-static void restore_cavlc_nnz_row( x264_t *h, int mb_y, uint8_t (*buf)[16] )
-{
- uint8_t (*dst)[24] = h->mb.non_zero_count + mb_y * h->sps->i_mb_width;
- for( int x = 0; x < h->sps->i_mb_width; x++ )
- memcpy( dst+x, buf+x, 16 );
-}
-
-static void munge_cavlc_nnz( x264_t *h, int mb_y, uint8_t (*buf)[16], void (*func)(x264_t*, int, uint8_t (*)[16]) )
-{
- func( h, mb_y, buf );
- if( mb_y > 0 )
- func( h, mb_y-1, buf + h->sps->i_mb_width );
- if( h->sh.b_mbaff )
- {
- func( h, mb_y+1, buf + h->sps->i_mb_width * 2 );
- if( mb_y > 0 )
- func( h, mb_y-2, buf + h->sps->i_mb_width * 3 );
- }
-}
-
-
-/* Deblocking filter */
-static const uint8_t i_alpha_table[52+12*2] =
-{
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 4, 4, 5, 6,
- 7, 8, 9, 10, 12, 13, 15, 17, 20, 22,
- 25, 28, 32, 36, 40, 45, 50, 56, 63, 71,
- 80, 90,101,113,127,144,162,182,203,226,
- 255,255,
- 255,255,255,255,255,255,255,255,255,255,255,255,
-};
-static const uint8_t i_beta_table[52+12*2] =
-{
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
- 0, 0, 0, 0, 0, 0, 2, 2, 2, 3,
- 3, 3, 3, 4, 4, 4, 6, 6, 7, 7,
- 8, 8, 9, 9, 10, 10, 11, 11, 12, 12,
- 13, 13, 14, 14, 15, 15, 16, 16, 17, 17,
- 18, 18,
- 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18,
-};
-static const int8_t i_tc0_table[52+12*2][4] =
-{
- {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 },
- {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 },
- {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 },
- {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 },
- {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 1 },
- {-1, 0, 0, 1 }, {-1, 0, 0, 1 }, {-1, 0, 0, 1 }, {-1, 0, 1, 1 }, {-1, 0, 1, 1 }, {-1, 1, 1, 1 },
- {-1, 1, 1, 1 }, {-1, 1, 1, 1 }, {-1, 1, 1, 1 }, {-1, 1, 1, 2 }, {-1, 1, 1, 2 }, {-1, 1, 1, 2 },
- {-1, 1, 1, 2 }, {-1, 1, 2, 3 }, {-1, 1, 2, 3 }, {-1, 2, 2, 3 }, {-1, 2, 2, 4 }, {-1, 2, 3, 4 },
- {-1, 2, 3, 4 }, {-1, 3, 3, 5 }, {-1, 3, 4, 6 }, {-1, 3, 4, 6 }, {-1, 4, 5, 7 }, {-1, 4, 5, 8 },
- {-1, 4, 6, 9 }, {-1, 5, 7,10 }, {-1, 6, 8,11 }, {-1, 6, 8,13 }, {-1, 7,10,14 }, {-1, 8,11,16 },
- {-1, 9,12,18 }, {-1,10,13,20 }, {-1,11,15,23 }, {-1,13,17,25 },
- {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 },
- {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 },
-};
-#define alpha_table(x) i_alpha_table[(x)+12]
-#define beta_table(x) i_beta_table[(x)+12]
-#define tc0_table(x) i_tc0_table[(x)+12]
-
-/* From ffmpeg */
-static inline void deblock_luma_c( uint8_t *pix, int xstride, int ystride, int alpha, int beta, int8_t *tc0 )
-{
- for( int i = 0; i < 4; i++ )
- {
- if( tc0[i] < 0 )
- {
- pix += 4*ystride;
- continue;
- }
- for( int d = 0; d < 4; d++ )
- {
- int p2 = pix[-3*xstride];
- int p1 = pix[-2*xstride];
- int p0 = pix[-1*xstride];
- int q0 = pix[ 0*xstride];
- int q1 = pix[ 1*xstride];
- int q2 = pix[ 2*xstride];
-
- if( abs( p0 - q0 ) < alpha && abs( p1 - p0 ) < beta && abs( q1 - q0 ) < beta )
- {
- int tc = tc0[i];
- int delta;
- if( abs( p2 - p0 ) < beta )
- {
- if( tc0[i] )
- pix[-2*xstride] = p1 + x264_clip3( (( p2 + ((p0 + q0 + 1) >> 1)) >> 1) - p1, -tc0[i], tc0[i] );
- tc++;
- }
- if( abs( q2 - q0 ) < beta )
- {
