis *AA;
- AssumptionTracker *AT;
+ AssumptionCache *AC;
bool DisableUnrolling;
bool AlwaysVectorize;
SE = &getAnalysis<ScalarEvolution>();
DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
DL = DLP ? &DLP->getDataLayout() : nullptr;
- LI = &getAnalysis<LoopInfo>();
- TTI = &getAnalysis<TargetTransformInfo>();
+ LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
+ TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI();
DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
BFI = &getAnalysis<BlockFrequencyInfo>();
- TLI = getAnalysisIfAvailable<TargetLibraryInfo>();
+ auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
+ TLI = TLIP ? &TLIP->getTLI() : nullptr;
AA = &getAnalysis<AliasAnalysis>();
- AT = &getAnalysis<AssumptionTracker>();
+ AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
// Compute some weights outside of the loop over the loops. Compute this
// using a BranchProbability to re-use its scaling math.
}
// Use the cost model.
- LoopVectorizationCostModel CM(L, SE, LI, &LVL, *TTI, DL, TLI, AT, F,
+ LoopVectorizationCostModel CM(L, SE, LI, &LVL, *TTI, DL, TLI, AC, F,
&Hints);
// Check the function attributes to find out if this function should be
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
- AU.addRequired<AssumptionTracker>();
+ AU.addRequired<AssumptionCacheTracker>();
AU.addRequiredID(LoopSimplifyID);
AU.addRequiredID(LCSSAID);
AU.addRequired<BlockFrequencyInfo>();
AU.addRequired<DominatorTreeWrapperPass>();
- AU.addRequired<LoopInfo>();
+ AU.addRequired<LoopInfoWrapperPass>();
AU.addRequired<ScalarEvolution>();
- AU.addRequired<TargetTransformInfo>();
+ AU.addRequired<TargetTransformInfoWrapperPass>();
AU.addRequired<AliasAnalysis>();
- AU.addPreserved<LoopInfo>();
+ AU.addPreserved<LoopInfoWrapperPass>();
AU.addPreserved<DominatorTreeWrapperPass>();
AU.addPreserved<AliasAnalysis>();
}
return Shuf;
}
-Value *InnerLoopVectorizer::getConsecutiveVector(Value* Val, int StartIdx,
- bool Negate) {
+Value *InnerLoopVectorizer::getStepVector(Value *Val, int StartIdx,
+ Value *Step) {
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());
SmallVector<Constant*, 8> Indices;
// Create a vector of consecutive numbers from zero to VF.
- for (int i = 0; i < VLen; ++i) {
- int64_t Idx = Negate ? (-i) : i;
- Indices.push_back(ConstantInt::get(ITy, StartIdx + Idx, Negate));
- }
+ for (int i = 0; i < VLen; ++i)
+ Indices.push_back(ConstantInt::get(ITy, StartIdx + i));
// Add the consecutive indices to the vector value.
Constant *Cv = ConstantVector::get(Indices);
assert(Cv->getType() == Val->getType() && "Invalid consecutive vec");
- return Builder.CreateAdd(Val, Cv, "induction");
+ 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");
}
/// \brief Find the operand of the GEP that should be checked for consecutive
PHINode *Phi = dyn_cast_or_null<PHINode>(Ptr);
if (Phi && Inductions.count(Phi)) {
InductionInfo II = Inductions[Phi];
- if (IK_PtrInduction == II.IK)
- return 1;
- else if (IK_ReversePtrInduction == II.IK)
- return -1;
+ return II.getConsecutiveDirection();
}
GetElementPtrInst *Gep = dyn_cast_or_null<GetElementPtrInst>(Ptr);
return 0;
InductionInfo II = Inductions[Phi];
- if (IK_PtrInduction == II.IK)
- return 1;
- else if (IK_ReversePtrInduction == II.IK)
- return -1;
+ return II.getConsecutiveDirection();
}
unsigned InductionOperand = getGEPInductionOperand(DL, Gep);
// wide store needs to start at the last vector element.
PartPtr = Builder.CreateGEP(Ptr, Builder.getInt32(-Part * VF));
PartPtr = Builder.CreateGEP(PartPtr, Builder.getInt32(1 - VF));
+ Mask[Part] = reverseVector(Mask[Part]);
}
Value *VecPtr = Builder.CreateBitCast(PartPtr,
// wide load needs to start at the last vector element.
PartPtr = Builder.CreateGEP(Ptr, Builder.getInt32(-Part * VF));
PartPtr = Builder.CreateGEP(PartPtr, Builder.getInt32(1 - VF));
+ Mask[Part] = reverseVector(Mask[Part]);
}
Instruction* NewLI;
Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Cmp, ConstantInt::get(Cmp->getType(), 1));
CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
LoopVectorBody.push_back(CondBlock);
- VectorLp->addBasicBlockToLoop(CondBlock, LI->getBase());
+ VectorLp->addBasicBlockToLoop(CondBlock, *LI);
// Update Builder with newly created basic block.
Builder.SetInsertPoint(InsertPt);
}
if (IfPredicateStore) {
BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
LoopVectorBody.push_back(NewIfBlock);
- VectorLp->addBasicBlockToLoop(NewIfBlock, LI->getBase());
+ VectorLp->addBasicBlockToLoop(NewIfBlock, *LI);
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
// before calling any utilities such as SCEV that require valid LoopInfo.
if (ParentLoop) {
ParentLoop->addChildLoop(Lp);
- ParentLoop->addBasicBlockToLoop(ScalarPH, LI->getBase());
- ParentLoop->addBasicBlockToLoop(VectorPH, LI->getBase());
- ParentLoop->addBasicBlockToLoop(MiddleBlock, LI->getBase());
+ ParentLoop->addBasicBlockToLoop(ScalarPH, *LI);
+ ParentLoop->addBasicBlockToLoop(VectorPH, *LI);
+ ParentLoop->addBasicBlockToLoop(MiddleBlock, *LI);
} else {
LI->addTopLevelLoop(Lp);
}
- Lp->addBasicBlockToLoop(VecBody, LI->getBase());
+ Lp->addBasicBlockToLoop(VecBody, *LI);
// Use this IR builder to create the loop instructions (Phi, Br, Cmp)
// inside the loop.
BasicBlock *CheckBlock =
LastBypassBlock->splitBasicBlock(PastOverflowCheck, "overflow.checked");
if (ParentLoop)
- ParentLoop->addBasicBlockToLoop(CheckBlock, LI->getBase());
+ ParentLoop->addBasicBlockToLoop(CheckBlock, *LI);
LoopBypassBlocks.push_back(CheckBlock);
Instruction *OldTerm = LastBypassBlock->getTerminator();
BranchInst::Create(ScalarPH, CheckBlock, CheckBCOverflow, OldTerm);
BasicBlock *CheckBlock =
LastBypassBlock->splitBasicBlock(FirstCheckInst, "vector.stridecheck");
if (ParentLoop)
- ParentLoop->addBasicBlockToLoop(CheckBlock, LI->getBase());
+ ParentLoop->addBasicBlockToLoop(CheckBlock, *LI);
LoopBypassBlocks.push_back(CheckBlock);
// Replace the branch into the memory check block with a conditional branch
BasicBlock *CheckBlock =
LastBypassBlock->splitBasicBlock(MemRuntimeCheck, "vector.memcheck");
if (ParentLoop)
- ParentLoop->addBasicBlockToLoop(CheckBlock, LI->getBase());
+ ParentLoop->addBasicBlockToLoop(CheckBlock, *LI);
LoopBypassBlocks.push_back(CheckBlock);
// Replace the branch into the memory check block with a conditional branch
Value *CRD = BypassBuilder.CreateSExtOrTrunc(CountRoundDown,
II.StartValue->getType(),
"cast.crd");
- EndValue = BypassBuilder.CreateAdd(CRD, II.StartValue , "ind.end");
- break;
- }
- case LoopVectorizationLegality::IK_ReverseIntInduction: {
- // Convert the CountRoundDown variable to the PHI size.
