static void fdec_filter_row( x264_t *h, int mb_y, int pass )
{
/* mb_y is the mb to be encoded next, not the mb to be filtered here */
int b_hpel = h->fdec->b_kept_as_ref;
int b_deblock = h->sh.i_disable_deblocking_filter_idc != 1;
int b_end = mb_y == h->i_threadslice_end;
int b_measure_quality = 1;
int min_y = mb_y - (1 << SLICE_MBAFF);
int b_start = min_y == h->i_threadslice_start;
/* Even in interlaced mode, deblocking never modifies more than 4 pixels
* above each MB, as bS=4 doesn't happen for the top of interlaced mbpairs. */
int minpix_y = min_y*16 - 4 * !b_start;
int maxpix_y = mb_y*16 - 4 * !b_end;
b_deblock &= b_hpel || h->param.b_full_recon || h->param.psz_dump_yuv;
if( h->param.b_sliced_threads )
{
switch( pass )
{
/* During encode: only do deblock if asked for */
default:
case 0:
b_deblock &= h->param.b_full_recon;
b_hpel = 0;
break;
/* During post-encode pass: do deblock if not done yet, do hpel for all
* rows except those between slices. */
case 1:
b_deblock &= !h->param.b_full_recon;
b_hpel &= !(b_start && min_y > 0);
b_measure_quality = 0;
break;
/* Final pass: do the rows between slices in sequence. */
case 2:
b_deblock = 0;
b_measure_quality = 0;
break;
}
}
if( mb_y & SLICE_MBAFF )
return;
if( min_y < h->i_threadslice_start )
return;
if( b_deblock )
for( int y = min_y; y < mb_y; y += (1 << SLICE_MBAFF) )
x264_frame_deblock_row( h, y );
/* FIXME: Prediction requires different borders for interlaced/progressive mc,
* but the actual image data is equivalent. For now, maintain this
* consistency by copying deblocked pixels between planes. */
if( PARAM_INTERLACED && (!h->param.b_sliced_threads || pass == 1) )
for( int p = 0; p < h->fdec->i_plane; p++ )
for( int i = minpix_y>>(CHROMA_V_SHIFT && p); i < maxpix_y>>(CHROMA_V_SHIFT && p); i++ )
memcpy( h->fdec->plane_fld[p] + i*h->fdec->i_stride[p],
h->fdec->plane[p] + i*h->fdec->i_stride[p],
h->mb.i_mb_width*16*SIZEOF_PIXEL );
if( h->fdec->b_kept_as_ref && (!h->param.b_sliced_threads || pass == 1) )
x264_frame_expand_border( h, h->fdec, min_y );
if( b_hpel )
{
int end = mb_y == h->mb.i_mb_height;
/* Can't do hpel until the previous slice is done encoding. */
if( h->param.analyse.i_subpel_refine )
{
x264_frame_filter( h, h->fdec, min_y, end );
x264_frame_expand_border_filtered( h, h->fdec, min_y, end );
}
}
if( SLICE_MBAFF && pass == 0 )
for( int i = 0; i < 3; i++ )
{
XCHG( pixel *, h->intra_border_backup[0][i], h->intra_border_backup[3][i] );
XCHG( pixel *, h->intra_border_backup[1][i], h->intra_border_backup[4][i] );
}
if( h->i_thread_frames > 1 && h->fdec->b_kept_as_ref )
x264_frame_cond_broadcast( h->fdec, mb_y*16 + (b_end ? 10000 : -(X264_THREAD_HEIGHT << SLICE_MBAFF)) );
if( b_measure_quality )
{
maxpix_y = X264_MIN( maxpix_y, h->param.i_height );
if( h->param.analyse.b_psnr )
{
for( int p = 0; p < (CHROMA444 ? 3 : 1); p++ )
h->stat.frame.i_ssd[p] += x264_pixel_ssd_wxh( &h->pixf,
h->fdec->plane[p] + minpix_y * h->fdec->i_stride[p], h->fdec->i_stride[p],
h->fenc->plane[p] + minpix_y * h->fenc->i_stride[p], h->fenc->i_stride[p],
h->param.i_width, maxpix_y-minpix_y );
if( !CHROMA444 )
{
uint64_t ssd_u, ssd_v;
int v_shift = CHROMA_V_SHIFT;
x264_pixel_ssd_nv12( &h->pixf,
h->fdec->plane[1] + (minpix_y>>v_shift) * h->fdec->i_stride[1], h->fdec->i_stride[1],
h->fenc->plane[1] + (minpix_y>>v_shift) * h->fenc->i_stride[1], h->fenc->i_stride[1],
h->param.i_width>>1, (maxpix_y-minpix_y)>>v_shift, &ssd_u, &ssd_v );
h->stat.frame.i_ssd[1] += ssd_u;
h->stat.frame.i_ssd[2] += ssd_v;
}
}
if( h->param.analyse.b_ssim )
{
int ssim_cnt;
x264_emms();
/* offset by 2 pixels to avoid alignment of ssim blocks with dct blocks,
* and overlap by 4 */
minpix_y += b_start ? 2 : -6;
h->stat.frame.f_ssim +=
x264_pixel_ssim_wxh( &h->pixf,
h->fdec->plane[0] + 2+minpix_y*h->fdec->i_stride[0], h->fdec->i_stride[0],
h->fenc->plane[0] + 2+minpix_y*h->fenc->i_stride[0], h->fenc->i_stride[0],
h->param.i_width-2, maxpix_y-minpix_y, h->scratch_buffer, &ssim_cnt );
h->stat.frame.i_ssim_cnt += ssim_cnt;
}
}
}