acle_sve_dup.c
24.7 KB
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
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
// REQUIRES: aarch64-registered-target
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -DSVE_OVERLOADED_FORMS -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -Wall -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +sve -fallow-half-arguments-and-returns -S -O1 -Werror -o - %s >/dev/null 2>%t
// RUN: FileCheck --check-prefix=ASM --allow-empty %s <%t
// If this check fails please read test/CodeGen/aarch64-sve-intrinsics/README for instructions on how to resolve it.
// ASM-NOT: warning
#include <arm_sve.h>
#ifdef SVE_OVERLOADED_FORMS
// A simple used,unused... macro, long enough to represent any SVE builtin.
#define SVE_ACLE_FUNC(A1,A2_UNUSED,A3,A4_UNUSED) A1##A3
#else
#define SVE_ACLE_FUNC(A1,A2,A3,A4) A1##A2##A3##A4
#endif
svint8_t test_svdup_n_s8(int8_t op)
{
// CHECK-LABEL: test_svdup_n_s8
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s8,)(op);
}
svint16_t test_svdup_n_s16(int16_t op)
{
// CHECK-LABEL: test_svdup_n_s16
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s16,)(op);
}
svint32_t test_svdup_n_s32(int32_t op)
{
// CHECK-LABEL: test_svdup_n_s32
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s32,)(op);
}
svint64_t test_svdup_n_s64(int64_t op)
{
// CHECK-LABEL: test_svdup_n_s64
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s64,)(op);
}
svuint8_t test_svdup_n_u8(uint8_t op)
{
// CHECK-LABEL: test_svdup_n_u8
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u8,)(op);
}
svuint16_t test_svdup_n_u16(uint16_t op)
{
// CHECK-LABEL: test_svdup_n_u16
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u16,)(op);
}
svuint32_t test_svdup_n_u32(uint32_t op)
{
// CHECK-LABEL: test_svdup_n_u32
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u32,)(op);
}
svuint64_t test_svdup_n_u64(uint64_t op)
{
// CHECK-LABEL: test_svdup_n_u64
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u64,)(op);
}
svfloat16_t test_svdup_n_f16(float16_t op)
{
// CHECK-LABEL: test_svdup_n_f16
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half %op)
// CHECK: ret <vscale x 8 x half> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f16,)(op);
}
svfloat32_t test_svdup_n_f32(float32_t op)
{
// CHECK-LABEL: test_svdup_n_f32
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float %op)
// CHECK: ret <vscale x 4 x float> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f32,)(op);
}
svfloat64_t test_svdup_n_f64(float64_t op)
{
// CHECK-LABEL: test_svdup_n_f64
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double %op)
// CHECK: ret <vscale x 2 x double> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f64,)(op);
}
svint8_t test_svdup_n_s8_z(svbool_t pg, int8_t op)
{
// CHECK-LABEL: test_svdup_n_s8_z
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i1> %pg, i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s8_z,)(pg, op);
}
svint16_t test_svdup_n_s16_z(svbool_t pg, int16_t op)
{
// CHECK-LABEL: test_svdup_n_s16_z
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i1> %[[PG]], i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s16_z,)(pg, op);
}
svint32_t test_svdup_n_s32_z(svbool_t pg, int32_t op)
{
// CHECK-LABEL: test_svdup_n_s32_z
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i1> %[[PG]], i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s32_z,)(pg, op);
}
svint64_t test_svdup_n_s64_z(svbool_t pg, int64_t op)
{
// CHECK-LABEL: test_svdup_n_s64_z
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i1> %[[PG]], i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s64_z,)(pg, op);
}
svuint8_t test_svdup_n_u8_z(svbool_t pg, uint8_t op)
{
// CHECK-LABEL: test_svdup_n_u8_z
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i1> %pg, i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u8_z,)(pg, op);
}
svuint16_t test_svdup_n_u16_z(svbool_t pg, uint16_t op)
{
// CHECK-LABEL: test_svdup_n_u16_z
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i1> %[[PG]], i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u16_z,)(pg, op);
}
svuint32_t test_svdup_n_u32_z(svbool_t pg, uint32_t op)
{
// CHECK-LABEL: test_svdup_n_u32_z
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i1> %[[PG]], i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u32_z,)(pg, op);
