Skip to content

F
ffmpeg.wasm-core
Commit aac8b769 authored by Jason Garrett-Glaser's avatar Jason Garrett-Glaser
Browse files
Options

H.264 loopfilter speed tweaks 

Originally committed as revision 16240 to svn://svn.ffmpeg.org/ffmpeg/trunk
parent a22eff36
Hide whitespace changes
Inline Side-by-side
Showing with 46 additions and 38 deletions
libavcodec/h264.c
View file @ aac8b769
...@@ -5848,8 +5848,10 @@ static void filter_mb_edgev( H264Context *h, uint8_t *pix, int stride, int16_t b ...@@ -5848,8 +5848,10 @@ static void filter_mb_edgev( H264Context *h, uint8_t *pix, int stride, int16_t b
if( bS[0] < 4 ) { if( bS[0] < 4 ) {
int8_t tc[4]; int8_t tc[4];
for(i=0; i<4; i++) tc[0] = (tc0_table+52)[index_a][bS[0]];
tc[i] = bS[i] ? (tc0_table+52)[index_a][bS[i] - 1] : -1; tc[1] = (tc0_table+52)[index_a][bS[1]];
tc[2] = (tc0_table+52)[index_a][bS[2]];
tc[3] = (tc0_table+52)[index_a][bS[3]];
h->s.dsp.h264_h_loop_filter_luma(pix, stride, alpha, beta, tc); h->s.dsp.h264_h_loop_filter_luma(pix, stride, alpha, beta, tc);
} else { } else {
h->s.dsp.h264_h_loop_filter_luma_intra(pix, stride, alpha, beta); h->s.dsp.h264_h_loop_filter_luma_intra(pix, stride, alpha, beta);
...@@ -5863,8 +5865,10 @@ static void filter_mb_edgecv( H264Context *h, uint8_t *pix, int stride, int16_t ...@@ -5863,8 +5865,10 @@ static void filter_mb_edgecv( H264Context *h, uint8_t *pix, int stride, int16_t
if( bS[0] < 4 ) { if( bS[0] < 4 ) {
int8_t tc[4]; int8_t tc[4];
for(i=0; i<4; i++) tc[0] = (tc0_table+52)[index_a][bS[0]]+1;
tc[i] = bS[i] ? (tc0_table+52)[index_a][bS[i] - 1] + 1 : 0; tc[1] = (tc0_table+52)[index_a][bS[1]]+1;
tc[2] = (tc0_table+52)[index_a][bS[2]]+1;
tc[3] = (tc0_table+52)[index_a][bS[3]]+1;
h->s.dsp.h264_h_loop_filter_chroma(pix, stride, alpha, beta, tc); h->s.dsp.h264_h_loop_filter_chroma(pix, stride, alpha, beta, tc);
} else { } else {
h->s.dsp.h264_h_loop_filter_chroma_intra(pix, stride, alpha, beta); h->s.dsp.h264_h_loop_filter_chroma_intra(pix, stride, alpha, beta);
...@@ -5895,7 +5899,7 @@ static void filter_mb_mbaff_edgev( H264Context *h, uint8_t *pix, int stride, int ...@@ -5895,7 +5899,7 @@ static void filter_mb_mbaff_edgev( H264Context *h, uint8_t *pix, int stride, int
beta = (beta_table+52)[qp[qp_index] + h->slice_beta_offset]; beta = (beta_table+52)[qp[qp_index] + h->slice_beta_offset];
if( bS[bS_index] < 4 ) { if( bS[bS_index] < 4 ) {
const int tc0 = (tc0_table+52)[index_a][bS[bS_index] - 1]; const int tc0 = (tc0_table+52)[index_a][bS[bS_index]];
const int p0 = pix[-1]; const int p0 = pix[-1];
const int p1 = pix[-2]; const int p1 = pix[-2];
const int p2 = pix[-3]; const int p2 = pix[-3];
...@@ -5989,7 +5993,7 @@ static void filter_mb_mbaff_edgecv( H264Context *h, uint8_t *pix, int stride, in ...@@ -5989,7 +5993,7 @@ static void filter_mb_mbaff_edgecv( H264Context *h, uint8_t *pix, int stride, in
beta = (beta_table+52)[qp[qp_index] + h->slice_beta_offset]; beta = (beta_table+52)[qp[qp_index] + h->slice_beta_offset];
if( bS[bS_index] < 4 ) { if( bS[bS_index] < 4 ) {
const int tc = (tc0_table+52)[index_a][bS[bS_index] - 1] + 1; const int tc = (tc0_table+52)[index_a][bS[bS_index]] + 1;
const int p0 = pix[-1]; const int p0 = pix[-1];
const int p1 = pix[-2]; const int p1 = pix[-2];
const int q0 = pix[0]; const int q0 = pix[0];
