aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Headers/arm_acle.h
blob: 096cc261af2c62a51f92d820c040363830f63c3d (plain) (blame)
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
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
/*===---- arm_acle.h - ARM Non-Neon intrinsics -----------------------------===
 *
 * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 * See https://llvm.org/LICENSE.txt for license information.
 * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 *
 *===-----------------------------------------------------------------------===
 */

#ifndef __ARM_ACLE_H
#define __ARM_ACLE_H

#ifndef __ARM_ACLE
#error "ACLE intrinsics support not enabled."
#endif

#include <stdint.h>

#if defined(__cplusplus)
extern "C" {
#endif

/* 8 SYNCHRONIZATION, BARRIER AND HINT INTRINSICS */
/* 8.3 Memory barriers */
#if !defined(_MSC_VER)
#define __dmb(i) __builtin_arm_dmb(i)
#define __dsb(i) __builtin_arm_dsb(i)
#define __isb(i) __builtin_arm_isb(i)
#endif

/* 8.4 Hints */

#if !defined(_MSC_VER)
static __inline__ void __attribute__((__always_inline__, __nodebug__)) __wfi(void) {
  __builtin_arm_wfi();
}

static __inline__ void __attribute__((__always_inline__, __nodebug__)) __wfe(void) {
  __builtin_arm_wfe();
}

static __inline__ void __attribute__((__always_inline__, __nodebug__)) __sev(void) {
  __builtin_arm_sev();
}

static __inline__ void __attribute__((__always_inline__, __nodebug__)) __sevl(void) {
  __builtin_arm_sevl();
}

static __inline__ void __attribute__((__always_inline__, __nodebug__)) __yield(void) {
  __builtin_arm_yield();
}
#endif

#if __ARM_32BIT_STATE
#define __dbg(t) __builtin_arm_dbg(t)
#endif

/* 8.5 Swap */
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__swp(uint32_t __x, volatile uint32_t *__p) {
  uint32_t v;
  do
    v = __builtin_arm_ldrex(__p);
  while (__builtin_arm_strex(__x, __p));
  return v;
}

/* 8.6 Memory prefetch intrinsics */
/* 8.6.1 Data prefetch */
#define __pld(addr) __pldx(0, 0, 0, addr)

#if __ARM_32BIT_STATE
#define __pldx(access_kind, cache_level, retention_policy, addr) \
  __builtin_arm_prefetch(addr, access_kind, 1)
#else
#define __pldx(access_kind, cache_level, retention_policy, addr) \
  __builtin_arm_prefetch(addr, access_kind, cache_level, retention_policy, 1)
#endif

/* 8.6.2 Instruction prefetch */
#define __pli(addr) __plix(0, 0, addr)

#if __ARM_32BIT_STATE
#define __plix(cache_level, retention_policy, addr) \
  __builtin_arm_prefetch(addr, 0, 0)
#else
#define __plix(cache_level, retention_policy, addr) \
  __builtin_arm_prefetch(addr, 0, cache_level, retention_policy, 0)
#endif

/* 8.7 NOP */
static __inline__ void __attribute__((__always_inline__, __nodebug__)) __nop(void) {
  __builtin_arm_nop();
}

/* 9 DATA-PROCESSING INTRINSICS */
/* 9.2 Miscellaneous data-processing intrinsics */
/* ROR */
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__ror(uint32_t __x, uint32_t __y) {
  __y %= 32;
  if (__y == 0)
    return __x;
  return (__x >> __y) | (__x << (32 - __y));
}

static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
__rorll(uint64_t __x, uint32_t __y) {
  __y %= 64;
  if (__y == 0)
    return __x;
  return (__x >> __y) | (__x << (64 - __y));
}

static __inline__ unsigned long __attribute__((__always_inline__, __nodebug__))
__rorl(unsigned long __x, uint32_t __y) {
#if __SIZEOF_LONG__ == 4
  return __ror(__x, __y);
#else
  return __rorll(__x, __y);
#endif
}


/* CLZ */
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__clz(uint32_t __t) {
  return __builtin_clz(__t);
}

static __inline__ unsigned long __attribute__((__always_inline__, __nodebug__))
__clzl(unsigned long __t) {
  return __builtin_clzl(__t);
}

static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
__clzll(uint64_t __t) {
  return __builtin_clzll(__t);
}

