]> git.sesse.net Git - ffmpeg/commit
Rather call filter_mb_mbaff_edge*v() more often than do extra calculations
authorMichael Niedermayer <michaelni@gmx.at>
Mon, 18 Jan 2010 21:22:09 +0000 (21:22 +0000)
committerMichael Niedermayer <michaelni@gmx.at>
Mon, 18 Jan 2010 21:22:09 +0000 (21:22 +0000)
commitbffe82f504622c56a41918b5a5e06cf0826d6953
treeb0bedb3e026395e16b4acb124be9ec2f4fc36eb5
parent34ba23c975a598de58c1feb5b799d2f5d78f5dbc
Rather call filter_mb_mbaff_edge*v() more often than do extra calculations
in the innerst loop. ~150 cpu cycles faster

Originally committed as revision 21299 to svn://svn.ffmpeg.org/ffmpeg/trunk
libavcodec/h264_loopfilter.c