（十四）x264_slicetype_frame_cost帧损耗

x264_slicetype_frame_cost主要用来计算一个待编码帧的最优(最小)损耗，它内部最重要的操作是调用x264_slicetype_slice_cost函数，x264_slicetype_slice_cost函数会循环遍历一个编码帧中的所有宏块，对每个宏块进行帧内预测，帧间预测，并比较两种模式的损耗，得出损耗较小的值，并把它累计到frame的总损耗中。x264_slicetype_frame_cost的源码如下：

static int x264_slicetype_frame_cost( x264_t *h, x264_mb_analysis_t *a,
                                      x264_frame_t **frames, int p0, int p1, int b )
{
    int i_score = 0;
    int do_search[2];
    const x264_weight_t *w = x264_weight_none;
    x264_frame_t *fenc = frames[b];  //从预测队列中取出待编码帧

    /* Check whether we already evaluated this frame
     * If we have tried this frame as P, then we have also tried
     * the preceding frames as B. (is this still true?) */
    /* Also check that we already calculated the row SATDs for the current frame. */
    if( fenc->i_cost_est[b-p0][p1-b] >= 0 && (!h->param.rc.i_vbv_buffer_size || fenc->i_row_satds[b-p0][p1-b][0] != -1) )  //如果已经计算过损耗了
        i_score = fenc->i_cost_est[b-p0][p1-b];
    else
    {
        int dist_scale_factor = 128;

        /* For each list, check to see whether we have lowres motion-searched this reference frame before. */
        do_search[0] = b != p0 && fenc->lowres_mvs[0][b-p0-1][0][0] == 0x7FFF; //0x7FFF表示前向参考尚未进行运动搜索
        do_search[1] = b != p1 && fenc->lowres_mvs[1][p1-b-1][0][0] == 0x7FFF; //后向参考判断
        if( do_search[0] )
        {
            if( h->param.analyse.i_weighted_pred && b == p1 )
            {
                x264_emms();
                x264_weights_analyse( h, fenc, frames[p0], 1 );
                w = fenc->weight[0];
            }
            fenc->lowres_mvs[0][b-p0-1][0][0] = 0;
        }
        if( do_search[1] ) fenc->lowres_mvs[1][p1-b-1][0][0] = 0;

        if( p1 != p0 )
            dist_scale_factor = ( ((b-p0) << 8) + ((p1-p0) >> 1) ) / (p1-p0);

        int output_buf_size = h->mb.i_mb_height + (NUM_INTS + PAD_SIZE) * h->param.i_lookahead_threads;
        int *output_inter[X264_LOOKAHEAD_THREAD_MAX+1];  //保存帧间编码各类损耗，COST_EST，COST_EST_AQ等等
        int *output_intra[X264_LOOKAHEAD_THREAD_MAX+1];  //帧间的，同上
        output_inter[0] = h->scratch_buffer2;
        output_intra[0] = output_inter[0] + output_buf_size;

        {
            if( h->param.i_lookahead_threads > 1 )  //多线程的，暂不分析
            {
                x264_slicetype_slice_t s[X264_LOOKAHEAD_THREAD_MAX];

                for( int i = 0; i < h->param.i_lookahead_threads; i++ )
                {
                    x264_t *t = h->lookahead_thread[i];

                    /* FIXME move this somewhere else */
                    t->mb.i_me_method = h->mb.i_me_method;
                    t->mb.i_subpel_refine = h->mb.i_subpel_refine;
                    t->mb.b_chroma_me = h->mb.b_chroma_me;

                    s[i] = (x264_slicetype_slice_t){ t, a, frames, p0, p1, b, dist_scale_factor, do_search, w,
                        output_inter[i], output_intra[i] };

                    t->i_threadslice_start = ((h->mb.i_mb_height *  i    + h->param.i_lookahead_threads/2) / h->param.i_lookahead_threads);
                    t->i_threadslice_end   = ((h->mb.i_mb_height * (i+1) + h->param.i_lookahead_threads/2) / h->param.i_lookahead_threads);