- Value *CRD = BypassBuilder.CreateSExtOrTrunc(CountRoundDown,
- II.StartValue->getType(),
- "cast.crd");
- // Handle reverse integer induction counter.
- EndValue = BypassBuilder.CreateSub(II.StartValue, CRD, "rev.ind.end");
+ EndValue = II.transform(BypassBuilder, CRD);
+ EndValue->setName("ind.end");
break;
}
case LoopVectorizationLegality::IK_PtrInduction: {
- // For pointer induction variables, calculate the offset using
- // the end index.
- EndValue = BypassBuilder.CreateGEP(II.StartValue, CountRoundDown,
- "ptr.ind.end");
- break;
- }
- case LoopVectorizationLegality::IK_ReversePtrInduction: {
- // The value at the end of the loop for the reverse pointer is calculated
- // by creating a GEP with a negative index starting from the start value.
- Value *Zero = ConstantInt::get(CountRoundDown->getType(), 0);
- Value *NegIdx = BypassBuilder.CreateSub(Zero, CountRoundDown,
- "rev.ind.end");
- EndValue = BypassBuilder.CreateGEP(II.StartValue, NegIdx,
- "rev.ptr.ind.end");
+ EndValue = II.transform(BypassBuilder, CountRoundDown);
+ EndValue->setName("ptr.ind.end");
break;
}
}// end of case
LoopVectorizationLegality::InductionInfo II =
Legal->getInductionVars()->lookup(P);
+ // FIXME: The newly created binary instructions should contain nsw/nuw flags,
+ // which can be found from the original scalar operations.
switch (II.IK) {
case LoopVectorizationLegality::IK_NoInduction:
llvm_unreachable("Unknown induction");
Value *NormalizedIdx = Builder.CreateSub(Induction, ExtendedIdx,
"normalized.idx");
NormalizedIdx = Builder.CreateSExtOrTrunc(NormalizedIdx, PhiTy);
- Broadcasted = Builder.CreateAdd(II.StartValue, NormalizedIdx,
- "offset.idx");
+ Broadcasted = II.transform(Builder, NormalizedIdx);
+ Broadcasted->setName("offset.idx");
}
Broadcasted = getBroadcastInstrs(Broadcasted);
// After broadcasting the induction variable we need to make the vector
// consecutive by adding 0, 1, 2, etc.
for (unsigned part = 0; part < UF; ++part)
- Entry[part] = getConsecutiveVector(Broadcasted, VF * part, false);
+ Entry[part] = getStepVector(Broadcasted, VF * part, II.StepValue);
return;
}
- case LoopVectorizationLegality::IK_ReverseIntInduction:
case LoopVectorizationLegality::IK_PtrInduction:
- case LoopVectorizationLegality::IK_ReversePtrInduction:
- // Handle reverse integer and pointer inductions.
- Value *StartIdx = ExtendedIdx;
- // This is the normalized GEP that starts counting at zero.
- Value *NormalizedIdx = Builder.CreateSub(Induction, StartIdx,
- "normalized.idx");
-
- // Handle the reverse integer induction variable case.
- if (LoopVectorizationLegality::IK_ReverseIntInduction == II.IK) {
- IntegerType *DstTy = cast<IntegerType>(II.StartValue->getType());
- Value *CNI = Builder.CreateSExtOrTrunc(NormalizedIdx, DstTy,
- "resize.norm.idx");
- Value *ReverseInd = Builder.CreateSub(II.StartValue, CNI,
- "reverse.idx");
-
- // This is a new value so do not hoist it out.
