[FFmpeg-cvslog] r16207 - trunk/libavcodec/h264.c
michael
subversion
Thu Dec 18 03:53:18 CET 2008
Author: michael
Date: Thu Dec 18 03:53:18 2008
New Revision: 16207
Log:
Use the new idct functions (except chroma as it was slower in benchmarks)
cathedral +0.5% speed
aladin +0.6% speed [note aladin has been cat-ed 10 times to reduce the influence
of init time]
Speedup also verified via START/STOP_TIMER (difference was very significant
for the changed parts)
Modified:
trunk/libavcodec/h264.c
Modified: trunk/libavcodec/h264.c
==============================================================================
--- trunk/libavcodec/h264.c (original)
+++ trunk/libavcodec/h264.c Thu Dec 18 03:53:18 2008
@@ -2515,27 +2515,34 @@ static av_always_inline void hl_decode_m
if(!IS_INTRA4x4(mb_type)){
if(is_h264){
if(IS_INTRA16x16(mb_type)){
- if(transform_bypass && h->sps.profile_idc==244 && (h->intra16x16_pred_mode==VERT_PRED8x8 || h->intra16x16_pred_mode==HOR_PRED8x8)){
+ if(transform_bypass){
+ if(h->sps.profile_idc==244 && (h->intra16x16_pred_mode==VERT_PRED8x8 || h->intra16x16_pred_mode==HOR_PRED8x8)){
h->hpc.pred16x16_add[h->intra16x16_pred_mode](dest_y, block_offset, h->mb, linesize);
}else{
for(i=0; i<16; i++){
- if(h->non_zero_count_cache[ scan8[i] ])
+ if(h->non_zero_count_cache[ scan8[i] ] || h->mb[i*16])
idct_add (dest_y + block_offset[i], h->mb + i*16, linesize);
- else if(h->mb[i*16])
- idct_dc_add(dest_y + block_offset[i], h->mb + i*16, linesize);
}
+ }
+ }else{
+ s->dsp.h264_idct_add16intra(dest_y, block_offset, h->mb, linesize, h->non_zero_count_cache);
}
}else if(h->cbp&15){
+ if(transform_bypass){
const int di = IS_8x8DCT(mb_type) ? 4 : 1;
for(i=0; i<16; i+=di){
int nnz = h->non_zero_count_cache[ scan8[i] ];
if(nnz){
- if(nnz==1 && h->mb[i*16])
- idct_dc_add(dest_y + block_offset[i], h->mb + i*16, linesize);
- else
idct_add(dest_y + block_offset[i], h->mb + i*16, linesize);
}
}
+ }else{
+ if(IS_8x8DCT(mb_type)){
+ s->dsp.h264_idct8_add4(dest_y, block_offset, h->mb, linesize, h->non_zero_count_cache);
+ }else{
+ s->dsp.h264_idct_add16(dest_y, block_offset, h->mb, linesize, h->non_zero_count_cache);
+ }
+ }
}
}else{
for(i=0; i<16; i++){
More information about the ffmpeg-cvslog
mailing list