1 ; RUN: llc < %s -march=arm -mattr=+neon -O0 | FileCheck %s
3 define void @vst3i8(i8* %A, <8 x i8>* %B) nounwind {
6 %tmp1 = load <8 x i8>* %B
7 call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1)
11 define void @vst3i16(i16* %A, <4 x i16>* %B) nounwind {
14 %tmp0 = bitcast i16* %A to i8*
15 %tmp1 = load <4 x i16>* %B
16 call void @llvm.arm.neon.vst3.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
20 define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind {
23 %tmp0 = bitcast i32* %A to i8*
24 %tmp1 = load <2 x i32>* %B
25 call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
29 define void @vst3f(float* %A, <2 x float>* %B) nounwind {
32 %tmp0 = bitcast float* %A to i8*
33 %tmp1 = load <2 x float>* %B
34 call void @llvm.arm.neon.vst3.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
38 define void @vst3i64(i64* %A, <1 x i64>* %B) nounwind {
41 %tmp0 = bitcast i64* %A to i8*
42 %tmp1 = load <1 x i64>* %B
43 call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 1)
47 define void @vst3Qi8(i8* %A, <16 x i8>* %B) nounwind {
51 %tmp1 = load <16 x i8>* %B
52 call void @llvm.arm.neon.vst3.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 1)
56 define void @vst3Qi16(i16* %A, <8 x i16>* %B) nounwind {
60 %tmp0 = bitcast i16* %A to i8*
61 %tmp1 = load <8 x i16>* %B
62 call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
66 define void @vst3Qi32(i32* %A, <4 x i32>* %B) nounwind {
70 %tmp0 = bitcast i32* %A to i8*
71 %tmp1 = load <4 x i32>* %B
72 call void @llvm.arm.neon.vst3.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1)
76 define void @vst3Qf(float* %A, <4 x float>* %B) nounwind {
80 %tmp0 = bitcast float* %A to i8*
81 %tmp1 = load <4 x float>* %B
82 call void @llvm.arm.neon.vst3.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
86 declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind
87 declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind
88 declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind
89 declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind
90 declare void @llvm.arm.neon.vst3.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind
92 declare void @llvm.arm.neon.vst3.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind
93 declare void @llvm.arm.neon.vst3.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind
94 declare void @llvm.arm.neon.vst3.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind
95 declare void @llvm.arm.neon.vst3.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32) nounwind