- Value *Broadcasted = getBroadcastInstrs(ReverseInd);
- // After broadcasting the induction variable we need to make the
- // vector consecutive by adding ... -3, -2, -1, 0.
- for (unsigned part = 0; part < UF; ++part)
- Entry[part] = getConsecutiveVector(Broadcasted, -(int)VF * part,
- true);
- return;
- }
-
// Handle the pointer induction variable case.
assert(P->getType()->isPointerTy() && "Unexpected type.");
-
- // Is this a reverse induction ptr or a consecutive induction ptr.
- bool Reverse = (LoopVectorizationLegality::IK_ReversePtrInduction ==
- II.IK);
-
+ // This is the normalized GEP that starts counting at zero.
+ Value *NormalizedIdx =
+ Builder.CreateSub(Induction, ExtendedIdx, "normalized.idx");
// This is the vector of results. Notice that we don't generate
// vector geps because scalar geps result in better code.
for (unsigned part = 0; part < UF; ++part) {
if (VF == 1) {
- int EltIndex = (part) * (Reverse ? -1 : 1);
+ int EltIndex = part;
Constant *Idx = ConstantInt::get(Induction->getType(), EltIndex);
- Value *GlobalIdx;
- if (Reverse)
- GlobalIdx = Builder.CreateSub(Idx, NormalizedIdx, "gep.ridx");
- else
- GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx, "gep.idx");
-
- Value *SclrGep = Builder.CreateGEP(II.StartValue, GlobalIdx,
- "next.gep");
+ Value *GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx);
+ Value *SclrGep = II.transform(Builder, GlobalIdx);
+ SclrGep->setName("next.gep");
Entry[part] = SclrGep;
continue;
}
Value *VecVal = UndefValue::get(VectorType::get(P->getType(), VF));
for (unsigned int i = 0; i < VF; ++i) {
- int EltIndex = (i + part * VF) * (Reverse ? -1 : 1);
+ int EltIndex = i + part * VF;
Constant *Idx = ConstantInt::get(Induction->getType(), EltIndex);
- Value *GlobalIdx;
- if (!Reverse)
- GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx, "gep.idx");
- else
- GlobalIdx = Builder.CreateSub(Idx, NormalizedIdx, "gep.ridx");
-
- Value *SclrGep = Builder.CreateGEP(II.StartValue, GlobalIdx,
- "next.gep");
+ Value *GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx);
+ Value *SclrGep = II.transform(Builder, GlobalIdx);
+ SclrGep->setName("next.gep");
VecVal = Builder.CreateInsertElement(VecVal, SclrGep,
Builder.getInt32(i),
"insert.gep");
// Nothing to do for PHIs and BR, since we already took care of the
// loop control flow instructions.
continue;
- case Instruction::PHI:{
+ case Instruction::PHI: {
// Vectorize PHINodes.
widenPHIInstruction(it, Entry, UF, VF, PV);
continue;
Value *ScalarCast = Builder.CreateCast(CI->getOpcode(), Induction,
CI->getType());
Value *Broadcasted = getBroadcastInstrs(ScalarCast);
+ LoopVectorizationLegality::InductionInfo II =
+ Legal->getInductionVars()->lookup(OldInduction);
+ Constant *Step =
+ ConstantInt::getSigned(CI->getType(), II.StepValue->getSExtValue());
for (unsigned Part = 0; Part < UF; ++Part)
- Entry[Part] = getConsecutiveVector(Broadcasted, VF * Part, false);
+ Entry[Part] = getStepVector(Broadcasted, VF * Part, Step);
propagateMetadata(Entry, it);
break;
}
}
// We can only vectorize innermost loops.
- if (TheLoop->getSubLoopsVector().size()) {
+ if (!TheLoop->getSubLoopsVector().empty()) {
emitAnalysis(Report() << "loop is not the innermost loop");
return false;
}
return false;
}
- // We only allow if-converted PHIs with more than two incoming values.