/* REV */
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__rev(uint32_t __t) {
  return __builtin_bswap32(__t);
}

static __inline__ unsigned long __attribute__((__always_inline__, __nodebug__))
__revl(unsigned long __t) {
#if __SIZEOF_LONG__ == 4
  return __builtin_bswap32(__t);
#else
  return __builtin_bswap64(__t);
#endif
}

static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
__revll(uint64_t __t) {
  return __builtin_bswap64(__t);
}

/* REV16 */
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__rev16(uint32_t __t) {
  return __ror(__rev(__t), 16);
}

static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
__rev16ll(uint64_t __t) {
  return (((uint64_t)__rev16(__t >> 32)) << 32) | __rev16(__t);
}

static __inline__ unsigned long __attribute__((__always_inline__, __nodebug__))
__rev16l(unsigned long __t) {
#if __SIZEOF_LONG__ == 4
    return __rev16(__t);
#else
    return __rev16ll(__t);
#endif
}

/* REVSH */
static __inline__ int16_t __attribute__((__always_inline__, __nodebug__))
__revsh(int16_t __t) {
  return __builtin_bswap16(__t);
}

/* RBIT */
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__rbit(uint32_t __t) {
  return __builtin_arm_rbit(__t);
}

static __inline__ uint64_t __attribute__((__always_inline__, __nodebug__))
__rbitll(uint64_t __t) {
#if __ARM_32BIT_STATE
  return (((uint64_t)__builtin_arm_rbit(__t)) << 32) |
         __builtin_arm_rbit(__t >> 32);
#else
  return __builtin_arm_rbit64(__t);
#endif
}

static __inline__ unsigned long __attribute__((__always_inline__, __nodebug__))
__rbitl(unsigned long __t) {
#if __SIZEOF_LONG__ == 4
  return __rbit(__t);
#else
  return __rbitll(__t);
#endif
}

/*
 * 9.3 16-bit multiplications
 */
#if __ARM_FEATURE_DSP
static __inline__ int32_t __attribute__((__always_inline__,__nodebug__))
__smulbb(int32_t __a, int32_t __b) {
  return __builtin_arm_smulbb(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__,__nodebug__))
__smulbt(int32_t __a, int32_t __b) {
  return __builtin_arm_smulbt(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__,__nodebug__))
__smultb(int32_t __a, int32_t __b) {
  return __builtin_arm_smultb(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__,__nodebug__))
__smultt(int32_t __a, int32_t __b) {
  return __builtin_arm_smultt(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__,__nodebug__))
__smulwb(int32_t __a, int32_t __b) {
  return __builtin_arm_smulwb(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__,__nodebug__))
__smulwt(int32_t __a, int32_t __b) {
  return __builtin_arm_smulwt(__a, __b);
}
#endif

/*
 * 9.4 Saturating intrinsics
 *
 * FIXME: Change guard to their corrosponding __ARM_FEATURE flag when Q flag
 * intrinsics are implemented and the flag is enabled.
 */
/* 9.4.1 Width-specified saturation intrinsics */
#if __ARM_FEATURE_SAT
#define __ssat(x, y) __builtin_arm_ssat(x, y)
#define __usat(x, y) __builtin_arm_usat(x, y)
#endif

/* 9.4.2 Saturating addition and subtraction intrinsics */
#if __ARM_FEATURE_DSP
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__qadd(int32_t __t, int32_t __v) {
  return __builtin_arm_qadd(__t, __v);
}

static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__qsub(int32_t __t, int32_t __v) {
  return __builtin_arm_qsub(__t, __v);
}

static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__qdbl(int32_t __t) {
  return __builtin_arm_qadd(__t, __t);
}
#endif

/* 9.4.3 Accumultating multiplications */
#if __ARM_FEATURE_DSP
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlabb(int32_t __a, int32_t __b, int32_t __c) {
  return __builtin_arm_smlabb(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlabt(int32_t __a, int32_t __b, int32_t __c) {
  return __builtin_arm_smlabt(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlatb(int32_t __a, int32_t __b, int32_t __c) {
  return __builtin_arm_smlatb(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlatt(int32_t __a, int32_t __b, int32_t __c) {
  return __builtin_arm_smlatt(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlawb(int32_t __a, int32_t __b, int32_t __c) {
  return __builtin_arm_smlawb(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlawt(int32_t __a, int32_t __b, int32_t __c) {
  return __builtin_arm_smlawt(__a, __b, __c);
}
#endif


/* 9.5.4 Parallel 16-bit saturation */
#if __ARM_FEATURE_SIMD32
#define __ssat16(x, y) __builtin_arm_ssat16(x, y)
#define __usat16(x, y) __builtin_arm_usat16(x, y)
#endif

