Mercurial > libavcodec.hg
comparison x86/vp56_arith.h @ 12256:6e6c92d36c4b libavcodec
Inline asm for VP56 arith coder
This is a lot more reliable to get cmov rather than trying to trick gcc into
generating it, useful since it's 2% faster overall.
Patch by Eli Friedman <eli.friedman at gmail>
author | conrad |
---|---|
date | Fri, 23 Jul 2010 21:46:30 +0000 |
parents | |
children | eba266986930 |
comparison
equal
deleted
inserted
replaced
12255:7db147ea02c4 | 12256:6e6c92d36c4b |
---|---|
1 /** | |
2 * VP5 and VP6 compatible video decoder (arith decoder) | |
3 * | |
4 * Copyright (C) 2006 Aurelien Jacobs <aurel@gnuage.org> | |
5 * Copyright (C) 2010 Eli Friedman | |
6 * | |
7 * This file is part of FFmpeg. | |
8 * | |
9 * FFmpeg is free software; you can redistribute it and/or | |
10 * modify it under the terms of the GNU Lesser General Public | |
11 * License as published by the Free Software Foundation; either | |
12 * version 2.1 of the License, or (at your option) any later version. | |
13 * | |
14 * FFmpeg is distributed in the hope that it will be useful, | |
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of | |
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
17 * Lesser General Public License for more details. | |
18 * | |
19 * You should have received a copy of the GNU Lesser General Public | |
20 * License along with FFmpeg; if not, write to the Free Software | |
21 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA | |
22 */ | |
23 | |
24 #ifndef AVCODEC_X86_VP56_ARITH_H | |
25 #define AVCODEC_X86_VP56_ARITH_H | |
26 | |
27 #if HAVE_FAST_CMOV | |
28 #define vp56_rac_get_prob vp56_rac_get_prob | |
29 static inline int vp56_rac_get_prob(VP56RangeCoder *c, uint8_t prob) | |
30 { | |
31 unsigned int code_word = vp56_rac_renorm(c); | |
32 unsigned int high = c->high; | |
33 unsigned int low = 1 + (((high - 1) * prob) >> 8); | |
34 unsigned int low_shift = low << 8; | |
35 int bit = 0; | |
36 | |
37 __asm__( | |
38 "subl %4, %1 \n\t" | |
39 "subl %3, %2 \n\t" | |
40 "leal (%2, %3), %3 \n\t" | |
41 "setae %b0 \n\t" | |
42 "cmovb %4, %1 \n\t" | |
43 "cmovb %3, %2 \n\t" | |
44 : "+q"(bit), "+r"(high), "+r"(code_word), "+r"(low_shift) | |
45 : "r"(low) | |
46 ); | |
47 | |
48 c->high = high; | |
49 c->code_word = code_word; | |
50 return bit; | |
51 } | |
52 #endif | |
53 | |
54 #endif /* AVCODEC_X86_VP56_ARITH_H */ |