Mercurial > libavcodec.hg
view xiph.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 | 2acf0ae7b041 |
children |
line wrap: on
line source
/* * Copyright (C) 2007 FFmpeg Project * * 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 */ #include "libavutil/intreadwrite.h" #include "xiph.h" int ff_split_xiph_headers(uint8_t *extradata, int extradata_size, int first_header_size, uint8_t *header_start[3], int header_len[3]) { int i; if (extradata_size >= 6 && AV_RB16(extradata) == first_header_size) { int overall_len = 6; for (i=0; i<3; i++) { header_len[i] = AV_RB16(extradata); extradata += 2; header_start[i] = extradata; extradata += header_len[i]; if (overall_len > extradata_size - header_len[i]) return -1; overall_len += header_len[i]; } } else if (extradata_size >= 3 && extradata_size < INT_MAX - 0x1ff && extradata[0] == 2) { int overall_len = 3; extradata++; for (i=0; i<2; i++, extradata++) { header_len[i] = 0; for (; overall_len < extradata_size && *extradata==0xff; extradata++) { header_len[i] += 0xff; overall_len += 0xff + 1; } header_len[i] += *extradata; overall_len += *extradata; if (overall_len > extradata_size) return -1; } header_len[2] = extradata_size - overall_len; header_start[0] = extradata; header_start[1] = header_start[0] + header_len[0]; header_start[2] = header_start[1] + header_len[1]; } else { return -1; } return 0; }