[x264-devel] commit: add AltiVec implementation of x264_pixel_var_16x16 and x264_pixel_var_8x8 (Guillaume Poirier )

[Guillaume POIRIER]

Hello,

On Sun, Feb 1, 2009 at 6:46 AM, Loren Merritt <lorenm at u.washington.edu> wrote:
>> sqr_v = vec_add( sqr_v, vec_sld( sqr_v, sqr_v, 8 ) );
>> sqr_v = vec_add( sqr_v, vec_sld( sqr_v, sqr_v, 4 ) );
>
> vec_sums. I said that the biggest sum (16x16 squared) fits in 24 bits.

That's right. I don't know why I didn't make this change as well. I
pushed these changes so that the attached patch has only the
permutation optimizations in it.

Guillaume
-- 
Only a very small fraction of our DNA does anything; the rest is all
comments and ifdefs.

Rodney Dangerfield  - "My marriage is on the rocks again, yeah, my
wife just broke up with her boyfriend."
-------------- next part --------------
A non-text attachment was scrubbed...
Name: improve_load_permutations.0.diff
Type: application/octet-stream
Size: 2538 bytes
Desc: not available
Url : http://mailman.videolan.org/pipermail/x264-devel/attachments/20090201/d0e4ed8f/attachment.obj