rdopt.c 107 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"
Christian Duvivier's avatar
Christian Duvivier committed
28
#include "vp8/common/quant_common.h"
John Koleszar's avatar
John Koleszar committed
29
30
#include "encodemb.h"
#include "quantize.h"
John Koleszar's avatar
John Koleszar committed
31
32
#include "vp8/common/idct.h"
#include "vp8/common/g_common.h"
John Koleszar's avatar
John Koleszar committed
33
34
#include "variance.h"
#include "mcomp.h"
Yunqing Wang's avatar
Yunqing Wang committed
35
#include "rdopt.h"
Paul Wilkins's avatar
Paul Wilkins committed
36
#include "ratectrl.h"
John Koleszar's avatar
John Koleszar committed
37
38
#include "vpx_mem/vpx_mem.h"
#include "dct.h"
John Koleszar's avatar
John Koleszar committed
39
#include "vp8/common/systemdependent.h"
John Koleszar's avatar
John Koleszar committed
40

41
#include "vp8/common/seg_common.h"
42
#include "vp8/common/pred_common.h"
43

John Koleszar's avatar
John Koleszar committed
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
{
    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,
106
    I8X8_PRED,
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123

    /* dual prediction modes */
    ZEROMV,
    NEARESTMV,
    NEARMV,

    ZEROMV,
    NEARESTMV,
    NEARMV,

    ZEROMV,
    NEARESTMV,
    NEARMV,

    NEWMV,
    NEWMV,
    NEWMV,
John Koleszar's avatar
John Koleszar committed
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
};

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,
156
    INTRA_FRAME,
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

    /* dual prediction modes */
    LAST_FRAME,
    LAST_FRAME,
    LAST_FRAME,

    ALTREF_FRAME,
    ALTREF_FRAME,
    ALTREF_FRAME,

    GOLDEN_FRAME,
    GOLDEN_FRAME,
    GOLDEN_FRAME,

    LAST_FRAME,
    ALTREF_FRAME,
    GOLDEN_FRAME,
};

const MV_REFERENCE_FRAME vp8_second_ref_frame_order[MAX_MODES] =
{
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0,

    /* dual prediction modes */
    GOLDEN_FRAME,
    GOLDEN_FRAME,
    GOLDEN_FRAME,

    LAST_FRAME,
    LAST_FRAME,
    LAST_FRAME,

    ALTREF_FRAME,
    ALTREF_FRAME,
    ALTREF_FRAME,

    GOLDEN_FRAME,
    LAST_FRAME,
    ALTREF_FRAME,
John Koleszar's avatar
John Koleszar committed
198
199
200
};

static void fill_token_costs(
201
202
    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
203
204
205
206
207
208
209
210
211
212
213
214
)
{
    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
215
static int rd_iifactor [ 32 ] =  {    4,   4,   3,   2,   1,   0,   0,   0,
John Koleszar's avatar
John Koleszar committed
216
217
218
219
220
                                      0,   0,   0,   0,   0,   0,   0,   0,
                                      0,   0,   0,   0,   0,   0,   0,   0,
                                      0,   0,   0,   0,   0,   0,   0,   0,
                                 };

221
// 3* dc_qlookup[Q]*dc_qlookup[Q];
222

223
/* values are now correlated to quantizer */
Paul Wilkins's avatar
Paul Wilkins committed
224
225
226
227
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
228
{
Paul Wilkins's avatar
Paul Wilkins committed
229
230
231
232
233
234
235
236
237
238
239
240
    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
241

242
243
244
245
246
247
248
249
int compute_rd_mult( int qindex )
{
    int q;

    q = vp8_dc_quant(qindex,0);
    return (3 * q * q) >> 4;
}

John Koleszar's avatar
John Koleszar committed
250
251
void vp8cx_initialize_me_consts(VP8_COMP *cpi, int QIndex)
{
Yaowu Xu's avatar
Yaowu Xu committed
252
253
    cpi->mb.sadperbit16 =  sad_per_bit16lut[QIndex];
    cpi->mb.sadperbit4  =  sad_per_bit4lut[QIndex];
John Koleszar's avatar
John Koleszar committed
254
255
}

256
257

void vp8_initialize_rd_consts(VP8_COMP *cpi, int QIndex)
John Koleszar's avatar
John Koleszar committed
258
259
260
261
262
263
{
    int q;
    int i;

    vp8_clear_system_state();  //__asm emms;

264
265
266
267
    // 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)
Paul Wilkins's avatar
Paul Wilkins committed
268
    QIndex=(QIndex<0)? 0 : ((QIndex>MAXQ)?MAXQ : QIndex);
269
270

    cpi->RDMULT = compute_rd_mult(QIndex);
John Koleszar's avatar
John Koleszar committed
271

272
273
274
275
276
277
278
279
    // 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);
280
        cpi->RDMULT = (int)((double)cpi->RDMULT * oq_factor * oq_factor);
281
    }
John Koleszar's avatar
John Koleszar committed
282

Paul Wilkins's avatar
Paul Wilkins committed
283
    if (cpi->pass == 2 && (cpi->common.frame_type != KEY_FRAME))
John Koleszar's avatar
John Koleszar committed
284
    {
285
        if (cpi->twopass.next_iiratio > 31)
Paul Wilkins's avatar
Paul Wilkins committed
286
            cpi->RDMULT += (cpi->RDMULT * rd_iifactor[31]) >> 4;
John Koleszar's avatar
John Koleszar committed
287
        else
288
289
            cpi->RDMULT +=
                (cpi->RDMULT * rd_iifactor[cpi->twopass.next_iiratio]) >> 4;
John Koleszar's avatar
John Koleszar committed
290
291
    }

292
293
    if (cpi->RDMULT < 7)
        cpi->RDMULT = 7;
294

295
    cpi->mb.errorperbit = (cpi->RDMULT / 110);
296
297
    cpi->mb.errorperbit += (cpi->mb.errorperbit==0);

John Koleszar's avatar
John Koleszar committed
298
299
    vp8_set_speed_features(cpi);

300
301
    q = (int)pow(vp8_dc_quant(QIndex,0)>>2, 1.25);
    q = q << 2;
302
    cpi->RDMULT = cpi->RDMULT << 4;
Paul Wilkins's avatar
Paul Wilkins committed
303

304
305
    if (q < 8)
        q = 8;
306

John Koleszar's avatar
John Koleszar committed
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
    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
    );

350
351
352
353
354
355
#if CONFIG_T8X8
    fill_token_costs(
        cpi->mb.token_costs_8x8,
        (const vp8_prob( *)[8][3][11]) cpi->common.fc.coef_probs_8x8
    );
#endif
356
357
358
359
#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
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
    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
386
387
388
389
    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
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
    */

    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;
                }
            }

412
            if (milliseconds_for_compress * 100 > cpi->avg_encode_time * auto_speed_thresh[cpi->Speed])
John Koleszar's avatar
John Koleszar committed
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
            {
                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;
509
510
    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
511
512
513
    int offset;
    int pre_stride = x->e_mbd.block[16].pre_stride;

514
515
516
517
518
519
520
521
522
523
524
525
    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
526
527
528
529
530
531
532

    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)
    {
533
534
535
536
        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
537
538
539
540
        sse2 += sse1;
    }
    else
    {
541
542
543
544
        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
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
        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
583
static int vp8_rdcost_mby(MACROBLOCK *mb)
John Koleszar's avatar
John Koleszar committed
584
585
586
587
{
    int cost = 0;
    int b;
    MACROBLOCKD *x = &mb->e_mbd;
588
589
590
591
592
593
    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
594

595
596
    ta = (ENTROPY_CONTEXT *)&t_above;
    tl = (ENTROPY_CONTEXT *)&t_left;
John Koleszar's avatar
John Koleszar committed
597
598

    for (b = 0; b < 16; b++)
Scott LaVarnway's avatar
Scott LaVarnway committed
599
        cost += cost_coeffs(mb, x->block + b, PLANE_TYPE_Y_NO_DC,
600
                    ta + vp8_block2above[b], tl + vp8_block2left[b]);
John Koleszar's avatar
John Koleszar committed
601

Scott LaVarnway's avatar
Scott LaVarnway committed
602
    cost += cost_coeffs(mb, x->block + 24, PLANE_TYPE_Y2,
Scott LaVarnway's avatar
Scott LaVarnway committed
603
                ta + vp8_block2above[24], tl + vp8_block2left[24]);
John Koleszar's avatar
John Koleszar committed
604
605
606
607

    return cost;
}

608
609
610
611
612
613
614
615
616
617
618
619
620
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;

621
622
    ENCODEMB_INVOKE(rtcd, submby)( mb->src_diff, *(mb->block[0].base_src),
                                   mb->e_mbd.predictor, mb->block[0].src_stride );
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645

    // 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;
646
647

    d += ENCODEMB_INVOKE(rtcd, berr)(mb_y2->coeff, x_y2->dqcoeff)<<2;
648
649
650
651
652

    *Distortion = (d >> 4);
    // rate
    *Rate = vp8_rdcost_mby(mb);
}
John Koleszar's avatar
John Koleszar committed
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
#if CONFIG_T8X8

static int cost_coeffs_2x2(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);
    assert(eob<=4);

