diff options
| author | Bob Wilson <bob.wilson@apple.com> | 2011-02-07 17:43:21 +0000 |
|---|---|---|
| committer | Bob Wilson <bob.wilson@apple.com> | 2011-02-07 17:43:21 +0000 |
| commit | 06fce87c4a1ca0c93cf527c389da3fc7cb53db20 (patch) | |
| tree | f57efc5126dd21ffcf77aed6cfd4825aabe9919e /llvm/test/CodeGen/ARM/vst1.ll | |
| parent | a609b8954ebd52928f0bc9334e33e50aea312118 (diff) | |
| download | bcm5719-llvm-06fce87c4a1ca0c93cf527c389da3fc7cb53db20.tar.gz bcm5719-llvm-06fce87c4a1ca0c93cf527c389da3fc7cb53db20.zip | |
Add codegen support for using post-increment NEON load/store instructions.
The vld1-lane, vld1-dup and vst1-lane instructions do not yet support using
post-increment versions, but all the rest of the NEON load/store instructions
should be handled now.
llvm-svn: 125014
Diffstat (limited to 'llvm/test/CodeGen/ARM/vst1.ll')
| -rw-r--r-- | llvm/test/CodeGen/ARM/vst1.ll | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/ARM/vst1.ll b/llvm/test/CodeGen/ARM/vst1.ll index 70f3a4cfa28..364d44b7116 100644 --- a/llvm/test/CodeGen/ARM/vst1.ll +++ b/llvm/test/CodeGen/ARM/vst1.ll @@ -36,6 +36,19 @@ define void @vst1f(float* %A, <2 x float>* %B) nounwind { ret void } +;Check for a post-increment updating store. +define void @vst1f_update(float** %ptr, <2 x float>* %B) nounwind { +;CHECK: vst1f_update: +;CHECK: vst1.32 {d16}, [r1]! + %A = load float** %ptr + %tmp0 = bitcast float* %A to i8* + %tmp1 = load <2 x float>* %B + call void @llvm.arm.neon.vst1.v2f32(i8* %tmp0, <2 x float> %tmp1, i32 1) + %tmp2 = getelementptr float* %A, i32 2 + store float* %tmp2, float** %ptr + ret void +} + define void @vst1i64(i64* %A, <1 x i64>* %B) nounwind { ;CHECK: vst1i64: ;CHECK: vst1.64 @@ -64,6 +77,19 @@ define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind { ret void } +;Check for a post-increment updating store with register increment. +define void @vst1Qi16_update(i16** %ptr, <8 x i16>* %B, i32 %inc) nounwind { +;CHECK: vst1Qi16_update: +;CHECK: vst1.16 {d16, d17}, [r1, :64], r2 + %A = load i16** %ptr + %tmp0 = bitcast i16* %A to i8* + %tmp1 = load <8 x i16>* %B + call void @llvm.arm.neon.vst1.v8i16(i8* %tmp0, <8 x i16> %tmp1, i32 8) + %tmp2 = getelementptr i16* %A, i32 %inc + store i16* %tmp2, i16** %ptr + ret void +} + define void @vst1Qi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst1Qi32: ;CHECK: vst1.32 |