}
svuint64_t test_svdup_n_u64_z(svbool_t pg, uint64_t op)
{
// CHECK-LABEL: test_svdup_n_u64_z
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i1> %[[PG]], i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u64_z,)(pg, op);
}
svfloat16_t test_svdup_n_f16_z(svbool_t pg, float16_t op)
{
// CHECK-LABEL: test_svdup_n_f16_z
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x i1> %[[PG]], half %op)
// CHECK: ret <vscale x 8 x half> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f16_z,)(pg, op);
}
svfloat32_t test_svdup_n_f32_z(svbool_t pg, float32_t op)
{
// CHECK-LABEL: test_svdup_n_f32_z
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x i1> %[[PG]], float %op)
// CHECK: ret <vscale x 4 x float> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f32_z,)(pg, op);
}
svfloat64_t test_svdup_n_f64_z(svbool_t pg, float64_t op)
{
// CHECK-LABEL: test_svdup_n_f64_z
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x i1> %[[PG]], double %op)
// CHECK: ret <vscale x 2 x double> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f64_z,)(pg, op);
}
svint8_t test_svdup_n_s8_m(svint8_t inactive, svbool_t pg, int8_t op)
{
// CHECK-LABEL: test_svdup_n_s8_m
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> %inactive, <vscale x 16 x i1> %pg, i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s8_m,)(inactive, pg, op);
}
svint16_t test_svdup_n_s16_m(svint16_t inactive, svbool_t pg, int16_t op)
{
// CHECK-LABEL: test_svdup_n_s16_m
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> %inactive, <vscale x 8 x i1> %[[PG]], i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s16_m,)(inactive, pg, op);
}
svint32_t test_svdup_n_s32_m(svint32_t inactive, svbool_t pg, int32_t op)
{
// CHECK-LABEL: test_svdup_n_s32_m
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> %inactive, <vscale x 4 x i1> %[[PG]], i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s32_m,)(inactive, pg, op);
}
svint64_t test_svdup_n_s64_m(svint64_t inactive, svbool_t pg, int64_t op)
{
// CHECK-LABEL: test_svdup_n_s64_m
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> %inactive, <vscale x 2 x i1> %[[PG]], i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s64_m,)(inactive, pg, op);
}
svuint8_t test_svdup_n_u8_m(svuint8_t inactive, svbool_t pg, uint8_t op)
{
// CHECK-LABEL: test_svdup_n_u8_m
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> %inactive, <vscale x 16 x i1> %pg, i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u8_m,)(inactive, pg, op);
}
svuint16_t test_svdup_n_u16_m(svuint16_t inactive, svbool_t pg, uint16_t op)
{
// CHECK-LABEL: test_svdup_n_u16_m
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> %inactive, <vscale x 8 x i1> %[[PG]], i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u16_m,)(inactive, pg, op);
}
svuint32_t test_svdup_n_u32_m(svuint32_t inactive, svbool_t pg, uint32_t op)
{
// CHECK-LABEL: test_svdup_n_u32_m
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> %inactive, <vscale x 4 x i1> %[[PG]], i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u32_m,)(inactive, pg, op);
}
svuint64_t test_svdup_n_u64_m(svuint64_t inactive, svbool_t pg, uint64_t op)
{
// CHECK-LABEL: test_svdup_n_u64_m
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> %inactive, <vscale x 2 x i1> %[[PG]], i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u64_m,)(inactive, pg, op);
}
svfloat16_t test_svdup_n_f16_m(svfloat16_t inactive, svbool_t pg, float16_t op)
{
// CHECK-LABEL: test_svdup_n_f16_m
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.nxv8f16(<vscale x 8 x half> %inactive, <vscale x 8 x i1> %[[PG]], half %op)
// CHECK: ret <vscale x 8 x half> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f16_m,)(inactive, pg, op);
}
svfloat32_t test_svdup_n_f32_m(svfloat32_t inactive, svbool_t pg, float32_t op)
{
// CHECK-LABEL: test_svdup_n_f32_m
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.nxv4f32(<vscale x 4 x float> %inactive, <vscale x 4 x i1> %[[PG]], float %op)
// CHECK: ret <vscale x 4 x float> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f32_m,)(inactive, pg, op);
}
svfloat64_t test_svdup_n_f64_m(svfloat64_t inactive, svbool_t pg, float64_t op)
{
// CHECK-LABEL: test_svdup_n_f64_m
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.nxv2f64(<vscale x 2 x double> %inactive, <vscale x 2 x i1> %[[PG]], double %op)
// CHECK: ret <vscale x 2 x double> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f64_m,)(inactive, pg, op);
}
svint8_t test_svdup_n_s8_x(svbool_t pg, int8_t op)
{
// CHECK-LABEL: test_svdup_n_s8_x
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> %pg, i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s8_x,)(pg, op);
}
svint16_t test_svdup_n_s16_x(svbool_t pg, int16_t op)
{
// CHECK-LABEL: test_svdup_n_s16_x
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> %[[PG]], i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s16_x,)(pg, op);
}
svint32_t test_svdup_n_s32_x(svbool_t pg, int32_t op)
{
// CHECK-LABEL: test_svdup_n_s32_x
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> %[[PG]], i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s32_x,)(pg, op);
}
svint64_t test_svdup_n_s64_x(svbool_t pg, int64_t op)
{
// CHECK-LABEL: test_svdup_n_s64_x
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> %[[PG]], i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_s64_x,)(pg, op);
}
svuint8_t test_svdup_n_u8_x(svbool_t pg, uint8_t op)
{
// CHECK-LABEL: test_svdup_n_u8_x
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i1> %pg, i8 %op)
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u8_x,)(pg, op);
}
svuint16_t test_svdup_n_u16_x(svbool_t pg, uint16_t op)
{
// CHECK-LABEL: test_svdup_n_u16_x
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i1> %[[PG]], i16 %op)
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u16_x,)(pg, op);
}
svuint32_t test_svdup_n_u32_x(svbool_t pg, uint32_t op)
{
// CHECK-LABEL: test_svdup_n_u32_x
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i1> %[[PG]], i32 %op)
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u32_x,)(pg, op);
}
svuint64_t test_svdup_n_u64_x(svbool_t pg, uint64_t op)
{
// CHECK-LABEL: test_svdup_n_u64_x
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i1> %[[PG]], i64 %op)
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_u64_x,)(pg, op);
}
svfloat16_t test_svdup_n_f16_x(svbool_t pg, float16_t op)
{
// CHECK-LABEL: test_svdup_n_f16_x
// CHECK: %[[PG:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.dup.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> %[[PG]], half %op)
// CHECK: ret <vscale x 8 x half> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f16_x,)(pg, op);
}
svfloat32_t test_svdup_n_f32_x(svbool_t pg, float32_t op)
{
// CHECK-LABEL: test_svdup_n_f32_x
// CHECK: %[[PG:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.dup.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x i1> %[[PG]], float %op)
// CHECK: ret <vscale x 4 x float> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f32_x,)(pg, op);
}
svfloat64_t test_svdup_n_f64_x(svbool_t pg, float64_t op)
{
// CHECK-LABEL: test_svdup_n_f64_x
// CHECK: %[[PG:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %pg)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> %[[PG]], double %op)
// CHECK: ret <vscale x 2 x double> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup,_n,_f64_x,)(pg, op);
}
svint8_t test_svdup_lane_s8(svint8_t data, uint8_t index)
{
// CHECK-LABEL: test_svdup_lane_s8
// CHECK: %[[DUP:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.tbl.nxv16i8(<vscale x 16 x i8> %data, <vscale x 16 x i8> %[[DUP]])
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_s8,,)(data, index);
}
svint16_t test_svdup_lane_s16(svint16_t data, uint16_t index)
{
// CHECK-LABEL: test_svdup_lane_s16
// CHECK: %[[DUP:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.tbl.nxv8i16(<vscale x 8 x i16> %data, <vscale x 8 x i16> %[[DUP]])
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_s16,,)(data, index);
}
svint32_t test_svdup_lane_s32(svint32_t data, uint32_t index)
{
// CHECK-LABEL: test_svdup_lane_s32
// CHECK: %[[DUP:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.tbl.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32> %[[DUP]])
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_s32,,)(data, index);
}
svint64_t test_svdup_lane_s64(svint64_t data, uint64_t index)
{
// CHECK-LABEL: test_svdup_lane_s64
