1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
|
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
%struct.__neon_int8x8x2_t = type { <8 x i8>, <8 x i8> }
%struct.__neon_int16x4x2_t = type { <4 x i16>, <4 x i16> }
%struct.__neon_int32x2x2_t = type { <2 x i32>, <2 x i32> }
%struct.__neon_float32x2x2_t = type { <2 x float>, <2 x float> }
%struct.__neon_int16x8x2_t = type { <8 x i16>, <8 x i16> }
%struct.__neon_int32x4x2_t = type { <4 x i32>, <4 x i32> }
%struct.__neon_float32x4x2_t = type { <4 x float>, <4 x float> }
define <8 x i8> @vld2lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK: vld2lanei8:
;CHECK: vld2.8
%tmp1 = load <8 x i8>* %B
%tmp2 = call %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x2_t %tmp2, 1
%tmp5 = add <8 x i8> %tmp3, %tmp4
ret <8 x i8> %tmp5
}
define <4 x i16> @vld2lanei16(i16* %A, <4 x i16>* %B) nounwind {
;CHECK: vld2lanei16:
;CHECK: vld2.16
%tmp1 = load <4 x i16>* %B
%tmp2 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 1
%tmp5 = add <4 x i16> %tmp3, %tmp4
ret <4 x i16> %tmp5
}
define <2 x i32> @vld2lanei32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK: vld2lanei32:
;CHECK: vld2.32
%tmp1 = load <2 x i32>* %B
%tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 1
%tmp5 = add <2 x i32> %tmp3, %tmp4
ret <2 x i32> %tmp5
}
define <2 x float> @vld2lanef(float* %A, <2 x float>* %B) nounwind {
;CHECK: vld2lanef:
;CHECK: vld2.32
%tmp1 = load <2 x float>* %B
%tmp2 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 1
%tmp5 = add <2 x float> %tmp3, %tmp4
ret <2 x float> %tmp5
}
define <8 x i16> @vld2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
;CHECK: vld2laneQi16:
;CHECK: vld2.16
%tmp1 = load <8 x i16>* %B
%tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 1
%tmp5 = add <8 x i16> %tmp3, %tmp4
ret <8 x i16> %tmp5
}
define <4 x i32> @vld2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
;CHECK: vld2laneQi32:
;CHECK: vld2.32
%tmp1 = load <4 x i32>* %B
%tmp2 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
%tmp3 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 1
%tmp5 = add <4 x i32> %tmp3, %tmp4
ret <4 x i32> %tmp5
}
define <4 x float> @vld2laneQf(float* %A, <4 x float>* %B) nounwind {
;CHECK: vld2laneQf:
;CHECK: vld2.32
%tmp1 = load <4 x float>* %B
%tmp2 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 1
%tmp5 = add <4 x float> %tmp3, %tmp4
ret <4 x float> %tmp5
}
declare %struct.__neon_int8x8x2_t @llvm.arm.neon.vld2lane.v8i8(i8*, <8 x i8>, <8 x i8>, i32) nounwind readonly
declare %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8*, <4 x i16>, <4 x i16>, i32) nounwind readonly
declare %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8*, <2 x i32>, <2 x i32>, i32) nounwind readonly
declare %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(i8*, <2 x float>, <2 x float>, i32) nounwind readonly
declare %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8*, <8 x i16>, <8 x i16>, i32) nounwind readonly
declare %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8*, <4 x i32>, <4 x i32>, i32) nounwind readonly
declare %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8*, <4 x float>, <4 x float>, i32) nounwind readonly
%struct.__neon_int8x8x3_t = type { <8 x i8>, <8 x i8>, <8 x i8> }
%struct.__neon_int16x4x3_t = type { <4 x i16>, <4 x i16>, <4 x i16> }
%struct.__neon_int32x2x3_t = type { <2 x i32>, <2 x i32>, <2 x i32> }
%struct.__neon_float32x2x3_t = type { <2 x float>, <2 x float>, <2 x float> }
%struct.__neon_int16x8x3_t = type { <8 x i16>, <8 x i16>, <8 x i16> }
%struct.__neon_int32x4x3_t = type { <4 x i32>, <4 x i32>, <4 x i32> }
%struct.__neon_float32x4x3_t = type { <4 x float>, <4 x float>, <4 x float> }
define <8 x i8> @vld3lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK: vld3lanei8:
;CHECK: vld3.8
%tmp1 = load <8 x i8>* %B
%tmp2 = call %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int8x8x3_t %tmp2, 2
%tmp6 = add <8 x i8> %tmp3, %tmp4
%tmp7 = add <8 x i8> %tmp5, %tmp6
ret <8 x i8> %tmp7
}
define <4 x i16> @vld3lanei16(i16* %A, <4 x i16>* %B) nounwind {
;CHECK: vld3lanei16:
;CHECK: vld3.16
%tmp1 = load <4 x i16>* %B
%tmp2 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 2
%tmp6 = add <4 x i16> %tmp3, %tmp4
%tmp7 = add <4 x i16> %tmp5, %tmp6
ret <4 x i16> %tmp7
}
define <2 x i32> @vld3lanei32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK: vld3lanei32:
;CHECK: vld3.32
%tmp1 = load <2 x i32>* %B
%tmp2 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 2
%tmp6 = add <2 x i32> %tmp3, %tmp4
%tmp7 = add <2 x i32> %tmp5, %tmp6
ret <2 x i32> %tmp7
}
define <2 x float> @vld3lanef(float* %A, <2 x float>* %B) nounwind {
;CHECK: vld3lanef:
;CHECK: vld3.32
%tmp1 = load <2 x float>* %B
%tmp2 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 2
%tmp6 = add <2 x float> %tmp3, %tmp4
%tmp7 = add <2 x float> %tmp5, %tmp6
ret <2 x float> %tmp7
}
define <8 x i16> @vld3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
;CHECK: vld3laneQi16:
;CHECK: vld3.16
%tmp1 = load <8 x i16>* %B
%tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 2
%tmp6 = add <8 x i16> %tmp3, %tmp4
