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, i32 1)
11 define void @vst2lanei16(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.vst2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1)
20 define void @vst2lanei32(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.vst2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
29 define void @vst2lanef(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.vst2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1)
38 define void @vst2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
41 %tmp0 = bitcast i16* %A to i8*
42 %tmp1 = load <8 x i16>* %B
43 call void @llvm.arm.neon.vst2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1, i32 1)
47 define void @vst2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
50 %tmp0 = bitcast i32* %A to i8*
51 %tmp1 = load <4 x i32>* %B
52 call void @llvm.arm.neon.vst2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 1)
56 define void @vst2laneQf(float* %A, <4 x float>* %B) nounwind {
59 %tmp0 = bitcast float* %A to i8*
60 %tmp1 = load <4 x float>* %B
61 call void @llvm.arm.neon.vst2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 3, i32 1)
65 declare void @llvm.arm.neon.vst2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32, i32) nounwind
66 declare void @llvm.arm.neon.vst2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32, i32) nounwind
67 declare void @llvm.arm.neon.vst2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32, i32) nounwind
68 declare void @llvm.arm.neon.vst2lane.v2f32(i8*, <2 x float>, <2 x float>, i32, i32) nounwind
70 declare void @llvm.arm.neon.vst2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32, i32) nounwind
71 declare void @llvm.arm.neon.vst2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32, i32) nounwind
72 declare void @llvm.arm.neon.vst2lane.v4f32(i8*, <4 x float>, <4 x float>, i32, i32) nounwind
74 define void @vst3lanei8(i8* %A, <8 x i8>* %B) nounwind {
77 %tmp1 = load <8 x i8>* %B
78 call void @llvm.arm.neon.vst3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 1)
82 define void @vst3lanei16(i16* %A, <4 x i16>* %B) nounwind {
85 %tmp0 = bitcast i16* %A to i8*
86 %tmp1 = load <4 x i16>* %B
87 call void @llvm.arm.neon.vst3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1)
91 define void @vst3lanei32(i32* %A, <2 x i32>* %B) nounwind {
94 %tmp0 = bitcast i32* %A to i8*
95 %tmp1 = load <2 x i32>* %B
96 call void @llvm.arm.neon.vst3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
100 define void @vst3lanef(float* %A, <2 x float>* %B) nounwind {
103 %tmp0 = bitcast float* %A to i8*
104 %tmp1 = load <2 x float>* %B
105 call void @llvm.arm.neon.vst3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1)
109 define void @vst3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
110 ;CHECK: vst3laneQi16:
112 %tmp0 = bitcast i16* %A to i8*
113 %tmp1 = load <8 x i16>* %B
114 call void @llvm.arm.neon.vst3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 6, i32 1)
118 define void @vst3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
119 ;CHECK: vst3laneQi32:
121 %tmp0 = bitcast i32* %A to i8*
122 %tmp1 = load <4 x i32>* %B
123 call void @llvm.arm.neon.vst3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 0, i32 1)
127 define void @vst3laneQf(float* %A, <4 x float>* %B) nounwind {
130 %tmp0 = bitcast float* %A to i8*
131 %tmp1 = load <4 x float>* %B
132 call void @llvm.arm.neon.vst3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1)
136 declare void @llvm.arm.neon.vst3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind
137 declare void @llvm.arm.neon.vst3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind
138 declare void @llvm.arm.neon.vst3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind
139 declare void @llvm.arm.neon.vst3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind
141 declare void @llvm.arm.neon.vst3lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind
142 declare void @llvm.arm.neon.vst3lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind
143 declare void @llvm.arm.neon.vst3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind
146 define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind {
149 %tmp1 = load <8 x i8>* %B
150 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, i32 1)
154 define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind {
157 %tmp0 = bitcast i16* %A to i8*
158 %tmp1 = load <4 x i16>* %B
159 call void @llvm.arm.neon.vst4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 1)
163 define void @vst4lanei32(i32* %A, <2 x i32>* %B) nounwind {
166 %tmp0 = bitcast i32* %A to i8*
167 %tmp1 = load <2 x i32>* %B
168 call void @llvm.arm.neon.vst4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
172 define void @vst4lanef(float* %A, <2 x float>* %B) nounwind {
175 %tmp0 = bitcast float* %A to i8*
176 %tmp1 = load <2 x float>* %B
177 call void @llvm.arm.neon.vst4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1)
181 define void @vst4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
182 ;CHECK: vst4laneQi16:
184 %tmp0 = bitcast i16* %A to i8*
185 %tmp1 = load <8 x i16>* %B
186 call void @llvm.arm.neon.vst4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 7, i32 1)
190 define void @vst4laneQi32(i32* %A, <4 x i32>* %B) nounwind {
191 ;CHECK: vst4laneQi32:
193 %tmp0 = bitcast i32* %A to i8*
194 %tmp1 = load <4 x i32>* %B
195 call void @llvm.arm.neon.vst4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 1)
199 define void @vst4laneQf(float* %A, <4 x float>* %B) nounwind {
202 %tmp0 = bitcast float* %A to i8*
203 %tmp1 = load <4 x float>* %B
204 call void @llvm.arm.neon.vst4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1, i32 1)
208 declare void @llvm.arm.neon.vst4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind
209 declare void @llvm.arm.neon.vst4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind
210 declare void @llvm.arm.neon.vst4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind
211 declare void @llvm.arm.neon.vst4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind
213 declare void @llvm.arm.neon.vst4lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind
214 declare void @llvm.arm.neon.vst4lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind
215 declare void @llvm.arm.neon.vst4lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind