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
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
|
// RUN: %clang_cc1 -triple arm64-none-linux-gnu -target-feature +neon \
// RUN: -disable-O0-optnone -emit-llvm -o - %s | opt -S -mem2reg | FileCheck %s
// Test new aarch64 intrinsics and types
#include <arm_neon.h>
// CHECK-LABEL: define{{.*}} i16 @test_vaddlv_s8(<8 x i8> %a) #0 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.saddlv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDLV_I]] to i16
// CHECK: ret i16 [[TMP0]]
int16_t test_vaddlv_s8(int8x8_t a) {
return vaddlv_s8(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vaddlv_s16(<4 x i16> %a) #0 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.saddlv.i32.v4i16(<4 x i16> %a) #3
// CHECK: ret i32 [[VADDLV_I]]
int32_t test_vaddlv_s16(int16x4_t a) {
return vaddlv_s16(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vaddlv_u8(<8 x i8> %a) #0 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddlv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDLV_I]] to i16
// CHECK: ret i16 [[TMP0]]
uint16_t test_vaddlv_u8(uint8x8_t a) {
return vaddlv_u8(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vaddlv_u16(<4 x i16> %a) #0 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddlv.i32.v4i16(<4 x i16> %a) #3
// CHECK: ret i32 [[VADDLV_I]]
uint32_t test_vaddlv_u16(uint16x4_t a) {
return vaddlv_u16(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vaddlvq_s8(<16 x i8> %a) #1 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.saddlv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDLV_I]] to i16
// CHECK: ret i16 [[TMP0]]
int16_t test_vaddlvq_s8(int8x16_t a) {
return vaddlvq_s8(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vaddlvq_s16(<8 x i16> %a) #1 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.saddlv.i32.v8i16(<8 x i16> %a) #3
// CHECK: ret i32 [[VADDLV_I]]
int32_t test_vaddlvq_s16(int16x8_t a) {
return vaddlvq_s16(a);
}
// CHECK-LABEL: define{{.*}} i64 @test_vaddlvq_s32(<4 x i32> %a) #1 {
// CHECK: [[VADDLVQ_S32_I:%.*]] = call i64 @llvm.aarch64.neon.saddlv.i64.v4i32(<4 x i32> %a) #3
// CHECK: ret i64 [[VADDLVQ_S32_I]]
int64_t test_vaddlvq_s32(int32x4_t a) {
return vaddlvq_s32(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vaddlvq_u8(<16 x i8> %a) #1 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddlv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDLV_I]] to i16
// CHECK: ret i16 [[TMP0]]
uint16_t test_vaddlvq_u8(uint8x16_t a) {
return vaddlvq_u8(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vaddlvq_u16(<8 x i16> %a) #1 {
// CHECK: [[VADDLV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddlv.i32.v8i16(<8 x i16> %a) #3
// CHECK: ret i32 [[VADDLV_I]]
uint32_t test_vaddlvq_u16(uint16x8_t a) {
return vaddlvq_u16(a);
}
// CHECK-LABEL: define{{.*}} i64 @test_vaddlvq_u32(<4 x i32> %a) #1 {
// CHECK: [[VADDLVQ_U32_I:%.*]] = call i64 @llvm.aarch64.neon.uaddlv.i64.v4i32(<4 x i32> %a) #3
// CHECK: ret i64 [[VADDLVQ_U32_I]]
uint64_t test_vaddlvq_u32(uint32x4_t a) {
return vaddlvq_u32(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vmaxv_s8(<8 x i8> %a) #0 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8
// CHECK: ret i8 [[TMP0]]
int8_t test_vmaxv_s8(int8x8_t a) {
return vmaxv_s8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vmaxv_s16(<4 x i16> %a) #0 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v4i16(<4 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMAXV_I]] to i16
// CHECK: ret i16 [[TMP2]]
int16_t test_vmaxv_s16(int16x4_t a) {
return vmaxv_s16(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vmaxv_u8(<8 x i8> %a) #0 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8
// CHECK: ret i8 [[TMP0]]
uint8_t test_vmaxv_u8(uint8x8_t a) {
return vmaxv_u8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vmaxv_u16(<4 x i16> %a) #0 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v4i16(<4 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMAXV_I]] to i16
// CHECK: ret i16 [[TMP2]]
uint16_t test_vmaxv_u16(uint16x4_t a) {