- if( tc0[i] )
- pix[ 1*xstride] = q1 + x264_clip3( (( q2 + ((p0 + q0 + 1) >> 1)) >> 1) - q1, -tc0[i], tc0[i] );
- tc++;
- }
-
- delta = x264_clip3( (((q0 - p0 ) << 2) + (p1 - q1) + 4) >> 3, -tc, tc );
- pix[-1*xstride] = x264_clip_uint8( p0 + delta ); /* p0' */
- pix[ 0*xstride] = x264_clip_uint8( q0 - delta ); /* q0' */
- }
- pix += ystride;
- }
- }
-}
-static void deblock_v_luma_c( uint8_t *pix, int stride, int alpha, int beta, int8_t *tc0 )
-{
- deblock_luma_c( pix, stride, 1, alpha, beta, tc0 );
-}
-static void deblock_h_luma_c( uint8_t *pix, int stride, int alpha, int beta, int8_t *tc0 )
-{
- deblock_luma_c( pix, 1, stride, alpha, beta, tc0 );
-}
-
-static inline void deblock_chroma_c( uint8_t *pix, int xstride, int ystride, int alpha, int beta, int8_t *tc0 )
-{
- for( int i = 0; i < 4; i++ )
- {
- int tc = tc0[i];
- if( tc <= 0 )
- {
- pix += 2*ystride;
- continue;
- }
- for( int d = 0; d < 2; d++ )
- {
- int p1 = pix[-2*xstride];
- int p0 = pix[-1*xstride];
- int q0 = pix[ 0*xstride];
- int q1 = pix[ 1*xstride];
-
- if( abs( p0 - q0 ) < alpha && abs( p1 - p0 ) < beta && abs( q1 - q0 ) < beta )
- {
- int delta = x264_clip3( (((q0 - p0 ) << 2) + (p1 - q1) + 4) >> 3, -tc, tc );
- pix[-1*xstride] = x264_clip_uint8( p0 + delta ); /* p0' */
- pix[ 0*xstride] = x264_clip_uint8( q0 - delta ); /* q0' */
- }
- pix += ystride;
- }
- }
-}
-static void deblock_v_chroma_c( uint8_t *pix, int stride, int alpha, int beta, int8_t *tc0 )
-{
- deblock_chroma_c( pix, stride, 1, alpha, beta, tc0 );
-}
-static void deblock_h_chroma_c( uint8_t *pix, int stride, int alpha, int beta, int8_t *tc0 )
-{
- deblock_chroma_c( pix, 1, stride, alpha, beta, tc0 );
-}
-
-static inline void deblock_luma_intra_c( uint8_t *pix, int xstride, int ystride, int alpha, int beta )
-{
- for( int d = 0; d < 16; d++ )
- {
- int p2 = pix[-3*xstride];
- int p1 = pix[-2*xstride];
- int p0 = pix[-1*xstride];
- int q0 = pix[ 0*xstride];
- int q1 = pix[ 1*xstride];
- int q2 = pix[ 2*xstride];
-
- if( abs( p0 - q0 ) < alpha && abs( p1 - p0 ) < beta && abs( q1 - q0 ) < beta )
- {
- if(abs( p0 - q0 ) < ((alpha >> 2) + 2) )
- {
- if( abs( p2 - p0 ) < beta ) /* p0', p1', p2' */
- {
- const int p3 = pix[-4*xstride];
- pix[-1*xstride] = ( p2 + 2*p1 + 2*p0 + 2*q0 + q1 + 4 ) >> 3;
- pix[-2*xstride] = ( p2 + p1 + p0 + q0 + 2 ) >> 2;
- pix[-3*xstride] = ( 2*p3 + 3*p2 + p1 + p0 + q0 + 4 ) >> 3;
- }
- else /* p0' */
- pix[-1*xstride] = ( 2*p1 + p0 + q1 + 2 ) >> 2;
- if( abs( q2 - q0 ) < beta ) /* q0', q1', q2' */
- {
- const int q3 = pix[3*xstride];
- pix[0*xstride] = ( p1 + 2*p0 + 2*q0 + 2*q1 + q2 + 4 ) >> 3;
- pix[1*xstride] = ( p0 + q0 + q1 + q2 + 2 ) >> 2;
- pix[2*xstride] = ( 2*q3 + 3*q2 + q1 + q0 + p0 + 4 ) >> 3;
- }
- else /* q0' */
- pix[0*xstride] = ( 2*q1 + q0 + p1 + 2 ) >> 2;
- }
- else /* p0', q0' */
- {
- pix[-1*xstride] = ( 2*p1 + p0 + q1 + 2 ) >> 2;
- pix[ 0*xstride] = ( 2*q1 + q0 + p1 + 2 ) >> 2;
- }
- }
- pix += ystride;
- }
-}
-static void deblock_v_luma_intra_c( uint8_t *pix, int stride, int alpha, int beta )
-{
- deblock_luma_intra_c( pix, stride, 1, alpha, beta );
-}
-static void deblock_h_luma_intra_c( uint8_t *pix, int stride, int alpha, int beta )