rdopt.c 90.3 KB
Newer Older
John Koleszar's avatar
John Koleszar committed
1
/*
2
 *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
John Koleszar's avatar
John Koleszar committed
3
 *
4
 *  Use of this source code is governed by a BSD-style license
5
6
 *  that can be found in the LICENSE file in the root of the source
 *  tree. An additional intellectual property rights grant can be found
7
 *  in the file PATENTS.  All contributing project authors may
8
 *  be found in the AUTHORS file in the root of the source tree.
John Koleszar's avatar
John Koleszar committed
9
10
11
12
13
14
15
 */


#include <stdio.h>
#include <math.h>
#include <limits.h>
#include <assert.h>
John Koleszar's avatar
John Koleszar committed
16
#include "vp8/common/pragmas.h"
John Koleszar's avatar
John Koleszar committed
17
18
19
20
21
22

#include "tokenize.h"
#include "treewriter.h"
#include "onyx_int.h"
#include "modecosts.h"
#include "encodeintra.h"
John Koleszar's avatar
John Koleszar committed
23
24
25
26
27
#include "vp8/common/entropymode.h"
#include "vp8/common/reconinter.h"
#include "vp8/common/reconintra.h"
#include "vp8/common/reconintra4x4.h"
#include "vp8/common/findnearmv.h"
John Koleszar's avatar
John Koleszar committed
28
29
#include "encodemb.h"
#include "quantize.h"
John Koleszar's avatar
John Koleszar committed
30
31
#include "vp8/common/idct.h"
#include "vp8/common/g_common.h"
John Koleszar's avatar
John Koleszar committed
32
33
#include "variance.h"
#include "mcomp.h"
Yunqing Wang's avatar
Yunqing Wang committed
34
#include "rdopt.h"
Paul Wilkins's avatar
Paul Wilkins committed
35
#include "ratectrl.h"
John Koleszar's avatar
John Koleszar committed
36
37
#include "vpx_mem/vpx_mem.h"
#include "dct.h"
John Koleszar's avatar
John Koleszar committed
38
#include "vp8/common/systemdependent.h"
John Koleszar's avatar
John Koleszar committed
39

40
//#if CONFIG_SEGFEATURES
41
42
#include "vp8/common/seg_common.h"

John Koleszar's avatar
John Koleszar committed
43
44
45
46
47
48
49
#if CONFIG_RUNTIME_CPU_DETECT
#define IF_RTCD(x)  (x)
#else
#define IF_RTCD(x)  NULL
#endif


Scott LaVarnway's avatar
Scott LaVarnway committed
50
51
52
extern void vp8cx_mb_init_quantizer(VP8_COMP *cpi, MACROBLOCK *x);
extern void vp8_update_zbin_extra(VP8_COMP *cpi, MACROBLOCK *x);

John Koleszar's avatar
John Koleszar committed
53
54
#define MAXF(a,b)            (((a) > (b)) ? (a) : (b))

55
static const int auto_speed_thresh[17] =
John Koleszar's avatar
John Koleszar committed
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
{
    1000,
    200,
    150,
    130,
    150,
    125,
    120,
    115,
    115,
    115,
    115,
    115,
    115,
    115,
    115,
    115,
    105
};

const MB_PREDICTION_MODE vp8_mode_order[MAX_MODES] =
{
    ZEROMV,
    DC_PRED,

    NEARESTMV,
    NEARMV,

    ZEROMV,
    NEARESTMV,

    ZEROMV,
    NEARESTMV,

    NEARMV,
    NEARMV,

    V_PRED,
    H_PRED,
    TM_PRED,

    NEWMV,
    NEWMV,
    NEWMV,

    SPLITMV,
    SPLITMV,
    SPLITMV,

    B_PRED,
};

const MV_REFERENCE_FRAME vp8_ref_frame_order[MAX_MODES] =
{
    LAST_FRAME,
    INTRA_FRAME,

    LAST_FRAME,
    LAST_FRAME,

    GOLDEN_FRAME,
    GOLDEN_FRAME,

    ALTREF_FRAME,
    ALTREF_FRAME,

    GOLDEN_FRAME,
    ALTREF_FRAME,

    INTRA_FRAME,
    INTRA_FRAME,
    INTRA_FRAME,

    LAST_FRAME,
    GOLDEN_FRAME,
    ALTREF_FRAME,

    LAST_FRAME,
    GOLDEN_FRAME,
    ALTREF_FRAME,

    INTRA_FRAME,
};

static void fill_token_costs(
141
142
    unsigned int c      [BLOCK_TYPES] [COEF_BANDS] [PREV_COEF_CONTEXTS] [MAX_ENTROPY_TOKENS],
    const vp8_prob p    [BLOCK_TYPES] [COEF_BANDS] [PREV_COEF_CONTEXTS] [ENTROPY_NODES]
John Koleszar's avatar
John Koleszar committed
143
144
145
146
147
148
149
150
151
152
153
154
155
)
{
    int i, j, k;


    for (i = 0; i < BLOCK_TYPES; i++)
        for (j = 0; j < COEF_BANDS; j++)
            for (k = 0; k < PREV_COEF_CONTEXTS; k++)

                vp8_cost_tokens((int *)(c [i][j][k]), p [i][j][k], vp8_coef_tree);

}

Paul Wilkins's avatar
Paul Wilkins committed
156
static int rd_iifactor [ 32 ] =  {    4,   4,   3,   2,   1,   0,   0,   0,
John Koleszar's avatar
John Koleszar committed
157
158
159
160
161
                                      0,   0,   0,   0,   0,   0,   0,   0,
                                      0,   0,   0,   0,   0,   0,   0,   0,
                                      0,   0,   0,   0,   0,   0,   0,   0,
                                 };

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
// 3* dc_qlookup[Q]*dc_qlookup[Q];
#if !CONFIG_EXTEND_QRANGE
static int rdmult_lut[QINDEX_RANGE]=
{
    48,75,108,147,192,243,300,300,
    363,432,507,588,675,768,867,867,
    972,1083,1200,1200,1323,1323,1452,1452,
    1587,1587,1728,1875,1875,2028,2187,2352,
    2523,2700,2883,3072,3267,3468,3675,3888,
    4107,4107,4332,4563,4800,5043,5292,5547,
    5808,6075,6348,6348,6627,6912,7203,7500,
    7803,8112,8427,8748,9075,9408,9747,10092,
    10443,10800,11163,11532,11907,12288,12675,13068,
    13467,13872,14283,14700,15123,15552,15987,16428,
    16875,17328,17328,17787,18252,18723,19200,19683,
    20172,20667,21168,21675,22188,22707,23232,23763,
    24843,25947,27075,27648,28812,30000,30603,31212,
    32448,33708,34992,36300,37632,38988,40368,41772,
    44652,46128,47628,49152,50700,52272,53868,55488,
    57132,58800,61347,63075,65712,68403,71148,73947,
};
#else
static int rdmult_lut[QINDEX_RANGE]=
{
    3,5,7,9,12,15,19,23,
    27,32,37,42,48,54,61,68,
    75,83,91,99,108,117,127,137,
    147,169,192,217,243,271,300,331,
    363,397,450,507,567,631,698,768,
    842,919,999,1083,1170,1261,1355,1452,
    1587,1728,1875,2028,2187,2352,2523,2700,
    2883,3072,3267,3468,3675,3888,4107,4332,
    4563,4800,5043,5292,5547,5808,6075,6348,
    6627,6912,7203,7500,7880,8269,8667,9075,
    9492,9919,10355,10800,11255,11719,12192,12675,
    13167,13669,14180,14700,15230,15769,16317,16875,
    18019,19200,20419,21675,22969,24300,25669,27075,
    28519,30000,31519,33075,34669,36300,37969,39675,
    41772,43923,46128,48387,50700,53067,55488,57963,
    61347,64827,69312,73947,78732,83667,89787,97200,
};
#endif
204
/* values are now correlated to quantizer */
Paul Wilkins's avatar
Paul Wilkins committed
205
206
207
208
static int sad_per_bit16lut[QINDEX_RANGE];
static int sad_per_bit4lut[QINDEX_RANGE];

void vp8_init_me_luts()
John Koleszar's avatar
John Koleszar committed
209
{
Paul Wilkins's avatar
Paul Wilkins committed
210
211
212
213
214
215
216
217
218
219
220
221
    int i;

    // Initialize the sad lut tables using a formulaic calculation for now
    // This is to make it easier to resolve the impact of experimental changes
    // to the quantizer tables.
    for ( i = 0; i < QINDEX_RANGE; i++ )
    {
        sad_per_bit16lut[i] =
            (int)((0.0418*vp8_convert_qindex_to_q(i)) + 2.4107);
        sad_per_bit4lut[i] = (int)((0.063*vp8_convert_qindex_to_q(i)) + 2.742);
    }
}
John Koleszar's avatar
John Koleszar committed
222
223
224

void vp8cx_initialize_me_consts(VP8_COMP *cpi, int QIndex)
{
Yaowu Xu's avatar
Yaowu Xu committed
225
226
    cpi->mb.sadperbit16 =  sad_per_bit16lut[QIndex];
    cpi->mb.sadperbit4  =  sad_per_bit4lut[QIndex];
John Koleszar's avatar
John Koleszar committed
227
228
}

229
230

void vp8_initialize_rd_consts(VP8_COMP *cpi, int QIndex)
John Koleszar's avatar
John Koleszar committed
231
232
233
234
235
236
{
    int q;
    int i;

    vp8_clear_system_state();  //__asm emms;

237
238
239
240
    // Further tests required to see if optimum is different
    // for key frames, golden frames and arf frames.
    // if (cpi->common.refresh_golden_frame ||
    //     cpi->common.refresh_alt_ref_frame)
241
242
    QIndex=(QIndex<0)? 0 : ((QIndex>127)?127 : QIndex);
    cpi->RDMULT = rdmult_lut[QIndex];
John Koleszar's avatar
John Koleszar committed
243

244
245
246
247
248
249
250
251
    // Extend rate multiplier along side quantizer zbin increases
    if (cpi->zbin_over_quant  > 0)
    {
        double oq_factor;

        // Experimental code using the same basic equation as used for Q above
        // The units of cpi->zbin_over_quant are 1/128 of Q bin size
        oq_factor = 1.0 + ((double)0.0015625 * cpi->zbin_over_quant);
252
        cpi->RDMULT = (int)((double)cpi->RDMULT * oq_factor * oq_factor);
253
    }
John Koleszar's avatar
John Koleszar committed
254

