Mercurial > libavcodec.hg
diff x86/mlpdsp.c @ 12510:ef2f2db5b7be libavcodec
Unroll loop in h264_idct_add8_sse2(). This means we can inline scan8[] in the
code directly also and remove loop setup. 20% faster in function, 0.8% overall.
See "[PATCH] unroll loop in h264_idct_add8_sse2()" thread on ML.
author | rbultje |
---|---|
date | Fri, 24 Sep 2010 14:05:45 +0000 |
parents | de4a8f76b1b9 |
children |