diff options
author | Hal Finkel <hfinkel@anl.gov> | 2013-08-07 22:49:12 +0000 |
---|---|---|
committer | Hal Finkel <hfinkel@anl.gov> | 2013-08-07 22:49:12 +0000 |
commit | 41418d17cced656f91038b2482bc9d173b4974b0 (patch) | |
tree | ad9f68077baafc782e15513f310a8377e55c817a /test/Transforms | |
parent | 6fa33f5dd945015d79be42c5cff146e4e2b7c4f3 (diff) | |
download | llvm-41418d17cced656f91038b2482bc9d173b4974b0.tar.gz llvm-41418d17cced656f91038b2482bc9d173b4974b0.tar.bz2 llvm-41418d17cced656f91038b2482bc9d173b4974b0.tar.xz |
Add ISD::FROUND for libm round()
All libm floating-point rounding functions, except for round(), had their own
ISD nodes. Recent PowerPC cores have an instruction for round(), and so here I'm
adding ISD::FROUND so that round() can be custom lowered as well.
For the most part, this is straightforward. I've added an intrinsic
and a matching ISD node just like those for nearbyint() and friends. The
SelectionDAG pattern I've named frnd (because ISD::FP_ROUND has already claimed
fround).
This will be used by the PowerPC backend in a follow-up commit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187926 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms')
-rw-r--r-- | test/Transforms/LoopVectorize/intrinsic.ll | 52 |
1 files changed, 52 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/intrinsic.ll b/test/Transforms/LoopVectorize/intrinsic.ll index 95b53b70ea..566dcc75cd 100644 --- a/test/Transforms/LoopVectorize/intrinsic.ll +++ b/test/Transforms/LoopVectorize/intrinsic.ll @@ -728,6 +728,58 @@ for.end: ; preds = %for.body, %entry declare double @llvm.nearbyint.f64(double) nounwind readnone +;CHECK-LABEL: @round_f32( +;CHECK: llvm.round.v4f32 +;CHECK: ret void +define void @round_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable { +entry: + %cmp6 = icmp sgt i32 %n, 0 + br i1 %cmp6, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds float* %y, i64 %indvars.iv + %0 = load float* %arrayidx, align 4 + %call = tail call float @llvm.round.f32(float %0) nounwind readnone + %arrayidx2 = getelementptr inbounds float* %x, i64 %indvars.iv + store float %call, float* %arrayidx2, align 4 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +declare float @llvm.round.f32(float) nounwind readnone + +;CHECK-LABEL: @round_f64( +;CHECK: llvm.round.v4f64 +;CHECK: ret void +define void @round_f64(i32 %n, double* noalias %y, double* noalias %x) nounwind uwtable { +entry: + %cmp6 = icmp sgt i32 %n, 0 + br i1 %cmp6, label %for.body, label %for.end + +for.body: ; preds = %entry, %for.body + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds double* %y, i64 %indvars.iv + %0 = load double* %arrayidx, align 8 + %call = tail call double @llvm.round.f64(double %0) nounwind readnone + %arrayidx2 = getelementptr inbounds double* %x, i64 %indvars.iv + store double %call, double* %arrayidx2, align 8 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + ret void +} + +declare double @llvm.round.f64(double) nounwind readnone + ;CHECK-LABEL: @fma_f32( ;CHECK: llvm.fma.v4f32 ;CHECK: ret void |