[x265] [PATCH] integrate assembly code for psyCost_pp

[Steve Borho]

On 12/11, Divya Manivannan wrote:
> # HG changeset patch
> # User Divya Manivannan <divya at multicorewareinc.com>
> # Date 1418296477 -19800
> #      Thu Dec 11 16:44:37 2014 +0530
> # Node ID 440d264fcdf33889b665848f19e87ca3559d1b6c
> # Parent  667e4ea0899fcf026ee9df935381487d3148ed0c
> integrate assembly code for psyCost_pp
> 
> diff -r 667e4ea0899f -r 440d264fcdf3 source/common/pixel.cpp
> --- a/source/common/pixel.cpp	Thu Dec 11 09:36:16 2014 +0530
> +++ b/source/common/pixel.cpp	Thu Dec 11 16:44:37 2014 +0530
> @@ -815,10 +815,11 @@
>              for (int j = 0; j < dim; j+= 8)
>              {
>                  /* AC energy, measured by sa8d (AC + DC) minus SAD (DC) */
> -                int sourceEnergy = sa8d_8x8(source + i * sstride + j, sstride, zeroBuf, 0) - 
> -                                   (sad<8, 8>(source + i * sstride + j, sstride, zeroBuf, 0) >> 2);
> -                int reconEnergy =  sa8d_8x8(recon + i * rstride + j, rstride, zeroBuf, 0) - 
> -                                   (sad<8, 8>(recon + i * rstride + j, rstride, zeroBuf, 0) >> 2);
> +                // PartitionFromSizes(8, 8) = 1
> +                int sourceEnergy = primitives.sa8d[1](source + i * sstride + j, sstride, zeroBuf, 0) -
> +                                   (primitives.sad[1](source + i * sstride + j, sstride, zeroBuf, 0) >> 2);
> +                int reconEnergy = primitives.sa8d[1](recon + i * rstride + j, rstride, zeroBuf, 0) -
> +                                  (primitives.sad[1](recon + i * rstride + j, rstride, zeroBuf, 0) >> 2);

This is an improvement over just C code, but it is still vastly slower
than writing new assembly functions for these. The function call
overhead is non-trivial.

>  
>                  totEnergy += abs(sourceEnergy - reconEnergy);
>              }
> @@ -828,8 +829,11 @@
>      else
>      {
>          /* 4x4 is too small for sa8d */
> -        int sourceEnergy = satd_4x4(source, sstride, zeroBuf, 0) - (sad<4, 4>(source, sstride, zeroBuf, 0) >> 2);
> -        int reconEnergy = satd_4x4(recon, rstride, zeroBuf, 0) - (sad<4, 4>(recon, rstride, zeroBuf, 0) >> 2);
> +        // partitionFromSizes(4, 4) = 0
> +        int sourceEnergy = primitives.satd[0](source, sstride, zeroBuf, 0) -
> +                           (primitives.sad[0](source, sstride, zeroBuf, 0) >> 2);
> +        int reconEnergy = primitives.satd[0](recon, rstride, zeroBuf, 0) -
> +                          (primitives.sad[0](recon, rstride, zeroBuf, 0) >> 2);
>          return abs(sourceEnergy - reconEnergy);
>      }
>  }
> _______________________________________________
> x265-devel mailing list
> x265-devel at videolan.org
> https://mailman.videolan.org/listinfo/x265-devel

-- 
Steve Borho