[x265] [PATCH] no-rdo: cleanups. Remove unnecessary memsets, rearrange computations

[Steve Borho]

On Mon, Nov 11, 2013 at 4:16 AM, <deepthidevaki at multicorewareinc.com> wrote:

> # HG changeset patch
> # User Deepthi Devaki <deepthidevaki at multicorewareinc.com>
> # Date 1384164960 -19800
> # Node ID c4fea7f56081b96877cc01aae0cb3bcd47169bb6
> # Parent  8ca334701a92f895f0750c80f638189ce0d3cf97
> no-rdo: cleanups. Remove unnecessary memsets, rearrange computations.
>

Queued.

My only problem with this patch is it's limited scope.  Ideally this type
of cleanup would be done for all of the analysis functions in compress.cpp
and TEncSearch.cpp, etc.


>
> diff -r 8ca334701a92 -r c4fea7f56081 source/Lib/TLibEncoder/TEncSearch.cpp
> --- a/source/Lib/TLibEncoder/TEncSearch.cpp     Mon Nov 11 14:34:27 2013
> +0530
> +++ b/source/Lib/TLibEncoder/TEncSearch.cpp     Mon Nov 11 15:46:00 2013
> +0530
> @@ -1610,7 +1610,7 @@
>                  // Filtered and Unfiltered refAbove and refLeft pointing
> to above and left.
>                  above         = aboveScale;
>                  left          = leftScale;
> -                aboveFiltered = aboveScale;
> +                aboveFiltered = aboveScale;
>                  leftFiltered  = leftScale;
>              }
>
> @@ -2940,34 +2940,29 @@
>      if (zerocost < cost)
>      {
>          const uint32_t qpartnum = cu->getPic()->getNumPartInCU() >>
> (cu->getDepth(0) << 1);
> -        ::memset(cu->getTransformIdx(), 0, qpartnum * sizeof(UChar));
>          ::memset(cu->getCbf(TEXT_LUMA), 0, qpartnum * sizeof(UChar));
>          ::memset(cu->getCbf(TEXT_CHROMA_U), 0, qpartnum * sizeof(UChar));
>          ::memset(cu->getCbf(TEXT_CHROMA_V), 0, qpartnum * sizeof(UChar));
> -        ::memset(cu->getCoeffY(), 0, width * height * sizeof(TCoeff));
> -        ::memset(cu->getCoeffCb(), 0, width * height * sizeof(TCoeff) >>
> 2);
> -        ::memset(cu->getCoeffCr(), 0, width * height * sizeof(TCoeff) >>
> 2);
> -        cu->setTransformSkipSubParts(0, 0, 0, 0, cu->getDepth(0));
>          if (cu->getMergeFlag(0) && cu->getPartitionSize(0) == SIZE_2Nx2N)
>          {
> -            cu->setSkipFlagSubParts(true, 0, cu->getDepth(0));
> +            cu->getSkipFlag()[0] = true;
>          }
>          bits = zerobits;
> -        outBestResiYuv->clear();
>          generateRecon(cu, predYuv, outBestResiYuv, outReconYuv, true);
> +        distortion = zerodistortion;
>      }
>      else
>      {
>          xSetResidualQTData(cu, 0, 0, outBestResiYuv, cu->getDepth(0),
> true);
>          generateRecon(cu, predYuv, outBestResiYuv, outReconYuv, false);
> +
> +        int part = partitionFromSizes(width, height);
> +        distortion = primitives.sse_pp[part](fencYuv->getLumaAddr(),
> fencYuv->getStride(), outReconYuv->getLumaAddr(), outReconYuv->getStride());
> +        part = partitionFromSizes(width >> 1, height >> 1);
> +        distortion +=
> m_rdCost->scaleChromaDistCb(primitives.sse_pp[part](fencYuv->getCbAddr(),
> fencYuv->getCStride(), outReconYuv->getCbAddr(),
> outReconYuv->getCStride()));
> +        distortion +=
> m_rdCost->scaleChromaDistCr(primitives.sse_pp[part](fencYuv->getCrAddr(),
> fencYuv->getCStride(), outReconYuv->getCrAddr(),
> outReconYuv->getCStride()));
>      }
>
> -    int part = partitionFromSizes(width, height);
> -    distortion = primitives.sse_pp[part](fencYuv->getLumaAddr(),
> fencYuv->getStride(), outReconYuv->getLumaAddr(), outReconYuv->getStride());
> -    part = partitionFromSizes(width >> 1, height >> 1);
> -    distortion +=
> m_rdCost->scaleChromaDistCb(primitives.sse_pp[part](fencYuv->getCbAddr(),
> fencYuv->getCStride(), outReconYuv->getCbAddr(),
> outReconYuv->getCStride()));
> -    distortion +=
> m_rdCost->scaleChromaDistCr(primitives.sse_pp[part](fencYuv->getCrAddr(),
> fencYuv->getCStride(), outReconYuv->getCrAddr(),
> outReconYuv->getCStride()));
> -
>      cu->m_totalBits       = bits;
>      cu->m_totalDistortion = distortion;
>      cu->m_totalCost       = m_rdCost->calcRdCost(distortion, bits);
> @@ -2975,25 +2970,13 @@
>
>  uint32_t TEncSearch::estimateZerobits(TComDataCU* cu)
>  {
> -    if (cu->isIntra(0))
> -    {
> -        return 0;
> -    }
> -
>      uint32_t zeroResiBits = 0;
>
> -    uint32_t width  = cu->getWidth(0);
> -    uint32_t height = cu->getHeight(0);
> -
>      const uint32_t qpartnum = cu->getPic()->getNumPartInCU() >>
> (cu->getDepth(0) << 1);
> -    ::memset(cu->getTransformIdx(), 0, qpartnum * sizeof(UChar));
> +
>      ::memset(cu->getCbf(TEXT_LUMA), 0, qpartnum * sizeof(UChar));
>      ::memset(cu->getCbf(TEXT_CHROMA_U), 0, qpartnum * sizeof(UChar));
>      ::memset(cu->getCbf(TEXT_CHROMA_V), 0, qpartnum * sizeof(UChar));
> -    ::memset(cu->getCoeffY(), 0, width * height * sizeof(TCoeff));
> -    ::memset(cu->getCoeffCb(), 0, width * height * sizeof(TCoeff) >> 2);
> -    ::memset(cu->getCoeffCr(), 0, width * height * sizeof(TCoeff) >> 2);
> -    cu->setTransformSkipSubParts(0, 0, 0, 0, cu->getDepth(0));
>
>
>  m_rdGoOnSbacCoder->load(m_rdSbacCoders[cu->getDepth(0)][CI_CURR_BEST]);
>      zeroResiBits = xSymbolBitsInter(cu);
> @@ -3035,11 +3018,6 @@
>
>  void TEncSearch::estimateBitsDist(TComDataCU* cu, TShortYUV* resiYuv,
> uint32_t& bits, uint32_t& distortion, bool curUseRDOQ)
>  {
> -    if (cu->isIntra(0))
> -    {
> -        return;
> -    }
> -
>      bits = 0;
>      distortion = 0;
>      uint64_t cost = 0;
> _______________________________________________
> x265-devel mailing list
> x265-devel at videolan.org
> https://mailman.videolan.org/listinfo/x265-devel
>



-- 
Steve Borho
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.videolan.org/pipermail/x265-devel/attachments/20131111/61d252a6/attachment.html>