                    int thread_height = t->i_threadslice_end - t->i_threadslice_start;
                    int thread_output_size = thread_height + NUM_INTS;
                    memset( output_inter[i], 0, thread_output_size * sizeof(int) );
                    memset( output_intra[i], 0, thread_output_size * sizeof(int) );
                    output_inter[i][NUM_ROWS] = output_intra[i][NUM_ROWS] = thread_height;

                    output_inter[i+1] = output_inter[i] + thread_output_size + PAD_SIZE;
                    output_intra[i+1] = output_intra[i] + thread_output_size + PAD_SIZE;

                    x264_threadpool_run( h->lookaheadpool, (void*)x264_slicetype_slice_cost, &s[i] );
                }
                for( int i = 0; i < h->param.i_lookahead_threads; i++ )
                    x264_threadpool_wait( h->lookaheadpool, &s[i] );
            }
            else  //单线程模式跳到这里
            {
                h->i_threadslice_start = 0;
                h->i_threadslice_end = h->mb.i_mb_height;
                memset( output_inter[0], 0, (output_buf_size - PAD_SIZE) * sizeof(int) );
                memset( output_intra[0], 0, (output_buf_size - PAD_SIZE) * sizeof(int) );
                output_inter[0][NUM_ROWS] = output_intra[0][NUM_ROWS] = h->mb.i_mb_height;
                x264_slicetype_slice_t s = (x264_slicetype_slice_t){ h, a, frames, p0, p1, b, dist_scale_factor, do_search, w,
                    output_inter[0], output_intra[0] };
                x264_slicetype_slice_cost( &s );  //计算待编码帧所有宏块的相关损耗，结果存到s里
            }

            /* Sum up accumulators */  //计算各类损耗总和
            if( b == p1 )
                fenc->i_intra_mbs[b-p0] = 0;
            if( !fenc->b_intra_calculated )
            {
                fenc->i_cost_est[0][0] = 0;
                fenc->i_cost_est_aq[0][0] = 0;
            }
            fenc->i_cost_est[b-p0][p1-b] = 0;
            fenc->i_cost_est_aq[b-p0][p1-b] = 0;

            int *row_satd_inter = fenc->i_row_satds[b-p0][p1-b];
            int *row_satd_intra = fenc->i_row_satds[0][0];
            for( int i = 0; i < h->param.i_lookahead_threads; i++ )
            {
                if( b == p1 )
                    fenc->i_intra_mbs[b-p0] += output_inter[i][INTRA_MBS];
                if( !fenc->b_intra_calculated )
                {
                    fenc->i_cost_est[0][0] += output_intra[i][COST_EST];
                    fenc->i_cost_est_aq[0][0] += output_intra[i][COST_EST_AQ];
                }

                fenc->i_cost_est[b-p0][p1-b] += output_inter[i][COST_EST];
                fenc->i_cost_est_aq[b-p0][p1-b] += output_inter[i][COST_EST_AQ];

                if( h->param.rc.i_vbv_buffer_size )
                {
                    int row_count = output_inter[i][NUM_ROWS];
                    memcpy( row_satd_inter, output_inter[i] + NUM_INTS, row_count * sizeof(int) );
                    if( !fenc->b_intra_calculated )
                        memcpy( row_satd_intra, output_intra[i] + NUM_INTS, row_count * sizeof(int) );
                    row_satd_inter += row_count;
                    row_satd_intra += row_count;
                }
            }

            i_score = fenc->i_cost_est[b-p0][p1-b];
            if( b != p1 )
                i_score = (uint64_t)i_score * 100 / (120 + h->param.i_bframe_bias);
            else
                fenc->b_intra_calculated = 1;

            fenc->i_cost_est[b-p0][p1-b] = i_score;  //i_cost_est存放最优(最小)损耗
            x264_emms();
        }
    }

    return i_score;
}