HEVC代码追踪（七）:xCompressCu

// ====================================================================================================================
// Protected member functions
// ====================================================================================================================
/** Compress a CU block recursively with enabling sub-LCU-level delta QP
 *\param   rpcBestCU
 *\param   rpcTempCU
 *\param   uiDepth
 *\returns Void
 *
 *- for loop of QP value to compress the current CU with all possible QP
*/
#if AMP_ENC_SPEEDUP
Void TEncCu::xCompressCU( TComDataCU*& rpcBestCU, TComDataCU*& rpcTempCU, UInt uiDepth, PartSize eParentPartSize )
#else
Void TEncCu::xCompressCU( TComDataCU*& rpcBestCU, TComDataCU*& rpcTempCU, UInt uiDepth )
#endif
{
  TComPic* pcPic = rpcBestCU->getPic();

  // get Original YUV data from picture
  m_ppcOrigYuv[uiDepth]->copyFromPicYuv( pcPic->getPicYuvOrg(), rpcBestCU->getAddr(), rpcBestCU->getZorderIdxInCU() );

  // variable for Early CU determination
  Bool    bSubBranch = true;

  // variable for Cbf fast mode PU decision
  Bool    doNotBlockPu = true;
  Bool earlyDetectionSkipMode = false;

  Bool bBoundary = false;
  UInt uiLPelX   = rpcBestCU->getCUPelX();
  UInt uiRPelX   = uiLPelX + rpcBestCU->getWidth(0)  - 1;
  UInt uiTPelY   = rpcBestCU->getCUPelY();
  UInt uiBPelY   = uiTPelY + rpcBestCU->getHeight(0) - 1;

  Int iBaseQP = xComputeQP( rpcBestCU, uiDepth );
  Int iMinQP;
  Int iMaxQP;
  Bool isAddLowestQP = false;

  if( (g_uiMaxCUWidth>>uiDepth) >= rpcTempCU->getSlice()->getPPS()->getMinCuDQPSize() )
  {
    Int idQP = m_pcEncCfg->getMaxDeltaQP();
    iMinQP = Clip3( -rpcTempCU->getSlice()->getSPS()->getQpBDOffsetY(), MAX_QP, iBaseQP-idQP );
    iMaxQP = Clip3( -rpcTempCU->getSlice()->getSPS()->getQpBDOffsetY(), MAX_QP, iBaseQP+idQP );
  }
  else
  {
    iMinQP = rpcTempCU->getQP(0);
    iMaxQP = rpcTempCU->getQP(0);
  }

  if ( m_pcEncCfg->getUseRateCtrl() )
  {
    iMinQP = m_pcRateCtrl->getRCQP();
    iMaxQP = m_pcRateCtrl->getRCQP();
  }

  // transquant-bypass (TQB) processing loop variable initialisation ---

  const Int lowestQP = iMinQP; // For TQB, use this QP which is the lowest non TQB QP tested (rather than QP'=0) - that way delta QPs are smaller, and TQB can be tested at all CU levels.

  if ( (rpcTempCU->getSlice()->getPPS()->getTransquantBypassEnableFlag()) )
  {
    isAddLowestQP = true; // mark that the first iteration is to cost TQB mode.
    iMinQP = iMinQP - 1;  // increase loop variable range by 1, to allow testing of TQB mode along with other QPs
    if ( m_pcEncCfg->getCUTransquantBypassFlagForceValue() )
    {
      iMaxQP = iMinQP;
    }
  }

  // If slice start or slice end is within this cu...
  TComSlice * pcSlice = rpcTempCU->getPic()->getSlice(rpcTempCU->getPic()->getCurrSliceIdx());
  Bool bSliceStart = pcSlice->getSliceSegmentCurStartCUAddr()>rpcTempCU->getSCUAddr()&&pcSlice->getSliceSegmentCurStartCUAddr()<rpcTempCU->getSCUAddr()+rpcTempCU->getTotalNumPart();
  Bool bSliceEnd = (pcSlice->getSliceSegmentCurEndCUAddr()>rpcTempCU->getSCUAddr()&&pcSlice->getSliceSegmentCurEndCUAddr()<rpcTempCU->getSCUAddr()+rpcTempCU->getTotalNumPart());
  Bool bInsidePicture = ( uiRPelX < rpcBestCU->getSlice()->getSPS()->getPicWidthInLumaSamples() ) && ( uiBPelY < rpcBestCU->getSlice()->getSPS()->getPicHeightInLumaSamples() );
  // We need to split, so don't try these modes.
  if(!bSliceEnd && !bSliceStart && bInsidePicture )
  {
    for (Int iQP=iMinQP; iQP<=iMaxQP; iQP++)
    {
      const Bool bIsLosslessMode = isAddLowestQP && (iQP == iMinQP);

      if (bIsLosslessMode)
      {
        iQP = lowestQP;
      }

      rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );

      // do inter modes, SKIP and 2Nx2N
      if( rpcBestCU->getSlice()->getSliceType() != I_SLICE )
      {
        // 2Nx2N
        if(m_pcEncCfg->getUseEarlySkipDetection())
        {
          xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2Nx2N );
          rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );//by Competition for inter_2Nx2N
        }
        // SKIP
        xCheckRDCostMerge2Nx2N( rpcBestCU, rpcTempCU, &earlyDetectionSkipMode );//by Merge for inter_2Nx2N
        rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );

        if(!m_pcEncCfg->getUseEarlySkipDetection())
        {
          // 2Nx2N, NxN
          xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2Nx2N );
          rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
          if(m_pcEncCfg->getUseCbfFastMode())
          {
            doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
          }
        }
      }

      if (bIsLosslessMode)
      {
        iQP = iMinQP;
      }
    }

    if(!earlyDetectionSkipMode)
    {
      for (Int iQP=iMinQP; iQP<=iMaxQP; iQP++)
      {
        const Bool bIsLosslessMode = isAddLowestQP && (iQP == iMinQP);

        if (bIsLosslessMode)
        {
          iQP = lowestQP;
        }
        rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );

        // do inter modes, NxN, 2NxN, and Nx2N
        if( rpcBestCU->getSlice()->getSliceType() != I_SLICE )
        {
          // 2Nx2N, NxN
          if(!( (rpcBestCU->getWidth(0)==8) && (rpcBestCU->getHeight(0)==8) ))
          {
            if( uiDepth == g_uiMaxCUDepth - g_uiAddCUDepth && doNotBlockPu)
            {
              xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_NxN   );
              rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
            }
          }

          // 2NxN, Nx2N
          if(doNotBlockPu)
          {
            xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_Nx2N  );
            rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
            if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_Nx2N )
            {
              doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
            }
          }
          if(doNotBlockPu)
          {
            xCheckRDCostInter      ( rpcBestCU, rpcTempCU, SIZE_2NxN  );
            rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
            if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_2NxN)
            {
              doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
            }
          }

#if 1
          //! Try AMP (SIZE_2NxnU, SIZE_2NxnD, SIZE_nLx2N, SIZE_nRx2N)
          if( pcPic->getSlice(0)->getSPS()->getAMPAcc(uiDepth) )
          {
#if AMP_ENC_SPEEDUP        
            Bool bTestAMP_Hor = false, bTestAMP_Ver = false;

#if AMP_MRG
            Bool bTestMergeAMP_Hor = false, bTestMergeAMP_Ver = false;

            deriveTestModeAMP (rpcBestCU, eParentPartSize, bTestAMP_Hor, bTestAMP_Ver, bTestMergeAMP_Hor, bTestMergeAMP_Ver);
#else
            deriveTestModeAMP (rpcBestCU, eParentPartSize, bTestAMP_Hor, bTestAMP_Ver);
#endif

            //! Do horizontal AMP
            if ( bTestAMP_Hor )
            {
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2NxnU );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
                if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_2NxnU )
                {
                  doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
                }
              }
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2NxnD );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
                if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_2NxnD )
                {
                  doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
                }
              }
            }
#if AMP_MRG
            else if ( bTestMergeAMP_Hor ) 
            {
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2NxnU, true );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
                if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_2NxnU )
                {
                  doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
                }
              }
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2NxnD, true );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
                if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_2NxnD )
                {
                  doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
                }
              }
            }
#endif

            //! Do horizontal AMP
            if ( bTestAMP_Ver )
            {
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_nLx2N );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
                if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_nLx2N )
                {
                  doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
                }
              }
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_nRx2N );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
              }
            }
#if AMP_MRG
            else if ( bTestMergeAMP_Ver )
            {
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_nLx2N, true );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
                if(m_pcEncCfg->getUseCbfFastMode() && rpcBestCU->getPartitionSize(0) == SIZE_nLx2N )
                {
                  doNotBlockPu = rpcBestCU->getQtRootCbf( 0 ) != 0;
                }
              }
              if(doNotBlockPu)
              {
                xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_nRx2N, true );
                rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
              }
            }
#endif

#else
            xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2NxnU );
            rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
            xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_2NxnD );
            rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
            xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_nLx2N );
            rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );

            xCheckRDCostInter( rpcBestCU, rpcTempCU, SIZE_nRx2N );
            rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );

#endif
          }    
#endif
        }

        // do normal intra modes
        // speedup for inter frames
        if( rpcBestCU->getSlice()->getSliceType() == I_SLICE || 
          rpcBestCU->getCbf( 0, TEXT_LUMA     ) != 0   ||
          rpcBestCU->getCbf( 0, TEXT_CHROMA_U ) != 0   ||
          rpcBestCU->getCbf( 0, TEXT_CHROMA_V ) != 0     ) // avoid very complex intra if it is unlikely
        {
          xCheckRDCostIntra( rpcBestCU, rpcTempCU, SIZE_2Nx2N );
          rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
          if( uiDepth == g_uiMaxCUDepth - g_uiAddCUDepth )
          {
            if( rpcTempCU->getWidth(0) > ( 1 << rpcTempCU->getSlice()->getSPS()->getQuadtreeTULog2MinSize() ) )
            {
              xCheckRDCostIntra( rpcBestCU, rpcTempCU, SIZE_NxN   );
              rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
            }
          }
        }

        // test PCM
        if(pcPic->getSlice(0)->getSPS()->getUsePCM()
          && rpcTempCU->getWidth(0) <= (1<<pcPic->getSlice(0)->getSPS()->getPCMLog2MaxSize())
          && rpcTempCU->getWidth(0) >= (1<<pcPic->getSlice(0)->getSPS()->getPCMLog2MinSize()) )
        {
          UInt uiRawBits = (2 * g_bitDepthY + g_bitDepthC) * rpcBestCU->getWidth(0) * rpcBestCU->getHeight(0) / 2;
          UInt uiBestBits = rpcBestCU->getTotalBits();
          if((uiBestBits > uiRawBits) || (rpcBestCU->getTotalCost() > m_pcRdCost->calcRdCost(uiRawBits, 0)))
          {
            xCheckIntraPCM (rpcBestCU, rpcTempCU);
            rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );
          }
        }
        if (bIsLosslessMode)
        {
          iQP = iMinQP;
        }
      }
    }

    m_pcEntropyCoder->resetBits();
    m_pcEntropyCoder->encodeSplitFlag( rpcBestCU, 0, uiDepth, true );
    rpcBestCU->getTotalBits() += m_pcEntropyCoder->getNumberOfWrittenBits(); // split bits
    rpcBestCU->getTotalBins() += ((TEncBinCABAC *)((TEncSbac*)m_pcEntropyCoder->m_pcEntropyCoderIf)->getEncBinIf())->getBinsCoded();
    rpcBestCU->getTotalCost()  = m_pcRdCost->calcRdCost( rpcBestCU->getTotalBits(), rpcBestCU->getTotalDistortion() );

    // Early CU determination
    if( m_pcEncCfg->getUseEarlyCU() && rpcBestCU->isSkipped(0) )
    {
      bSubBranch = false;
    }
    else
    {
      bSubBranch = true;
    }
  }
  else if(!(bSliceEnd && bInsidePicture))
  {
    bBoundary = true;
  }

  // copy orginal YUV samples to PCM buffer
  if( rpcBestCU->isLosslessCoded(0) && (rpcBestCU->getIPCMFlag(0) == false))
  {
    xFillPCMBuffer(rpcBestCU, m_ppcOrigYuv[uiDepth]);
  }
  if( (g_uiMaxCUWidth>>uiDepth) == rpcTempCU->getSlice()->getPPS()->getMinCuDQPSize() )
  {
    Int idQP = m_pcEncCfg->getMaxDeltaQP();
    iMinQP = Clip3( -rpcTempCU->getSlice()->getSPS()->getQpBDOffsetY(), MAX_QP, iBaseQP-idQP );
    iMaxQP = Clip3( -rpcTempCU->getSlice()->getSPS()->getQpBDOffsetY(), MAX_QP, iBaseQP+idQP );
  }
  else if( (g_uiMaxCUWidth>>uiDepth) > rpcTempCU->getSlice()->getPPS()->getMinCuDQPSize() )
  {
    iMinQP = iBaseQP;
    iMaxQP = iBaseQP;
  }
  else
  {
    Int iStartQP;
    if( pcPic->getCU( rpcTempCU->getAddr() )->getSliceSegmentStartCU(rpcTempCU->getZorderIdxInCU()) == pcSlice->getSliceSegmentCurStartCUAddr())
    {
      iStartQP = rpcTempCU->getQP(0);
    }
    else
    {
      UInt uiCurSliceStartPartIdx = pcSlice->getSliceSegmentCurStartCUAddr() % pcPic->getNumPartInCU() - rpcTempCU->getZorderIdxInCU();
      iStartQP = rpcTempCU->getQP(uiCurSliceStartPartIdx);
    }
    iMinQP = iStartQP;
    iMaxQP = iStartQP;
  }
  if ( m_pcEncCfg->getUseRateCtrl() )
  {
    iMinQP = m_pcRateCtrl->getRCQP();
    iMaxQP = m_pcRateCtrl->getRCQP();
  }

  if ( m_pcEncCfg->getCUTransquantBypassFlagForceValue() )
  {
    iMaxQP = iMinQP; // If all blocks are forced into using transquant bypass, do not loop here.
  }

  for (Int iQP=iMinQP; iQP<=iMaxQP; iQP++)
  {
    const Bool bIsLosslessMode = false; // False at this level. Next level down may set it to true.
    rpcTempCU->initEstData( uiDepth, iQP, bIsLosslessMode );