+ // We only allow if-converted PHIs with exactly two incoming values.
if (Phi->getNumIncomingValues() != 2) {
emitAnalysis(Report(it)
<< "control flow not understood by vectorizer");
// This is the value coming from the preheader.
Value *StartValue = Phi->getIncomingValueForBlock(PreHeader);
+ ConstantInt *StepValue = nullptr;
// Check if this is an induction variable.
- InductionKind IK = isInductionVariable(Phi);
+ InductionKind IK = isInductionVariable(Phi, StepValue);
if (IK_NoInduction != IK) {
// Get the widest type.
WidestIndTy = getWiderType(*DL, PhiTy, WidestIndTy);
// Int inductions are special because we only allow one IV.
- if (IK == IK_IntInduction) {
+ if (IK == IK_IntInduction && StepValue->isOne()) {
// Use the phi node with the widest type as induction. Use the last
// one if there are multiple (no good reason for doing this other
// than it is expedient).
}
DEBUG(dbgs() << "LV: Found an induction variable.\n");
- Inductions[Phi] = InductionInfo(StartValue, IK);
+ Inductions[Phi] = InductionInfo(StartValue, IK, StepValue);
// Until we explicitly handle the case of an induction variable with
// an outside loop user we have to give up vectorizing this loop.
return false;
}
if (EnableMemAccessVersioning)
- collectStridedAcccess(ST);
+ collectStridedAccess(ST);
}
if (EnableMemAccessVersioning)
if (LoadInst *LI = dyn_cast<LoadInst>(it))
- collectStridedAcccess(LI);
+ collectStridedAccess(LI);
// Reduction instructions are allowed to have exit users.
// All other instructions must not have external users.
return Stride;
}
-void LoopVectorizationLegality::collectStridedAcccess(Value *MemAccess) {
+void LoopVectorizationLegality::collectStridedAccess(Value *MemAccess) {
Value *Ptr = nullptr;
if (LoadInst *LI = dyn_cast<LoadInst>(MemAccess))
Ptr = LI->getPointerOperand();
if (I->getType()->isPointerTy() && isConsecutivePtr(I))
Worklist.insert(Worklist.end(), I->op_begin(), I->op_end());
- while (Worklist.size()) {
+ while (!Worklist.empty()) {
Instruction *I = dyn_cast<Instruction>(Worklist.back());
Worklist.pop_back();
bool UseDeferred = SetIteration > 0;
PtrAccessSet &S = UseDeferred ? DeferredAccesses : Accesses;
- for (auto A : AS) {
- Value *Ptr = A.getValue();
- bool IsWrite = S.count(MemAccessInfo(Ptr, true));
+ for (auto AV : AS) {
+ Value *Ptr = AV.getValue();
- // If we're using the deferred access set, then it contains only reads.
- bool IsReadOnlyPtr = ReadOnlyPtr.count(Ptr) && !IsWrite;
- if (UseDeferred && !IsReadOnlyPtr)
- continue;
- // Otherwise, the pointer must be in the PtrAccessSet, either as a read
- // or a write.
- assert(((IsReadOnlyPtr && UseDeferred) || IsWrite ||
- S.count(MemAccessInfo(Ptr, false))) &&
- "Alias-set pointer not in the access set?");
-
- MemAccessInfo Access(Ptr, IsWrite);
- DepCands.insert(Access);
-
- // Memorize read-only pointers for later processing and skip them in the
- // first round (they need to be checked after we have seen all write
- // pointers). Note: we also mark pointer that are not consecutive as
- // "read-only" pointers (so that we check "a[b[i]] +="). Hence, we need
- // the second check for "!IsWrite".
- if (!UseDeferred && IsReadOnlyPtr) {
- DeferredAccesses.insert(Access);
- continue;
- }
+ // For a single memory access in AliasSetTracker, Accesses may contain
+ // both read and write, and they both need to be handled for CheckDeps.
