aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/vp5.c
diff options
context:
space:
mode:
authorChristophe Gisquet <christophe.gisquet@gmail.com>2014-02-14 15:03:09 +0000
committerJanne Grunau <janne-libav@jannau.net>2014-02-28 13:00:48 +0100
commit08e3ea60ff4059341b74be04a428a38f7c3630b0 (patch)
treee9e639f3b99004cdf785a88b17e06b1c28fb1b66 /libavcodec/vp5.c
parent57b1eb9f75b04571063ddec316e290c216c114ac (diff)
downloadffmpeg-08e3ea60ff4059341b74be04a428a38f7c3630b0.tar.gz
x86: synth filter float: implement SSE2 version
Timings for Arrandale: C SSE win32: 2108 334 win64: 1152 322 Factorizing the inner loop with a call/jmp is a >15 cycles cost, even with the jmp destination being aligned. Unrolling for ARCH_X86_64 is a 20 cycles gain. Signed-off-by: Janne Grunau <janne-libav@jannau.net>
Diffstat (limited to 'libavcodec/vp5.c')
0 files changed, 0 insertions, 0 deletions