aboutsummaryrefslogtreecommitdiff
path: root/Drivers/CMSIS/Include/core_cmSimd.h
blob: ee58eee56dd773194d453098a7f632aabf9610c0 (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
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
/**************************************************************************//**
 * @file     core_cmSimd.h
 * @brief    CMSIS Cortex-M SIMD Header File
 * @version  V4.00
 * @date     22. August 2014
 *
 * @note
 *
 ******************************************************************************/
/* Copyright (c) 2009 - 2014 ARM LIMITED

   All rights reserved.
   Redistribution and use in source and binary forms, with or without
   modification, are permitted provided that the following conditions are met:
   - Redistributions of source code must retain the above copyright
     notice, this list of conditions and the following disclaimer.
   - Redistributions in binary form must reproduce the above copyright
     notice, this list of conditions and the following disclaimer in the
     documentation and/or other materials provided with the distribution.
   - Neither the name of ARM nor the names of its contributors may be used
     to endorse or promote products derived from this software without
     specific prior written permission.
   *
   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
   AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
   IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
   ARE DISCLAIMED. IN NO EVENT SHALL COPYRIGHT HOLDERS AND CONTRIBUTORS BE
   LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
   CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
   SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
   INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
   CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
   ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
   POSSIBILITY OF SUCH DAMAGE.
   ---------------------------------------------------------------------------*/


#if defined ( __ICCARM__ )
 #pragma system_include  /* treat file as system include file for MISRA check */
#endif

#ifndef __CORE_CMSIMD_H
#define __CORE_CMSIMD_H

#ifdef __cplusplus
 extern "C" {
#endif


/*******************************************************************************
 *                Hardware Abstraction Layer
 ******************************************************************************/


/* ###################  Compiler specific Intrinsics  ########################### */
/** \defgroup CMSIS_SIMD_intrinsics CMSIS SIMD Intrinsics
  Access to dedicated SIMD instructions
  @{
*/

#if   defined ( __CC_ARM ) /*------------------RealView Compiler -----------------*/
/* ARM armcc specific functions */
#define __SADD8                           __sadd8
#define __QADD8                           __qadd8
#define __SHADD8                          __shadd8
#define __UADD8                           __uadd8
#define __UQADD8                          __uqadd8
#define __UHADD8                          __uhadd8
#define __SSUB8                           __ssub8
#define __QSUB8                           __qsub8
#define __SHSUB8                          __shsub8
#define __USUB8                           __usub8
#define __UQSUB8                          __uqsub8
#define __UHSUB8                          __uhsub8
#define __SADD16                          __sadd16
#define __QADD16                          __qadd16
#define __SHADD16                         __shadd16
#define __UADD16                          __uadd16
#define __UQADD16                         __uqadd16
#define __UHADD16                         __uhadd16
#define __SSUB16                          __ssub16
#define __QSUB16                          __qsub16
#define __SHSUB16                         __shsub16
#define __USUB16                          __usub16
#define __UQSUB16                         __uqsub16
#define __UHSUB16                         __uhsub16
#define __SASX                            __sasx
#define __QASX                            __qasx
#define __SHASX                           __shasx
#define __UASX                            __uasx
#define __UQASX                           __uqasx
#define __UHASX                           __uhasx
#define __SSAX                            __ssax
#define __QSAX                            __qsax
#define __SHSAX                           __shsax
#define __USAX                            __usax
#define __UQSAX                           __uqsax
#define __UHSAX                           __uhsax
#define __USAD8                           __usad8
#define __USADA8                          __usada8
#define __SSAT16                          __ssat16
#define __USAT16                          __usat16
#define __UXTB16                          __uxtb16
#define __UXTAB16                         __uxtab16
#define __SXTB16                          __sxtb16
#define __SXTAB16                         __sxtab16
#define __SMUAD                           __smuad
#define __SMUADX                          __smuadx
#define __SMLAD                           __smlad
#define __SMLADX                          __smladx
#define __SMLALD                          __smlald
#define __SMLALDX                         __smlaldx
#define __SMUSD                           __smusd
#define __SMUSDX                          __smusdx
#define __SMLSD                           __smlsd
#define __SMLSDX                          __smlsdx
#define __SMLSLD                          __smlsld
#define __SMLSLDX                         __smlsldx
#define __SEL                             __sel
#define __QADD                            __qadd
#define __QSUB                            __qsub

#define __PKHBT(ARG1,ARG2,ARG3)          ( ((((uint32_t)(ARG1))          ) & 0x0000FFFFUL) |  \
                                           ((((uint32_t)(ARG2)) << (ARG3)) & 0xFFFF0000UL)  )

#define __PKHTB(ARG1,ARG2,ARG3)          ( ((((uint32_t)(ARG1))          ) & 0xFFFF0000UL) |  \
                                           ((((uint32_t)(ARG2)) >> (ARG3)) & 0x0000FFFFUL)  )

#define __SMMLA(ARG1,ARG2,ARG3)          ( (int32_t)((((int64_t)(ARG1) * (ARG2)) + \
                                                      ((int64_t)(ARG3) << 32)      ) >> 32))


#elif defined ( __GNUC__ ) /*------------------ GNU Compiler ---------------------*/
/* GNU gcc specific functions */
__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SADD8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("sadd8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QADD8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qadd8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SHADD8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("shadd8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UADD8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uadd8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UQADD8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uqadd8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UHADD8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uhadd8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}


__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SSUB8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("ssub8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QSUB8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qsub8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SHSUB8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("shsub8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __USUB8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("usub8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UQSUB8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uqsub8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UHSUB8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uhsub8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}


__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SADD16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("sadd16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QADD16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qadd16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SHADD16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("shadd16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UADD16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uadd16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UQADD16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uqadd16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UHADD16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uhadd16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SSUB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("ssub16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QSUB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qsub16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SHSUB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("shsub16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __USUB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("usub16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UQSUB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uqsub16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UHSUB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uhsub16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SASX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("sasx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QASX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qasx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SHASX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("shasx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UASX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uasx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UQASX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uqasx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UHASX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uhasx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SSAX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("ssax %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QSAX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qsax %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SHSAX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("shsax %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __USAX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("usax %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UQSAX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uqsax %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UHSAX(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uhsax %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __USAD8(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("usad8 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __USADA8(uint32_t op1, uint32_t op2, uint32_t op3)
{
  uint32_t result;

  __ASM volatile ("usada8 %0, %1, %2, %3" : "=r" (result) : "r" (op1), "r" (op2), "r" (op3) );
  return(result);
}

#define __SSAT16(ARG1,ARG2) \
({                          \
  uint32_t __RES, __ARG1 = (ARG1); \
  __ASM ("ssat16 %0, %1, %2" : "=r" (__RES) :  "I" (ARG2), "r" (__ARG1) ); \
  __RES; \
 })

#define __USAT16(ARG1,ARG2) \
({                          \
  uint32_t __RES, __ARG1 = (ARG1); \
  __ASM ("usat16 %0, %1, %2" : "=r" (__RES) :  "I" (ARG2), "r" (__ARG1) ); \
  __RES; \
 })

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UXTB16(uint32_t op1)
{
  uint32_t result;

  __ASM volatile ("uxtb16 %0, %1" : "=r" (result) : "r" (op1));
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __UXTAB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("uxtab16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SXTB16(uint32_t op1)
{
  uint32_t result;

  __ASM volatile ("sxtb16 %0, %1" : "=r" (result) : "r" (op1));
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SXTAB16(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("sxtab16 %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMUAD  (uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("smuad %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMUADX (uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("smuadx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMLAD (uint32_t op1, uint32_t op2, uint32_t op3)
{
  uint32_t result;

  __ASM volatile ("smlad %0, %1, %2, %3" : "=r" (result) : "r" (op1), "r" (op2), "r" (op3) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMLADX (uint32_t op1, uint32_t op2, uint32_t op3)
{
  uint32_t result;

  __ASM volatile ("smladx %0, %1, %2, %3" : "=r" (result) : "r" (op1), "r" (op2), "r" (op3) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint64_t __SMLALD (uint32_t op1, uint32_t op2, uint64_t acc)
{
  union llreg_u{
    uint32_t w32[2];
    uint64_t w64;
  } llr;
  llr.w64 = acc;

#ifndef __ARMEB__   // Little endian
  __ASM volatile ("smlald %0, %1, %2, %3" : "=r" (llr.w32[0]), "=r" (llr.w32[1]): "r" (op1), "r" (op2) , "0" (llr.w32[0]), "1" (llr.w32[1]) );
#else               // Big endian
  __ASM volatile ("smlald %0, %1, %2, %3" : "=r" (llr.w32[1]), "=r" (llr.w32[0]): "r" (op1), "r" (op2) , "0" (llr.w32[1]), "1" (llr.w32[0]) );
#endif

  return(llr.w64);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint64_t __SMLALDX (uint32_t op1, uint32_t op2, uint64_t acc)
{
  union llreg_u{
    uint32_t w32[2];
    uint64_t w64;
  } llr;
  llr.w64 = acc;

#ifndef __ARMEB__   // Little endian
  __ASM volatile ("smlaldx %0, %1, %2, %3" : "=r" (llr.w32[0]), "=r" (llr.w32[1]): "r" (op1), "r" (op2) , "0" (llr.w32[0]), "1" (llr.w32[1]) );
#else               // Big endian
  __ASM volatile ("smlaldx %0, %1, %2, %3" : "=r" (llr.w32[1]), "=r" (llr.w32[0]): "r" (op1), "r" (op2) , "0" (llr.w32[1]), "1" (llr.w32[0]) );
#endif

  return(llr.w64);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMUSD  (uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("smusd %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMUSDX (uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("smusdx %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMLSD (uint32_t op1, uint32_t op2, uint32_t op3)
{
  uint32_t result;