+ for (auto AC : S) {
+ if (AC.getPointer() != Ptr)
+ continue;
- // If this is a write - check other reads and writes for conflicts. If
- // this is a read only check other writes for conflicts (but only if
- // there is no other write to the ptr - this is an optimization to
- // catch "a[i] = a[i] + " without having to do a dependence check).
- if ((IsWrite || IsReadOnlyPtr) && SetHasWrite) {
- CheckDeps.insert(Access);
- IsRTCheckNeeded = true;
- }
+ bool IsWrite = AC.getInt();
+
+ // If we're using the deferred access set, then it contains only
+ // reads.
+ bool IsReadOnlyPtr = ReadOnlyPtr.count(Ptr) && !IsWrite;
+ if (UseDeferred && !IsReadOnlyPtr)
+ continue;
+ // Otherwise, the pointer must be in the PtrAccessSet, either as a
+ // read or a write.
+ assert(((IsReadOnlyPtr && UseDeferred) || IsWrite ||
+ S.count(MemAccessInfo(Ptr, false))) &&
+ "Alias-set pointer not in the access set?");
+
+ MemAccessInfo Access(Ptr, IsWrite);
+ DepCands.insert(Access);
+
+ // Memorize read-only pointers for later processing and skip them in
+ // the first round (they need to be checked after we have seen all
+ // write pointers). Note: we also mark pointer that are not
+ // consecutive as "read-only" pointers (so that we check
+ // "a[b[i]] +="). Hence, we need the second check for "!IsWrite".
+ if (!UseDeferred && IsReadOnlyPtr) {
+ DeferredAccesses.insert(Access);
+ continue;
+ }
+
+ // If this is a write - check other reads and writes for conflicts. If
+ // this is a read only check other writes for conflicts (but only if
+ // there is no other write to the ptr - this is an optimization to
+ // catch "a[i] = a[i] + " without having to do a dependence check).
+ if ((IsWrite || IsReadOnlyPtr) && SetHasWrite) {
+ CheckDeps.insert(Access);
+ IsRTCheckNeeded = true;
+ }
- if (IsWrite)
- SetHasWrite = true;
-
- // Create sets of pointers connected by a shared alias set and
- // underlying object.
- typedef SmallVector<Value *, 16> ValueVector;
- ValueVector TempObjects;
- GetUnderlyingObjects(Ptr, TempObjects, DL);
- for (Value *UnderlyingObj : TempObjects) {
- UnderlyingObjToAccessMap::iterator Prev =
- ObjToLastAccess.find(UnderlyingObj);
- if (Prev != ObjToLastAccess.end())
- DepCands.unionSets(Access, Prev->second);
-
- ObjToLastAccess[UnderlyingObj] = Access;
+ if (IsWrite)
+ SetHasWrite = true;
+
+ // Create sets of pointers connected by a shared alias set and
+ // underlying object.
+ typedef SmallVector<Value *, 16> ValueVector;
+ ValueVector TempObjects;
+ GetUnderlyingObjects(Ptr, TempObjects, DL);
+ for (Value *UnderlyingObj : TempObjects) {
+ UnderlyingObjToAccessMap::iterator Prev =
+ ObjToLastAccess.find(UnderlyingObj);
+ if (Prev != ObjToLastAccess.end())
+ DepCands.unionSets(Access, Prev->second);
+
+ ObjToLastAccess[UnderlyingObj] = Access;
+ }
}
}
}
}
LoopVectorizationLegality::InductionKind
-LoopVectorizationLegality::isInductionVariable(PHINode *Phi) {
+LoopVectorizationLegality::isInductionVariable(PHINode *Phi,
+ ConstantInt *&StepValue) {
Type *PhiTy = Phi->getType();
// We only handle integer and pointer inductions variables.
if (!PhiTy->isIntegerTy() && !PhiTy->isPointerTy())
DEBUG(dbgs() << "LV: PHI is not a poly recurrence.\n");
return IK_NoInduction;
}
- const SCEV *Step = AR->getStepRecurrence(*SE);
-
- // Integer inductions need to have a stride of one.
