From d6f179cad6c93a517d3ab62ed61680678365cde3 Mon Sep 17 00:00:00 2001 From: Matthew Simpson Date: Wed, 24 May 2017 15:26:15 +0000 Subject: [LV] Update type in cost model for scalarization For non-uniform instructions marked for scalarization, we should update `VectorTy` when computing instruction costs to reflect the scalar type. In addition to determining instruction costs, this type is also used to signal that all instructions in the loop will be scalarized. This currently affects memory instructions and non-pointer induction variables and their updates. (We also mark GEPs scalar after vectorization, but their cost is computed together with memory instructions.) For scalarized induction updates, this patch also scales the scalar cost by the vectorization factor, corresponding to each induction step. llvm-svn: 303763 --- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'llvm/lib/Transforms') diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index 2b83b8426d1..3b036a6ac43 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -7173,7 +7173,7 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) { // Note: Even if all instructions are scalarized, return true if any memory // accesses appear in the loop to get benefits from address folding etc. bool TypeNotScalarized = - VF > 1 && !VectorTy->isVoidTy() && TTI.getNumberOfParts(VectorTy) < VF; + VF > 1 && VectorTy->isVectorTy() && TTI.getNumberOfParts(VectorTy) < VF; return VectorizationCostTy(C, TypeNotScalarized); } @@ -7312,7 +7312,7 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I, Type *RetTy = I->getType(); if (canTruncateToMinimalBitwidth(I, VF)) RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]); - VectorTy = ToVectorTy(RetTy, VF); + VectorTy = isScalarAfterVectorization(I, VF) ? RetTy : ToVectorTy(RetTy, VF); auto SE = PSE.getSE(); // TODO: We need to estimate the cost of intrinsic calls. @@ -7445,9 +7445,10 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I, } else if (Legal->isUniform(Op2)) { Op2VK = TargetTransformInfo::OK_UniformValue; } - SmallVector Operands(I->operand_values()); - return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK, - Op2VK, Op1VP, Op2VP, Operands); + SmallVector Operands(I->operand_values()); + unsigned N = isScalarAfterVectorization(I, VF) ? VF : 1; + return N * TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK, + Op2VK, Op1VP, Op2VP, Operands); } case Instruction::Select: { SelectInst *SI = cast(I); @@ -7470,7 +7471,15 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I, } case Instruction::Store: case Instruction::Load: { - VectorTy = ToVectorTy(getMemInstValueType(I), VF); + unsigned Width = VF; + if (Width > 1) { + InstWidening Decision = getWideningDecision(I, Width); + assert(Decision != CM_Unknown && + "CM decision should be taken at this point"); + if (Decision == CM_Scalarize) + Width = 1; + } + VectorTy = ToVectorTy(getMemInstValueType(I), Width); return getMemoryInstructionCost(I, VF); } case Instruction::ZExt: -- cgit v1.2.3