%tmp7 = add <8 x i16> %tmp5, %tmp6
ret <8 x i16> %tmp7
}
define <4 x i32> @vld3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
;CHECK: vld3laneQi32:
;CHECK: vld3.32
%tmp1 = load <4 x i32>* %B
%tmp2 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 3)
%tmp3 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 2
%tmp6 = add <4 x i32> %tmp3, %tmp4
%tmp7 = add <4 x i32> %tmp5, %tmp6
ret <4 x i32> %tmp7
}
define <4 x float> @vld3laneQf(float* %A, <4 x float>* %B) nounwind {
;CHECK: vld3laneQf:
;CHECK: vld3.32
%tmp1 = load <4 x float>* %B
%tmp2 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 2
%tmp6 = add <4 x float> %tmp3, %tmp4
%tmp7 = add <4 x float> %tmp5, %tmp6
ret <4 x float> %tmp7
}
declare %struct.__neon_int8x8x3_t @llvm.arm.neon.vld3lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind readonly
declare %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind readonly
declare %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind readonly
declare %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind readonly
declare %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind readonly
declare %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind readonly
declare %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32) nounwind readonly
%struct.__neon_int8x8x4_t = type { <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8> }
%struct.__neon_int16x4x4_t = type { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> }
%struct.__neon_int32x2x4_t = type { <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32> }
%struct.__neon_float32x2x4_t = type { <2 x float>, <2 x float>, <2 x float>, <2 x float> }
%struct.__neon_int16x8x4_t = type { <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16> }
%struct.__neon_int32x4x4_t = type { <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32> }
%struct.__neon_float32x4x4_t = type { <4 x float>, <4 x float>, <4 x float>, <4 x float> }
define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK: vld4lanei8:
;CHECK: vld4.8
%tmp1 = load <8 x i8>* %B
%tmp2 = call %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_int8x8x4_t %tmp2, 3
%tmp7 = add <8 x i8> %tmp3, %tmp4
%tmp8 = add <8 x i8> %tmp5, %tmp6
%tmp9 = add <8 x i8> %tmp7, %tmp8
ret <8 x i8> %tmp9
}
define <4 x i16> @vld4lanei16(i16* %A, <4 x i16>* %B) nounwind {
;CHECK: vld4lanei16:
;CHECK: vld4.16
%tmp1 = load <4 x i16>* %B
%tmp2 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 3
%tmp7 = add <4 x i16> %tmp3, %tmp4
%tmp8 = add <4 x i16> %tmp5, %tmp6
%tmp9 = add <4 x i16> %tmp7, %tmp8
ret <4 x i16> %tmp9
}
define <2 x i32> @vld4lanei32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK: vld4lanei32:
;CHECK: vld4.32
%tmp1 = load <2 x i32>* %B
%tmp2 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 3
%tmp7 = add <2 x i32> %tmp3, %tmp4
%tmp8 = add <2 x i32> %tmp5, %tmp6
%tmp9 = add <2 x i32> %tmp7, %tmp8
ret <2 x i32> %tmp9
}
define <2 x float> @vld4lanef(float* %A, <2 x float>* %B) nounwind {
;CHECK: vld4lanef:
;CHECK: vld4.32
%tmp1 = load <2 x float>* %B
%tmp2 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 3
%tmp7 = add <2 x float> %tmp3, %tmp4
%tmp8 = add <2 x float> %tmp5, %tmp6
%tmp9 = add <2 x float> %tmp7, %tmp8
ret <2 x float> %tmp9
}
define <8 x i16> @vld4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
;CHECK: vld4laneQi16:
;CHECK: vld4.16
%tmp1 = load <8 x i16>* %B
%tmp2 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 3
%tmp7 = add <8 x i16> %tmp3, %tmp4
%tmp8 = add <8 x i16> %tmp5, %tmp6
%tmp9 = add <8 x i16> %tmp7, %tmp8
ret <8 x i16> %tmp9
}
define <4 x i32> @vld4laneQi32(i32* %A, <4 x i32>* %B) nounwind {
;CHECK: vld4laneQi32:
;CHECK: vld4.32
%tmp1 = load <4 x i32>* %B
%tmp2 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 3
%tmp7 = add <4 x i32> %tmp3, %tmp4
%tmp8 = add <4 x i32> %tmp5, %tmp6
%tmp9 = add <4 x i32> %tmp7, %tmp8
ret <4 x i32> %tmp9
}
define <4 x float> @vld4laneQf(float* %A, <4 x float>* %B) nounwind {
;CHECK: vld4laneQf:
;CHECK: vld4.32
%tmp1 = load <4 x float>* %B
%tmp2 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
%tmp3 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 0
%tmp4 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 1
%tmp5 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 2
%tmp6 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 3
%tmp7 = add <4 x float> %tmp3, %tmp4
%tmp8 = add <4 x float> %tmp5, %tmp6
%tmp9 = add <4 x float> %tmp7, %tmp8
ret <4 x float> %tmp9
}
declare %struct.__neon_int8x8x4_t @llvm.arm.neon.vld4lane.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind readonly
declare %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind readonly
declare %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind readonly
declare %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind readonly
declare %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind readonly
declare %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind readonly
declare %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32) nounwind readonly
|
