aboutsummaryrefslogtreecommitdiffstats
path: root/libswscale/bfin/internal_bfin.S
blob: 5ea0f1f90e08e6a099e35de9c873a6ad2a60dc9e (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
/*
 * Copyright (C) 2007 Marc Hoffman <marc.hoffman@analog.com>
 *                    April 20, 2007
 *
 * Blackfin video color space converter operations
 * convert I420 YV12 to RGB in various formats
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */


/*
YUV420 to RGB565 conversion. This routine takes a YUV 420 planar macroblock
and converts it to RGB565. R:5 bits, G:6 bits, B:5 bits.. packed into shorts.


The following calculation is used for the conversion:

  r = clipz((y - oy) * cy  + crv * (v - 128))
  g = clipz((y - oy) * cy  + cgv * (v - 128) + cgu * (u - 128))
  b = clipz((y - oy) * cy  + cbu * (u - 128))

y, u, v are prescaled by a factor of 4 i.e. left-shifted to gain precision.


New factorization to eliminate the truncation error which was
occurring due to the byteop3p.


1) Use the bytop16m to subtract quad bytes we use this in U8 this
 then so the offsets need to be renormalized to 8bits.

2) Scale operands up by a factor of 4 not 8 because Blackfin
   multiplies include a shift.

3) Compute into the accumulators cy * yx0, cy * yx1.

4) Compute each of the linear equations:
     r = clipz((y - oy) * cy  + crv * (v - 128))

     g = clipz((y - oy) * cy  + cgv * (v - 128) + cgu * (u - 128))

     b = clipz((y - oy) * cy  + cbu * (u - 128))

   Reuse of the accumulators requires that we actually multiply
   twice once with addition and the second time with a subtraction.

   Because of this we need to compute the equations in the order R B
   then G saving the writes for B in the case of 24/32 bit color
   formats.

   API: yuv2rgb_kind (uint8_t *Y, uint8_t *U, uint8_t *V, int *out,
                      int dW, uint32_t *coeffs);

       A          B
       ---        ---
       i2 = cb    i3 = cr
       i1 = coeff i0 = y

Where coeffs have the following layout in memory.

uint32_t oy, oc, zero, cy, crv, rmask, cbu, bmask, cgu, cgv;

coeffs is a pointer to oy.

The {rgb} masks are only utilized by the 565 packing algorithm. Note the data
replication is used to simplify the internal algorithms for the dual Mac
architecture of BlackFin.

All routines are exported with _ff_bfin_ as a symbol prefix.

Rough performance gain compared against -O3:

2779809/1484290 187.28%

which translates to ~33c/pel to ~57c/pel for the reference vs 17.5
c/pel for the optimized implementations. Not sure why there is such a
huge variation on the reference codes on Blackfin I guess it must have
to do with the memory system.
*/

#include "libavutil/bfin/asm.h"

#define MEM mL1


.text

#define COEFF_LEN        11*4
#define COEFF_REL_CY_OFF 4*4

#define ARG_OUT   20
#define ARG_W     24
#define ARG_COEFF 28

DEFUN(yuv2rgb565_line,MEM,
   (uint8_t *Y, uint8_t *U, uint8_t *V, int *out, int dW, uint32_t *coeffs)):
        link 0;
        [--sp] = (r7:4);
        p1 = [fp+ARG_OUT];
        r3 = [fp+ARG_W];

        i0 = r0;
        i2 = r1;
        i3 = r2;

        r0 = [fp+ARG_COEFF];
        i1 = r0;
        b1 = i1;
        l1 = COEFF_LEN;
        m0 = COEFF_REL_CY_OFF;
        p0 = r3;

        r0   = [i0++];         // 2Y
        r1.l = w[i2++];        // 2u
        r1.h = w[i3++];        // 2v
        p0 = p0>>2;

        lsetup (.L0565, .L1565) lc0 = p0;

