Add the nearbyint -> FNEARBYINT mapping to BasicTargetTransformInfo

This fixes an oversight that Intrinsic::nearbyint was not being mapped to
ISD::FNEARBYINT (thus fixing the over-optimistic cost we were assigning to
nearbyint calls for some targets).

llvm-svn: 185783
This commit is contained in:
Hal Finkel 2013-07-08 03:24:07 +00:00
parent 8c96263ee3
commit ec474f28e3
2 changed files with 30 additions and 0 deletions

View File

@ -443,6 +443,8 @@ unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
case Intrinsic::floor: ISD = ISD::FFLOOR; break;
case Intrinsic::ceil: ISD = ISD::FCEIL; break;
case Intrinsic::trunc: ISD = ISD::FTRUNC; break;
case Intrinsic::nearbyint:
ISD = ISD::FNEARBYINT; break;
case Intrinsic::rint: ISD = ISD::FRINT; break;
case Intrinsic::pow: ISD = ISD::FPOW; break;
case Intrinsic::fma: ISD = ISD::FMA; break;

View File

@ -30,3 +30,31 @@ for.end: ; preds = %vector.body
}
declare <4 x float> @llvm.ceil.v4f32(<4 x float>) nounwind readnone
define void @test2(float* nocapture %f) nounwind {
vector.ph:
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%0 = getelementptr inbounds float* %f, i64 %index
%1 = bitcast float* %0 to <4 x float>*
%wide.load = load <4 x float>* %1, align 4
%2 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> %wide.load)
store <4 x float> %2, <4 x float>* %1, align 4
%index.next = add i64 %index, 4
%3 = icmp eq i64 %index.next, 1024
br i1 %3, label %for.end, label %vector.body
for.end: ; preds = %vector.body
ret void
; CORE2: Printing analysis 'Cost Model Analysis' for function 'test2':
; CORE2: Cost Model: Found an estimated cost of 400 for instruction: %2 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> %wide.load)
; COREI7: Printing analysis 'Cost Model Analysis' for function 'test2':
; COREI7: Cost Model: Found an estimated cost of 1 for instruction: %2 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> %wide.load)
}
declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>) nounwind readnone