Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

  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
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
/*===---- tmmintrin.h - SSSE3 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 __TMMINTRIN_H
#define __TMMINTRIN_H

#include <pmmintrin.h>

/* Define the default attributes for the functions in this file. */
#define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("ssse3"), __min_vector_width__(64)))
#define __DEFAULT_FN_ATTRS_MMX __attribute__((__always_inline__, __nodebug__, __target__("mmx,ssse3"), __min_vector_width__(64)))

/// Computes the absolute value of each of the packed 8-bit signed
///    integers in the source operand and stores the 8-bit unsigned integer
///    results in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PABSB instruction.
///
/// \param __a
///    A 64-bit vector of [8 x i8].
/// \returns A 64-bit integer vector containing the absolute values of the
///    elements in the operand.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_abs_pi8(__m64 __a)
{
    return (__m64)__builtin_ia32_pabsb((__v8qi)__a);
}

/// Computes the absolute value of each of the packed 8-bit signed
///    integers in the source operand and stores the 8-bit unsigned integer
///    results in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPABSB instruction.
///
/// \param __a
///    A 128-bit vector of [16 x i8].
/// \returns A 128-bit integer vector containing the absolute values of the
///    elements in the operand.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_abs_epi8(__m128i __a)
{
    return (__m128i)__builtin_ia32_pabsb128((__v16qi)__a);
}

/// Computes the absolute value of each of the packed 16-bit signed
///    integers in the source operand and stores the 16-bit unsigned integer
///    results in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PABSW instruction.
///
/// \param __a
///    A 64-bit vector of [4 x i16].
/// \returns A 64-bit integer vector containing the absolute values of the
///    elements in the operand.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_abs_pi16(__m64 __a)
{
    return (__m64)__builtin_ia32_pabsw((__v4hi)__a);
}

/// Computes the absolute value of each of the packed 16-bit signed
///    integers in the source operand and stores the 16-bit unsigned integer
///    results in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPABSW instruction.
///
/// \param __a
///    A 128-bit vector of [8 x i16].
/// \returns A 128-bit integer vector containing the absolute values of the
///    elements in the operand.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_abs_epi16(__m128i __a)
{
    return (__m128i)__builtin_ia32_pabsw128((__v8hi)__a);
}

/// Computes the absolute value of each of the packed 32-bit signed
///    integers in the source operand and stores the 32-bit unsigned integer
///    results in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PABSD instruction.
///
/// \param __a
///    A 64-bit vector of [2 x i32].
/// \returns A 64-bit integer vector containing the absolute values of the
///    elements in the operand.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_abs_pi32(__m64 __a)
{
    return (__m64)__builtin_ia32_pabsd((__v2si)__a);
}

/// Computes the absolute value of each of the packed 32-bit signed
///    integers in the source operand and stores the 32-bit unsigned integer
///    results in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPABSD instruction.
///
/// \param __a
///    A 128-bit vector of [4 x i32].
/// \returns A 128-bit integer vector containing the absolute values of the
///    elements in the operand.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_abs_epi32(__m128i __a)
{
    return (__m128i)__builtin_ia32_pabsd128((__v4si)__a);
}

/// Concatenates the two 128-bit integer vector operands, and
///    right-shifts the result by the number of bytes specified in the immediate
///    operand.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// __m128i _mm_alignr_epi8(__m128i a, __m128i b, const int n);
/// \endcode
///
/// This intrinsic corresponds to the \c PALIGNR instruction.
///
/// \param a
///    A 128-bit vector of [16 x i8] containing one of the source operands.
/// \param b
///    A 128-bit vector of [16 x i8] containing one of the source operands.
/// \param n
///    An immediate operand specifying how many bytes to right-shift the result.
/// \returns A 128-bit integer vector containing the concatenated right-shifted
///    value.
#define _mm_alignr_epi8(a, b, n) \
  (__m128i)__builtin_ia32_palignr128((__v16qi)(__m128i)(a), \
                                     (__v16qi)(__m128i)(b), (n))

/// Concatenates the two 64-bit integer vector operands, and right-shifts
///    the result by the number of bytes specified in the immediate operand.
///
/// \headerfile <x86intrin.h>
///
/// \code
/// __m64 _mm_alignr_pi8(__m64 a, __m64 b, const int n);
/// \endcode
///
/// This intrinsic corresponds to the \c PALIGNR instruction.
///
/// \param a
///    A 64-bit vector of [8 x i8] containing one of the source operands.
/// \param b
///    A 64-bit vector of [8 x i8] containing one of the source operands.
/// \param n
///    An immediate operand specifying how many bytes to right-shift the result.
/// \returns A 64-bit integer vector containing the concatenated right-shifted
///    value.
#define _mm_alignr_pi8(a, b, n) \
  (__m64)__builtin_ia32_palignr((__v8qi)(__m64)(a), (__v8qi)(__m64)(b), (n))

