Mercurial > libavcodec.hg
view cavsdsp.h @ 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 | 1241c824de46 |
children |
line wrap: on
line source
/* * Chinese AVS video (AVS1-P2, JiZhun profile) decoder. * Copyright (c) 2006 Stefan Gehrer <stefan.gehrer@gmx.de> * * 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 */ #ifndef AVCODEC_CAVSDSP_H #define AVCODEC_CAVSDSP_H #include <stdint.h> #include "dsputil.h" typedef struct CAVSDSPContext { qpel_mc_func put_cavs_qpel_pixels_tab[2][16]; qpel_mc_func avg_cavs_qpel_pixels_tab[2][16]; void (*cavs_filter_lv)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); void (*cavs_filter_lh)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); void (*cavs_filter_cv)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); void (*cavs_filter_ch)(uint8_t *pix, int stride, int alpha, int beta, int tc, int bs1, int bs2); void (*cavs_idct8_add)(uint8_t *dst, DCTELEM *block, int stride); } CAVSDSPContext; void ff_cavsdsp_init(CAVSDSPContext* c, AVCodecContext *avctx); void ff_cavsdsp_init_mmx(CAVSDSPContext* c, AVCodecContext *avctx); #endif