Skip to content

[SLP][NFC]Remove handling of duplicates from getGatherCost #135834

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 16, 2025
Merged

[SLP][NFC]Remove handling of duplicates from getGatherCost #135834

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 2 additions & 32 deletions llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15349,13 +15349,10 @@ InstructionCost BoUpSLP::getGatherCost(ArrayRef<Value *> VL, bool ForPoisonSrc,
Type *ScalarTy) const {
const unsigned VF = VL.size();
auto *VecTy = getWidenedType(ScalarTy, VF);
bool DuplicateNonConst = false;
// Find the cost of inserting/extracting values from the vector.
// Check if the same elements are inserted several times and count them as
// shuffle candidates.
APInt ShuffledElements = APInt::getZero(VF);
APInt DemandedElements = APInt::getZero(VF);
DenseMap<Value *, unsigned> UniqueElements;
constexpr TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
InstructionCost Cost;
auto EstimateInsertCost = [&](unsigned I, Value *V) {
Expand All @@ -15364,32 +15361,18 @@ InstructionCost BoUpSLP::getGatherCost(ArrayRef<Value *> VL, bool ForPoisonSrc,
Cost += TTI->getCastInstrCost(Instruction::Trunc, ScalarTy, V->getType(),
TTI::CastContextHint::None, CostKind);
};
SmallVector<int> ShuffleMask(VF, PoisonMaskElem);
SmallVector<int> ConstantShuffleMask(VF, PoisonMaskElem);
std::iota(ConstantShuffleMask.begin(), ConstantShuffleMask.end(), 0);
for (auto [I, V] : enumerate(VL)) {
// No need to shuffle duplicates for constants.
if ((ForPoisonSrc && isConstant(V)) || isa<UndefValue>(V)) {
ShuffledElements.setBit(I);
ShuffleMask[I] = isa<PoisonValue>(V) ? PoisonMaskElem : I;
if ((ForPoisonSrc && isConstant(V)) || isa<UndefValue>(V))
continue;
}

if (isConstant(V)) {
ConstantShuffleMask[I] = I + VF;
ShuffleMask[I] = I;
continue;
}
auto Res = UniqueElements.try_emplace(V, I);
if (Res.second) {
EstimateInsertCost(I, V);
ShuffleMask[I] = I;
continue;
}

DuplicateNonConst = true;
ShuffledElements.setBit(I);
ShuffleMask[I] = Res.first->second;
EstimateInsertCost(I, V);
}
// FIXME: add a cost for constant vector materialization.
bool IsAnyNonUndefConst =
Expand All @@ -15398,15 +15381,6 @@ InstructionCost BoUpSLP::getGatherCost(ArrayRef<Value *> VL, bool ForPoisonSrc,
if (!ForPoisonSrc && IsAnyNonUndefConst) {
Cost += ::getShuffleCost(*TTI, TargetTransformInfo::SK_PermuteTwoSrc, VecTy,
ConstantShuffleMask);
// Update the shuffle mask for shuffling with incoming source (all elements
// are used!) or with constant subvector.
for_each(enumerate(ShuffleMask), [&](auto P) {
if ((!ForPoisonSrc && P.value() == PoisonMaskElem) ||
ConstantShuffleMask[P.index()] != PoisonMaskElem)
P.value() = P.index();
else if (P.value() != PoisonMaskElem)
P.value() += VF;
});
}

// 2. Insert unique non-constants.
Expand All @@ -15415,10 +15389,6 @@ InstructionCost BoUpSLP::getGatherCost(ArrayRef<Value *> VL, bool ForPoisonSrc,
/*Insert=*/true,
/*Extract=*/false, CostKind,
ForPoisonSrc && !IsAnyNonUndefConst, VL);
// 3. Shuffle duplicates.
if (DuplicateNonConst)
Cost += ::getShuffleCost(*TTI, TargetTransformInfo::SK_PermuteSingleSrc,
VecTy, ShuffleMask, CostKind);
return Cost;
}

Expand Down
Loading