nicolas/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[LV] Update type in cost model for scalarization

Browse Source 
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
This commit is contained in:
Matthew Simpson
2017-05-24 15:26:15 +00:00
parent 5f16986271
commit d6f179cad6
2 changed files with 41 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@@ -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<const Value *, 4> Operands(I->operand_values());
return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
Op2VK, Op1VP, Op2VP, Operands);
SmallVector<const Value *, 4> 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<SelectInst>(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: