Thanks, Min. The point is that we need to measure the speedup relative to
SSE3/AVX, the best that's already available, rather than measuring speedup
against  C-ref.

On Tue, Mar 10, 2015 at 2:23 AM, chen <[email protected]> wrote:

> MMX2
>
> sad_x3[  8x4]  15.44x   166.02          2562.99
>
>
>
> AVX2
> sad_x3[  8x4]  11.49x   224.21          2576.13
>
>
> At 2015-03-09 17:56:21,[email protected] wrote:
> ># HG changeset patch
> ># User Sumalatha Polureddy<[email protected]>
> ># Date 1425894973 -19800
> ># Node ID 5d1aded9d2c14288510a1838db301a804aaa59d9
> ># Parent  12ee2fe1b2f5e19b3f24c4108bc7e7eb6775d54e
> >asm: avx2 code for sad_x3[8x4] for 8bpp - 41x
> >
> >sad_x3[  8x4]  41.00x   1160.20         47568.03
> >
>
>
> _______________________________________________
> x265-devel mailing list
> [email protected]
> https://mailman.videolan.org/listinfo/x265-devel
>
>
_______________________________________________
x265-devel mailing list
[email protected]
https://mailman.videolan.org/listinfo/x265-devel

Reply via email to