On 04/10/2012 07:39 AM, Kieran Kunhya wrote: > Seemed to be a little faster with ALIGN 16. > > > 0001-Convert-vector_fmul-to-yasm-and-add-AVX.patch > > > From 3bdd5b7a8904c8f9e4c1c9a8991b5e078dcc4082 Mon Sep 17 00:00:00 2001 > From: Kieran Kunhya <[email protected]> > Date: Tue, 10 Apr 2012 12:34:20 +0100 > Subject: [PATCH] Convert vector_fmul to yasm and add AVX > > --- > libavcodec/aactab.h | 4 +- > libavcodec/dsputil.h | 2 +- > libavcodec/ra288.c | 10 +++--- > libavcodec/ra288.h | 8 +++--- > libavcodec/sinewin.h | 2 +- > libavcodec/x86/dsputil_mmx.c | 53 +++++++------------------------------- > libavcodec/x86/dsputil_yasm.asm | 34 +++++++++++++++++++++++++ > 7 files changed, 57 insertions(+), 56 deletions(-)
LGTM Thanks, Justin _______________________________________________ libav-devel mailing list [email protected] https://lists.libav.org/mailman/listinfo/libav-devel