/* 9.5.5 Packing and unpacking */
#if __ARM_FEATURE_SIMD32
typedef int32_t int8x4_t;
typedef int32_t int16x2_t;
typedef uint32_t uint8x4_t;
typedef uint32_t uint16x2_t;

static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__sxtab16(int16x2_t __a, int8x4_t __b) {
  return __builtin_arm_sxtab16(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__sxtb16(int8x4_t __a) {
  return __builtin_arm_sxtb16(__a);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__uxtab16(int16x2_t __a, int8x4_t __b) {
  return __builtin_arm_uxtab16(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__uxtb16(int8x4_t __a) {
  return __builtin_arm_uxtb16(__a);
}
#endif

/* 9.5.6 Parallel selection */
#if __ARM_FEATURE_SIMD32
static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
__sel(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_sel(__a, __b);
}
#endif

/* 9.5.7 Parallel 8-bit addition and subtraction */
#if __ARM_FEATURE_SIMD32
static __inline__ int8x4_t __attribute__((__always_inline__, __nodebug__))
__qadd8(int8x4_t __a, int8x4_t __b) {
  return __builtin_arm_qadd8(__a, __b);
}
static __inline__ int8x4_t __attribute__((__always_inline__, __nodebug__))
__qsub8(int8x4_t __a, int8x4_t __b) {
  return __builtin_arm_qsub8(__a, __b);
}
static __inline__ int8x4_t __attribute__((__always_inline__, __nodebug__))
__sadd8(int8x4_t __a, int8x4_t __b) {
  return __builtin_arm_sadd8(__a, __b);
}
static __inline__ int8x4_t __attribute__((__always_inline__, __nodebug__))
__shadd8(int8x4_t __a, int8x4_t __b) {
  return __builtin_arm_shadd8(__a, __b);
}
static __inline__ int8x4_t __attribute__((__always_inline__, __nodebug__))
__shsub8(int8x4_t __a, int8x4_t __b) {
  return __builtin_arm_shsub8(__a, __b);
}
static __inline__ int8x4_t __attribute__((__always_inline__, __nodebug__))
__ssub8(int8x4_t __a, int8x4_t __b) {
  return __builtin_arm_ssub8(__a, __b);
}
static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
__uadd8(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_uadd8(__a, __b);
}
static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
__uhadd8(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_uhadd8(__a, __b);
}
static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
__uhsub8(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_uhsub8(__a, __b);
}
static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
__uqadd8(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_uqadd8(__a, __b);
}
static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
__uqsub8(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_uqsub8(__a, __b);
}
static __inline__ uint8x4_t __attribute__((__always_inline__, __nodebug__))
__usub8(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_usub8(__a, __b);
}
#endif

/* 9.5.8 Sum of 8-bit absolute differences */
#if __ARM_FEATURE_SIMD32
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__usad8(uint8x4_t __a, uint8x4_t __b) {
  return __builtin_arm_usad8(__a, __b);
}
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__usada8(uint8x4_t __a, uint8x4_t __b, uint32_t __c) {
  return __builtin_arm_usada8(__a, __b, __c);
}
#endif

/* 9.5.9 Parallel 16-bit addition and subtraction */
#if __ARM_FEATURE_SIMD32
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__qadd16(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_qadd16(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__qasx(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_qasx(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__qsax(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_qsax(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__qsub16(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_qsub16(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__sadd16(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_sadd16(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__sasx(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_sasx(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__shadd16(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_shadd16(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__shasx(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_shasx(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__shsax(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_shsax(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__shsub16(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_shsub16(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__ssax(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_ssax(__a, __b);
}
static __inline__ int16x2_t __attribute__((__always_inline__, __nodebug__))
__ssub16(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_ssub16(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uadd16(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uadd16(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uasx(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uasx(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uhadd16(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uhadd16(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uhasx(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uhasx(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uhsax(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uhsax(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uhsub16(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uhsub16(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uqadd16(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uqadd16(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uqasx(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uqasx(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uqsax(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uqsax(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__uqsub16(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_uqsub16(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__usax(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_usax(__a, __b);
}
static __inline__ uint16x2_t __attribute__((__always_inline__, __nodebug__))
__usub16(uint16x2_t __a, uint16x2_t __b) {
  return __builtin_arm_usub16(__a, __b);
}
#endif

