diff options
| author | Chris Lattner <sabre@nondot.org> | 2008-01-26 20:06:45 +0000 |
|---|---|---|
| committer | Chris Lattner <sabre@nondot.org> | 2008-01-26 20:06:45 +0000 |
| commit | b8f43875c3e532666dd736aa3823c5edf4114a05 (patch) | |
| tree | 4e018fa9c9819bf0a43094b1df454edcdfa051f4 /test/CodeGen/X86/vec_align.ll | |
| parent | dc97d4cb2f0eb99a8143272128b76ab45db4ab09 (diff) | |
| download | llvm-b8f43875c3e532666dd736aa3823c5edf4114a05.tar.gz llvm-b8f43875c3e532666dd736aa3823c5edf4114a05.tar.bz2 llvm-b8f43875c3e532666dd736aa3823c5edf4114a05.tar.xz | |
New test to verify that "merging 4 loads into a vec load" continues to work and
continues to infer alignment info.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@46403 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/vec_align.ll')
| -rw-r--r-- | test/CodeGen/X86/vec_align.ll | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/test/CodeGen/X86/vec_align.ll b/test/CodeGen/X86/vec_align.ll new file mode 100644 index 0000000000..8d70c9ae7e --- /dev/null +++ b/test/CodeGen/X86/vec_align.ll @@ -0,0 +1,35 @@ +; RUN: llvm-as < %s | llc -mcpu=yonah -relocation-model=static | grep movaps | count 2 + +target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128" +target triple = "i686-apple-darwin8" + +%f4 = type <4 x float> + +@G = external global { float,float,float,float}, align 16 + +define %f4 @test1(float %W, float %X, float %Y, float %Z) { + %tmp = insertelement %f4 undef, float %W, i32 0 + %tmp2 = insertelement %f4 %tmp, float %X, i32 1 + %tmp4 = insertelement %f4 %tmp2, float %Y, i32 2 + %tmp6 = insertelement %f4 %tmp4, float %Z, i32 3 + ret %f4 %tmp6 +} + +define %f4 @test2() { + %Wp = getelementptr { float,float,float,float}* @G, i32 0, i32 0 + %Xp = getelementptr { float,float,float,float}* @G, i32 0, i32 1 + %Yp = getelementptr { float,float,float,float}* @G, i32 0, i32 2 + %Zp = getelementptr { float,float,float,float}* @G, i32 0, i32 3 + + %W = load float* %Wp + %X = load float* %Xp + %Y = load float* %Yp + %Z = load float* %Zp + + %tmp = insertelement %f4 undef, float %W, i32 0 + %tmp2 = insertelement %f4 %tmp, float %X, i32 1 + %tmp4 = insertelement %f4 %tmp2, float %Y, i32 2 + %tmp6 = insertelement %f4 %tmp4, float %Z, i32 3 + ret %f4 %tmp6 +} + |