/// Horizontally adds the adjacent pairs of values contained in 2 packed
///    128-bit vectors of [8 x i16].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPHADDW instruction.
///
/// \param __a
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the lower bits of the
///    destination.
/// \param __b
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the upper bits of the
///    destination.
/// \returns A 128-bit vector of [8 x i16] containing the horizontal sums of
///    both operands.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_hadd_epi16(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_phaddw128((__v8hi)__a, (__v8hi)__b);
}

/// Horizontally adds the adjacent pairs of values contained in 2 packed
///    128-bit vectors of [4 x i32].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPHADDD instruction.
///
/// \param __a
///    A 128-bit vector of [4 x i32] containing one of the source operands. The
///    horizontal sums of the values are stored in the lower bits of the
///    destination.
/// \param __b
///    A 128-bit vector of [4 x i32] containing one of the source operands. The
///    horizontal sums of the values are stored in the upper bits of the
///    destination.
/// \returns A 128-bit vector of [4 x i32] containing the horizontal sums of
///    both operands.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_hadd_epi32(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_phaddd128((__v4si)__a, (__v4si)__b);
}

/// Horizontally adds the adjacent pairs of values contained in 2 packed
///    64-bit vectors of [4 x i16].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PHADDW instruction.
///
/// \param __a
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the lower bits of the
///    destination.
/// \param __b
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the upper bits of the
///    destination.
/// \returns A 64-bit vector of [4 x i16] containing the horizontal sums of both
///    operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_hadd_pi16(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_phaddw((__v4hi)__a, (__v4hi)__b);
}

/// Horizontally adds the adjacent pairs of values contained in 2 packed
///    64-bit vectors of [2 x i32].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PHADDD instruction.
///
/// \param __a
///    A 64-bit vector of [2 x i32] containing one of the source operands. The
///    horizontal sums of the values are stored in the lower bits of the
///    destination.
/// \param __b
///    A 64-bit vector of [2 x i32] containing one of the source operands. The
///    horizontal sums of the values are stored in the upper bits of the
///    destination.
/// \returns A 64-bit vector of [2 x i32] containing the horizontal sums of both
///    operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_hadd_pi32(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_phaddd((__v2si)__a, (__v2si)__b);
}

/// Horizontally adds the adjacent pairs of values contained in 2 packed
///    128-bit vectors of [8 x i16]. Positive sums greater than 0x7FFF are
///    saturated to 0x7FFF. Negative sums less than 0x8000 are saturated to
///    0x8000.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPHADDSW instruction.
///
/// \param __a
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the lower bits of the
///    destination.
/// \param __b
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the upper bits of the
///    destination.
/// \returns A 128-bit vector of [8 x i16] containing the horizontal saturated
///    sums of both operands.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_hadds_epi16(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_phaddsw128((__v8hi)__a, (__v8hi)__b);
}

/// Horizontally adds the adjacent pairs of values contained in 2 packed
///    64-bit vectors of [4 x i16]. Positive sums greater than 0x7FFF are
///    saturated to 0x7FFF. Negative sums less than 0x8000 are saturated to
///    0x8000.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PHADDSW instruction.
///
/// \param __a
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the lower bits of the
///    destination.
/// \param __b
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal sums of the values are stored in the upper bits of the
///    destination.
/// \returns A 64-bit vector of [4 x i16] containing the horizontal saturated
///    sums of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_hadds_pi16(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_phaddsw((__v4hi)__a, (__v4hi)__b);
}

/// Horizontally subtracts the adjacent pairs of values contained in 2
///    packed 128-bit vectors of [8 x i16].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPHSUBW instruction.
///
/// \param __a
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the lower bits of
///    the destination.
/// \param __b
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the upper bits of
///    the destination.
/// \returns A 128-bit vector of [8 x i16] containing the horizontal differences
///    of both operands.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_hsub_epi16(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_phsubw128((__v8hi)__a, (__v8hi)__b);
}

