From 1c3ef90cab9a563427bdd3c2fcd875c717750562 Mon Sep 17 00:00:00 2001 From: Bob Wilson Date: Mon, 7 Feb 2011 17:43:21 +0000 Subject: 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. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@125014 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/CodeGen/ARM/vst4.ll | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'test/CodeGen/ARM/vst4.ll') diff --git a/test/CodeGen/ARM/vst4.ll b/test/CodeGen/ARM/vst4.ll index 6a7e91dee9..e94acb66bf 100644 --- a/test/CodeGen/ARM/vst4.ll +++ b/test/CodeGen/ARM/vst4.ll @@ -9,6 +9,18 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind { ret void } +;Check for a post-increment updating store with register increment. +define void @vst4i8_update(i8** %ptr, <8 x i8>* %B, i32 %inc) nounwind { +;CHECK: vst4i8_update: +;CHECK: vst4.8 {d16, d17, d18, d19}, [r1, :128], r2 + %A = load i8** %ptr + %tmp1 = load <8 x i8>* %B + call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 16) + %tmp2 = getelementptr i8* %A, i32 %inc + store i8* %tmp2, i8** %ptr + ret void +} + define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst4i16: ;Check the alignment value. Max for this instruction is 256 bits: @@ -89,6 +101,20 @@ define void @vst4Qf(float* %A, <4 x float>* %B) nounwind { ret void } +;Check for a post-increment updating store. +define void @vst4Qf_update(float** %ptr, <4 x float>* %B) nounwind { +;CHECK: vst4Qf_update: +;CHECK: vst4.32 {d16, d18, d20, d22}, [r1]! +;CHECK: vst4.32 {d17, d19, d21, d23}, [r1]! + %A = load float** %ptr + %tmp0 = bitcast float* %A to i8* + %tmp1 = load <4 x float>* %B + call void @llvm.arm.neon.vst4.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) + %tmp2 = getelementptr float* %A, i32 16 + store float* %tmp2, float** %ptr + ret void +} + declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind -- cgit v1.2.3