1 ; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
3 define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind {
5 ;Check the alignment value. Max for this instruction is 16 bits:
6 ;CHECK: vst2.8 {d16[1], d17[1]}, [r0, :16]
7 %tmp1 = load <8 x i8>* %B
8 call void @llvm.arm.neon.vst2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1, i32 4)
12 define void @vst2lanei16(i16* %A, <4 x i16>* %B) nounwind {
14 ;Check the alignment value. Max for this instruction is 32 bits:
15 ;CHECK: vst2.16 {d16[1], d17[1]}, [r0, :32]
16 %tmp0 = bitcast i16* %A to i8*
17 %tmp1 = load <4 x i16>* %B
18 call void @llvm.arm.neon.vst2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 8)
22 define void @vst2lanei32(i32* %A, <2 x i32>* %B) nounwind {
25 %tmp0 = bitcast i32* %A to i8*
26 %tmp1 = load <2 x i32>* %B
27 call void @llvm.arm.neon.vst2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1, i32 1)
31 define void @vst2lanef(float* %A, <2 x float>* %B) nounwind {
34 %tmp0 = bitcast float* %A to i8*
35 %tmp1 = load <2 x float>* %B
36 call void @llvm.arm.neon.vst2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1, i32 1)
40 define void @vst2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
42 ;Check the (default) alignment.
43 ;CHECK: vst2.16 {d17[1], d19[1]}, [r0]
44 %tmp0 = bitcast i16* %A to i8*
45 %tmp1 = load <8 x i16>* %B
46 call void @llvm.arm.neon.vst2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 5, i32 1)
50 define void @vst2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
52 ;Check the alignment value. Max for this instruction is 64 bits:
53 ;CHECK: vst2.32 {d17[0], d19[0]}, [r0, :64]
54 %tmp0 = bitcast i32* %A to i8*
55 %tmp1 = load <4 x i32>* %B
56 call void @llvm.arm.neon.vst2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2, i32 16)
60 define void @vst2laneQf(float* %A, <4 x float>* %B) nounwind {
63 %tmp0 = bitcast float* %A to i8*
64 %tmp1 = load <4 x float>* %B
65 call void @llvm.arm.neon.vst2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 3, i32 1)
69 declare void @llvm.arm.neon.vst2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32, i32) nounwind
70 declare void @llvm.arm.neon.vst2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32, i32) nounwind
71 declare void @llvm.arm.neon.vst2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32, i32) nounwind
72 declare void @llvm.arm.neon.vst2lane.v2f32(i8*, <2 x float>, <2 x float>, i32, i32) nounwind
74 declare void @llvm.arm.neon.vst2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32, i32) nounwind
75 declare void @llvm.arm.neon.vst2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32, i32) nounwind
76 declare void @llvm.arm.neon.vst2lane.v4f32(i8*, <4 x float>, <4 x float>, i32, i32) nounwind
78 define void @vst3lanei8(i8* %A, <8 x i8>* %B) nounwind {
81 %tmp1 = load <8 x i8>* %B
82 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)
86 define void @vst3lanei16(i16* %A, <4 x i16>* %B) nounwind {
88 ;Check the (default) alignment value. VST3 does not support alignment.
89 ;CHECK: vst3.16 {d16[1], d17[1], d18[1]}, [r0]
90 %tmp0 = bitcast i16* %A to i8*
91 %tmp1 = load <4 x i16>* %B
92 call void @llvm.arm.neon.vst3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1, i32 8)
96 define void @vst3lanei32(i32* %A, <2 x i32>* %B) nounwind {
99 %tmp0 = bitcast i32* %A to i8*
100 %tmp1 = load <2 x i32>* %B
101 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)
105 define void @vst3lanef(float* %A, <2 x float>* %B) nounwind {
108 %tmp0 = bitcast float* %A to i8*
109 %tmp1 = load <2 x float>* %B
110 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)
114 define void @vst3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
115 ;CHECK: vst3laneQi16:
116 ;Check the (default) alignment value. VST3 does not support alignment.
117 ;CHECK: vst3.16 {d17[2], d19[2], d21[2]}, [r0]
118 %tmp0 = bitcast i16* %A to i8*
119 %tmp1 = load <8 x i16>* %B
120 call void @llvm.arm.neon.vst3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 6, i32 8)
124 define void @vst3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
125 ;CHECK: vst3laneQi32:
127 %tmp0 = bitcast i32* %A to i8*
128 %tmp1 = load <4 x i32>* %B
129 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)
133 define void @vst3laneQf(float* %A, <4 x float>* %B) nounwind {
136 %tmp0 = bitcast float* %A to i8*
137 %tmp1 = load <4 x float>* %B
138 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)
142 declare void @llvm.arm.neon.vst3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind
143 declare void @llvm.arm.neon.vst3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind
144 declare void @llvm.arm.neon.vst3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind
145 declare void @llvm.arm.neon.vst3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind
147 declare void @llvm.arm.neon.vst3lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind
148 declare void @llvm.arm.neon.vst3lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind
149 declare void @llvm.arm.neon.vst3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind
152 define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind {
154 ;Check the alignment value. Max for this instruction is 32 bits:
155 ;CHECK: vst4.8 {d16[1], d17[1], d18[1], d19[1]}, [r0, :32]
156 %tmp1 = load <8 x i8>* %B
157 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 8)
161 define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind {
164 %tmp0 = bitcast i16* %A to i8*
165 %tmp1 = load <4 x i16>* %B
166 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)
170 define void @vst4lanei32(i32* %A, <2 x i32>* %B) nounwind {
172 ;Check the alignment value. Max for this instruction is 128 bits:
173 ;CHECK: vst4.32 {d16[1], d17[1], d18[1], d19[1]}, [r0, :128]
174 %tmp0 = bitcast i32* %A to i8*
175 %tmp1 = load <2 x i32>* %B
176 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 16)
180 define void @vst4lanef(float* %A, <2 x float>* %B) nounwind {
183 %tmp0 = bitcast float* %A to i8*
184 %tmp1 = load <2 x float>* %B
185 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)
189 define void @vst4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
190 ;CHECK: vst4laneQi16:
191 ;Check the alignment value. Max for this instruction is 64 bits:
192 ;CHECK: vst4.16 {d17[3], d19[3], d21[3], d23[3]}, [r0, :64]
193 %tmp0 = bitcast i16* %A to i8*
194 %tmp1 = load <8 x i16>* %B
195 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 16)
199 define void @vst4laneQi32(i32* %A, <4 x i32>* %B) nounwind {
200 ;CHECK: vst4laneQi32:
201 ;Check the (default) alignment.
202 ;CHECK: vst4.32 {d17[0], d19[0], d21[0], d23[0]}, [r0]
203 %tmp0 = bitcast i32* %A to i8*
204 %tmp1 = load <4 x i32>* %B
205 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)
209 define void @vst4laneQf(float* %A, <4 x float>* %B) nounwind {
212 %tmp0 = bitcast float* %A to i8*
213 %tmp1 = load <4 x float>* %B
214 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)
218 declare void @llvm.arm.neon.vst4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32, i32) nounwind
219 declare void @llvm.arm.neon.vst4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32, i32) nounwind
220 declare void @llvm.arm.neon.vst4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32, i32) nounwind
221 declare void @llvm.arm.neon.vst4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32, i32) nounwind
223 declare void @llvm.arm.neon.vst4lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32, i32) nounwind
224 declare void @llvm.arm.neon.vst4lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32, i32) nounwind
225 declare void @llvm.arm.neon.vst4lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32, i32) nounwind