diff options
| author | Bob Wilson <bob.wilson@apple.com> | 2009-10-07 20:49:18 +0000 |
|---|---|---|
| committer | Bob Wilson <bob.wilson@apple.com> | 2009-10-07 20:49:18 +0000 |
| commit | 63c906343468dca4ac67ed85242d5a9fee95d57f (patch) | |
| tree | b3aeeb8cac80f73107391f6b42c95d005b584b2a /test/CodeGen/ARM/vst4.ll | |
| parent | 66a70639dae4cbead3f9799406d98cb4293f2af5 (diff) | |
| download | external_llvm-63c906343468dca4ac67ed85242d5a9fee95d57f.zip external_llvm-63c906343468dca4ac67ed85242d5a9fee95d57f.tar.gz external_llvm-63c906343468dca4ac67ed85242d5a9fee95d57f.tar.bz2 | |
Add codegen support for NEON vst4 intrinsics with 128-bit vectors.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@83486 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/ARM/vst4.ll')
| -rw-r--r-- | test/CodeGen/ARM/vst4.ll | 41 |
1 files changed, 41 insertions, 0 deletions
diff --git a/test/CodeGen/ARM/vst4.ll b/test/CodeGen/ARM/vst4.ll index 8966b62..c7d4da0 100644 --- a/test/CodeGen/ARM/vst4.ll +++ b/test/CodeGen/ARM/vst4.ll @@ -32,7 +32,48 @@ define void @vst4f(float* %A, <2 x float>* %B) nounwind { ret void } +define void @vst4Qi8(i8* %A, <16 x i8>* %B) nounwind { +;CHECK: vst4Qi8: +;CHECK: vst4.8 +;CHECK: vst4.8 + %tmp1 = load <16 x i8>* %B + call void @llvm.arm.neon.vst4.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1) + ret void +} + +define void @vst4Qi16(i16* %A, <8 x i16>* %B) nounwind { +;CHECK: vst4Qi16: +;CHECK: vst4.16 +;CHECK: vst4.16 + %tmp1 = load <8 x i16>* %B + call void @llvm.arm.neon.vst4.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1) + ret void +} + +define void @vst4Qi32(i32* %A, <4 x i32>* %B) nounwind { +;CHECK: vst4Qi32: +;CHECK: vst4.32 +;CHECK: vst4.32 + %tmp1 = load <4 x i32>* %B + call void @llvm.arm.neon.vst4.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1) + ret void +} + +define void @vst4Qf(float* %A, <4 x float>* %B) nounwind { +;CHECK: vst4Qf: +;CHECK: vst4.32 +;CHECK: vst4.32 + %tmp1 = load <4 x float>* %B + call void @llvm.arm.neon.vst4.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1) + ret void +} + declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>) nounwind declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>) nounwind declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>) nounwind declare void @llvm.arm.neon.vst4.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>) nounwind + +declare void @llvm.arm.neon.vst4.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>) nounwind +declare void @llvm.arm.neon.vst4.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>) nounwind +declare void @llvm.arm.neon.vst4.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>) nounwind +declare void @llvm.arm.neon.vst4.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>) nounwind |