diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp index 58dbff143929..9087eea9001b 100644 --- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -4295,9 +4295,12 @@ BoUpSLP::LoadsState BoUpSLP::canVectorizeLoads( llvm_unreachable( "Expected only consecutive, strided or masked gather loads."); } + SmallVector ShuffleMask(VL.size()); + for (int Idx : seq(0, VL.size())) + ShuffleMask[Idx] = Idx / VF == I ? VL.size() + Idx % VF : Idx; VecLdCost += TTI.getShuffleCost(TTI ::SK_InsertSubvector, VecTy, - std::nullopt, CostKind, I * VF, SubVecTy); + ShuffleMask, CostKind, I * VF, SubVecTy); } // If masked gather cost is higher - better to vectorize, so // consider it as a gather node. It will be better estimated @@ -7401,7 +7404,7 @@ getShuffleCost(const TargetTransformInfo &TTI, TTI::ShuffleKind Kind, Index + NumSrcElts <= static_cast(Mask.size())) return TTI.getShuffleCost( TTI::SK_InsertSubvector, - FixedVectorType::get(Tp->getElementType(), Mask.size()), std::nullopt, + FixedVectorType::get(Tp->getElementType(), Mask.size()), Mask, TTI::TCK_RecipThroughput, Index, Tp); } return TTI.getShuffleCost(Kind, Tp, Mask, CostKind, Index, SubTp, Args); @@ -7674,9 +7677,13 @@ class BoUpSLP::ShuffleCostEstimator : public BaseShuffleAnalysis { } if (NeedInsertSubvectorAnalysis) { // Add the cost for the subvectors insert. - for (int I = VF, E = VL.size(); I < E; I += VF) + SmallVector ShuffleMask(VL.size()); + for (int I = VF, E = VL.size(); I < E; I += VF) { + for (int Idx : seq(0, E)) + ShuffleMask[Idx] = Idx / VF == I ? E + Idx % VF : Idx; GatherCost += TTI.getShuffleCost(TTI::SK_InsertSubvector, VecTy, - std::nullopt, CostKind, I, LoadTy); + ShuffleMask, CostKind, I, LoadTy); + } } GatherCost -= ScalarsCost; }