diff --git a/llvm/include/llvm/Analysis/VectorUtils.h b/llvm/include/llvm/Analysis/VectorUtils.h --- a/llvm/include/llvm/Analysis/VectorUtils.h +++ b/llvm/include/llvm/Analysis/VectorUtils.h @@ -398,6 +398,10 @@ bool widenShuffleMaskElts(int Scale, ArrayRef Mask, SmallVectorImpl &ScaledMask); +SmallVector>> +computeShuffleMasks(ArrayRef Mask, unsigned NumOfSrcRegs, + unsigned NumOfDestRegs); + /// Compute a map of integer instructions to their minimum legal type /// size. /// diff --git a/llvm/lib/Analysis/VectorUtils.cpp b/llvm/lib/Analysis/VectorUtils.cpp --- a/llvm/lib/Analysis/VectorUtils.cpp +++ b/llvm/lib/Analysis/VectorUtils.cpp @@ -496,6 +496,43 @@ return true; } +SmallVector>> +llvm::computeShuffleMasks(ArrayRef Mask, unsigned NumOfSrcRegs, + unsigned NumOfDestRegs) { + SmallVector>> Res(NumOfDestRegs); + // Try to perform better estimation of the permutation. + // 1. Split the source/destination vectors into real registers. + // 2. Do the mask analysis to identify which real registers are + // permuted. + int Sz = Mask.size(); + unsigned SzDest = Sz / NumOfDestRegs; + unsigned SzSrc = Sz / NumOfSrcRegs; + for (unsigned I = 0; I < NumOfDestRegs; ++I) { + int FirstReg = -1; + auto &RegMasks = Res[I]; + RegMasks.assign(NumOfSrcRegs, {}); + // Check that the values in dest registers are in the one src + // register. + for (unsigned K = 0; K < SzDest; ++K) { + int Idx = I * SzDest + K; + if (Idx == Sz) + break; + if (Mask[Idx] >= Sz || Mask[Idx] == UndefMaskElem) + continue; + int SrcRegIdx = Mask[Idx] / SzSrc; + // Add a cost of PermuteTwoSrc for each new source register permute, + // if we have more than one source registers. + if (RegMasks[SrcRegIdx].empty()) { + if (FirstReg < 0) + FirstReg = SrcRegIdx; + RegMasks[SrcRegIdx].assign(SzDest, UndefMaskElem); + } + RegMasks[SrcRegIdx][K] = Mask[Idx] % SzSrc; + } + } + return Res; +} + MapVector llvm::computeMinimumValueSizes(ArrayRef Blocks, DemandedBits &DB, const TargetTransformInfo *TTI) { diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp @@ -21,6 +21,7 @@ #include "LegalizeTypes.h" #include "llvm/Analysis/MemoryLocation.h" +#include "llvm/Analysis/VectorUtils.h" #include "llvm/IR/DataLayout.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/TypeSize.h" @@ -2047,99 +2048,97 @@ // If Lo or Hi uses elements from at most two of the four input vectors, then // express it as a vector shuffle of those two inputs. Otherwise extract the // input elements by hand and construct the Lo/Hi output using a BUILD_VECTOR. - SmallVector Ops; for (unsigned High = 0; High < 2; ++High) { SDValue &Output = High ? Hi : Lo; // Build a shuffle mask for the output, discovering on the fly which // input vectors to use as shuffle operands (recorded in InputUsed). - // If building a suitable shuffle vector proves too hard, then bail - // out with useBuildVector set. - unsigned InputUsed[2] = { -1U, -1U }; // Not yet discovered. unsigned FirstMaskIdx = High * NewElts; - bool useBuildVector = false; - for (unsigned MaskOffset = 0; MaskOffset < NewElts; ++MaskOffset) { - // The mask element. This indexes into the input. - int Idx = N->getMaskElt(FirstMaskIdx + MaskOffset); - - // The input vector this mask element indexes into. - unsigned Input = (unsigned)Idx / NewElts; - - if (Input >= array_lengthof(Inputs)) { - // The mask element does not index into any input vector. - Ops.push_back(-1); - continue; - } - - // Turn the index into an offset from the start of the input vector. - Idx -= Input * NewElts; - - // Find or create a shuffle vector operand to hold this input. - unsigned OpNo; - for (OpNo = 0; OpNo < array_lengthof(InputUsed); ++OpNo) { - if (InputUsed[OpNo] == Input) { - // This input vector is already an operand. - break; - } else if (InputUsed[OpNo] == -1U) { - // Create a new operand for this input vector. - InputUsed[OpNo] = Input; - break; - } - } - - if (OpNo >= array_lengthof(InputUsed)) { - // More than two input vectors used! Give up on trying to create a - // shuffle vector. Insert all elements into a BUILD_VECTOR instead. - useBuildVector = true; - break; - } - - // Add the mask index for the new shuffle vector. - Ops.push_back(Idx + OpNo * NewElts); - } - - if (useBuildVector) { + SmallVector Mask(NewElts * array_lengthof(Inputs), UndefMaskElem); + copy(N->getMask().slice(FirstMaskIdx, NewElts), Mask.begin()); + SmallVector>> DestVectors = + computeShuffleMasks(Mask, array_lengthof(Inputs), + array_lengthof(Inputs)); + assert(DestVectors.size() == array_lengthof(Inputs) && + "Destination vectors and permutations not synced."); + auto &Dest = DestVectors.front(); + int NumSrcRegs = + count_if(Dest, [](ArrayRef Mask) { return !Mask.empty(); }); + if (NumSrcRegs > 2) { + // Use build vector currently. + // TODO: investigate if we can switch to shuffles for > 2 inputs. EVT EltVT = NewVT.getVectorElementType(); - SmallVector SVOps; - - // Extract the input elements by hand. - for (unsigned MaskOffset = 0; MaskOffset < NewElts; ++MaskOffset) { - // The mask element. This indexes into the input. - int Idx = N->getMaskElt(FirstMaskIdx + MaskOffset); - - // The input vector this mask element indexes into. - unsigned Input = (unsigned)Idx / NewElts; - - if (Input >= array_lengthof(Inputs)) { - // The mask element is "undef" or indexes off the end of the