return vmaxv_u16(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vmaxvq_s8(<16 x i8> %a) #1 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8
// CHECK: ret i8 [[TMP0]]
int8_t test_vmaxvq_s8(int8x16_t a) {
return vmaxvq_s8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vmaxvq_s16(<8 x i16> %a) #1 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v8i16(<8 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMAXV_I]] to i16
// CHECK: ret i16 [[TMP2]]
int16_t test_vmaxvq_s16(int16x8_t a) {
return vmaxvq_s16(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vmaxvq_s32(<4 x i32> %a) #1 {
// CHECK: [[VMAXVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.smaxv.i32.v4i32(<4 x i32> %a) #3
// CHECK: ret i32 [[VMAXVQ_S32_I]]
int32_t test_vmaxvq_s32(int32x4_t a) {
return vmaxvq_s32(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vmaxvq_u8(<16 x i8> %a) #1 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMAXV_I]] to i8
// CHECK: ret i8 [[TMP0]]
uint8_t test_vmaxvq_u8(uint8x16_t a) {
return vmaxvq_u8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vmaxvq_u16(<8 x i16> %a) #1 {
// CHECK: [[VMAXV_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v8i16(<8 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMAXV_I]] to i16
// CHECK: ret i16 [[TMP2]]
uint16_t test_vmaxvq_u16(uint16x8_t a) {
return vmaxvq_u16(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vmaxvq_u32(<4 x i32> %a) #1 {
// CHECK: [[VMAXVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.umaxv.i32.v4i32(<4 x i32> %a) #3
// CHECK: ret i32 [[VMAXVQ_U32_I]]
uint32_t test_vmaxvq_u32(uint32x4_t a) {
return vmaxvq_u32(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vminv_s8(<8 x i8> %a) #0 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8
// CHECK: ret i8 [[TMP0]]
int8_t test_vminv_s8(int8x8_t a) {
return vminv_s8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vminv_s16(<4 x i16> %a) #0 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v4i16(<4 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMINV_I]] to i16
// CHECK: ret i16 [[TMP2]]
int16_t test_vminv_s16(int16x4_t a) {
return vminv_s16(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vminv_u8(<8 x i8> %a) #0 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8
// CHECK: ret i8 [[TMP0]]
uint8_t test_vminv_u8(uint8x8_t a) {
return vminv_u8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vminv_u16(<4 x i16> %a) #0 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v4i16(<4 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMINV_I]] to i16
// CHECK: ret i16 [[TMP2]]
uint16_t test_vminv_u16(uint16x4_t a) {
return vminv_u16(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vminvq_s8(<16 x i8> %a) #1 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8
// CHECK: ret i8 [[TMP0]]
int8_t test_vminvq_s8(int8x16_t a) {
return vminvq_s8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vminvq_s16(<8 x i16> %a) #1 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v8i16(<8 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMINV_I]] to i16
// CHECK: ret i16 [[TMP2]]
int16_t test_vminvq_s16(int16x8_t a) {
return vminvq_s16(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vminvq_s32(<4 x i32> %a) #1 {
// CHECK: [[VMINVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.sminv.i32.v4i32(<4 x i32> %a) #3
// CHECK: ret i32 [[VMINVQ_S32_I]]
int32_t test_vminvq_s32(int32x4_t a) {
return vminvq_s32(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vminvq_u8(<16 x i8> %a) #1 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VMINV_I]] to i8
// CHECK: ret i8 [[TMP0]]
uint8_t test_vminvq_u8(uint8x16_t a) {
return vminvq_u8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vminvq_u16(<8 x i16> %a) #1 {
// CHECK: [[VMINV_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v8i16(<8 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VMINV_I]] to i16
// CHECK: ret i16 [[TMP2]]
uint16_t test_vminvq_u16(uint16x8_t a) {
return vminvq_u16(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vminvq_u32(<4 x i32> %a) #1 {
// CHECK: [[VMINVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uminv.i32.v4i32(<4 x i32> %a) #3
