diff options
| author | Nadav Rotem <nrotem@apple.com> | 2013-06-19 17:33:16 +0000 |
|---|---|---|
| committer | Nadav Rotem <nrotem@apple.com> | 2013-06-19 17:33:16 +0000 |
| commit | 80a6d6526c4ea4de90327c1404e2689a260a9fee (patch) | |
| tree | 1ce8ce13b766cda1ba0f291bd7d2b8483de6bee0 /test/Transforms/SLPVectorizer | |
| parent | dd3ef1a13b57b9086de5473d2576b16acba98e82 (diff) | |
| download | external_llvm-80a6d6526c4ea4de90327c1404e2689a260a9fee.zip external_llvm-80a6d6526c4ea4de90327c1404e2689a260a9fee.tar.gz external_llvm-80a6d6526c4ea4de90327c1404e2689a260a9fee.tar.bz2 | |
SLPVectorizer: handle scalars that are extracted from vectors (using ExtractElementInst).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184325 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/SLPVectorizer')
| -rw-r--r-- | test/Transforms/SLPVectorizer/X86/extract.ll | 59 |
1 files changed, 59 insertions, 0 deletions
diff --git a/test/Transforms/SLPVectorizer/X86/extract.ll b/test/Transforms/SLPVectorizer/X86/extract.ll new file mode 100644 index 0000000..f611fd4 --- /dev/null +++ b/test/Transforms/SLPVectorizer/X86/extract.ll @@ -0,0 +1,59 @@ +; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s + +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-apple-macosx10.8.0" +;CHECK: fextr +;CHECK-NOT: insertelement +;CHECK-NOT: extractelement +;CHECK: fadd <2 x double> +;CHECK: ret void +define void @fextr(double* %ptr) { +entry: + %LD = load <2 x double>* undef + %V0 = extractelement <2 x double> %LD, i32 0 + %V1 = extractelement <2 x double> %LD, i32 1 + %P0 = getelementptr inbounds double* %ptr, i64 0 + %P1 = getelementptr inbounds double* %ptr, i64 1 + %A0 = fadd double %V0, 0.0 + %A1 = fadd double %V1, 1.1 + store double %A0, double* %P0, align 4 + store double %A1, double* %P1, align 4 + ret void +} + +;CHECK: fextr1 +;CHECK: insertelement +;CHECK: insertelement +;CHECK: ret void +define void @fextr1(double* %ptr) { +entry: + %LD = load <2 x double>* undef + %V0 = extractelement <2 x double> %LD, i32 0 + %V1 = extractelement <2 x double> %LD, i32 1 + %P0 = getelementptr inbounds double* %ptr, i64 1 ; <--- incorrect order + %P1 = getelementptr inbounds double* %ptr, i64 0 + %A0 = fadd double %V0, 1.2 + %A1 = fadd double %V1, 3.4 + store double %A0, double* %P0, align 4 + store double %A1, double* %P1, align 4 + ret void +} + +;CHECK: fextr2 +;CHECK: insertelement +;CHECK: insertelement +;CHECK: ret void +define void @fextr2(double* %ptr) { +entry: + %LD = load <4 x double>* undef + %V0 = extractelement <4 x double> %LD, i32 0 ; <--- invalid size. + %V1 = extractelement <4 x double> %LD, i32 1 + %P0 = getelementptr inbounds double* %ptr, i64 0 + %P1 = getelementptr inbounds double* %ptr, i64 1 + %A0 = fadd double %V0, 5.5 + %A1 = fadd double %V1, 6.6 + store double %A0, double* %P0, align 4 + store double %A1, double* %P1, align 4 + ret void +} + |