input. - SVOps.push_back(DAG.getUNDEF(EltVT)); - continue; - } - - // Turn the index into an offset from the start of the input vector. - Idx -= Input * NewElts; - - // Extract the vector element by hand. - SVOps.push_back(DAG.getNode(ISD::EXTRACT_VECTOR_ELT, dl, EltVT, - Inputs[Input], - DAG.getVectorIdxConstant(Idx, dl))); + SmallVector SVOps(NewElts); + for (unsigned Input = 0, E = Dest.size(); Input < E; ++Input) { + ArrayRef Mask = Dest[Input]; + for (int I = 0, E = Mask.size(); I < E; ++I) + if (Mask[I] != UndefMaskElem) { + assert(!SVOps[I] && "Expected no ops yet."); + SVOps[I] = + DAG.getNode(ISD::EXTRACT_VECTOR_ELT, dl, EltVT, Inputs[Input], + DAG.getVectorIdxConstant(Mask[I], dl)); + } + } + for (unsigned I = 0; I < NewElts; ++I) { + if (!SVOps[I]) + SVOps[I] = DAG.getUNDEF(EltVT); } // Construct the Lo/Hi output using a BUILD_VECTOR. Output = DAG.getBuildVector(NewVT, dl, SVOps); - } else if (InputUsed[0] == -1U) { + } else if (NumSrcRegs == 0) { // No input vectors were used! The result is undefined. Output = DAG.getUNDEF(NewVT); + } else if (NumSrcRegs == 1) { + // Find the only mask with at least single undef mask elem. + auto *It = + find_if(Dest, [](ArrayRef Mask) { return !Mask.empty(); }); + Output = DAG.getVectorShuffle(NewVT, dl, + Inputs[std::distance(Dest.begin(), It)], + DAG.getUNDEF(NewVT), *It); } else { - SDValue Op0 = Inputs[InputUsed[0]]; - // If only one input was used, use an undefined vector for the other. - SDValue Op1 = InputUsed[1] == -1U ? - DAG.getUNDEF(NewVT) : Inputs[InputUsed[1]]; - // At least one input vector was used. Create a new shuffle vector. - Output = DAG.getVectorShuffle(NewVT, dl, Op0, Op1, Ops); + assert(NumSrcRegs > 1 && "Expected more than one input register."); + // Try to merge any masked elements. + auto *It = + find_if(Dest, [](ArrayRef Mask) { return !Mask.empty(); }); + unsigned InitIdx = std::distance(Dest.begin(), It); + SDValue Op0 = Inputs[InitIdx]; + auto *FirstNotInitIt = + find_if(drop_begin(Dest, InitIdx + 1), + [](ArrayRef Mask) { return !Mask.empty(); }); + unsigned SecondIdx = std::distance(Dest.begin(), FirstNotInitIt); + SDValue Op1 = Inputs[SecondIdx]; + auto &MergedMask = *It; + for (unsigned Idx = 0; Idx < NewElts; ++Idx) { + if ((*FirstNotInitIt)[Idx] != UndefMaskElem) { + assert(MergedMask[Idx] == UndefMaskElem && + "Expected undefined mask element."); + MergedMask[Idx] = (*FirstNotInitIt)[Idx] + NewElts; + } + } + Op0 = DAG.getVectorShuffle(NewVT, dl, Op0, Op1, MergedMask); + // At least two input vector were used. Create shuffles. + for (unsigned I = SecondIdx + 1, E = array_lengthof(Inputs); I < E; ++I) { + MutableArrayRef RegMask = Dest[I]; + if (RegMask.empty()) + continue; + for (unsigned Idx = 0; Idx < NewElts; ++Idx) { + if (RegMask[Idx] == UndefMaskElem) { + if (MergedMask[Idx] != UndefMaskElem) + RegMask[Idx] = Idx; + } else { + assert(MergedMask[Idx] == UndefMaskElem && + "Expected undefined mask element."); + RegMask[Idx] += NewElts; + } + MergedMask[Idx] = RegMask[Idx]; + } + assert(RegMask.size() == NewElts && + "Mask size does not match the vector length."); + Op0 = DAG.getVectorShuffle(NewVT, dl, Op0, Inputs[I], RegMask); + } + Output = Op0; } - - Ops.clear(); } } diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp --- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp +++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp @@ -1223,6 +1223,101 @@ auto *SingleOpTy = FixedVectorType::get(BaseTp->getElementType(), LegalVT.getVectorNumElements()); + if (!Mask.empty() && NumOfDests.isValid()) { + // Try to perform better estimation of the permutation. + // 1. Split the source/destination vectors into real registers. + // 2. Do the mask analysis to identify which real registers are + // permuted. If more than 1 source registers are used for the + // destination register building, the cost for this destination register + // is (Number_of_source_register - 1) * Cost_PermuteTwoSrc. If only one + // source register is used, build mask and calculate the cost as a cost + // of PermuteSingleSrc. + // Also, for the single register permute we try to identify if the + // destination register is just a copy of the source register or the + // copy of the previous destination register (the cost is + // TTI::TCC_Basic). If the source register is just reused, the cost for + // this operation is 0. + unsigned E = *NumOfDests.getValue(); + SmallVector>> DestVectors = + computeShuffleMasks(Mask, NumOfSrcs, E); + assert(E == DestVectors.size() && + "Destination vectors and permutations not synced."); + InstructionCost Cost = 0; + unsigned PrevSrcReg = 0; + ArrayRef PrevRegMask; + for (unsigned I = 0; I < E; ++I) { + auto &Dest = DestVectors[I]; + int NumSrcRegs = + count_if(Dest, [](ArrayRef Mask) { return !Mask.empty(); }); + // NumSrcRegs might be 0 if the mask is just undef. + if (NumSrcRegs == 1) { + // Analysis of the single source register permutation. + auto *It = + find_if(Dest, [](ArrayRef Mask) { return !Mask.empty(); }); + unsigned SrcReg = std::distance(Dest.begin(), It); + ArrayRef RegMask = *It; + if (!ShuffleVectorInst::isIdentityMask(RegMask)) { + // Check if the previous register can be just copied to the next + // one. + if (PrevRegMask.empty() || PrevSrcReg != SrcReg || + PrevRegMask != RegMask) + Cost += getShuffleCost(TTI::SK_PermuteSingleSrc, SingleOpTy, + RegMask, 