# define QC2X2( I)  ( qcoeff_ptr [vp8_default_zig_zag1d[I]] )

    for (; c < eob; c++)
    {
        int v = QC2X2(c);
        int t = vp8_dct_value_tokens_ptr[v].Token;
        cost += mb->token_costs_8x8[type] [vp8_coef_bands[c]] [pt] [t];
        cost += vp8_dct_value_cost_ptr[v];
        pt = vp8_prev_token_class[t];
    }

# undef QC2X2
    if (c < 4)
        cost += mb->token_costs_8x8 [type][vp8_coef_bands[c]]
                                    [pt] [DCT_EOB_TOKEN];

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


static int cost_coeffs_8x8(MACROBLOCK *mb,
                           BLOCKD *b, int type,
                           ENTROPY_CONTEXT *a, ENTROPY_CONTEXT *l,
                           ENTROPY_CONTEXT *a1, ENTROPY_CONTEXT *l1)
{
    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_8x8(pt, *a, *l, *a1, *l1);

# define QC8X8( I)  ( qcoeff_ptr [vp8_default_zig_zag1d_8x8[I]] )

    for (; c < eob; c++)
    {
        int v = QC8X8(c);
        int t = vp8_dct_value_tokens_ptr[v].Token;
        cost += mb->token_costs_8x8[type] [vp8_coef_bands_8x8[c]] [pt] [t];
        cost += vp8_dct_value_cost_ptr[v];
        pt = vp8_prev_token_class[t];
    }

# undef QC8X8
    if (c < 64)
        cost += mb->token_costs_8x8 [type][vp8_coef_bands_8x8[c]]
                                    [pt] [DCT_EOB_TOKEN];

    pt = (c != !type); // is eob first coefficient;
    *a = *l = pt;
    return cost;
}
static int vp8_rdcost_mby_8x8(MACROBLOCK *mb)
{
    int cost = 0;
    int b;
    MACROBLOCKD *x = &mb->e_mbd;
    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));

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

    for (b = 0; b < 16; b+=4)
        cost += cost_coeffs_8x8(mb, x->block + b, PLANE_TYPE_Y_NO_DC,
                    ta + vp8_block2above[b], tl + vp8_block2left[b],
742
                    ta + vp8_block2above[b+1], tl + vp8_block2left[b+4]);
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
772
773
774
775
776
777
778
779

    cost += cost_coeffs_2x2(mb, x->block + 24, PLANE_TYPE_Y2,
                ta + vp8_block2above[24], tl + vp8_block2left[24]);
    return cost;
}

static void macro_block_yrd_8x8( MACROBLOCK *mb,
                             int *Rate,
                             int *Distortion,
                             const VP8_ENCODER_RTCD *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;

    ENCODEMB_INVOKE(&rtcd->encodemb, submby)
        ( mb->src_diff, *(mb->block[0].base_src),
        mb->e_mbd.predictor, mb->block[0].src_stride );

    vp8_transform_mby_8x8(mb);
    vp8_quantize_mby_8x8(mb);

    /* remove 1st order dc to properly combine 1st/2nd order distortion */
    mb->coeff[0] = 0;
    mb->coeff[64] = 0;
    mb->coeff[128] = 0;
    mb->coeff[192] = 0;
    mb->e_mbd.dqcoeff[0] = 0;
    mb->e_mbd.dqcoeff[64] = 0;
    mb->e_mbd.dqcoeff[128] = 0;
    mb->e_mbd.dqcoeff[192] = 0;
    d = ENCODEMB_INVOKE(&rtcd->encodemb, mberr)(mb, 0) << 2;

780
    d += ENCODEMB_INVOKE(&rtcd->encodemb, berr)(mb_y2->coeff, x_y2->dqcoeff)<<2;
781
782
783
784
785
786

    *Distortion = (d >> 4);
    // rate
    *Rate = vp8_rdcost_mby_8x8(mb);
}
#endif
787

788
static void copy_predictor(unsigned char *dst, const unsigned char *predictor)
789
{
790
791
792
793
794
795
    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];
796
}
Yaowu Xu's avatar
Yaowu Xu committed
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819

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];
}

820
static int rd_pick_intra4x4block(
John Koleszar's avatar
John Koleszar committed
821
822
823
824
825
    VP8_COMP *cpi,
    MACROBLOCK *x,
    BLOCK *be,
    BLOCKD *b,
    B_PREDICTION_MODE *best_mode,
826
    unsigned int *bmode_costs,
John Koleszar's avatar
John Koleszar committed
827
828
829
830
831
832
833
834
    ENTROPY_CONTEXT *a,
    ENTROPY_CONTEXT *l,

    int *bestrate,
    int *bestratey,
    int *bestdistortion)
{
    B_PREDICTION_MODE mode;
835
    int best_rd = INT_MAX;
John Koleszar's avatar
John Koleszar committed
836
837
838
839
840
    int rate = 0;
    int distortion;

