Mercurial > libavcodec.hg
view h261.c @ 12492:58a960d6e34c libavcodec
Rename h264_idct_sse2.asm to h264_idct.asm; move inline IDCT asm from
h264dsp_mmx.c to h264_idct.asm (as yasm code). Because the loops are now
coded in asm instead of C, this is (depending on the function) up to 50%
faster for cases where gcc didn't do a great job at looping.
Since h264_idct_add8() is now faster than the manual loop setup in h264.c,
in-asm idct calling can now be enabled for chroma as well (see r16207). For
MMX, this is 5% faster. For SSE2 (which isn't done for chroma if h264.c does
the looping), this makes it up to 50% faster. Speed gain overall is ~0.5-1.0%.
author | rbultje |
---|---|
date | Tue, 14 Sep 2010 13:36:26 +0000 |
parents | 7dd2a45249a9 |
children |
line wrap: on
line source
/* * H261 common code * Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at> * Copyright (c) 2004 Maarten Daniels * * This file is part of FFmpeg. * * FFmpeg is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * * FFmpeg is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public * License along with FFmpeg; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA */ /** * @file * h261codec. */ #include "dsputil.h" #include "avcodec.h" #include "h261.h" #define IS_FIL(a) ((a)&MB_TYPE_H261_FIL) uint8_t ff_h261_rl_table_store[2][2*MAX_RUN + MAX_LEVEL + 3]; void ff_h261_loop_filter(MpegEncContext *s){ H261Context * h= (H261Context*)s; const int linesize = s->linesize; const int uvlinesize= s->uvlinesize; uint8_t *dest_y = s->dest[0]; uint8_t *dest_cb= s->dest[1]; uint8_t *dest_cr= s->dest[2]; if(!(IS_FIL (h->mtype))) return; s->dsp.h261_loop_filter(dest_y , linesize); s->dsp.h261_loop_filter(dest_y + 8, linesize); s->dsp.h261_loop_filter(dest_y + 8 * linesize , linesize); s->dsp.h261_loop_filter(dest_y + 8 * linesize + 8, linesize); s->dsp.h261_loop_filter(dest_cb, uvlinesize); s->dsp.h261_loop_filter(dest_cr, uvlinesize); }