/// Horizontally subtracts the adjacent pairs of values contained in 2
///    packed 128-bit vectors of [4 x i32].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPHSUBD instruction.
///
/// \param __a
///    A 128-bit vector of [4 x i32] containing one of the source operands. The
///    horizontal differences between the values are stored in the lower bits of
///    the destination.
/// \param __b
///    A 128-bit vector of [4 x i32] containing one of the source operands. The
///    horizontal differences between the values are stored in the upper bits of
///    the destination.
/// \returns A 128-bit vector of [4 x i32] containing the horizontal differences
///    of both operands.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_hsub_epi32(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_phsubd128((__v4si)__a, (__v4si)__b);
}

/// Horizontally subtracts the adjacent pairs of values contained in 2
///    packed 64-bit vectors of [4 x i16].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PHSUBW instruction.
///
/// \param __a
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the lower bits of
///    the destination.
/// \param __b
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the upper bits of
///    the destination.
/// \returns A 64-bit vector of [4 x i16] containing the horizontal differences
///    of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_hsub_pi16(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_phsubw((__v4hi)__a, (__v4hi)__b);
}

/// Horizontally subtracts the adjacent pairs of values contained in 2
///    packed 64-bit vectors of [2 x i32].
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PHSUBD instruction.
///
/// \param __a
///    A 64-bit vector of [2 x i32] containing one of the source operands. The
///    horizontal differences between the values are stored in the lower bits of
///    the destination.
/// \param __b
///    A 64-bit vector of [2 x i32] containing one of the source operands. The
///    horizontal differences between the values are stored in the upper bits of
///    the destination.
/// \returns A 64-bit vector of [2 x i32] containing the horizontal differences
///    of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_hsub_pi32(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_phsubd((__v2si)__a, (__v2si)__b);
}

/// Horizontally subtracts the adjacent pairs of values contained in 2
///    packed 128-bit vectors of [8 x i16]. Positive differences greater than
///    0x7FFF are saturated to 0x7FFF. Negative differences less than 0x8000 are
///    saturated to 0x8000.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPHSUBSW instruction.
///
/// \param __a
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the lower bits of
///    the destination.
/// \param __b
///    A 128-bit vector of [8 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the upper bits of
///    the destination.
/// \returns A 128-bit vector of [8 x i16] containing the horizontal saturated
///    differences of both operands.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_hsubs_epi16(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_phsubsw128((__v8hi)__a, (__v8hi)__b);
}

/// Horizontally subtracts the adjacent pairs of values contained in 2
///    packed 64-bit vectors of [4 x i16]. Positive differences greater than
///    0x7FFF are saturated to 0x7FFF. Negative differences less than 0x8000 are
///    saturated to 0x8000.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PHSUBSW instruction.
///
/// \param __a
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the lower bits of
///    the destination.
/// \param __b
///    A 64-bit vector of [4 x i16] containing one of the source operands. The
///    horizontal differences between the values are stored in the upper bits of
///    the destination.
/// \returns A 64-bit vector of [4 x i16] containing the horizontal saturated
///    differences of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_hsubs_pi16(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_phsubsw((__v4hi)__a, (__v4hi)__b);
}

/// Multiplies corresponding pairs of packed 8-bit unsigned integer
///    values contained in the first source operand and packed 8-bit signed
///    integer values contained in the second source operand, adds pairs of
///    contiguous products with signed saturation, and writes the 16-bit sums to
///    the corresponding bits in the destination.
///
///    For example, bits [7:0] of both operands are multiplied, bits [15:8] of
///    both operands are multiplied, and the sum of both results is written to
///    bits [15:0] of the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPMADDUBSW instruction.
///
/// \param __a
///    A 128-bit integer vector containing the first source operand.
/// \param __b
///    A 128-bit integer vector containing the second source operand.
/// \returns A 128-bit integer vector containing the sums of products of both
///    operands: \n
///    \a R0 := (\a __a0 * \a __b0) + (\a __a1 * \a __b1) \n
///    \a R1 := (\a __a2 * \a __b2) + (\a __a3 * \a __b3) \n
///    \a R2 := (\a __a4 * \a __b4) + (\a __a5 * \a __b5) \n
///    \a R3 := (\a __a6 * \a __b6) + (\a __a7 * \a __b7) \n
///    \a R4 := (\a __a8 * \a __b8) + (\a __a9 * \a __b9) \n
///    \a R5 := (\a __a10 * \a __b10) + (\a __a11 * \a __b11) \n
///    \a R6 := (\a __a12 * \a __b12) + (\a __a13 * \a __b13) \n
///    \a R7 := (\a __a14 * \a __b14) + (\a __a15 * \a __b15)
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_maddubs_epi16(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_pmaddubsw128((__v16qi)__a, (__v16qi)__b);
}