    ENTROPY_CONTEXT ta = *a, tempa = *a;
    ENTROPY_CONTEXT tl = *l, templ = *l;
841
842
843
844
845
846
847
    /*
     * 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
848
849
850
851
852
853

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

854
855
856
857
858
#if CONFIG_SUPERBLOCKS
        // Ignore modes thact need the above-right data
        if (mode==B_LD_PRED || mode==B_VL_PRED)
            continue;
#endif
859
860
        rate = bmode_costs[mode];

861
862
        RECON_INVOKE(&cpi->rtcd.common->recon, intra4x4_predict)
                     (b, mode, b->predictor);
863
864
865
        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
866
867
868
869

        tempa = ta;
        templ = tl;

Scott LaVarnway's avatar
Scott LaVarnway committed
870
        ratey = cost_coeffs(x, b, PLANE_TYPE_Y_WITH_DC, &tempa, &templ);
John Koleszar's avatar
John Koleszar committed
871
872
873
874
875
876
877
878
879
880
881
882
883
884
        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;
885
886
            copy_predictor(best_predictor, b->predictor);
            vpx_memcpy(best_dqcoeff, b->dqcoeff, 32);
John Koleszar's avatar
John Koleszar committed
887
888
        }
    }
Scott LaVarnway's avatar
Scott LaVarnway committed
889
    b->bmi.as_mode = (B_PREDICTION_MODE)(*best_mode);
890

891
892
    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
893

894
    return best_rd;
John Koleszar's avatar
John Koleszar committed
895
896
}

897
898
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
899
900
901
902
903
904
{
    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;
905
    int64_t total_rd = 0;
906
907
908
    ENTROPY_CONTEXT_PLANES t_above, t_left;
    ENTROPY_CONTEXT *ta;
    ENTROPY_CONTEXT *tl;
909
    unsigned int *bmode_costs;
910
911
912
913
914
915

    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
916

917
#if !CONFIG_SUPERBLOCKS
John Koleszar's avatar
John Koleszar committed
918
    vp8_intra_prediction_down_copy(xd);
919
#endif
John Koleszar's avatar
John Koleszar committed
920

921
922
    bmode_costs = mb->inter_bmode_costs;

John Koleszar's avatar
John Koleszar committed
923
924
925
926
927
928
929
    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);

930
931
        if (mb->e_mbd.frame_type == KEY_FRAME)
        {
Scott LaVarnway's avatar
Scott LaVarnway committed
932
933
            const B_PREDICTION_MODE A = above_block_mode(mic, i, mis);
            const B_PREDICTION_MODE L = left_block_mode(mic, i);
934
935
936
937

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

938
        total_rd += rd_pick_intra4x4block(
939
            cpi, mb, mb->block + i, xd->block + i, &best_mode, bmode_costs,
940
941
            ta + vp8_block2above[i],
            tl + vp8_block2left[i], &r, &ry, &d);
John Koleszar's avatar
John Koleszar committed
942
943
944
945

        cost += r;
        distortion += d;
        tot_rate_y += ry;
Scott LaVarnway's avatar
Scott LaVarnway committed
946
947

        mic->bmi[i].as_mode = best_mode;
948

949
        if(total_rd >= (int64_t)best_rd)
950
            break;
John Koleszar's avatar
John Koleszar committed
951
952
    }

953
    if(total_rd >= (int64_t)best_rd)
954
        return INT_MAX;
955

John Koleszar's avatar
John Koleszar committed
956
957
958
959
960
961
    *Rate = cost;
    *rate_y += tot_rate_y;
    *Distortion = distortion;

    return RDCOST(mb->rdmult, mb->rddiv, cost, distortion);
}
962
963
964
965
966
967
968


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
969
970
971
972
{
    MB_PREDICTION_MODE mode;
    MB_PREDICTION_MODE UNINITIALIZED_IS_SAFE(mode_selected);
    int rate, ratey;
973
    int distortion;
John Koleszar's avatar
John Koleszar committed
974
    int best_rd = INT_MAX;
975
    int this_rd;
John Koleszar's avatar
John Koleszar committed
976
977
978
979

    //Y Search for 16x16 intra prediction mode
    for (mode = DC_PRED; mode <= TM_PRED; mode++)
    {
980
        x->e_mbd.mode_info_context->mbmi.mode = mode;
John Koleszar's avatar
John Koleszar committed
981

982
983
        RECON_INVOKE(&cpi->common.rtcd.recon, build_intra_predictors_mby)
            (&x->e_mbd);
John Koleszar's avatar
John Koleszar committed
984

985
986
987
        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
988
989
990
991
992
993
994
995
996

        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;
997
            *Distortion = distortion;
John Koleszar's avatar
John Koleszar committed
998
999
1000
        }
    }

For faster browsing, not all history is shown. View entire blame