forked from OSchip/llvm-project
Revert r303763, results in asserts i.e. while building Ruby.
llvm-svn: 304179
This commit is contained in:
parent
638b1021bf
commit
9375a25342
|
@ -7173,7 +7173,7 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
|
||||||
// Note: Even if all instructions are scalarized, return true if any memory
|
// Note: Even if all instructions are scalarized, return true if any memory
|
||||||
// accesses appear in the loop to get benefits from address folding etc.
|
// accesses appear in the loop to get benefits from address folding etc.
|
||||||
bool TypeNotScalarized =
|
bool TypeNotScalarized =
|
||||||
VF > 1 && VectorTy->isVectorTy() && TTI.getNumberOfParts(VectorTy) < VF;
|
VF > 1 && !VectorTy->isVoidTy() && TTI.getNumberOfParts(VectorTy) < VF;
|
||||||
return VectorizationCostTy(C, TypeNotScalarized);
|
return VectorizationCostTy(C, TypeNotScalarized);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -7312,7 +7312,7 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
|
||||||
Type *RetTy = I->getType();
|
Type *RetTy = I->getType();
|
||||||
if (canTruncateToMinimalBitwidth(I, VF))
|
if (canTruncateToMinimalBitwidth(I, VF))
|
||||||
RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
|
RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
|
||||||
VectorTy = isScalarAfterVectorization(I, VF) ? RetTy : ToVectorTy(RetTy, VF);
|
VectorTy = ToVectorTy(RetTy, VF);
|
||||||
auto SE = PSE.getSE();
|
auto SE = PSE.getSE();
|
||||||
|
|
||||||
// TODO: We need to estimate the cost of intrinsic calls.
|
// TODO: We need to estimate the cost of intrinsic calls.
|
||||||
|
@ -7446,9 +7446,8 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
|
||||||
Op2VK = TargetTransformInfo::OK_UniformValue;
|
Op2VK = TargetTransformInfo::OK_UniformValue;
|
||||||
}
|
}
|
||||||
SmallVector<const Value *, 4> Operands(I->operand_values());
|
SmallVector<const Value *, 4> Operands(I->operand_values());
|
||||||
unsigned N = isScalarAfterVectorization(I, VF) ? VF : 1;
|
return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
|
||||||
return N * TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK,
|
Op2VK, Op1VP, Op2VP, Operands);
|
||||||
Op2VK, Op1VP, Op2VP, Operands);
|
|
||||||
}
|
}
|
||||||
case Instruction::Select: {
|
case Instruction::Select: {
|
||||||
SelectInst *SI = cast<SelectInst>(I);
|
SelectInst *SI = cast<SelectInst>(I);
|
||||||
|
@ -7471,15 +7470,7 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
|
||||||
}
|
}
|
||||||
case Instruction::Store:
|
case Instruction::Store:
|
||||||
case Instruction::Load: {
|
case Instruction::Load: {
|
||||||
unsigned Width = VF;
|
VectorTy = ToVectorTy(getMemInstValueType(I), 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);
|
return getMemoryInstructionCost(I, VF);
|
||||||
}
|
}
|
||||||
case Instruction::ZExt:
|
case Instruction::ZExt:
|
||||||
|
|
|
@ -1,26 +0,0 @@
|
||||||
; REQUIRES: asserts
|
|
||||||
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -S -debug-only=loop-vectorize 2>&1 | FileCheck %s
|
|
||||||
|
|
||||||
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
||||||
target triple = "aarch64--linux-gnu"
|
|
||||||
|
|
||||||
; CHECK-LABEL: all_scalar
|
|
||||||
; CHECK: LV: Found scalar instruction: %i.next = add nuw nsw i64 %i, 2
|
|
||||||
; CHECK: LV: Found an estimated cost of 2 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2
|
|
||||||
; CHECK: LV: Not considering vector loop of width 2 because it will not generate any vector instructions
|
|
||||||
;
|
|
||||||
define void @all_scalar(i64* %a, i64 %n) {
|
|
||||||
entry:
|
|
||||||
br label %for.body
|
|
||||||
|
|
||||||
for.body:
|
|
||||||
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
|
|
||||||
%tmp0 = getelementptr i64, i64* %a, i64 %i
|
|
||||||
store i64 0, i64* %tmp0, align 1
|
|
||||||
%i.next = add nuw nsw i64 %i, 2
|
|
||||||
%cond = icmp eq i64 %i.next, %n
|
|
||||||
br i1 %cond, label %for.end, label %for.body
|
|
||||||
|
|
||||||
for.end:
|
|
||||||
ret void
|
|
||||||
}
|
|
Loading…
Reference in New Issue