0, nullptr); + else + // Just a copy of previous destination register. + Cost += TTI::TCC_Basic; + } else if (SrcReg != I && any_of(RegMask, [](int I) { + return I != UndefMaskElem; + })) { + // Just a copy of the source register. + Cost += TTI::TCC_Basic; + } + PrevSrcReg = SrcReg; + PrevRegMask = RegMask; + } else if (NumSrcRegs > 1) { + // The first mask is a permutation of a single register, which can + // be transformed into a shuffle of 2 registers instead of 1 reg + // shuffle + 2 reg shuffles in case if we have 2+ input vectors. + auto *It = + find_if(Dest, [](ArrayRef Mask) { return !Mask.empty(); }); + auto *FirstNotInitIt = + find_if(drop_begin(Dest, std::distance(Dest.begin(), It) + 1), + [](ArrayRef Mask) { return !Mask.empty(); }); + int VF = It->size(); + auto &MergedMask = *It; + for (int Idx = 0; Idx < VF; ++Idx) { + if ((*FirstNotInitIt)[Idx] != UndefMaskElem) { + assert(MergedMask[Idx] == UndefMaskElem && + "Expected undefined mask element."); + MergedMask[Idx] = (*FirstNotInitIt)[Idx] + VF; + } + } + Cost += getShuffleCost(TTI::SK_PermuteTwoSrc, SingleOpTy, + MergedMask, 0, nullptr); + for (MutableArrayRef RegMask : + make_range(FirstNotInitIt + 1, Dest.end())) { + if (RegMask.empty()) + continue; + + for (int Idx = 0; Idx < VF; ++Idx) { + if (RegMask[Idx] == UndefMaskElem) { + if (MergedMask[Idx] != UndefMaskElem) + RegMask[Idx] = Idx; + } else { + assert(MergedMask[Idx] == UndefMaskElem && + "Expected undefined mask element."); + RegMask[Idx] += VF; + } + MergedMask[Idx] = RegMask[Idx]; + } + Cost += getShuffleCost(TTI::SK_PermuteTwoSrc, SingleOpTy, RegMask, + 0, nullptr); + } + } + } + return Cost; + } + InstructionCost NumOfShuffles = (NumOfSrcs - 1) * NumOfDests; return NumOfShuffles * getShuffleCost(TTI::SK_PermuteTwoSrc, SingleOpTy, None, 0, nullptr); diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp --- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -4524,6 +4524,7 @@ // Process extracts in blocks of EltsPerVector to check if the source vector // operand can be re-used directly. If not, add the cost of creating a shuffle // to extract the values into a vector register. + SmallVector RegMask(EltsPerVector, UndefMaskElem); for (auto *V : VL) { ++Idx; @@ -4533,6 +4534,7 @@ // Reached the start of a new vector registers. if (Idx % EltsPerVector == 0) { + RegMask.assign(EltsPerVector, UndefMaskElem); AllConsecutive = true; continue; } @@ -4544,6 +4546,7 @@ unsigned PrevIdx = *getExtractIndex(cast(VL[Idx - 1])); AllConsecutive &= PrevIdx + 1 == CurrentIdx && CurrentIdx % EltsPerVector == Idx % EltsPerVector; + RegMask[Idx % EltsPerVector] = CurrentIdx % EltsPerVector; } if (AllConsecutive) @@ -4558,7 +4561,7 @@ // cost to extract the a vector with EltsPerVector elements. Cost += TTI.getShuffleCost( TargetTransformInfo::SK_PermuteSingleSrc, - FixedVectorType::get(VecTy->getElementType(), EltsPerVector)); + FixedVectorType::get(VecTy->getElementType(), EltsPerVector), RegMask); } return Cost; } @@ -5314,16 +5317,21 @@ TTI::CastContextHint::None, CostKind); } - SmallVector Mask; - buildSuffleEntryMask( - E->Scalars, E->ReorderIndices, E->ReuseShuffleIndices, - [E](Instruction *I) { - assert(E->isOpcodeOrAlt(I) && "Unexpected main/alternate opcode"); - return I->getOpcode() == E->getAltOpcode(); - }, - Mask); - CommonCost = - TTI->getShuffleCost(TargetTransformInfo::SK_Select, FinalVecTy, Mask); + if (E->ReuseShuffleIndices.empty()) { + CommonCost = + TTI->getShuffleCost(TargetTransformInfo::SK_Select, FinalVecTy); + } else { + SmallVector Mask; + buildSuffleEntryMask( + E->Scalars, E->ReorderIndices, E->ReuseShuffleIndices, + [E](Instruction *I) { + assert(E->isOpcodeOrAlt(I) && "Unexpected main/alternate opcode"); + return I->getOpcode() == E->getAltOpcode(); + }, + Mask); + CommonCost = TTI->getShuffleCost(TargetTransformInfo::SK_PermuteTwoSrc, + FinalVecTy, Mask); + } LLVM_DEBUG(dumpTreeCosts(E, CommonCost, VecCost, ScalarCost)); return CommonCost + VecCost - ScalarCost; } @@ -5713,7 +5721,8 @@ Cost += SpillCost + ExtractCost; if (FirstUsers.size() == 1) { int Limit = ShuffleMask.front().size() * 2; - if (all_of(ShuffleMask.front(), [Limit](int Idx) { return Idx < Limit; }) && + if (!all_of(ShuffleMask.front(), + [Limit](int Idx) { return Idx < Limit; }) || !ShuffleVectorInst::isIdentityMask(ShuffleMask.front())) { InstructionCost C = TTI->getShuffleCost( TTI::SK_PermuteSingleSrc, @@ -5762,6 +5771,8 @@ << "SLP: Current total cost = " << Cost << "\n"); Cost -= InsertCost; for (int I = 2, E = FirstUsers.size(); I < E; ++I) { + if (ShuffleMask[I].empty()) + continue; // Other elements - permutation of 2 vectors (the initial one and the // next Ith incoming vector). unsigned VF = ShuffleMask[I].size(); diff --git a/llvm/test/Analysis/CostModel/X86/reduction.ll b/llvm/test/Analysis/CostModel/X86/reduction.ll --- a/llvm/test/Analysis/CostModel/X86/reduction.ll +++ b/llvm/test/Analysis/CostModel/X86/reduction.ll @@ -61,11 +61,11 @@ define fastcc i32 @reduction_cost_int(<8 x i32> %rdx) { ; SSE-LABEL: 'reduction_cost_int' -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2 -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3 ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r @@ -91,11 +91,11 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; ; SLM-LABEL: 