1 ; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
3 define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind {
6 %tmp1 = load <8 x i8>* %B
7 call void @llvm.arm.neon.vst2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1)
11 define void @vst2lanei16(i16* %A, <4 x i16>* %B) nounwind {
14 %tmp1 = load <4 x i16>* %B
15 call void @llvm.arm.neon.vst2lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
19 define void @vst2lanei32(i32* %A, <2 x i32>* %B) nounwind {
22 %tmp1 = load <2 x i32>* %B
23 call void @llvm.arm.neon.vst2lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
27 define void @vst2lanef(float* %A, <2 x float>* %B) nounwind {
30 %tmp1 = load <2 x float>* %B
31 call void @llvm.arm.neon.vst2lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
35 declare void @llvm.arm.neon.vst2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind
36 declare void @llvm.arm.neon.vst2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32) nounwind
37 declare void @llvm.arm.neon.vst2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32) nounwind
38 declare void @llvm.arm.neon.vst2lane.v2f32(i8*, <2 x float>, <2 x float>, i32) nounwind
40 define void @vst3lanei8(i8* %A, <8 x i8>* %B) nounwind {
43 %tmp1 = load <8 x i8>* %B
44 call void @llvm.arm.neon.vst3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1)
48 define void @vst3lanei16(i16* %A, <4 x i16>* %B) nounwind {
51 %tmp1 = load <4 x i16>* %B
52 call void @llvm.arm.neon.vst3lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
56 define void @vst3lanei32(i32* %A, <2 x i32>* %B) nounwind {
59 %tmp1 = load <2 x i32>* %B
60 call void @llvm.arm.neon.vst3lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
64 define void @vst3lanef(float* %A, <2 x float>* %B) nounwind {
67 %tmp1 = load <2 x float>* %B
68 call void @llvm.arm.neon.vst3lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
72 declare void @llvm.arm.neon.vst3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind
73 declare void @llvm.arm.neon.vst3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind
74 declare void @llvm.arm.neon.vst3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind
75 declare void @llvm.arm.neon.vst3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind
78 define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind {
81 %tmp1 = load <8 x i8>* %B
82 call void @llvm.arm.neon.vst4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1)
86 define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind {
89 %tmp1 = load <4 x i16>* %B
90 call void @llvm.arm.neon.vst4lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
94 define void @vst4lanei32(i32* %A, <2 x i32>* %B) nounwind {
97 %tmp1 = load <2 x i32>* %B
98 call void @llvm.arm.neon.vst4lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
102 define void @vst4lanef(float* %A, <2 x float>* %B) nounwind {
105 %tmp1 = load <2 x float>* %B
106 call void @llvm.arm.neon.vst4lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
110 declare void @llvm.arm.neon.vst4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind
111 declare void @llvm.arm.neon.vst4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind
112 declare void @llvm.arm.neon.vst4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind
113 declare void @llvm.arm.neon.vst4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind