videolan
/
ffmpeg
mirror of https://git.videolan.org/git/ffmpeg.git
1
Fork 0
Code Releases Activity

Optimize decoding high freqs. 

this is 10-20cpu cycles faster on duron (whole is about 50-60 cpu cylses)
I wonder why gcc isnt doing this on its own ...

Originally committed as revision 23097 to svn://svn.ffmpeg.org/ffmpeg/trunk
This commit is contained in:
Michael Niedermayer 2010-05-11 21:10:55 +00:00
parent fd9451c68f
commit 0c0d88aed5
1 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
libavcodec/mpegaudiodec.c
View File

@ -1535,14 +1535,22 @@ static int huffman_decode(MPADecodeContext *s, GranuleDef *g,
g->sb_hybrid[s_index+3]= 0; g->sb_hybrid[s_index+3]= 0;
while(code){ while(code){
static const int idxtab[16]={3,3,2,2,1,1,1,1,0,0,0,0,0,0,0,0}; static const int idxtab[16]={3,3,2,2,1,1,1,1,0,0,0,0,0,0,0,0};
INTFLOAT v; int v;
int pos= s_index+idxtab[code]; int pos= s_index+idxtab[code];
code ^= 8>>idxtab[code]; code ^= 8>>idxtab[code];
v = RENAME(exp_table)[ exponents[pos] ]; /* Following is a optimized code for
// v = RENAME(exp_table)[ (exponents[pos]&3) ] >> FFMIN(0 - (exponents[pos]>>2), 31); INTFLOAT v = RENAME(exp_table)[ exponents[pos] ];
if(get_bits1(&s->gb)) //FIXME try to flip the sign bit in int32_t, same above if(get_bits1(&s->gb))
v = -v; v = -v;
g->sb_hybrid[pos] = v; g->sb_hybrid[pos] = v;
*/
#if CONFIG_FLOAT
v = AV_RN32A(RENAME(exp_table)+exponents[pos]) ^ (get_bits1(&s->gb)<<31);
AV_WN32A(g->sb_hybrid+pos, v);
#else
v= -get_bits1(&s->gb);
g->sb_hybrid[pos] = (RENAME(exp_table)[ exponents[pos] ] ^ v) - v;
#endif
} }
s_index+=4; s_index+=4;
} }