/* 9.5.10 Parallel 16-bit multiplications */
#if __ARM_FEATURE_SIMD32
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlad(int16x2_t __a, int16x2_t __b, int32_t __c) {
  return __builtin_arm_smlad(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smladx(int16x2_t __a, int16x2_t __b, int32_t __c) {
  return __builtin_arm_smladx(__a, __b, __c);
}
static __inline__ int64_t __attribute__((__always_inline__, __nodebug__))
__smlald(int16x2_t __a, int16x2_t __b, int64_t __c) {
  return __builtin_arm_smlald(__a, __b, __c);
}
static __inline__ int64_t __attribute__((__always_inline__, __nodebug__))
__smlaldx(int16x2_t __a, int16x2_t __b, int64_t __c) {
  return __builtin_arm_smlaldx(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlsd(int16x2_t __a, int16x2_t __b, int32_t __c) {
  return __builtin_arm_smlsd(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smlsdx(int16x2_t __a, int16x2_t __b, int32_t __c) {
  return __builtin_arm_smlsdx(__a, __b, __c);
}
static __inline__ int64_t __attribute__((__always_inline__, __nodebug__))
__smlsld(int16x2_t __a, int16x2_t __b, int64_t __c) {
  return __builtin_arm_smlsld(__a, __b, __c);
}
static __inline__ int64_t __attribute__((__always_inline__, __nodebug__))
__smlsldx(int16x2_t __a, int16x2_t __b, int64_t __c) {
  return __builtin_arm_smlsldx(__a, __b, __c);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smuad(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_smuad(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smuadx(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_smuadx(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smusd(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_smusd(__a, __b);
}
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__smusdx(int16x2_t __a, int16x2_t __b) {
  return __builtin_arm_smusdx(__a, __b);
}
#endif

/* 9.7 CRC32 intrinsics */
#if __ARM_FEATURE_CRC32
static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32b(uint32_t __a, uint8_t __b) {
  return __builtin_arm_crc32b(__a, __b);
}

static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32h(uint32_t __a, uint16_t __b) {
  return __builtin_arm_crc32h(__a, __b);
}

static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32w(uint32_t __a, uint32_t __b) {
  return __builtin_arm_crc32w(__a, __b);
}

static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32d(uint32_t __a, uint64_t __b) {
  return __builtin_arm_crc32d(__a, __b);
}

static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32cb(uint32_t __a, uint8_t __b) {
  return __builtin_arm_crc32cb(__a, __b);
}

static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32ch(uint32_t __a, uint16_t __b) {
  return __builtin_arm_crc32ch(__a, __b);
}

static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32cw(uint32_t __a, uint32_t __b) {
  return __builtin_arm_crc32cw(__a, __b);
}

static __inline__ uint32_t __attribute__((__always_inline__, __nodebug__))
__crc32cd(uint32_t __a, uint64_t __b) {
  return __builtin_arm_crc32cd(__a, __b);
}
#endif

/* Armv8.3-A Javascript conversion intrinsic */
#if __ARM_64BIT_STATE && defined(__ARM_FEATURE_JCVT)
static __inline__ int32_t __attribute__((__always_inline__, __nodebug__))
__jcvt(double __a) {
  return __builtin_arm_jcvt(__a);
}
#endif

/* 10.1 Special register intrinsics */
#define __arm_rsr(sysreg) __builtin_arm_rsr(sysreg)
#define __arm_rsr64(sysreg) __builtin_arm_rsr64(sysreg)
#define __arm_rsrp(sysreg) __builtin_arm_rsrp(sysreg)
#define __arm_wsr(sysreg, v) __builtin_arm_wsr(sysreg, v)
#define __arm_wsr64(sysreg, v) __builtin_arm_wsr64(sysreg, v)
#define __arm_wsrp(sysreg, v) __builtin_arm_wsrp(sysreg, v)

// Memory Tagging Extensions (MTE) Intrinsics
#if __ARM_FEATURE_MEMORY_TAGGING
#define __arm_mte_create_random_tag(__ptr, __mask)  __builtin_arm_irg(__ptr, __mask)
#define __arm_mte_increment_tag(__ptr, __tag_offset)  __builtin_arm_addg(__ptr, __tag_offset)
#define __arm_mte_exclude_tag(__ptr, __excluded)  __builtin_arm_gmi(__ptr, __excluded)
#define __arm_mte_get_tag(__ptr) __builtin_arm_ldg(__ptr)
#define __arm_mte_set_tag(__ptr) __builtin_arm_stg(__ptr)
#define __arm_mte_ptrdiff(__ptra, __ptrb) __builtin_arm_subp(__ptra, __ptrb)
#endif

#if defined(__cplusplus)
}
#endif

#endif /* __ARM_ACLE_H */