maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[LoopVectorizer] Enable support for floating-point subtraction reductions 

llvm-svn: 215200
This commit is contained in:
James Molloy 2014-08-08 12:41:08 +00:00
parent 3feea9c11a
commit 65b08f5e46
2 changed files with 24 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -5136,7 +5136,7 @@ LoopVectorizationLegality::isReductionInstr(Instruction *I,
ReductionKind Kind, ReductionKind Kind,
ReductionInstDesc &Prev) { ReductionInstDesc &Prev) {
bool FP = I->getType()->isFloatingPointTy(); bool FP = I->getType()->isFloatingPointTy();
bool FastMath = (FP && I->isCommutative() && I->isAssociative()); bool FastMath = FP && I->hasUnsafeAlgebra();
switch (I->getOpcode()) { switch (I->getOpcode()) {
default: default:
return ReductionInstDesc(false, I); return ReductionInstDesc(false, I);
@ -5158,6 +5158,7 @@ LoopVectorizationLegality::isReductionInstr(Instruction *I,
return ReductionInstDesc(Kind == RK_IntegerXor, I); return ReductionInstDesc(Kind == RK_IntegerXor, I);
case Instruction::FMul: case Instruction::FMul:
return ReductionInstDesc(Kind == RK_FloatMult && FastMath, I); return ReductionInstDesc(Kind == RK_FloatMult && FastMath, I);
case Instruction::FSub:
case Instruction::FAdd: case Instruction::FAdd:
return ReductionInstDesc(Kind == RK_FloatAdd && FastMath, I); return ReductionInstDesc(Kind == RK_FloatAdd && FastMath, I);
case Instruction::FCmp: case Instruction::FCmp:

22
llvm/test/Transforms/LoopVectorize/float-reduction.ll
View File

@ -23,3 +23,25 @@ for.body: ; preds = %for.body, %entry
for.end: ; preds = %for.body for.end: ; preds = %for.body
ret float %add ret float %add
} }
;CHECK-LABEL: @foosub(
;CHECK: fsub fast <4 x float>
;CHECK: ret
define float @foosub(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%sum.04 = phi float [ 0.000000e+00, %entry ], [ %sub, %for.body ]
%arrayidx = getelementptr inbounds float* %A, i64 %indvars.iv
%0 = load float* %arrayidx, align 4
%sub = fsub fast float %sum.04, %0
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 200
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret float %sub
}