Paul Wilkins's avatar
Paul Wilkins committed
255
    if (cpi->pass == 2 && (cpi->common.frame_type != KEY_FRAME))
John Koleszar's avatar
John Koleszar committed
256
    {
257
        if (cpi->twopass.next_iiratio > 31)
Paul Wilkins's avatar
Paul Wilkins committed
258
            cpi->RDMULT += (cpi->RDMULT * rd_iifactor[31]) >> 4;
John Koleszar's avatar
John Koleszar committed
259
        else
260
261
            cpi->RDMULT +=
                (cpi->RDMULT * rd_iifactor[cpi->twopass.next_iiratio]) >> 4;
John Koleszar's avatar
John Koleszar committed
262
263
    }

264
265
266
267
268
#if !CONFIG_EXTEND_QRANGE
#else
    if (cpi->RDMULT < 7)
        cpi->RDMULT = 7;
#endif
269
    cpi->mb.errorperbit = (cpi->RDMULT / 110);
270
271
    cpi->mb.errorperbit += (cpi->mb.errorperbit==0);

272
273
274
275
#if CONFIG_EXTEND_QRANGE
    if(cpi->mb.errorperbit<1)
        cpi->mb.errorperbit=1;
#endif
John Koleszar's avatar
John Koleszar committed
276
277
    vp8_set_speed_features(cpi);

278
    q = (int)pow(vp8_dc_quant(QIndex,0), 1.25);
John Koleszar's avatar
John Koleszar committed
279
280
281
282

    if (q < 8)
        q = 8;

283
284
285
286
287
288


#if CONFIG_EXTEND_QRANGE
    cpi->RDMULT *= 16;
#endif

John Koleszar's avatar
John Koleszar committed
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
    if (cpi->RDMULT > 1000)
    {
        cpi->RDDIV = 1;
        cpi->RDMULT /= 100;

        for (i = 0; i < MAX_MODES; i++)
        {
            if (cpi->sf.thresh_mult[i] < INT_MAX)
            {
                cpi->rd_threshes[i] = cpi->sf.thresh_mult[i] * q / 100;
            }
            else
            {
                cpi->rd_threshes[i] = INT_MAX;
            }

            cpi->rd_baseline_thresh[i] = cpi->rd_threshes[i];
        }
    }
    else
    {
        cpi->RDDIV = 100;

        for (i = 0; i < MAX_MODES; i++)
        {
            if (cpi->sf.thresh_mult[i] < (INT_MAX / q))
            {
                cpi->rd_threshes[i] = cpi->sf.thresh_mult[i] * q;
            }
            else
            {
                cpi->rd_threshes[i] = INT_MAX;
            }

            cpi->rd_baseline_thresh[i] = cpi->rd_threshes[i];
        }
    }

    fill_token_costs(
        cpi->mb.token_costs,
        (const vp8_prob( *)[8][3][11]) cpi->common.fc.coef_probs
    );

332
333
334
335
#if CONFIG_QIMODE
    //rough estimate for costing
    cpi->common.kf_ymode_probs_index = cpi->common.base_qindex>>4;
#endif
John Koleszar's avatar
John Koleszar committed
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
    vp8_init_mode_costs(cpi);

}

void vp8_auto_select_speed(VP8_COMP *cpi)
{
    int milliseconds_for_compress = (int)(1000000 / cpi->oxcf.frame_rate);

    milliseconds_for_compress = milliseconds_for_compress * (16 - cpi->oxcf.cpu_used) / 16;

#if 0

    if (0)
    {
        FILE *f;

        f = fopen("speed.stt", "a");
        fprintf(f, " %8ld %10ld %10ld %10ld\n",
                cpi->common.current_video_frame, cpi->Speed, milliseconds_for_compress, cpi->avg_pick_mode_time);
        fclose(f);
    }

#endif

    /*
    // this is done during parameter valid check
Johann's avatar
Johann committed
362
363
364
365
    if( cpi->oxcf.cpu_used > 16)
        cpi->oxcf.cpu_used = 16;
    if( cpi->oxcf.cpu_used < -16)
        cpi->oxcf.cpu_used = -16;
John Koleszar's avatar
John Koleszar committed
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
    */

    if (cpi->avg_pick_mode_time < milliseconds_for_compress && (cpi->avg_encode_time - cpi->avg_pick_mode_time) < milliseconds_for_compress)
    {
        if (cpi->avg_pick_mode_time == 0)
        {
            cpi->Speed = 4;
        }
        else
        {
            if (milliseconds_for_compress * 100 < cpi->avg_encode_time * 95)
            {
                cpi->Speed          += 2;
                cpi->avg_pick_mode_time = 0;
                cpi->avg_encode_time = 0;

                if (cpi->Speed > 16)
                {
                    cpi->Speed = 16;
                }
            }

388
            if (milliseconds_for_compress * 100 > cpi->avg_encode_time * auto_speed_thresh[cpi->Speed])
John Koleszar's avatar
John Koleszar committed
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
            {
                cpi->Speed          -= 1;
                cpi->avg_pick_mode_time = 0;
                cpi->avg_encode_time = 0;

                // In real-time mode, cpi->speed is in [4, 16].
                if (cpi->Speed < 4)        //if ( cpi->Speed < 0 )
                {
                    cpi->Speed = 4;        //cpi->Speed = 0;
                }
            }
        }
    }
    else
    {
        cpi->Speed += 4;

        if (cpi->Speed > 16)
            cpi->Speed = 16;


        cpi->avg_pick_mode_time = 0;
        cpi->avg_encode_time = 0;
    }
}

int vp8_block_error_c(short *coeff, short *dqcoeff)
{
    int i;
    int error = 0;

    for (i = 0; i < 16; i++)
    {
        int this_diff = coeff[i] - dqcoeff[i];
        error += this_diff * this_diff;
    }

    return error;
}

int vp8_mbblock_error_c(MACROBLOCK *mb, int dc)
{
    BLOCK  *be;
    BLOCKD *bd;
    int i, j;
    int berror, error = 0;

    for (i = 0; i < 16; i++)
    {
        be = &mb->block[i];
        bd = &mb->e_mbd.block[i];

        berror = 0;

        for (j = dc; j < 16; j++)
        {
            int this_diff = be->coeff[j] - bd->dqcoeff[j];
            berror += this_diff * this_diff;
        }

        error += berror;
    }

    return error;
}

int vp8_mbuverror_c(MACROBLOCK *mb)
{

    BLOCK  *be;
    BLOCKD *bd;


    int i;
    int error = 0;

    for (i = 16; i < 24; i++)
    {
        be = &mb->block[i];
        bd = &mb->e_mbd.block[i];

        error += vp8_block_error_c(be->coeff, bd->dqcoeff);
    }

    return error;
}

int VP8_UVSSE(MACROBLOCK *x, const vp8_variance_rtcd_vtable_t *rtcd)
{
    unsigned char *uptr, *vptr;
    unsigned char *upred_ptr = (*(x->block[16].base_src) + x->block[16].src);
    unsigned char *vpred_ptr = (*(x->block[20].base_src) + x->block[20].src);
    int uv_stride = x->block[16].src_stride;

    unsigned int sse1 = 0;
    unsigned int sse2 = 0;
485
486
    int mv_row = x->e_mbd.mode_info_context->mbmi.mv.as_mv.row;
    int mv_col = x->e_mbd.mode_info_context->mbmi.mv.as_mv.col;
John Koleszar's avatar
John Koleszar committed
487
488
489
    int offset;
    int pre_stride = x->e_mbd.block[16].pre_stride;

490
491
492
493
494
495
496
497
498
499
500
501
    if (mv_row < 0)
        mv_row -= 1;
    else
        mv_row += 1;

    if (mv_col < 0)
        mv_col -= 1;
    else
        mv_col += 1;

    mv_row /= 2;
    mv_col /= 2;
John Koleszar's avatar
John Koleszar committed
502
503
504
505
506
507
508

    offset = (mv_row >> 3) * pre_stride + (mv_col >> 3);
    uptr = x->e_mbd.pre.u_buffer + offset;
    vptr = x->e_mbd.pre.v_buffer + offset;

    if ((mv_row | mv_col) & 7)
    {
509
510
511
512
        VARIANCE_INVOKE(rtcd, subpixvar8x8)(uptr, pre_stride,
            mv_col & 7, mv_row & 7, upred_ptr, uv_stride, &sse2);
        VARIANCE_INVOKE(rtcd, subpixvar8x8)(vptr, pre_stride,
            mv_col & 7, mv_row & 7, vpred_ptr, uv_stride, &sse1);
John Koleszar's avatar
John Koleszar committed
513
514
515
516
        sse2 += sse1;
    }
    else
    {
517
518
519
520
        VARIANCE_INVOKE(rtcd, var8x8)(uptr, pre_stride,
            upred_ptr, uv_stride, &sse2);
        VARIANCE_INVOKE(rtcd, var8x8)(vptr, pre_stride,
            vpred_ptr, uv_stride, &sse1);
John Koleszar's avatar
John Koleszar committed
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
        sse2 += sse1;
    }
    return sse2;

}

static int cost_coeffs(MACROBLOCK *mb, BLOCKD *b, int type, ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l)
{
    int c = !type;              /* start at coef 0, unless Y with Y2 */
    int eob = b->eob;
    int pt ;    /* surrounding block/prev coef predictor */
    int cost = 0;
    short *qcoeff_ptr = b->qcoeff;

    VP8_COMBINEENTROPYCONTEXTS(pt, *a, *l);

# define QC( I)  ( qcoeff_ptr [vp8_default_zig_zag1d[I]] )

    for (; c < eob; c++)
    {
        int v = QC(c);
        int t = vp8_dct_value_tokens_ptr[v].Token;
        cost += mb->token_costs [type] [vp8_coef_bands[c]] [pt] [t];
        cost += vp8_dct_value_cost_ptr[v];
        pt = vp8_prev_token_class[t];
    }

# undef QC

    if (c < 16)
        cost += mb->token_costs [type] [vp8_coef_bands[c]] [pt] [DCT_EOB_TOKEN];

    pt = (c != !type); // is eob first coefficient;
    *a = *l = pt;

    return cost;
}

Scott LaVarnway's avatar
Scott LaVarnway committed
559
static int vp8_rdcost_mby(MACROBLOCK *mb)
John Koleszar's avatar
John Koleszar committed
560
561
562
563
{
    int cost = 0;
    int b;
    MACROBLOCKD *x = &mb->e_mbd;
564
565
566
567
568
569
    ENTROPY_CONTEXT_PLANES t_above, t_left;
    ENTROPY_CONTEXT *ta;
    ENTROPY_CONTEXT *tl;

    vpx_memcpy(&t_above, mb->e_mbd.above_context, sizeof(ENTROPY_CONTEXT_PLANES));
    vpx_memcpy(&t_left, mb->e_mbd.left_context, sizeof(ENTROPY_CONTEXT_PLANES));
John Koleszar's avatar
John Koleszar committed
570