- if (PhiTy->isIntegerTy()) {
- if (Step->isOne())
- return IK_IntInduction;
- if (Step->isAllOnesValue())
- return IK_ReverseIntInduction;
- return IK_NoInduction;
- }
+ const SCEV *Step = AR->getStepRecurrence(*SE);
// Calculate the pointer stride and check if it is consecutive.
const SCEVConstant *C = dyn_cast<SCEVConstant>(Step);
if (!C)
return IK_NoInduction;
+ ConstantInt *CV = C->getValue();
+ if (PhiTy->isIntegerTy()) {
+ StepValue = CV;
+ return IK_IntInduction;
+ }
+
assert(PhiTy->isPointerTy() && "The PHI must be a pointer");
Type *PointerElementType = PhiTy->getPointerElementType();
// The pointer stride cannot be determined if the pointer element type is not
if (!PointerElementType->isSized())
return IK_NoInduction;
- uint64_t Size = DL->getTypeAllocSize(PointerElementType);
- if (C->getValue()->equalsInt(Size))
- return IK_PtrInduction;
- else if (C->getValue()->equalsInt(0 - Size))
- return IK_ReversePtrInduction;
-
- return IK_NoInduction;
+ int64_t Size = static_cast<int64_t>(DL->getTypeAllocSize(PointerElementType));
+ int64_t CVSize = CV->getSExtValue();
+ if (CVSize % Size)
+ return IK_NoInduction;
+ StepValue = ConstantInt::getSigned(CV->getType(), CVSize / Size);
+ return IK_PtrInduction;
}
bool LoopVectorizationLegality::isInductionVariable(const Value *V) {
char LoopVectorize::ID = 0;
static const char lv_name[] = "Loop Vectorization";
INITIALIZE_PASS_BEGIN(LoopVectorize, LV_NAME, lv_name, false, false)
-INITIALIZE_AG_DEPENDENCY(TargetTransformInfo)
+INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_AG_DEPENDENCY(AliasAnalysis)
-INITIALIZE_PASS_DEPENDENCY(AssumptionTracker)
+INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(BlockFrequencyInfo)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
INITIALIZE_PASS_DEPENDENCY(LCSSA)
-INITIALIZE_PASS_DEPENDENCY(LoopInfo)
+INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_END(LoopVectorize, LV_NAME, lv_name, false, false)
ConstantInt::get(Cond[Part]->getType(), 1));
CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
LoopVectorBody.push_back(CondBlock);
- VectorLp->addBasicBlockToLoop(CondBlock, LI->getBase());
+ VectorLp->addBasicBlockToLoop(CondBlock, *LI);
// Update Builder with newly created basic block.
Builder.SetInsertPoint(InsertPt);
}
if (IfPredicateStore) {
BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
LoopVectorBody.push_back(NewIfBlock);
- VectorLp->addBasicBlockToLoop(NewIfBlock, LI->getBase());
+ VectorLp->addBasicBlockToLoop(NewIfBlock, *LI);
Builder.SetInsertPoint(InsertPt);
Instruction *OldBr = IfBlock->getTerminator();
BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
return V;
}
-Value *InnerLoopUnroller::getConsecutiveVector(Value* Val, int StartIdx,
- bool Negate) {
+Value *InnerLoopUnroller::getStepVector(Value *Val, int StartIdx, Value *Step) {
// 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, Negate);
- return Builder.CreateAdd(Val, C, "induction");
+ Constant *C = ConstantInt::get(ITy, StartIdx);
+ return Builder.CreateAdd(Val, Builder.CreateMul(C, Step), "induction");
}