'reduction_cost_int' -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx, %rdx.shuf -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.2 = add <8 x i32> %bin.rdx, %rdx.shuf.2 -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.3 = shufflevector <8 x i32> %bin.rdx.2, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx.3 = add <8 x i32> %bin.rdx.2, %rdx.shuf.3 ; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx.3, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r @@ -416,25 +416,25 @@ define fastcc double @no_pairwise_reduction4double(<4 x double> %rdx, double %f1) { ; SSE2-LABEL: 'no_pairwise_reduction4double' -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSSE3-LABEL: 'no_pairwise_reduction4double' -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSE42-LABEL: 'no_pairwise_reduction4double' -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r @@ -456,9 +456,9 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SLM-LABEL: 'no_pairwise_reduction4double' -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx, %rdx.shuf -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %bin.rdx, %rdx.shuf7 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r @@ -474,31 +474,31 @@ define fastcc float @no_pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; SSE2-LABEL: 'no_pairwise_reduction8float' -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3 -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSSE3-LABEL: 'no_pairwise_reduction8float' -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSE42-LABEL: 'no_pairwise_reduction8float' -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3 -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r @@ -524,11 +524,11 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SLM-LABEL: 'no_pairwise_reduction8float' -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf3 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = fadd <8 x float> %rdx, %rdx.shuf3 -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x float> %bin.rdx4, <8 x float> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %bin.rdx4, %rdx.shuf -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %bin.rdx, %rdx.shuf7 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx8, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r @@ -592,9 +592,9 @@ define fastcc i64 @no_pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) { ; SSE-LABEL: 'no_pairwise_reduction4i64' -; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf -; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7 ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r @@ -616,9 +616,9 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; ; SLM-LABEL: 'no_pairwise_reduction4i64' -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx = add <4 x i64> %rdx, %rdx.shuf -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx8 = add <4 x i64> %bin.rdx, %rdx.shuf7 ; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r @@ -696,11 +696,11 @@ define fastcc i32 @no_pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) { ; SSE-LABEL: 'no_pairwise_reduction8i32' -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7 ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r @@ -726,11 +726,11 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; ; SLM-LABEL: 'no_pairwise_reduction8i32' -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf3 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx4 = add <8 x i32> %rdx, %rdx.shuf3 -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf = shufflevector <8 x i32> %bin.rdx4, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %bin.rdx4, %rdx.shuf -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf7 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %bin.rdx, %rdx.shuf7 ; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx8, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r @@ -854,31 +854,31 @@ define fastcc double @pairwise_reduction4double(<4 x double> %rdx, double %f1) { ; SSE2-LABEL: 'pairwise_reduction4double' -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSSE3-LABEL: 'pairwise_reduction4double' -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SSE42-LABEL: 'pairwise_reduction4double' -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r @@ -904,11 +904,11 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r ; ; SLM-LABEL: 'pairwise_reduction4double' -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x double> %rdx, <4 x double> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <4 x double> %rdx.shuf.0.0, %rdx.shuf.0.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x double> %bin.rdx, <4 x double> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <4 x double> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <4 x double> %bin.rdx8, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret double %r @@ -926,40 +926,40 @@ define fastcc float @pairwise_reduction8float(<8 x float> %rdx, float %f1) { ; SSE2-LABEL: 'pairwise_reduction8float' -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSSE3-LABEL: 'pairwise_reduction8float' -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SSE42-LABEL: 'pairwise_reduction8float' -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r @@ -991,14 +991,14 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r ; ; SLM-LABEL: 'pairwise_reduction8float' -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <8 x float> %rdx, <8 x float> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = fadd <8 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x float> %bin.rdx, <8 x float> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = fadd <8 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x float> %bin.rdx8, <8 x float> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = fadd <8 x float> %rdx.shuf.2.0, %rdx.shuf.2.