571
572
    ta = (ENTROPY_CONTEXT *)&t_above;
    tl = (ENTROPY_CONTEXT *)&t_left;
John Koleszar's avatar
John Koleszar committed
573
574

    for (b = 0; b < 16; b++)
Scott LaVarnway's avatar
Scott LaVarnway committed
575
        cost += cost_coeffs(mb, x->block + b, PLANE_TYPE_Y_NO_DC,
576
                    ta + vp8_block2above[b], tl + vp8_block2left[b]);
John Koleszar's avatar
John Koleszar committed
577

Scott LaVarnway's avatar
Scott LaVarnway committed
578
    cost += cost_coeffs(mb, x->block + 24, PLANE_TYPE_Y2,
Scott LaVarnway's avatar
Scott LaVarnway committed
579
                ta + vp8_block2above[24], tl + vp8_block2left[24]);
John Koleszar's avatar
John Koleszar committed
580
581
582
583

    return cost;
}

584
585
586
587
588
589
590
591
592
593
594
595
596
static void macro_block_yrd( MACROBLOCK *mb,
                             int *Rate,
                             int *Distortion,
                             const vp8_encodemb_rtcd_vtable_t *rtcd)
{
    int b;
    MACROBLOCKD *const x = &mb->e_mbd;
    BLOCK   *const mb_y2 = mb->block + 24;
    BLOCKD *const x_y2  = x->block + 24;
    short *Y2DCPtr = mb_y2->src_diff;
    BLOCK *beptr;
    int d;

597
598
    ENCODEMB_INVOKE(rtcd, submby)( mb->src_diff, *(mb->block[0].base_src),
                                   mb->e_mbd.predictor, mb->block[0].src_stride );
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621

    // Fdct and building the 2nd order block
    for (beptr = mb->block; beptr < mb->block + 16; beptr += 2)
    {
        mb->vp8_short_fdct8x4(beptr->src_diff, beptr->coeff, 32);
        *Y2DCPtr++ = beptr->coeff[0];
        *Y2DCPtr++ = beptr->coeff[16];
    }

    // 2nd order fdct
    mb->short_walsh4x4(mb_y2->src_diff, mb_y2->coeff, 8);

    // Quantization
    for (b = 0; b < 16; b++)
    {
        mb->quantize_b(&mb->block[b], &mb->e_mbd.block[b]);
    }

    // DC predication and Quantization of 2nd Order block
    mb->quantize_b(mb_y2, x_y2);

    // Distortion
    d = ENCODEMB_INVOKE(rtcd, mberr)(mb, 1) << 2;
622
623
624
625

#if CONFIG_EXTEND_QRANGE
    d += ENCODEMB_INVOKE(rtcd, berr)(mb_y2->coeff, x_y2->dqcoeff)<<2;
#else
626
    d += ENCODEMB_INVOKE(rtcd, berr)(mb_y2->coeff, x_y2->dqcoeff);
627
#endif
628
629
630
631
632
633

    *Distortion = (d >> 4);

    // rate
    *Rate = vp8_rdcost_mby(mb);
}
John Koleszar's avatar
John Koleszar committed
634

635
static void copy_predictor(unsigned char *dst, const unsigned char *predictor)
636
{
637
638
639
640
641
642
    const unsigned int *p = (const unsigned int *)predictor;
    unsigned int *d = (unsigned int *)dst;
    d[0] = p[0];
    d[4] = p[4];
    d[8] = p[8];
    d[12] = p[12];
643
}
Yaowu Xu's avatar
Yaowu Xu committed
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666

static void copy_predictor_8x8(unsigned char *dst, const unsigned char *predictor)
{
    const unsigned int *p = (const unsigned int *)predictor;
    unsigned int *d = (unsigned int *)dst;
    d[0] = p[0];
    d[1] = p[1];
    d[4] = p[4];
    d[5] = p[5];
    d[8] = p[8];
    d[9] = p[9];
    d[12] = p[12];
    d[13] = p[13];
    d[16] = p[16];
    d[17] = p[17];
    d[20] = p[20];
    d[21] = p[21];
    d[24] = p[24];
    d[25] = p[25];
    d[28] = p[28];
    d[29] = p[29];
}

667
static int rd_pick_intra4x4block(
John Koleszar's avatar
John Koleszar committed
668
669
670
671
672
    VP8_COMP *cpi,
    MACROBLOCK *x,
    BLOCK *be,
    BLOCKD *b,
    B_PREDICTION_MODE *best_mode,
673
    unsigned int *bmode_costs,
John Koleszar's avatar
John Koleszar committed
674
675
676
677
678
679
680
681
    ENTROPY_CONTEXT *a,
    ENTROPY_CONTEXT *l,

    int *bestrate,
    int *bestratey,
    int *bestdistortion)
{
    B_PREDICTION_MODE mode;
682
    int best_rd = INT_MAX;
John Koleszar's avatar
John Koleszar committed
683
684
685
686
687
    int rate = 0;
    int distortion;

    ENTROPY_CONTEXT ta = *a, tempa = *a;
    ENTROPY_CONTEXT tl = *l, templ = *l;
688
689
690
691
692
693
694
    /*
     * The predictor buffer is a 2d buffer with a stride of 16.  Create
     * a temp buffer that meets the stride requirements, but we are only
     * interested in the left 4x4 block
     * */
    DECLARE_ALIGNED_ARRAY(16, unsigned char,  best_predictor, 16*4);
    DECLARE_ALIGNED_ARRAY(16, short, best_dqcoeff, 16);
John Koleszar's avatar
John Koleszar committed
695
696
697
698
699
700

    for (mode = B_DC_PRED; mode <= B_HU_PRED; mode++)
    {
        int this_rd;
        int ratey;

701
702
        rate = bmode_costs[mode];

703
704
        RECON_INVOKE(&cpi->rtcd.common->recon, intra4x4_predict)
                     (b, mode, b->predictor);
705
706
707
        ENCODEMB_INVOKE(IF_RTCD(&cpi->rtcd.encodemb), subb)(be, b, 16);
        x->vp8_short_fdct4x4(be->src_diff, be->coeff, 32);
        x->quantize_b(be, b);
John Koleszar's avatar
John Koleszar committed
708
709
710
711

        tempa = ta;
        templ = tl;

Scott LaVarnway's avatar
Scott LaVarnway committed
712
        ratey = cost_coeffs(x, b, PLANE_TYPE_Y_WITH_DC, &tempa, &templ);
John Koleszar's avatar
John Koleszar committed
713
714
715
716
717
718
719
720
721
722
723
724
725
726
        rate += ratey;
        distortion = ENCODEMB_INVOKE(IF_RTCD(&cpi->rtcd.encodemb), berr)(be->coeff, b->dqcoeff) >> 2;

        this_rd = RDCOST(x->rdmult, x->rddiv, rate, distortion);

        if (this_rd < best_rd)
        {
            *bestrate = rate;
            *bestratey = ratey;
            *bestdistortion = distortion;
            best_rd = this_rd;
            *best_mode = mode;
            *a = tempa;
            *l = templ;
727
728
            copy_predictor(best_predictor, b->predictor);
            vpx_memcpy(best_dqcoeff, b->dqcoeff, 32);
John Koleszar's avatar
John Koleszar committed
729
730
        }
    }
Scott LaVarnway's avatar
Scott LaVarnway committed
731
    b->bmi.as_mode = (B_PREDICTION_MODE)(*best_mode);
732

733
734
    IDCT_INVOKE(IF_RTCD(&cpi->rtcd.common->idct), idct16)(best_dqcoeff, b->diff, 32);
    RECON_INVOKE(IF_RTCD(&cpi->rtcd.common->recon), recon)(best_predictor, b->diff, *(b->base_dst) + b->dst, b->dst_stride);
John Koleszar's avatar
John Koleszar committed
735

736
    return best_rd;
John Koleszar's avatar
John Koleszar committed
737
738
}

739
740
static int rd_pick_intra4x4mby_modes(VP8_COMP *cpi, MACROBLOCK *mb, int *Rate,
                                     int *rate_y, int *Distortion, int best_rd)
John Koleszar's avatar
John Koleszar committed
741
742
743
744
745
746
{
    MACROBLOCKD *const xd = &mb->e_mbd;
    int i;
    int cost = mb->mbmode_cost [xd->frame_type] [B_PRED];
    int distortion = 0;
    int tot_rate_y = 0;
747
    int64_t total_rd = 0;
748
749
750
    ENTROPY_CONTEXT_PLANES t_above, t_left;
    ENTROPY_CONTEXT *ta;
    ENTROPY_CONTEXT *tl;
751
    unsigned int *bmode_costs;
752
753
754
755
756
757

    vpx_memcpy(&t_above, mb->e_mbd.above_context, sizeof(ENTROPY_CONTEXT_PLANES));
    vpx_memcpy(&t_left, mb->e_mbd.left_context, sizeof(ENTROPY_CONTEXT_PLANES));

    ta = (ENTROPY_CONTEXT *)&t_above;
    tl = (ENTROPY_CONTEXT *)&t_left;
John Koleszar's avatar
John Koleszar committed
758
759
760

    vp8_intra_prediction_down_copy(xd);

761
762
    bmode_costs = mb->inter_bmode_costs;

John Koleszar's avatar
John Koleszar committed
763
764
765
766
767
768
769
    for (i = 0; i < 16; i++)
    {
        MODE_INFO *const mic = xd->mode_info_context;
        const int mis = xd->mode_info_stride;
        B_PREDICTION_MODE UNINITIALIZED_IS_SAFE(best_mode);
        int UNINITIALIZED_IS_SAFE(r), UNINITIALIZED_IS_SAFE(ry), UNINITIALIZED_IS_SAFE(d);

770
771
        if (mb->e_mbd.frame_type == KEY_FRAME)
        {
Scott LaVarnway's avatar
Scott LaVarnway committed
772
773
            const B_PREDICTION_MODE A = above_block_mode(mic, i, mis);
            const B_PREDICTION_MODE L = left_block_mode(mic, i);
774
775
776
777

            bmode_costs  = mb->bmode_costs[A][L];
        }

778
        total_rd += rd_pick_intra4x4block(
779
            cpi, mb, mb->block + i, xd->block + i, &best_mode, bmode_costs,
780
781
            ta + vp8_block2above[i],
            tl + vp8_block2left[i], &r, &ry, &d);
John Koleszar's avatar
John Koleszar committed
782
783
784
785

        cost += r;
        distortion += d;
        tot_rate_y += ry;
Scott LaVarnway's avatar
Scott LaVarnway committed
786
787

        mic->bmi[i].as_mode = best_mode;
788

789
        if(total_rd >= (int64_t)best_rd)
790
            break;
John Koleszar's avatar
John Koleszar committed
791
792
    }

793
    if(total_rd >= (int64_t)best_rd)
794
        return INT_MAX;
795

John Koleszar's avatar
John Koleszar committed
796
797
798
799
800
801
    *Rate = cost;
    *rate_y += tot_rate_y;
    *Distortion = distortion;

    return RDCOST(mb->rdmult, mb->rddiv, cost, distortion);
}
802
803
804
805
806
807
808


static int rd_pick_intra16x16mby_mode(VP8_COMP *cpi,
                                      MACROBLOCK *x,
                                      int *Rate,
                                      int *rate_y,
                                      int *Distortion)
John Koleszar's avatar
John Koleszar committed
809
810
811
812
{
    MB_PREDICTION_MODE mode;
    MB_PREDICTION_MODE UNINITIALIZED_IS_SAFE(mode_selected);
    int rate, ratey;
813
    int distortion;
John Koleszar's avatar
John Koleszar committed
814
    int best_rd = INT_MAX;
815
    int this_rd;
John Koleszar's avatar
John Koleszar committed
816
817
818
819

    //Y Search for 16x16 intra prediction mode
    for (mode = DC_PRED; mode <= TM_PRED; mode++)
    {
820
        x->e_mbd.mode_info_context->mbmi.mode = mode;
John Koleszar's avatar
John Koleszar committed
821

822
823
        RECON_INVOKE(&cpi->common.rtcd.recon, build_intra_predictors_mby)
            (&x->e_mbd);
John Koleszar's avatar
John Koleszar committed
824

825
826
827
        macro_block_yrd(x, &ratey, &distortion, IF_RTCD(&cpi->rtcd.encodemb));
        rate = ratey + x->mbmode_cost[x->e_mbd.frame_type]
                                     [x->e_mbd.mode_info_context->mbmi.mode];
John Koleszar's avatar
John Koleszar committed
828
829
830
831
832
833
834
835
836

        this_rd = RDCOST(x->rdmult, x->rddiv, rate, distortion);

        if (this_rd < best_rd)
        {
            mode_selected = mode;
            best_rd = this_rd;
            *Rate = rate;
            *rate_y = ratey;
837
            *Distortion = distortion;
John Koleszar's avatar
John Koleszar committed
838
839
840
        }
    }

841
    x->e_mbd.mode_info_context->mbmi.mode = mode_selected;
John Koleszar's avatar
John Koleszar committed
842
843
    return best_rd;
}
Yaowu Xu's avatar
Yaowu Xu committed
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
#if CONFIG_I8X8
static int rd_pick_intra8x8block(
    VP8_COMP *cpi,
    MACROBLOCK *x,
    int ib,
    B_PREDICTION_MODE *best_mode,
    unsigned int *mode_costs,
    ENTROPY_CONTEXT *a,
    ENTROPY_CONTEXT *l,
    int *bestrate,
    int *bestratey,
    int *bestdistortion)
{
    MB_PREDICTION_MODE mode;
    MACROBLOCKD *xd = &x->e_mbd;
    int best_rd = INT_MAX;
    int rate = 0;
    int distortion;
    BLOCK  *be=x->block + ib;
    BLOCKD *b=x->e_mbd.block + ib;
    ENTROPY_CONTEXT ta0, ta1, besta0, besta1;
    ENTROPY_CONTEXT tl0, tl1, bestl0, bestl1;


    /*
     * The predictor buffer is a 2d buffer with a stride of 16.  Create
     * a temp buffer that meets the stride requirements, but we are only
     * interested in the left 8x8 block
     * */

    DECLARE_ALIGNED_ARRAY(16, unsigned char,  best_predictor, 16*8);
    DECLARE_ALIGNED_ARRAY(16, short, best_dqcoeff, 16*4);

    for (mode = DC_PRED; mode <= TM_PRED; mode++)
    {
        int this_rd;
        int rate_t;

        rate = mode_costs[mode];