        /*
           uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv
           r0 -- used to load 4ys
           r1 -- used to load 2us,2vs
           r4 -- y3,y2
           r5 -- y1,y0
           r6 -- u1,u0
           r7 -- v1,v0
        */
                                                              r2=[i1++]; // oy
.L0565:
        /*
        rrrrrrrr gggggggg bbbbbbbb
         5432109876543210
                    bbbbb >>3
              gggggggg    <<3
         rrrrrrrr         <<8
         rrrrrggggggbbbbb
        */
        (r4,r5) = byteop16m (r1:0, r3:2)                   || r3=[i1++]; // oc
        (r7,r6) = byteop16m (r1:0, r3:2) (r);
        r5 = r5 << 2 (v);                                                // y1,y0
        r4 = r4 << 2 (v);                                                // y3,y2
        r6 = r6 << 2 (v)                                   || r0=[i1++]; // u1,u0, r0=zero
        r7 = r7 << 2 (v)                                   || r1=[i1++]; // v1,v0  r1=cy
        /* Y' = y*cy */
        a1 = r1.h*r5.h, a0 = r1.l*r5.l                     || r1=[i1++]; // crv

        /* R = Y+ crv*(Cr-128) */
        r2.h = (a1 += r1.h*r7.l), r2.l = (a0 += r1.l*r7.l);
                a1 -= r1.h*r7.l,          a0 -= r1.l*r7.l  || r5=[i1++]; // rmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cbu
        r2 = r2 >> 3 (v);
        r3 = r2 & r5;

        /* B = Y+ cbu*(Cb-128) */
        r2.h = (a1 += r1.h*r6.l), r2.l = (a0 += r1.l*r6.l);
                a1 -= r1.h*r6.l,          a0 -= r1.l*r6.l  || r5=[i1++]; // bmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cgu
        r2 = r2 << 8 (v);
        r2 = r2 & r5;
        r3 = r3 | r2;

        /* G = Y+ cgu*(Cb-128)+cgv*(Cr-128) */
                a1 += r1.h*r6.l,          a0 += r1.l*r6.l  || r1=[i1++]; // cgv
        r2.h = (a1 += r1.h*r7.l), r2.l = (a0 += r1.l*r7.l);
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r5=[i1++m0]; // gmask
        r2 = r2 << 3 (v);
        r2 = r2 & r5;
        r3 = r3 | r2;
        [p1++]=r3                                          || r1=[i1++]; // cy

        /* Y' = y*cy */

        a1 = r1.h*r4.h, a0 = r1.l*r4.l                     || r1=[i1++]; // crv

        /* R = Y+ crv*(Cr-128) */
        r2.h = (a1 += r1.h*r7.h), r2.l = (a0 += r1.l*r7.h);
                a1 -= r1.h*r7.h,          a0 -= r1.l*r7.h  || r5=[i1++]; // rmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cbu
        r2 = r2 >> 3 (v);
        r3 = r2 & r5;

        /* B = Y+ cbu*(Cb-128) */
        r2.h = (a1 += r1.h*r6.h), r2.l = (a0 += r1.l*r6.h);
                a1 -= r1.h*r6.h,          a0 -= r1.l*r6.h  || r5=[i1++]; // bmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cgu
        r2 = r2 << 8 (v);
        r2 = r2 & r5;
        r3 = r3 | r2;

        /* G = Y+ cgu*(Cb-128)+cgv*(Cr-128) */
                a1 += r1.h*r6.h,          a0 += r1.l*r6.h  || r1=[i1++]; // cgv
        r2.h = (a1 += r1.h*r7.h), r2.l = (a0 += r1.l*r7.h) || r5=[i1++]; // gmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r0   =  [i0++];        // 2Y
        r2 = r2 << 3 (v)                                   || r1.l = w[i2++];        // 2u
        r2 = r2 & r5;
        r3 = r3 | r2;
        [p1++]=r3                                          || r1.h = w[i3++];        // 2v
.L1565:                                                       r2=[i1++]; // oy

        l1 = 0;

        (r7:4) = [sp++];
        unlink;
        rts;
DEFUN_END(yuv2rgb565_line)

DEFUN(yuv2rgb555_line,MEM,
   (uint8_t *Y, uint8_t *U, uint8_t *V, int *out, int dW, uint32_t *coeffs)):
        link 0;
        [--sp] = (r7:4);
        p1 = [fp+ARG_OUT];
        r3 = [fp+ARG_W];

        i0 = r0;
        i2 = r1;
        i3 = r2;

        r0 = [fp+ARG_COEFF];
        i1 = r0;
        b1 = i1;
        l1 = COEFF_LEN;
        m0 = COEFF_REL_CY_OFF;
        p0 = r3;

        r0   = [i0++];         // 2Y
        r1.l = w[i2++];        // 2u
        r1.h = w[i3++];        // 2v
        p0 = p0>>2;

        lsetup (.L0555, .L1555) lc0 = p0;

        /*
           uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv
           r0 -- used to load 4ys
           r1 -- used to load 2us,2vs
           r4 -- y3,y2
           r5 -- y1,y0
           r6 -- u1,u0
           r7 -- v1,v0
        */
                                                              r2=[i1++]; // oy
.L0555:
        /*
        rrrrrrrr gggggggg bbbbbbbb
         5432109876543210
                    bbbbb >>3
               gggggggg   <<2
          rrrrrrrr        <<7
         xrrrrrgggggbbbbb
        */

        (r4,r5) = byteop16m (r1:0, r3:2)                   || r3=[i1++]; // oc
        (r7,r6) = byteop16m (r1:0, r3:2) (r);
        r5 = r5 << 2 (v);                                                // y1,y0
        r4 = r4 << 2 (v);                                                // y3,y2
        r6 = r6 << 2 (v)                                   || r0=[i1++]; // u1,u0, r0=zero
        r7 = r7 << 2 (v)                                   || r1=[i1++]; // v1,v0  r1=cy
        /* Y' = y*cy */
        a1 = r1.h*r5.h, a0 = r1.l*r5.l                     || r1=[i1++]; // crv

        /* R = Y+ crv*(Cr-128) */
        r2.h = (a1 += r1.h*r7.l), r2.l = (a0 += r1.l*r7.l);
                a1 -= r1.h*r7.l,          a0 -= r1.l*r7.l  || r5=[i1++]; // rmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cbu
        r2 = r2 >> 3 (v);
        r3 = r2 & r5;

        /* B = Y+ cbu*(Cb-128) */
        r2.h = (a1 += r1.h*r6.l), r2.l = (a0 += r1.l*r6.l);
                a1 -= r1.h*r6.l,          a0 -= r1.l*r6.l  || r5=[i1++]; // bmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cgu
        r2 = r2 << 7 (v);
        r2 = r2 & r5;
        r3 = r3 | r2;

        /* G = Y+ cgu*(Cb-128)+cgv*(Cr-128) */
                a1 += r1.h*r6.l,          a0 += r1.l*r6.l  || r1=[i1++]; // cgv
        r2.h = (a1 += r1.h*r7.l), r2.l = (a0 += r1.l*r7.l);
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r5=[i1++m0]; // gmask
        r2 = r2 << 2 (v);
        r2 = r2 & r5;
        r3 = r3 | r2;
        [p1++]=r3                                          || r1=[i1++]; // cy

        /* Y' = y*cy */

        a1 = r1.h*r4.h, a0 = r1.l*r4.l                     || r1=[i1++]; // crv

        /* R = Y+ crv*(Cr-128) */
        r2.h = (a1 += r1.h*r7.h), r2.l = (a0 += r1.l*r7.h);
                a1 -= r1.h*r7.h,          a0 -= r1.l*r7.h  || r5=[i1++]; // rmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cbu
        r2 = r2 >> 3 (v);
        r3 = r2 & r5;

        /* B = Y+ cbu*(Cb-128) */
        r2.h = (a1 += r1.h*r6.h), r2.l = (a0 += r1.l*r6.h);
                a1 -= r1.h*r6.h,          a0 -= r1.l*r6.h  || r5=[i1++]; // bmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cgu
        r2 = r2 << 7 (v);
        r2 = r2 & r5;
        r3 = r3 | r2;

        /* G = Y+ cgu*(Cb-128)+cgv*(Cr-128) */
                a1 += r1.h*r6.h,          a0 += r1.l*r6.h  || r1=[i1++]; // cgv
        r2.h = (a1 += r1.h*r7.h), r2.l = (a0 += r1.l*r7.h) || r5=[i1++]; // gmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r0=[i0++];     // 4Y
        r2 = r2 << 2 (v)                                   || r1.l=w[i2++];  // 2u
        r2 = r2 & r5;
        r3 = r3 | r2;
        [p1++]=r3                                          || r1.h=w[i3++]; // 2v

.L1555:                                                       r2=[i1++]; // oy

        l1 = 0;

        (r7:4) = [sp++];
        unlink;
        rts;
DEFUN_END(yuv2rgb555_line)

DEFUN(yuv2rgb24_line,MEM,
   (uint8_t *Y, uint8_t *U, uint8_t *V, int *out, int dW, uint32_t *coeffs)):
        link 0;
        [--sp] = (r7:4);
        p1 = [fp+ARG_OUT];
        r3 = [fp+ARG_W];
        p2 = p1;
        p2 += 3;

        i0 = r0;
        i2 = r1;
        i3 = r2;

        r0 = [fp+ARG_COEFF]; // coeff buffer
        i1 = r0;
        b1 = i1;
        l1 = COEFF_LEN;
        m0 = COEFF_REL_CY_OFF;
        p0 = r3;

        r0   = [i0++];         // 2Y
        r1.l = w[i2++];        // 2u
        r1.h = w[i3++];        // 2v
        p0 = p0>>2;

        lsetup (.L0888, .L1888) lc0 = p0;

        /*
           uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv
           r0 -- used to load 4ys
           r1 -- used to load 2us,2vs
           r4 -- y3,y2
           r5 -- y1,y0
           r6 -- u1,u0
           r7 -- v1,v0
        */
                                                              r2=[i1++]; // oy
.L0888:
        (r4,r5) = byteop16m (r1:0, r3:2)                   || r3=[i1++]; // oc
        (r7,r6) = byteop16m (r1:0, r3:2) (r);
        r5 = r5 << 2 (v);               // y1,y0
        r4 = r4 << 2 (v);               // y3,y2
        r6 = r6 << 2 (v) || r0=[i1++];  // u1,u0, r0=zero
        r7 = r7 << 2 (v) || r1=[i1++];  // v1,v0  r1=cy

        /* Y' = y*cy */
        a1 = r1.h*r5.h, a0 = r1.l*r5.l                     || r1=[i1++]; // crv

        /* R = Y+ crv*(Cr-128) */
        r2.h = (a1 += r1.h*r7.l), r2.l = (a0 += r1.l*r7.l);
                a1 -= r1.h*r7.l,          a0 -= r1.l*r7.l  || r5=[i1++]; // rmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cbu
        r2=r2>>16 || B[p1++]=r2;
                     B[p2++]=r2;

        /* B = Y+ cbu*(Cb-128) */
        r2.h = (a1 += r1.h*r6.l), r2.l = (a0 += r1.l*r6.l);
                a1 -= r1.h*r6.l,          a0 -= r1.l*r6.l  || r5=[i1++]; // bmask
        r3 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cgu

        /* G = Y+ cgu*(Cb-128)+cgv*(Cr-128) */
                a1 += r1.h*r6.l,          a0 += r1.l*r6.l  || r1=[i1++]; // cgv
        r2.h = (a1 += r1.h*r7.l), r2.l = (a0 += r1.l*r7.l);
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r5=[i1++m0]; // gmask, oy,cy,zero

        r2=r2>>16 || B[p1++]=r2;
                     B[p2++]=r2;

        r3=r3>>16 || B[p1++]=r3;
                     B[p2++]=r3                            || r1=[i1++]; // cy

        p1+=3;
        p2+=3;
        /* Y' = y*cy */
        a1 = r1.h*r4.h, a0 = r1.l*r4.l                     || r1=[i1++]; // crv

        /* R = Y+ crv*(Cr-128) */
        r2.h = (a1 += r1.h*r7.h), r2.l = (a0 += r1.l*r7.h);
                a1 -= r1.h*r7.h,          a0 -= r1.l*r7.h  || r5=[i1++]; // rmask
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cbu
        r2=r2>>16 || B[p1++]=r2;
        B[p2++]=r2;

        /* B = Y+ cbu*(Cb-128) */
        r2.h = (a1 += r1.h*r6.h), r2.l = (a0 += r1.l*r6.h);
                a1 -= r1.h*r6.h,          a0 -= r1.l*r6.h  || r5=[i1++]; // bmask
        r3 = byteop3p(r3:2, r1:0)(LO)                      || r1=[i1++]; // cgu

        /* G = Y+ cgu*(Cb-128)+cgv*(Cr-128) */
                a1 += r1.h*r6.h,          a0 += r1.l*r6.h  || r1=[i1++]; // cgv
        r2.h = (a1 += r1.h*r7.h), r2.l = (a0 += r1.l*r7.h);
        r2 = byteop3p(r3:2, r1:0)(LO)                      || r5=[i1++]; // gmask
        r2=r2>>16 || B[p1++]=r2 || r0 = [i0++];    // 4y
                     B[p2++]=r2 || r1.l = w[i2++]; // 2u
        r3=r3>>16 || B[p1++]=r3 || r1.h = w[i3++]; // 2v
                     B[p2++]=r3 || r2=[i1++];      // oy

        p1+=3;
.L1888: p2+=3;

        l1 = 0;

        (r7:4) = [sp++];
        unlink;
        rts;
DEFUN_END(yuv2rgb24_line)



#define ARG_vdst        20
#define ARG_width       24
#define ARG_height      28
#define ARG_lumStride   32
#define ARG_chromStride 36
#define ARG_srcStride   40

DEFUN(uyvytoyv12, mL3,  (const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
                         int width, int height,
                         int lumStride, int chromStride, int srcStride)):
        link 0;
        [--sp] = (r7:4,p5:4);

        p0 = r1;       // Y top even

        i2 = r2; // *u
        r2 = [fp + ARG_vdst];
        i3 = r2; // *v

        r1 = [fp + ARG_srcStride];
        r2 = r0 + r1;
        i0 = r0;  // uyvy_T even
        i1 = r2;  // uyvy_B odd

        p2 = [fp + ARG_lumStride];
        p1 = p0 + p2;  // Y bot odd

        p5 = [fp + ARG_width];
        p4 = [fp + ARG_height];
        r0 = p5;
        p4 = p4 >> 1;
        p5 = p5 >> 2;

        r2 = r0 << 1;
        r1 = r1 << 1;
        r1 = r1 - r2;  // srcStride + (srcStride - 2*width)
        r1 += -8;  // i0,i1 is pre read need to correct
        m0 = r1;

        r2 = [fp + ARG_chromStride];
        r0 = r0 >> 1;
        r2 = r2 - r0;
        m1 = r2;

        /*   I0,I1 - src input line pointers
         *   p0,p1 - luma output line pointers
         *   I2    - dstU
         *   I3    - dstV
         */

        lsetup (0f, 1f) lc1 = p4;   // H/2
0:        r0 = [i0++] || r2 = [i1++];
          r1 = [i0++] || r3 = [i1++];
          r4 = byteop1p(r1:0, r3:2);
          r5 = byteop1p(r1:0, r3:2) (r);
          lsetup (2f, 3f) lc0 = p5; // W/4
2:          r0 = r0 >> 8(v);
            r1 = r1 >> 8(v);
            r2 = r2 >> 8(v);
            r3 = r3 >> 8(v);
            r0 = bytepack(r0, r1);
            r2 = bytepack(r2, r3)         ||  [p0++] = r0;    // yyyy
            r6 = pack(r5.l, r4.l)         ||  [p1++] = r2;    // yyyy
            r7 = pack(r5.h, r4.h)         ||  r0 = [i0++] || r2 = [i1++];
            r6 = bytepack(r6, r7)         ||  r1 = [i0++] || r3 = [i1++];
            r4 = byteop1p(r1:0, r3:2)     ||  w[i2++] = r6.l; // uu
3:          r5 = byteop1p(r1:0, r3:2) (r) ||  w[i3++] = r6.h; // vv

          i0 += m0;
          i1 += m0;
          i2 += m1;
          i3 += m1;
          p0 = p0 + p2;
1:        p1 = p1 + p2;

        (r7:4,p5:4) = [sp++];
        unlink;
        rts;
DEFUN_END(uyvytoyv12)

DEFUN(yuyvtoyv12, mL3,  (const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
                         int width, int height,
                         int lumStride, int chromStride, int srcStride)):
        link 0;
        [--sp] = (r7:4,p5:4);

        p0 = r1;       // Y top even

        i2 = r2; // *u
        r2 = [fp + ARG_vdst];
        i3 = r2; // *v

        r1 = [fp + ARG_srcStride];
        r2 = r0 + r1;

        i0 = r0;  // uyvy_T even
        i1 = r2;  // uyvy_B odd

        p2 = [fp + ARG_lumStride];
        p1 = p0 + p2;  // Y bot odd

        p5 = [fp + ARG_width];
        p4 = [fp + ARG_height];
        r0 = p5;
        p4 = p4 >> 1;
        p5 = p5 >> 2;

        r2 = r0 << 1;
        r1 = r1 << 1;
        r1 = r1 - r2;  // srcStride + (srcStride - 2*width)
        r1 += -8;  // i0,i1 is pre read need to correct
        m0 = r1;

        r2 = [fp + ARG_chromStride];
        r0 = r0 >> 1;
        r2 = r2 - r0;
        m1 = r2;

        /*   I0,I1 - src input line pointers
         *   p0,p1 - luma output line pointers
         *   I2    - dstU
         *   I3    - dstV
         */

        lsetup (0f, 1f) lc1 = p4;   // H/2
0:        r0 = [i0++] || r2 = [i1++];
          r1 = [i0++] || r3 = [i1++];
          r4 = bytepack(r0, r1);
          r5 = bytepack(r2, r3);
          lsetup (2f, 3f) lc0 = p5; // W/4
2:          r0 = r0 >> 8(v) || [p0++] = r4;  // yyyy-even
            r1 = r1 >> 8(v) || [p1++] = r5;  // yyyy-odd
            r2 = r2 >> 8(v);
            r3 = r3 >> 8(v);
            r4 = byteop1p(r1:0, r3:2);
            r5 = byteop1p(r1:0, r3:2) (r);
            r6 = pack(r5.l, r4.l);
            r7 = pack(r5.h, r4.h)         ||  r0 = [i0++] || r2 = [i1++];
            r6 = bytepack(r6, r7)         ||  r1 = [i0++] || r3 = [i1++];
            r4 = bytepack(r0, r1)         ||  w[i2++] = r6.l; // uu
3:          r5 = bytepack(r2, r3)         ||  w[i3++] = r6.h; // vv

          i0 += m0;
          i1 += m0;
          i2 += m1;
          i3 += m1;
          p0 = p0 + p2;
1:        p1 = p1 + p2;

        (r7:4,p5:4) = [sp++];
        unlink;
        rts;
DEFUN_END(yuyvtoyv12)