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %r = extractelement <8 x float> %bin.rdx9, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret float %r @@ -1074,11 +1074,11 @@ define fastcc i64 @pairwise_reduction4i64(<4 x i64> %rdx, i64 %f1) { ; SSE-LABEL: 'pairwise_reduction4i64' -; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1 ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r @@ -1104,11 +1104,11 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r ; ; SLM-LABEL: 'pairwise_reduction4i64' -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.0 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.0.1 = shufflevector <4 x i64> %rdx, <4 x i64> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx = add <4 x i64> %rdx.shuf.0.0, %rdx.shuf.0.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.1.0 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <4 x i64> %bin.rdx, <4 x i64> undef, <4 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %bin.rdx8 = add <4 x i64> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <4 x i64> %bin.rdx8, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i64 %r @@ -1206,14 +1206,14 @@ define fastcc i32 @pairwise_reduction8i32(<8 x i32> %rdx, i32 %f1) { ; SSE-LABEL: 'pairwise_reduction8i32' -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1 -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1 ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r @@ -1245,14 +1245,14 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r ; ; SLM-LABEL: 'pairwise_reduction8i32' -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.0 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %rdx.shuf.0.1 = shufflevector <8 x i32> %rdx, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx = add <8 x i32> %rdx.shuf.0.0, %rdx.shuf.0.1 -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.0 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.1.1 = shufflevector <8 x i32> %bin.rdx, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx8 = add <8 x i32> %rdx.shuf.1.0, %rdx.shuf.1.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %rdx.shuf.2.0 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> -; SLM-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> +; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %rdx.shuf.2.1 = shufflevector <8 x i32> %bin.rdx8, <8 x i32> undef, <8 x i32> ; SLM-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %bin.rdx9 = add <8 x i32> %rdx.shuf.2.0, %rdx.shuf.2.1 ; SLM-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %r = extractelement <8 x i32> %bin.rdx9, i32 0 ; SLM-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %r diff --git a/llvm/test/Analysis/CostModel/X86/shuffle-single-src.ll b/llvm/test/Analysis/CostModel/X86/shuffle-single-src.ll --- a/llvm/test/Analysis/CostModel/X86/shuffle-single-src.ll +++ b/llvm/test/Analysis/CostModel/X86/shuffle-single-src.ll @@ -21,29 +21,29 @@ ; SSE-LABEL: 'test_vXf64' ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %src128, <2 x double> undef, <2 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x double> %src256, <4 x double> undef, <4 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 56 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; XOP-LABEL: 'test_vXf64' ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %src128, <2 x double> undef, <2 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x double> %src256, <4 x double> undef, <4 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX1-LABEL: 'test_vXf64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %src128, <2 x double> undef, <2 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x double> %src256, <4 x double> undef, <4 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX2-LABEL: 'test_vXf64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x double> %src128, <2 x double> undef, <2 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <4 x double> %src256, <4 x double> undef, <4 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <8 x double> %src512, <8 x double> undef, <8 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V1024 = shufflevector <16 x double> %src1024, <16 x double> undef, <16 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX512-LABEL: 'test_vXf64' @@ -64,25 +64,25 @@ ; SSE-LABEL: 'test_vXi64' ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %src128, <2 x i64> undef, <2 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x i64> %src256, <4 x i64> undef, <4 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; XOP-LABEL: 'test_vXi64' ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %src128, <2 x i64> undef, <2 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x i64> %src256, <4 x i64> undef, <4 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX1-LABEL: 'test_vXi64' ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %src128, <2 x i64> undef, <2 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <4 x i64> %src256, <4 x i64> undef, <4 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX2-LABEL: 'test_vXi64' ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <2 x i64> %src128, <2 x i64> undef, <2 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <4 x i64> %src256, <4 x i64> undef, <4 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <8 x i64> %src512, <8 x i64> undef, <8 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX512-LABEL: 'test_vXi64' @@ -101,29 +101,29 @@ ; SSE-LABEL: 'test_vXf32' ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x float> %src64, <2 x float> undef, <2 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %src128, <4 x float> undef, <4 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x float> %src256, <8 x float> undef, <8 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x float> %src256, <8 x float> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; XOP-LABEL: 'test_vXf32' ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x float> %src64, <2 x float> undef, <2 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %src128, <4 x float> undef, <4 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x float> %src256, <8 x float> undef, <8 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX1-LABEL: 'test_vXf32' ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x float> %src64, <2 x float> undef, <2 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %src128, <4 x float> undef, <4 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x float> %src256, <8 x float> undef, <8 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX2-LABEL: 'test_vXf32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x float> %src64, <2 x float> undef, <2 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x float> %src128, <4 x float> undef, <4 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <8 x float> %src256, <8 x float> undef, <8 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V512 = shufflevector <16 x float> %src512, <16 x float> undef, <16 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX512-LABEL: 'test_vXf32' @@ -144,17 +144,17 @@ ; SSE-LABEL: 'test_vXi32' ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x i32> %src64, <2 x i32> undef, <2 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x i32> %src128, <4 x i32> undef, <4 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x i32> %src256, <8 x i32> undef, <8 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <16 x i32> %src512, <16 x i32> undef, <16 x i32> -; SSE-NEXT: Cost Model: Found an estimated cost of 112 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x i32> %src256, <8 x i32> undef, <8 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <16 x i32> %src512, <16 x i32> undef, <16 x i32> +; SSE-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> ; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; XOP-LABEL: 'test_vXi32' ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x i32> %src64, <2 x i32> undef, <2 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x i32> %src128, <4 x i32> undef, <4 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <8 x i32> %src256, <8 x i32> undef, <8 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <16 x i32> %src512, <16 x i32> undef, <16 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <16 x i32> %src512, <16 x i32> undef, <16 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX1-LABEL: 'test_vXi32' @@ -162,15 +162,15 @@ ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x i32> %src128, <4 x i32> undef, <4 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <8 x i32> %src256, <8 x i32> undef, <8 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <16 x i32> %src512, <16 x i32> undef, <16 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 48 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX2-LABEL: 'test_vXi32' ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <2 x i32> %src64, <2 x i32> undef, <2 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <4 x i32> %src128, <4 x i32> undef, <4 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V256 = shufflevector <8 x i32> %src256, <8 x i32> undef, <8 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <16 x i32> %src512, <16 x i32> undef, <16 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <16 x i32> %src512, <16 x i32> undef, <16 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V1024 = shufflevector <32 x i32> %src1024, <32 x i32> undef, <32 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX512-LABEL: 'test_vXi32' @@ -194,27 +194,27 @@ ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 96 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 448 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; SSSE3-LABEL: 'test_vXi16' ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; SSE42-LABEL: 'test_vXi16' ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <2 x i16> %src32, <2 x i16> undef, <2 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 168 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; XOP-LABEL: 'test_vXi16' @@ -222,8 +222,8 @@ ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 108 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX1-LABEL: 'test_vXi16' @@ -231,8 +231,8 @@ ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 180 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX2-LABEL: 'test_vXi16' @@ -240,8 +240,8 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <4 x i16> %src64, <4 x i16> undef, <4 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX512F-LABEL: 'test_vXi16' @@ -250,7 +250,7 @@ ; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <8 x i16> %src128, <8 x i16> undef, <8 x i32> ; AVX512F-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <16 x i16> %src256, <16 x i16> undef, <16 x i32> ; AVX512F-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V512 = shufflevector <32 x i16> %src512, <32 x i16> undef, <32 x i32> -; AVX512F-NEXT: Cost Model: Found an estimated cost of 84 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> +; AVX512F-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %V1024 = shufflevector <64 x i16> %src1024, <64 x i16> undef, <64 x i32> ; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX512BW-LABEL: 'test_vXi16' @@ -286,8 +286,8 @@ ; SSE2-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> undef, <4 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> -; SSE2-NEXT: Cost Model: Found an estimated cost of 156 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 19 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> +; SSE2-NEXT: Cost Model: Found an estimated cost of 37 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> ; SSE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; SSSE3-LABEL: 'test_vXi8' @@ -295,8 +295,8 @@ ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> undef, <4 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> -; SSSE3-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> +; SSSE3-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> ; SSSE3-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; SSE42-LABEL: 'test_vXi8' @@ -304,8 +304,8 @@ ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V32 = shufflevector <4 x i8> %src32, <4 x i8> undef, <4 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> -; SSE42-NEXT: Cost Model: Found an estimated cost of 36 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> +; SSE42-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> ; SSE42-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; XOP-LABEL: 'test_vXi8' @@ -314,7 +314,7 @@ ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> -; XOP-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> +; XOP-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> ; XOP-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX1-LABEL: 'test_vXi8' @@ -323,7 +323,7 @@ ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> -; AVX1-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> +; AVX1-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> ; AVX1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX2-LABEL: 'test_vXi8' @@ -332,7 +332,7 @@ ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V64 = shufflevector <8 x i8> %src64, <8 x i8> undef, <8 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V128 = shufflevector <16 x i8> %src128, <16 x i8> undef, <16 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V256 = shufflevector <32 x i8> %src256, <32 x i8> undef, <32 x i32> -; AVX2-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> +; AVX2-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V512 = shufflevector <64 x i8> %src512, <64 x i8> undef, <64 x i32> ; AVX2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; ; AVX512F-LABEL: 'test_vXi8' diff --git a/llvm/test/CodeGen/X86/haddsub-4.ll b/llvm/test/CodeGen/X86/haddsub-4.ll --- a/llvm/test/CodeGen/X86/haddsub-4.ll +++ b/llvm/test/CodeGen/X86/haddsub-4.ll @@ -330,19 +330,19 @@ define <16 x float> @hadd_reverse_v16f32(<16 x float> %a0, <16 x float> %a1) nounwind { ; SSE-LABEL: hadd_reverse_v16f32: ; SSE: # %bb.0: -; SSE-NEXT: movaps %xmm5, %xmm8 -; SSE-NEXT: movaps %xmm1, %xmm5 -; SSE-NEXT: haddps %xmm2, %xmm3 -; SSE-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,0,3,2] -; SSE-NEXT: haddps %xmm6, %xmm7 -; SSE-NEXT: shufps {{.*#+}} xmm7 = xmm7[1,0,3,2] -; SSE-NEXT: haddps %xmm0, %xmm5 -; SSE-NEXT: shufps {{.*#+}} xmm5 = xmm5[1,0,3,2] -; SSE-NEXT: haddps %xmm4, %xmm8 -; SSE-NEXT: shufps {{.*#+}} xmm8 = xmm8[1,0,3,2] -; SSE-NEXT: movaps %xmm3, %xmm0 -; SSE-NEXT: movaps %xmm7, %xmm1 -; SSE-NEXT: movaps %xmm5, %xmm2 +; SSE-NEXT: movaps %xmm4, %xmm8 +; SSE-NEXT: movaps %xmm0, %xmm4 +; SSE-NEXT: haddps %xmm3, %xmm2 +; SSE-NEXT: shufps {{.*#+}} xmm2 = xmm2[3,2,1,0] +; SSE-NEXT: haddps %xmm7, %xmm6 +; SSE-NEXT: shufps {{.*#+}} xmm6 = xmm6[3,2,1,0] +; SSE-NEXT: haddps %xmm1, %xmm4 +; SSE-NEXT: shufps {{.*#+}} xmm4 = xmm4[3,2,1,0] +; SSE-NEXT: haddps %xmm5, %xmm8 +; SSE-NEXT: shufps {{.*#+}} xmm8 = xmm8[3,2,1,0] +; SSE-NEXT: movaps %xmm2, %xmm0 +; SSE-NEXT: movaps %xmm6, %xmm1 +; SSE-NEXT: movaps %xmm4, %xmm2 ; SSE-NEXT: movaps %xmm8, %xmm3 ; SSE-NEXT: retq ; diff --git a/llvm/test/CodeGen/X86/pr51615.ll b/llvm/test/CodeGen/X86/pr51615.ll --- a/llvm/test/CodeGen/X86/pr51615.ll +++ b/llvm/test/CodeGen/X86/pr51615.ll @@ -11,15 +11,14 @@ ; AVX-LABEL: volatile_load_2_elts: ; AVX: # %bb.0: ; AVX-NEXT: vmovaps g0(%rip), %xmm0 -; AVX-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0] -; AVX-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm1 -; AVX-NEXT: vpermilpd {{.