[FFmpeg-cvslog] r8992 - trunk/libavcodec/i386/motion_est_mmx.c

Loren Merritt lorenm
Sat May 12 02:33:12 CEST 2007

On Fri, 11 May 2007, Michael Niedermayer wrote:
> On Thu, May 10, 2007 at 09:42:19PM -0600, Loren Merritt wrote:
>> On Fri, 11 May 2007, lorenm wrote:
>>> sse2 version of fullpel sad. 16% faster than mmx2 on core2, but slower on k8.
>>> Modified:
>>>   trunk/libavcodec/i386/motion_est_mmx.c
>> Oops, this crashes in svq1. How is one supposed to deal with codecs that
>> encode 16x16 blocks with stride not divisible by 16? I could increase the
>> alignment in get_buffer, but it seems like wasted memory when svq1 is the
>> only codec that uses 16x16 for chroma.
> hmm odd
> avcodec_align_dimensions() should already ensure that chroma for svq1
> is 16 byte aligned or do i missunderstand something?

It tried, but wasn't quite right. fixed.

--Loren Merritt

More information about the ffmpeg-cvslog mailing list