/// Multiplies corresponding pairs of packed 8-bit unsigned integer
///    values contained in the first source operand and packed 8-bit signed
///    integer values contained in the second source operand, adds pairs of
///    contiguous products with signed saturation, and writes the 16-bit sums to
///    the corresponding bits in the destination.
///
///    For example, bits [7:0] of both operands are multiplied, bits [15:8] of
///    both operands are multiplied, and the sum of both results is written to
///    bits [15:0] of the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PMADDUBSW instruction.
///
/// \param __a
///    A 64-bit integer vector containing the first source operand.
/// \param __b
///    A 64-bit integer vector containing the second source operand.
/// \returns A 64-bit integer vector containing the sums of products of both
///    operands: \n
///    \a R0 := (\a __a0 * \a __b0) + (\a __a1 * \a __b1) \n
///    \a R1 := (\a __a2 * \a __b2) + (\a __a3 * \a __b3) \n
///    \a R2 := (\a __a4 * \a __b4) + (\a __a5 * \a __b5) \n
///    \a R3 := (\a __a6 * \a __b6) + (\a __a7 * \a __b7)
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_maddubs_pi16(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_pmaddubsw((__v8qi)__a, (__v8qi)__b);
}

/// Multiplies packed 16-bit signed integer values, truncates the 32-bit
///    products to the 18 most significant bits by right-shifting, rounds the
///    truncated value by adding 1, and writes bits [16:1] to the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPMULHRSW instruction.
///
/// \param __a
///    A 128-bit vector of [8 x i16] containing one of the source operands.
/// \param __b
///    A 128-bit vector of [8 x i16] containing one of the source operands.
/// \returns A 128-bit vector of [8 x i16] containing the rounded and scaled
///    products of both operands.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_mulhrs_epi16(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_pmulhrsw128((__v8hi)__a, (__v8hi)__b);
}

/// Multiplies packed 16-bit signed integer values, truncates the 32-bit
///    products to the 18 most significant bits by right-shifting, rounds the
///    truncated value by adding 1, and writes bits [16:1] to the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PMULHRSW instruction.
///
/// \param __a
///    A 64-bit vector of [4 x i16] containing one of the source operands.
/// \param __b
///    A 64-bit vector of [4 x i16] containing one of the source operands.
/// \returns A 64-bit vector of [4 x i16] containing the rounded and scaled
///    products of both operands.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_mulhrs_pi16(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_pmulhrsw((__v4hi)__a, (__v4hi)__b);
}

/// Copies the 8-bit integers from a 128-bit integer vector to the
///    destination or clears 8-bit values in the destination, as specified by
///    the second source operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPSHUFB instruction.
///
/// \param __a
///    A 128-bit integer vector containing the values to be copied.
/// \param __b
///    A 128-bit integer vector containing control bytes corresponding to
///    positions in the destination:
///    Bit 7: \n
///    1: Clear the corresponding byte in the destination. \n
///    0: Copy the selected source byte to the corresponding byte in the
///    destination. \n
///    Bits [6:4] Reserved.  \n
///    Bits [3:0] select the source byte to be copied.
/// \returns A 128-bit integer vector containing the copied or cleared values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_shuffle_epi8(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_pshufb128((__v16qi)__a, (__v16qi)__b);
}

/// Copies the 8-bit integers from a 64-bit integer vector to the
///    destination or clears 8-bit values in the destination, as specified by
///    the second source operand.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PSHUFB instruction.
///
/// \param __a
///    A 64-bit integer vector containing the values to be copied.
/// \param __b
///    A 64-bit integer vector containing control bytes corresponding to
///    positions in the destination:
///    Bit 7: \n
///    1: Clear the corresponding byte in the destination. \n
///    0: Copy the selected source byte to the corresponding byte in the
///    destination. \n
///    Bits [3:0] select the source byte to be copied.
/// \returns A 64-bit integer vector containing the copied or cleared values.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_shuffle_pi8(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_pshufb((__v8qi)__a, (__v8qi)__b);
}

/// For each 8-bit integer in the first source operand, perform one of
///    the following actions as specified by the second source operand.
///
///    If the byte in the second source is negative, calculate the two's
///    complement of the corresponding byte in the first source, and write that
///    value to the destination. If the byte in the second source is positive,
///    copy the corresponding byte from the first source to the destination. If
///    the byte in the second source is zero, clear the corresponding byte in
///    the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPSIGNB instruction.
///
/// \param __a
///    A 128-bit integer vector containing the values to be copied.
/// \param __b
///    A 128-bit integer vector containing control bytes corresponding to
///    positions in the destination.
/// \returns A 128-bit integer vector containing the resultant values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_sign_epi8(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_psignb128((__v16qi)__a, (__v16qi)__b);
}