// CHECK: ret i32 [[VMINVQ_U32_I]]
uint32_t test_vminvq_u32(uint32x4_t a) {
return vminvq_u32(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vaddv_s8(<8 x i8> %a) #0 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8
// CHECK: ret i8 [[TMP0]]
int8_t test_vaddv_s8(int8x8_t a) {
return vaddv_s8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vaddv_s16(<4 x i16> %a) #0 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v4i16(<4 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VADDV_I]] to i16
// CHECK: ret i16 [[TMP2]]
int16_t test_vaddv_s16(int16x4_t a) {
return vaddv_s16(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vaddv_u8(<8 x i8> %a) #0 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v8i8(<8 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8
// CHECK: ret i8 [[TMP0]]
uint8_t test_vaddv_u8(uint8x8_t a) {
return vaddv_u8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vaddv_u16(<4 x i16> %a) #0 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v4i16(<4 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VADDV_I]] to i16
// CHECK: ret i16 [[TMP2]]
uint16_t test_vaddv_u16(uint16x4_t a) {
return vaddv_u16(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vaddvq_s8(<16 x i8> %a) #1 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8
// CHECK: ret i8 [[TMP0]]
int8_t test_vaddvq_s8(int8x16_t a) {
return vaddvq_s8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vaddvq_s16(<8 x i16> %a) #1 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v8i16(<8 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VADDV_I]] to i16
// CHECK: ret i16 [[TMP2]]
int16_t test_vaddvq_s16(int16x8_t a) {
return vaddvq_s16(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vaddvq_s32(<4 x i32> %a) #1 {
// CHECK: [[VADDVQ_S32_I:%.*]] = call i32 @llvm.aarch64.neon.saddv.i32.v4i32(<4 x i32> %a) #3
// CHECK: ret i32 [[VADDVQ_S32_I]]
int32_t test_vaddvq_s32(int32x4_t a) {
return vaddvq_s32(a);
}
// CHECK-LABEL: define{{.*}} i8 @test_vaddvq_u8(<16 x i8> %a) #1 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v16i8(<16 x i8> %a) #3
// CHECK: [[TMP0:%.*]] = trunc i32 [[VADDV_I]] to i8
// CHECK: ret i8 [[TMP0]]
uint8_t test_vaddvq_u8(uint8x16_t a) {
return vaddvq_u8(a);
}
// CHECK-LABEL: define{{.*}} i16 @test_vaddvq_u16(<8 x i16> %a) #1 {
// CHECK: [[VADDV_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v8i16(<8 x i16> %a) #3
// CHECK: [[TMP2:%.*]] = trunc i32 [[VADDV_I]] to i16
// CHECK: ret i16 [[TMP2]]
uint16_t test_vaddvq_u16(uint16x8_t a) {
return vaddvq_u16(a);
}
// CHECK-LABEL: define{{.*}} i32 @test_vaddvq_u32(<4 x i32> %a) #1 {
// CHECK: [[VADDVQ_U32_I:%.*]] = call i32 @llvm.aarch64.neon.uaddv.i32.v4i32(<4 x i32> %a) #3
// CHECK: ret i32 [[VADDVQ_U32_I]]
uint32_t test_vaddvq_u32(uint32x4_t a) {
return vaddvq_u32(a);
}
// CHECK-LABEL: define{{.*}} float @test_vmaxvq_f32(<4 x float> %a) #1 {
// CHECK: [[VMAXVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fmaxv.f32.v4f32(<4 x float> %a) #3
// CHECK: ret float [[VMAXVQ_F32_I]]
float32_t test_vmaxvq_f32(float32x4_t a) {
return vmaxvq_f32(a);
}
// CHECK-LABEL: define{{.*}} float @test_vminvq_f32(<4 x float> %a) #1 {
// CHECK: [[VMINVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fminv.f32.v4f32(<4 x float> %a) #3
// CHECK: ret float [[VMINVQ_F32_I]]
float32_t test_vminvq_f32(float32x4_t a) {
return vminvq_f32(a);
}
// CHECK-LABEL: define{{.*}} float @test_vmaxnmvq_f32(<4 x float> %a) #1 {
// CHECK: [[VMAXNMVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fmaxnmv.f32.v4f32(<4 x float> %a) #3
// CHECK: ret float [[VMAXNMVQ_F32_I]]
float32_t test_vmaxnmvq_f32(float32x4_t a) {
return vmaxnmvq_f32(a);
}
// CHECK-LABEL: define{{.*}} float @test_vminnmvq_f32(<4 x float> %a) #1 {
// CHECK: [[VMINNMVQ_F32_I:%.*]] = call float @llvm.aarch64.neon.fminnmv.f32.v4f32(<4 x float> %a) #3
// CHECK: ret float [[VMINNMVQ_F32_I]]
float32_t test_vminnmvq_f32(float32x4_t a) {
return vminnmvq_f32(a);
}
// CHECK: attributes #0 ={{.*}}"min-legal-vector-width"="64"
// CHECK: attributes #1 ={{.*}}"min-legal-vector-width"="128"
|