        RECON_INVOKE(&cpi->rtcd.common->recon, intra8x8_predict)
                     (b, mode, b->predictor);

        vp8_subtract_4b_c(be, b, 16);

        x->vp8_short_fdct8x4(be->src_diff, be->coeff, 32);
        x->vp8_short_fdct8x4(be->src_diff + 64, be->coeff + 64, 32);

        x->quantize_b_pair(x->block+ib, x->block+ib+1,
                            xd->block+ib, xd->block+ib+1);
        x->quantize_b_pair(x->block+ib+4, x->block+ib+5,
                            xd->block+ib+4, xd->block+ib+5);

        distortion = ENCODEMB_INVOKE(IF_RTCD(&cpi->rtcd.encodemb), berr)
            ((x->block+ib)->coeff,(xd->block+ib)->dqcoeff)>>2;
        distortion += ENCODEMB_INVOKE(IF_RTCD(&cpi->rtcd.encodemb), berr)
            ((x->block+ib+1)->coeff,(xd->block+ib+1)->dqcoeff)>>2;
        distortion += ENCODEMB_INVOKE(IF_RTCD(&cpi->rtcd.encodemb), berr)
            ((x->block+ib+4)->coeff,(xd->block+ib+4)->dqcoeff)>>2;
        distortion += ENCODEMB_INVOKE(IF_RTCD(&cpi->rtcd.encodemb), berr)
            ((x->block+ib+5)->coeff,(xd->block+ib+5)->dqcoeff)>>2;

        ta0 = *(a + vp8_block2above[ib]);
        ta1 = *(a + vp8_block2above[ib+1]);
        tl0 = *(l + vp8_block2above[ib]);
        tl1 = *(l + vp8_block2above[ib+4]);
        rate_t = cost_coeffs(x, xd->block+ib, PLANE_TYPE_Y_WITH_DC,
            &ta0, &tl0);
        rate_t += cost_coeffs(x, xd->block+ib+1, PLANE_TYPE_Y_WITH_DC,
            &ta1, &tl0);
        rate_t += cost_coeffs(x, xd->block+ib+4, PLANE_TYPE_Y_WITH_DC,
            &ta0, &tl1);
        rate_t += cost_coeffs(x, xd->block+ib+5, PLANE_TYPE_Y_WITH_DC,
            &ta1, &tl1);
        rate += rate_t;
        this_rd = RDCOST(x->rdmult, x->rddiv, rate, distortion);
        if (this_rd < best_rd)
        {
            *bestrate = rate;
            *bestratey = rate_t;
            *bestdistortion = distortion;
            besta0 = ta0;
            besta1 = ta1;
            bestl0 = tl0;
            bestl1 = tl1;
            best_rd = this_rd;
            *best_mode = mode;
            copy_predictor_8x8(best_predictor, b->predictor);
            vpx_memcpy(best_dqcoeff, b->dqcoeff, 64);
            vpx_memcpy(best_dqcoeff+32, b->dqcoeff+64, 64);
        }
    }
    b->bmi.as_mode = (*best_mode);
    vp8_encode_intra8x8 (IF_RTCD(&cpi->rtcd), x, ib);
    *(a + vp8_block2above[ib])   = besta0;
    *(a + vp8_block2above[ib+1]) = besta1;
    *(l + vp8_block2above[ib])   = bestl0;
    *(l + vp8_block2above[ib+4]) = bestl1;
    return best_rd;
}

const int vp8_i8x8_block[4]={0, 2, 8, 10};
int rd_pick_intra8x8mby_modes(VP8_COMP *cpi,
                                      MACROBLOCK *mb,
                                      int *Rate,
                                      int *rate_y,
                                      int *Distortion,
                                      int best_rd)
{
    MACROBLOCKD *const xd = &mb->e_mbd;
    int i,ib;
    int cost = mb->mbmode_cost [xd->frame_type] [I8X8_PRED];
    int distortion = 0;
    int tot_rate_y = 0;
    long long total_rd = 0;
    ENTROPY_CONTEXT_PLANES t_above, t_left;
    ENTROPY_CONTEXT *ta;
    ENTROPY_CONTEXT *tl;
    unsigned int *i8x8mode_costs;

    vpx_memcpy(&t_above, mb->e_mbd.above_context, sizeof(ENTROPY_CONTEXT_PLANES));
    vpx_memcpy(&t_left, mb->e_mbd.left_context, sizeof(ENTROPY_CONTEXT_PLANES));

    ta = (ENTROPY_CONTEXT *)&t_above;
    tl = (ENTROPY_CONTEXT *)&t_left;

    i8x8mode_costs  = mb->i8x8_mode_costs;

    for (i = 0; i < 4; i++)
    {
        MODE_INFO *const mic = xd->mode_info_context;
        const int mis = xd->mode_info_stride;
        B_PREDICTION_MODE UNINITIALIZED_IS_SAFE(best_mode);
        int UNINITIALIZED_IS_SAFE(r), UNINITIALIZED_IS_SAFE(ry), UNINITIALIZED_IS_SAFE(d);

        ib = vp8_i8x8_block[i];
        total_rd += rd_pick_intra8x8block(
            cpi, mb, ib, &best_mode, i8x8mode_costs,
            ta, tl, &r, &ry, &d);
        cost += r;
        distortion += d;
        tot_rate_y += ry;
        mic->bmi[ib].as_mode = best_mode;
    }
    *Rate = cost;
    *rate_y += tot_rate_y;
    *Distortion = distortion;
    return RDCOST(mb->rdmult, mb->rddiv, cost, distortion);
}
#endif
John Koleszar's avatar
John Koleszar committed
994
995
996
997
998
999

static int rd_cost_mbuv(MACROBLOCK *mb)
{
    int b;
    int cost = 0;
    MACROBLOCKD *x = &mb->e_mbd;
1000
    ENTROPY_CONTEXT_PLANES t_above, t_left;
For faster browsing, not all history is shown. View entire blame