/// For each 16-bit integer in the first source operand, perform one of
///    the following actions as specified by the second source operand.
///
///    If the word in the second source is negative, calculate the two's
///    complement of the corresponding word in the first source, and write that
///    value to the destination. If the word in the second source is positive,
///    copy the corresponding word from the first source to the destination. If
///    the word in the second source is zero, clear the corresponding word in
///    the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPSIGNW instruction.
///
/// \param __a
///    A 128-bit integer vector containing the values to be copied.
/// \param __b
///    A 128-bit integer vector containing control words corresponding to
///    positions in the destination.
/// \returns A 128-bit integer vector containing the resultant values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_sign_epi16(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_psignw128((__v8hi)__a, (__v8hi)__b);
}

/// For each 32-bit integer in the first source operand, perform one of
///    the following actions as specified by the second source operand.
///
///    If the doubleword in the second source is negative, calculate the two's
///    complement of the corresponding word in the first source, and write that
///    value to the destination. If the doubleword in the second source is
///    positive, copy the corresponding word from the first source to the
///    destination. If the doubleword in the second source is zero, clear the
///    corresponding word in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c VPSIGND instruction.
///
/// \param __a
///    A 128-bit integer vector containing the values to be copied.
/// \param __b
///    A 128-bit integer vector containing control doublewords corresponding to
///    positions in the destination.
/// \returns A 128-bit integer vector containing the resultant values.
static __inline__ __m128i __DEFAULT_FN_ATTRS
_mm_sign_epi32(__m128i __a, __m128i __b)
{
    return (__m128i)__builtin_ia32_psignd128((__v4si)__a, (__v4si)__b);
}

/// For each 8-bit integer in the first source operand, perform one of
///    the following actions as specified by the second source operand.
///
///    If the byte in the second source is negative, calculate the two's
///    complement of the corresponding byte in the first source, and write that
///    value to the destination. If the byte in the second source is positive,
///    copy the corresponding byte from the first source to the destination. If
///    the byte in the second source is zero, clear the corresponding byte in
///    the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PSIGNB instruction.
///
/// \param __a
///    A 64-bit integer vector containing the values to be copied.
/// \param __b
///    A 64-bit integer vector containing control bytes corresponding to
///    positions in the destination.
/// \returns A 64-bit integer vector containing the resultant values.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_sign_pi8(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_psignb((__v8qi)__a, (__v8qi)__b);
}

/// For each 16-bit integer in the first source operand, perform one of
///    the following actions as specified by the second source operand.
///
///    If the word in the second source is negative, calculate the two's
///    complement of the corresponding word in the first source, and write that
///    value to the destination. If the word in the second source is positive,
///    copy the corresponding word from the first source to the destination. If
///    the word in the second source is zero, clear the corresponding word in
///    the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PSIGNW instruction.
///
/// \param __a
///    A 64-bit integer vector containing the values to be copied.
/// \param __b
///    A 64-bit integer vector containing control words corresponding to
///    positions in the destination.
/// \returns A 64-bit integer vector containing the resultant values.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_sign_pi16(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_psignw((__v4hi)__a, (__v4hi)__b);
}

/// For each 32-bit integer in the first source operand, perform one of
///    the following actions as specified by the second source operand.
///
///    If the doubleword in the second source is negative, calculate the two's
///    complement of the corresponding doubleword in the first source, and
///    write that value to the destination. If the doubleword in the second
///    source is positive, copy the corresponding doubleword from the first
///    source to the destination. If the doubleword in the second source is
///    zero, clear the corresponding doubleword in the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the \c PSIGND instruction.
///
/// \param __a
///    A 64-bit integer vector containing the values to be copied.
/// \param __b
///    A 64-bit integer vector containing two control doublewords corresponding
///    to positions in the destination.
/// \returns A 64-bit integer vector containing the resultant values.
static __inline__ __m64 __DEFAULT_FN_ATTRS_MMX
_mm_sign_pi32(__m64 __a, __m64 __b)
{
    return (__m64)__builtin_ia32_psignd((__v2si)__a, (__v2si)__b);
}

#undef __DEFAULT_FN_ATTRS
#undef __DEFAULT_FN_ATTRS_MMX

#endif /* __TMMINTRIN_H */