*#+}} ymm1 = ymm1[0,0,3,2] -; AVX-NEXT: vxorpd %xmm2, %xmm2, %xmm2 -; AVX-NEXT: vblendpd {{.*#+}} ymm1 = ymm2[0,1],ymm1[2],ymm2[3] -; AVX-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0 -; AVX-NEXT: vblendpd {{.*#+}} ymm0 = ymm2[0],ymm0[1],ymm2[2],ymm0[3] -; AVX-NEXT: vmovapd %ymm0, (%rax) -; AVX-NEXT: vmovapd %ymm1, (%rax) +; AVX-NEXT: vmovddup {{.*#+}} xmm1 = xmm0[0,0] +; AVX-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1 +; AVX-NEXT: vxorps %xmm2, %xmm2, %xmm2 +; AVX-NEXT: vblendps {{.*#+}} ymm1 = ymm2[0,1],ymm1[2,3],ymm2[4,5],ymm1[6,7] +; AVX-NEXT: vperm2f128 {{.*#+}} ymm0 = zero,zero,ymm0[0,1] +; AVX-NEXT: vblendps {{.*#+}} ymm0 = ymm2[0,1,2,3],ymm0[4,5],ymm2[6,7] +; AVX-NEXT: vmovaps %ymm0, (%rax) +; AVX-NEXT: vmovaps %ymm1, (%rax) ; AVX-NEXT: vzeroupper ; AVX-NEXT: retq ; diff --git a/llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-3.ll b/llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-3.ll --- a/llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-3.ll +++ b/llvm/test/CodeGen/X86/vector-interleaved-store-i16-stride-3.ll @@ -74,12 +74,12 @@ ; SSE-NEXT: pandn %xmm2, %xmm3 ; SSE-NEXT: por %xmm4, %xmm3 ; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,1,1] -; SSE-NEXT: movdqa {{.*#+}} xmm2 = [65535,0,0,65535,65535,65535,65535,65535] -; SSE-NEXT: pand %xmm2, %xmm1 +; SSE-NEXT: movdqa {{.*#+}} xmm2 = [0,65535,65535,0,65535,65535,65535,65535] ; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,2,3] ; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[0,3,1,3,4,5,6,7] -; SSE-NEXT: pandn %xmm0, %xmm2 -; SSE-NEXT: por %xmm1, %xmm2 +; SSE-NEXT: pand %xmm2, %xmm0 +; SSE-NEXT: pandn %xmm1, %xmm2 +; SSE-NEXT: por %xmm0, %xmm2 ; SSE-NEXT: movq %xmm2, 16(%rcx) ; SSE-NEXT: movdqa %xmm3, (%rcx) ; SSE-NEXT: retq diff --git a/llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-6.ll b/llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-6.ll --- a/llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-6.ll +++ b/llvm/test/CodeGen/X86/vector-interleaved-store-i32-stride-6.ll @@ -298,8 +298,8 @@ ; AVX512-NEXT: vinserti128 $1, (%rsi), %ymm0, %ymm0 ; AVX512-NEXT: vinserti64x4 $1, %ymm1, %zmm0, %zmm0 ; AVX512-NEXT: vinserti32x4 $1, (%r9), %zmm2, %zmm1 -; AVX512-NEXT: vmovdqa {{.*#+}} ymm2 = [2,6,19,23,27,31,3,7] -; AVX512-NEXT: vpermi2d %zmm0, %zmm1, %zmm2 +; AVX512-NEXT: vmovdqa {{.*#+}} ymm2 = [18,22,3,7,11,15,19,23] +; AVX512-NEXT: vpermi2d %zmm1, %zmm0, %zmm2 ; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm3 = [0,4,8,12,16,20,1,5,9,13,17,21,2,6,10,14] ; AVX512-NEXT: vpermi2d %zmm1, %zmm0, %zmm3 ; AVX512-NEXT: vmovdqu64 %zmm3, (%rax) diff --git a/llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-3.ll b/llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-3.ll --- a/llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-3.ll +++ b/llvm/test/CodeGen/X86/vector-interleaved-store-i64-stride-3.ll @@ -154,8 +154,8 @@ ; AVX512-NEXT: vmovdqa (%rdi), %ymm0 ; AVX512-NEXT: vmovdqa (%rdx), %ymm1 ; AVX512-NEXT: vinserti64x4 $1, (%rsi), %zmm0, %zmm0 -; AVX512-NEXT: vmovdqa {{.*#+}} ymm2 = [2,11,15,3] -; AVX512-NEXT: vpermi2q %zmm0, %zmm1, %zmm2 +; AVX512-NEXT: vmovdqa {{.*#+}} ymm2 = [10,3,7,11] +; AVX512-NEXT: vpermi2q %zmm1, %zmm0, %zmm2 ; AVX512-NEXT: vmovdqa64 {{.*#+}} zmm3 = [0,4,8,1,5,9,2,6] ; AVX512-NEXT: vpermi2q %zmm1, %zmm0, %zmm3 ; AVX512-NEXT: vmovdqu64 %zmm3, (%rcx) diff --git a/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-6.ll b/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-6.ll --- a/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-6.ll +++ b/llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-6.ll @@ -174,14 +174,14 @@ ; SSE-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,1,3,1,4,5,6,7] ; SSE-NEXT: punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0] ; SSE-NEXT: packuswb %xmm1, %xmm1 -; SSE-NEXT: movdqa {{.*#+}} xmm2 = [65535,0,0,65535,65535,65535,65535,65535] +; SSE-NEXT: movdqa {{.*#+}} xmm2 = [0,65535,65535,0,65535,65535,65535,65535] +; SSE-NEXT: pand %xmm2, %xmm1 ; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[3,1,1,3] ; SSE-NEXT: pshuflw {{.*#+}} xmm0 = xmm0[2,0,2,3,4,5,6,7] ; SSE-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,5,7] ; SSE-NEXT: packuswb %xmm0, %xmm0 -; SSE-NEXT: pand %xmm2, %xmm0 -; SSE-NEXT: pandn %xmm1, %xmm2 -; SSE-NEXT: por %xmm0, %xmm2 +; SSE-NEXT: pandn %xmm0, %xmm2 +; SSE-NEXT: por %xmm1, %xmm2 ; SSE-NEXT: movq %xmm2, 16(%rax) ; SSE-NEXT: movdqa %xmm3, (%rax) ; SSE-NEXT: retq diff --git a/llvm/test/Transforms/SLPVectorizer/X86/PR39774.ll b/llvm/test/Transforms/SLPVectorizer/X86/PR39774.ll --- a/llvm/test/Transforms/SLPVectorizer/X86/PR39774.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/PR39774.ll @@ -1,5 +1,5 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py -; RUN: opt -slp-vectorizer -S < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=skylake -slp-threshold=-6 | FileCheck %s --check-prefix=CHECK +; RUN: opt -slp-vectorizer -S < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=skylake -slp-threshold=-4 | FileCheck %s --check-prefix=CHECK ; RUN: opt -slp-vectorizer -S < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=skylake -slp-threshold=-7 -slp-min-tree-size=6 | FileCheck %s --check-prefix=FORCE_REDUCTION define void @Test(i32) {