Hi,

On Tue, Aug 9, 2011 at 3:59 PM, Luca Barbato <[email protected]> wrote:
> It just does that part in scalar form, I doubt using a vector store
> over 2 array would speed it up particularly.
>
> The function should be written to not use a scratch buffer.
> ---
>  libswscale/ppc/swscale_altivec.c |   15 +++++++++++++--
>  1 files changed, 13 insertions(+), 2 deletions(-)

LGTM. Maybe add a FIXME to the second part also to do it in vector form.

Ronald
_______________________________________________
libav-devel mailing list
[email protected]
https://lists.libav.org/mailman/listinfo/libav-devel

Reply via email to