...@@ -6031,8 +6035,10 @@ static void filter_mb_edgeh( H264Context *h, uint8_t *pix, int stride, int16_t b ...@@ -6031,8 +6035,10 @@ static void filter_mb_edgeh( H264Context *h, uint8_t *pix, int stride, int16_t b
if( bS[0] < 4 ) { if( bS[0] < 4 ) {
int8_t tc[4]; int8_t tc[4];
for(i=0; i<4; i++) tc[0] = (tc0_table+52)[index_a][bS[0]];
tc[i] = bS[i] ? (tc0_table+52)[index_a][bS[i] - 1] : -1; tc[1] = (tc0_table+52)[index_a][bS[1]];
tc[2] = (tc0_table+52)[index_a][bS[2]];
tc[3] = (tc0_table+52)[index_a][bS[3]];
h->s.dsp.h264_v_loop_filter_luma(pix, stride, alpha, beta, tc); h->s.dsp.h264_v_loop_filter_luma(pix, stride, alpha, beta, tc);
} else { } else {
h->s.dsp.h264_v_loop_filter_luma_intra(pix, stride, alpha, beta); h->s.dsp.h264_v_loop_filter_luma_intra(pix, stride, alpha, beta);
...@@ -6047,8 +6053,10 @@ static void filter_mb_edgech( H264Context *h, uint8_t *pix, int stride, int16_t ...@@ -6047,8 +6053,10 @@ static void filter_mb_edgech( H264Context *h, uint8_t *pix, int stride, int16_t
if( bS[0] < 4 ) { if( bS[0] < 4 ) {
int8_t tc[4]; int8_t tc[4];
for(i=0; i<4; i++) tc[0] = (tc0_table+52)[index_a][bS[0]]+1;
tc[i] = bS[i] ? (tc0_table+52)[index_a][bS[i] - 1] + 1 : 0; tc[1] = (tc0_table+52)[index_a][bS[1]]+1;
tc[2] = (tc0_table+52)[index_a][bS[2]]+1;
tc[3] = (tc0_table+52)[index_a][bS[3]]+1;
h->s.dsp.h264_v_loop_filter_chroma(pix, stride, alpha, beta, tc); h->s.dsp.h264_v_loop_filter_chroma(pix, stride, alpha, beta, tc);
} else { } else {
h->s.dsp.h264_v_loop_filter_chroma_intra(pix, stride, alpha, beta); h->s.dsp.h264_v_loop_filter_chroma_intra(pix, stride, alpha, beta);
......
libavcodec/h264data.h
View file @ aac8b769
...@@ -547,34 +547,34 @@ static const uint8_t beta_table[52*3] = { ...@@ -547,34 +547,34 @@ static const uint8_t beta_table[52*3] = {
18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18,
18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18,
}; };
static const uint8_t tc0_table[52*3][3] = { static const uint8_t tc0_table[52*3][4] = {
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 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 },
{ 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 0 }, { 0, 0, 1 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 0 }, {-1, 0, 0, 1 },
{ 0, 0, 1 }, { 0, 0, 1 }, { 0, 0, 1 }, { 0, 1, 1 }, { 0, 1, 1 }, { 1, 1, 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, 2 }, { 1, 1, 2 }, { 1, 1, 2 }, {-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, 2 }, { 1, 2, 3 }, { 1, 2, 3 }, { 2, 2, 3 }, { 2, 2, 4 }, { 2, 3, 4 }, {-1, 1, 1, 2 }, {-1, 1, 2, 3 }, {-1, 1, 2, 3 }, {-1, 2, 2, 3 }, {-1, 2, 2, 4 }, {-1, 2, 3, 4 },
{ 2, 3, 4 }, { 3, 3, 5 }, { 3, 4, 6 }, { 3, 4, 6 }, { 4, 5, 7 }, { 4, 5, 8 }, {-1, 2, 3, 4 }, {-1, 3, 3, 5 }, {-1, 3, 4, 6 }, {-1, 3, 4, 6 }, {-1, 4, 5, 7 }, {-1, 4, 5, 8 },
{ 4, 6, 9 }, { 5, 7,10 }, { 6, 8,11 }, { 6, 8,13 }, { 7,10,14 }, { 8,11,16 }, {-1, 4, 6, 9 }, {-1, 5, 7,10 }, {-1, 6, 8,11 }, {-1, 6, 8,13 }, {-1, 7,10,14 }, {-1, 8,11,16 },
{ 9,12,18 }, {10,13,20 }, {11,15,23 }, {13,17,25 }, {-1, 9,12,18 }, {-1,10,13,20 }, {-1,11,15,23 }, {-1,13,17,25 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {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 },
{13,17,25 }, {13,17,25 }, {13,17,25 }, {13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 }, {-1,13,17,25 },
}; };
/* Cabac pre state table */ /* Cabac pre state table */
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment