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
|
/* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person
* obtaining a copy of this software and associated documentation
* files (the "Software"), to deal in the Software without
* restriction, including without limitation the rights to use, copy,
* modify, merge, publish, distribute, sublicense, and/or sell copies
* of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be
* included in all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
* Copyright:
* 2020 Evan Nemerson <evan@nemerson.com>
* 2020 Sean Maher <seanptmaher@gmail.com> (Copyright owned by Google, LLC)
*/
#if !defined(SIMDE_ARM_NEON_TRN2_H)
#define SIMDE_ARM_NEON_TRN2_H
#include "types.h"
HEDLEY_DIAGNOSTIC_PUSH
SIMDE_DISABLE_UNWANTED_DIAGNOSTICS
SIMDE_BEGIN_DECLS_
SIMDE_FUNCTION_ATTRIBUTES
simde_float32x2_t
simde_vtrn2_f32(simde_float32x2_t a, simde_float32x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2_f32(a, b);
#else
simde_float32x2_private
r_,
a_ = simde_float32x2_to_private(a),
b_ = simde_float32x2_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_float32x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2_f32
#define vtrn2_f32(a, b) simde_vtrn2_f32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int8x8_t
simde_vtrn2_s8(simde_int8x8_t a, simde_int8x8_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2_s8(a, b);
#else
simde_int8x8_private
r_,
a_ = simde_int8x8_to_private(a),
b_ = simde_int8x8_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_int8x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2_s8
#define vtrn2_s8(a, b) simde_vtrn2_s8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int16x4_t
simde_vtrn2_s16(simde_int16x4_t a, simde_int16x4_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2_s16(a, b);
#else
simde_int16x4_private
r_,
a_ = simde_int16x4_to_private(a),
b_ = simde_int16x4_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_int16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2_s16
#define vtrn2_s16(a, b) simde_vtrn2_s16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int32x2_t
simde_vtrn2_s32(simde_int32x2_t a, simde_int32x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2_s32(a, b);
#else
simde_int32x2_private
r_,
a_ = simde_int32x2_to_private(a),
b_ = simde_int32x2_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_int32x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2_s32
#define vtrn2_s32(a, b) simde_vtrn2_s32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint8x8_t
simde_vtrn2_u8(simde_uint8x8_t a, simde_uint8x8_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2_u8(a, b);
#else
simde_uint8x8_private
r_,
a_ = simde_uint8x8_to_private(a),
b_ = simde_uint8x8_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_uint8x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2_u8
#define vtrn2_u8(a, b) simde_vtrn2_u8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint16x4_t
simde_vtrn2_u16(simde_uint16x4_t a, simde_uint16x4_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2_u16(a, b);
#else
simde_uint16x4_private
r_,
a_ = simde_uint16x4_to_private(a),
b_ = simde_uint16x4_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_uint16x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2_u16
#define vtrn2_u16(a, b) simde_vtrn2_u16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint32x2_t
simde_vtrn2_u32(simde_uint32x2_t a, simde_uint32x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2_u32(a, b);
#else
simde_uint32x2_private
r_,
a_ = simde_uint32x2_to_private(a),
b_ = simde_uint32x2_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_uint32x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2_u32
#define vtrn2_u32(a, b) simde_vtrn2_u32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_float32x4_t
simde_vtrn2q_f32(simde_float32x4_t a, simde_float32x4_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_f32(a, b);
#else
simde_float32x4_private
r_,
a_ = simde_float32x4_to_private(a),
b_ = simde_float32x4_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_float32x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_f32
#define vtrn2q_f32(a, b) simde_vtrn2q_f32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_float64x2_t
simde_vtrn2q_f64(simde_float64x2_t a, simde_float64x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_f64(a, b);
#else
simde_float64x2_private
r_,
a_ = simde_float64x2_to_private(a),
b_ = simde_float64x2_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_float64x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_f64
#define vtrn2q_f64(a, b) simde_vtrn2q_f64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int8x16_t
simde_vtrn2q_s8(simde_int8x16_t a, simde_int8x16_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_s8(a, b);
#else
simde_int8x16_private
r_,
a_ = simde_int8x16_to_private(a),
b_ = simde_int8x16_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_int8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_s8
#define vtrn2q_s8(a, b) simde_vtrn2q_s8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int16x8_t
simde_vtrn2q_s16(simde_int16x8_t a, simde_int16x8_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_s16(a, b);
#else
simde_int16x8_private
r_,
a_ = simde_int16x8_to_private(a),
b_ = simde_int16x8_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_int16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_s16
#define vtrn2q_s16(a, b) simde_vtrn2q_s16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int32x4_t
simde_vtrn2q_s32(simde_int32x4_t a, simde_int32x4_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_s32(a, b);
#else
simde_int32x4_private
r_,
a_ = simde_int32x4_to_private(a),
b_ = simde_int32x4_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_int32x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_s32
#define vtrn2q_s32(a, b) simde_vtrn2q_s32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_int64x2_t
simde_vtrn2q_s64(simde_int64x2_t a, simde_int64x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_s64(a, b);
#else
simde_int64x2_private
r_,
a_ = simde_int64x2_to_private(a),
b_ = simde_int64x2_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_int64x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_s64
#define vtrn2q_s64(a, b) simde_vtrn2q_s64((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint8x16_t
simde_vtrn2q_u8(simde_uint8x16_t a, simde_uint8x16_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_u8(a, b);
#else
simde_uint8x16_private
r_,
a_ = simde_uint8x16_to_private(a),
b_ = simde_uint8x16_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_uint8x16_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_u8
#define vtrn2q_u8(a, b) simde_vtrn2q_u8((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint16x8_t
simde_vtrn2q_u16(simde_uint16x8_t a, simde_uint16x8_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_u16(a, b);
#else
simde_uint16x8_private
r_,
a_ = simde_uint16x8_to_private(a),
b_ = simde_uint16x8_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_uint16x8_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_u16
#define vtrn2q_u16(a, b) simde_vtrn2q_u16((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint32x4_t
simde_vtrn2q_u32(simde_uint32x4_t a, simde_uint32x4_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_u32(a, b);
#else
simde_uint32x4_private
r_,
a_ = simde_uint32x4_to_private(a),
b_ = simde_uint32x4_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_uint32x4_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_u32
#define vtrn2q_u32(a, b) simde_vtrn2q_u32((a), (b))
#endif
SIMDE_FUNCTION_ATTRIBUTES
simde_uint64x2_t
simde_vtrn2q_u64(simde_uint64x2_t a, simde_uint64x2_t b) {
#if defined(SIMDE_ARM_NEON_A64V8_NATIVE)
return vtrn2q_u64(a, b);
#else
simde_uint64x2_private
r_,
a_ = simde_uint64x2_to_private(a),
b_ = simde_uint64x2_to_private(b);
const size_t halfway_point = sizeof(r_.values) / sizeof(r_.values[0]) / 2;
SIMDE_VECTORIZE
for (size_t i = 0 ; i < halfway_point ; i++) {
const size_t idx = i << 1;
r_.values[idx] = a_.values[idx | 1];
r_.values[idx | 1] = b_.values[idx | 1];
}
return simde_uint64x2_from_private(r_);
#endif
}
#if defined(SIMDE_ARM_NEON_A64V8_ENABLE_NATIVE_ALIASES)
#undef vtrn2q_u64
#define vtrn2q_u64(a, b) simde_vtrn2q_u64((a), (b))
#endif
SIMDE_END_DECLS_
HEDLEY_DIAGNOSTIC_POP
#endif /* !defined(SIMDE_ARM_NEON_TRN2_H) */
|
