diff options
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize/X86/veclib-calls.ll')
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/X86/veclib-calls.ll | 26 |
1 files changed, 25 insertions, 1 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/X86/veclib-calls.ll b/llvm/test/Transforms/LoopVectorize/X86/veclib-calls.ll index e7e36850f4e..6f8f5223ce4 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/veclib-calls.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/veclib-calls.ll @@ -3,6 +3,31 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" target triple = "x86_64-unknown-linux-gnu" +;CHECK-LABEL: @sqrt_f32( +;CHECK: vsqrtf{{.*}}<4 x float> +;CHECK: ret void +declare float @sqrtf(float) nounwind readnone +define void @sqrt_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, float* %y, i64 %indvars.iv + %0 = load float, float* %arrayidx, align 4 + %call = tail call float @sqrtf(float %0) nounwind readnone + %arrayidx2 = getelementptr inbounds float, 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 +} + ;CHECK-LABEL: @exp_f32( ;CHECK: vexpf{{.*}}<4 x float> ;CHECK: ret void @@ -135,7 +160,6 @@ for.end: ; preds = %for.body, %entry ;CHECK-LABEL: @sqrt_f32_nobuiltin( ;CHECK-NOT: vsqrtf{{.*}}<4 x float> ;CHECK: ret void -declare float @sqrtf(float) nounwind readnone define void @sqrt_f32_nobuiltin(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable { entry: %cmp6 = icmp sgt i32 %n, 0 |