  __ASM volatile ("smlsd %0, %1, %2, %3" : "=r" (result) : "r" (op1), "r" (op2), "r" (op3) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMLSDX (uint32_t op1, uint32_t op2, uint32_t op3)
{
  uint32_t result;

  __ASM volatile ("smlsdx %0, %1, %2, %3" : "=r" (result) : "r" (op1), "r" (op2), "r" (op3) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint64_t __SMLSLD (uint32_t op1, uint32_t op2, uint64_t acc)
{
  union llreg_u{
    uint32_t w32[2];
    uint64_t w64;
  } llr;
  llr.w64 = acc;

#ifndef __ARMEB__   // Little endian
  __ASM volatile ("smlsld %0, %1, %2, %3" : "=r" (llr.w32[0]), "=r" (llr.w32[1]): "r" (op1), "r" (op2) , "0" (llr.w32[0]), "1" (llr.w32[1]) );
#else               // Big endian
  __ASM volatile ("smlsld %0, %1, %2, %3" : "=r" (llr.w32[1]), "=r" (llr.w32[0]): "r" (op1), "r" (op2) , "0" (llr.w32[1]), "1" (llr.w32[0]) );
#endif

  return(llr.w64);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint64_t __SMLSLDX (uint32_t op1, uint32_t op2, uint64_t acc)
{
  union llreg_u{
    uint32_t w32[2];
    uint64_t w64;
  } llr;
  llr.w64 = acc;

#ifndef __ARMEB__   // Little endian
  __ASM volatile ("smlsldx %0, %1, %2, %3" : "=r" (llr.w32[0]), "=r" (llr.w32[1]): "r" (op1), "r" (op2) , "0" (llr.w32[0]), "1" (llr.w32[1]) );
#else               // Big endian
  __ASM volatile ("smlsldx %0, %1, %2, %3" : "=r" (llr.w32[1]), "=r" (llr.w32[0]): "r" (op1), "r" (op2) , "0" (llr.w32[1]), "1" (llr.w32[0]) );
#endif

  return(llr.w64);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SEL  (uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("sel %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QADD(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qadd %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __QSUB(uint32_t op1, uint32_t op2)
{
  uint32_t result;

  __ASM volatile ("qsub %0, %1, %2" : "=r" (result) : "r" (op1), "r" (op2) );
  return(result);
}

#define __PKHBT(ARG1,ARG2,ARG3) \
({                          \
  uint32_t __RES, __ARG1 = (ARG1), __ARG2 = (ARG2); \
  __ASM ("pkhbt %0, %1, %2, lsl %3" : "=r" (__RES) :  "r" (__ARG1), "r" (__ARG2), "I" (ARG3)  ); \
  __RES; \
 })

#define __PKHTB(ARG1,ARG2,ARG3) \
({                          \
  uint32_t __RES, __ARG1 = (ARG1), __ARG2 = (ARG2); \
  if (ARG3 == 0) \
    __ASM ("pkhtb %0, %1, %2" : "=r" (__RES) :  "r" (__ARG1), "r" (__ARG2)  ); \
  else \
    __ASM ("pkhtb %0, %1, %2, asr %3" : "=r" (__RES) :  "r" (__ARG1), "r" (__ARG2), "I" (ARG3)  ); \
  __RES; \
 })

__attribute__( ( always_inline ) ) __STATIC_INLINE uint32_t __SMMLA (int32_t op1, int32_t op2, int32_t op3)
{
 int32_t result;

 __ASM volatile ("smmla %0, %1, %2, %3" : "=r" (result): "r"  (op1), "r" (op2), "r" (op3) );
 return(result);
}


#elif defined ( __ICCARM__ ) /*------------------ ICC Compiler -------------------*/
/* IAR iccarm specific functions */
#include <cmsis_iar.h>


#elif defined ( __TMS470__ ) /*---------------- TI CCS Compiler ------------------*/
/* TI CCS specific functions */
#include <cmsis_ccs.h>


#elif defined ( __TASKING__ ) /*------------------ TASKING Compiler --------------*/
/* TASKING carm specific functions */
/* not yet supported */


#elif defined ( __CSMC__ ) /*------------------ COSMIC Compiler -------------------*/
/* Cosmic specific functions */
#include <cmsis_csm.h>

#endif

/*@} end of group CMSIS_SIMD_intrinsics */


#ifdef __cplusplus
}
#endif

#endif /* __CORE_CMSIMD_H */