// CHECK: %[[DUP:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.tbl.nxv2i64(<vscale x 2 x i64> %data, <vscale x 2 x i64> %[[DUP]])
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_s64,,)(data, index);
}
svuint8_t test_svdup_lane_u8(svuint8_t data, uint8_t index)
{
// CHECK-LABEL: test_svdup_lane_u8
// CHECK: %[[DUP:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.x.nxv16i8(i8 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 16 x i8> @llvm.aarch64.sve.tbl.nxv16i8(<vscale x 16 x i8> %data, <vscale x 16 x i8> %[[DUP]])
// CHECK: ret <vscale x 16 x i8> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_u8,,)(data, index);
}
svuint16_t test_svdup_lane_u16(svuint16_t data, uint16_t index)
{
// CHECK-LABEL: test_svdup_lane_u16
// CHECK: %[[DUP:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.tbl.nxv8i16(<vscale x 8 x i16> %data, <vscale x 8 x i16> %[[DUP]])
// CHECK: ret <vscale x 8 x i16> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_u16,,)(data, index);
}
svuint32_t test_svdup_lane_u32(svuint32_t data, uint32_t index)
{
// CHECK-LABEL: test_svdup_lane_u32
// CHECK: %[[DUP:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.tbl.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32> %[[DUP]])
// CHECK: ret <vscale x 4 x i32> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_u32,,)(data, index);
}
svuint64_t test_svdup_lane_u64(svuint64_t data, uint64_t index)
{
// CHECK-LABEL: test_svdup_lane_u64
// CHECK: %[[DUP:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.tbl.nxv2i64(<vscale x 2 x i64> %data, <vscale x 2 x i64> %[[DUP]])
// CHECK: ret <vscale x 2 x i64> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_u64,,)(data, index);
}
svfloat16_t test_svdup_lane_f16(svfloat16_t data, uint16_t index)
{
// CHECK-LABEL: test_svdup_lane_f16
// CHECK: %[[DUP:.*]] = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.x.nxv8i16(i16 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.tbl.nxv8f16(<vscale x 8 x half> %data, <vscale x 8 x i16> %[[DUP]])
// CHECK: ret <vscale x 8 x half> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_f16,,)(data, index);
}
svfloat32_t test_svdup_lane_f32(svfloat32_t data, uint32_t index)
{
// CHECK-LABEL: test_svdup_lane_f32
// CHECK: %[[DUP:.*]] = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.x.nxv4i32(i32 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.tbl.nxv4f32(<vscale x 4 x float> %data, <vscale x 4 x i32> %[[DUP]])
// CHECK: ret <vscale x 4 x float> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_f32,,)(data, index);
}
svfloat64_t test_svdup_lane_f64(svfloat64_t data, uint64_t index)
{
// CHECK-LABEL: test_svdup_lane_f64
// CHECK: %[[DUP:.*]] = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.x.nxv2i64(i64 %index)
// CHECK: %[[INTRINSIC:.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.tbl.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x i64> %[[DUP]])
// CHECK: ret <vscale x 2 x double> %[[INTRINSIC]]
return SVE_ACLE_FUNC(svdup_lane,_f64,,)(data, index);
}
svbool_t test_svdup_n_b8(bool op)
{
// CHECK-LABEL: test_svdup_n_b8
// CHECK: %[[DUP:.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.dup.x.nxv16i1(i1 %op)
// CHECK: ret <vscale x 16 x i1> %[[DUP]]
return SVE_ACLE_FUNC(svdup,_n,_b8,)(op);
}
svbool_t test_svdup_n_b16(bool op)
{
// CHECK-LABEL: test_svdup_n_b16
// CHECK: %[[DUP:.*]] = call <vscale x 8 x i1> @llvm.aarch64.sve.dup.x.nxv8i1(i1 %op)
// CHECK: %[[CVT:.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv8i1(<vscale x 8 x i1> %[[DUP]])
// CHECK: ret <vscale x 16 x i1> %[[CVT]]
return SVE_ACLE_FUNC(svdup,_n,_b16,)(op);
}
svbool_t test_svdup_n_b32(bool op)
{
// CHECK-LABEL: test_svdup_n_b32
// CHECK: %[[DUP:.*]] = call <vscale x 4 x i1> @llvm.aarch64.sve.dup.x.nxv4i1(i1 %op)
// CHECK: %[[CVT:.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv4i1(<vscale x 4 x i1> %[[DUP]])
// CHECK: ret <vscale x 16 x i1> %[[CVT]]
return SVE_ACLE_FUNC(svdup,_n,_b32,)(op);
}
svbool_t test_svdup_n_b64(bool op)
{
// CHECK-LABEL: test_svdup_n_b64
// CHECK: %[[DUP:.*]] = call <vscale x 2 x i1> @llvm.aarch64.sve.dup.x.nxv2i1(i1 %op)
// CHECK: %[[CVT:.*]] = call <vscale x 16 x i1> @llvm.aarch64.sve.convert.to.svbool.nxv2i1(<vscale x 2 x i1> %[[DUP]])
// CHECK: ret <vscale x 16 x i1> %[[CVT]]
return SVE_ACLE_FUNC(svdup,_n,_b64,)(op);
}