    // further split
    if( bSubBranch && uiDepth < g_uiMaxCUDepth - g_uiAddCUDepth )
    {
      UChar       uhNextDepth         = uiDepth+1;
      TComDataCU* pcSubBestPartCU     = m_ppcBestCU[uhNextDepth];
      TComDataCU* pcSubTempPartCU     = m_ppcTempCU[uhNextDepth];

      for ( UInt uiPartUnitIdx = 0; uiPartUnitIdx < 4; uiPartUnitIdx++ )
      {
        pcSubBestPartCU->initSubCU( rpcTempCU, uiPartUnitIdx, uhNextDepth, iQP );           // clear sub partition datas or init.
        pcSubTempPartCU->initSubCU( rpcTempCU, uiPartUnitIdx, uhNextDepth, iQP );           // clear sub partition datas or init.

        Bool bInSlice = pcSubBestPartCU->getSCUAddr()+pcSubBestPartCU->getTotalNumPart()>pcSlice->getSliceSegmentCurStartCUAddr()&&pcSubBestPartCU->getSCUAddr()<pcSlice->getSliceSegmentCurEndCUAddr();
        if(bInSlice && ( pcSubBestPartCU->getCUPelX() < pcSlice->getSPS()->getPicWidthInLumaSamples() ) && ( pcSubBestPartCU->getCUPelY() < pcSlice->getSPS()->getPicHeightInLumaSamples() ) )
        {
          if ( 0 == uiPartUnitIdx) //initialize RD with previous depth buffer
          {
            m_pppcRDSbacCoder[uhNextDepth][CI_CURR_BEST]->load(m_pppcRDSbacCoder[uiDepth][CI_CURR_BEST]);
          }
          else
          {
            m_pppcRDSbacCoder[uhNextDepth][CI_CURR_BEST]->load(m_pppcRDSbacCoder[uhNextDepth][CI_NEXT_BEST]);
          }

#if AMP_ENC_SPEEDUP
          if ( rpcBestCU->isIntra(0) )
          {
            xCompressCU( pcSubBestPartCU, pcSubTempPartCU, uhNextDepth, SIZE_NONE );
          }
          else
          {
            xCompressCU( pcSubBestPartCU, pcSubTempPartCU, uhNextDepth, rpcBestCU->getPartitionSize(0) );
          }
#else
          xCompressCU( pcSubBestPartCU, pcSubTempPartCU, uhNextDepth );
#endif

          rpcTempCU->copyPartFrom( pcSubBestPartCU, uiPartUnitIdx, uhNextDepth );         // Keep best part data to current temporary data.
          xCopyYuv2Tmp( pcSubBestPartCU->getTotalNumPart()*uiPartUnitIdx, uhNextDepth );
        }
        else if (bInSlice)
        {
          pcSubBestPartCU->copyToPic( uhNextDepth );
          rpcTempCU->copyPartFrom( pcSubBestPartCU, uiPartUnitIdx, uhNextDepth );
        }
      }

      if( !bBoundary )
      {
        m_pcEntropyCoder->resetBits();
        m_pcEntropyCoder->encodeSplitFlag( rpcTempCU, 0, uiDepth, true );

        rpcTempCU->getTotalBits() += m_pcEntropyCoder->getNumberOfWrittenBits(); // split bits
        rpcTempCU->getTotalBins() += ((TEncBinCABAC *)((TEncSbac*)m_pcEntropyCoder->m_pcEntropyCoderIf)->getEncBinIf())->getBinsCoded();
      }
      rpcTempCU->getTotalCost()  = m_pcRdCost->calcRdCost( rpcTempCU->getTotalBits(), rpcTempCU->getTotalDistortion() );

      if( (g_uiMaxCUWidth>>uiDepth) == rpcTempCU->getSlice()->getPPS()->getMinCuDQPSize() && rpcTempCU->getSlice()->getPPS()->getUseDQP())
      {
        Bool hasResidual = false;
        for( UInt uiBlkIdx = 0; uiBlkIdx < rpcTempCU->getTotalNumPart(); uiBlkIdx ++)
        {
          if( ( pcPic->getCU( rpcTempCU->getAddr() )->getSliceSegmentStartCU(uiBlkIdx+rpcTempCU->getZorderIdxInCU()) == rpcTempCU->getSlice()->getSliceSegmentCurStartCUAddr() ) && 
              ( rpcTempCU->getCbf( uiBlkIdx, TEXT_LUMA ) || rpcTempCU->getCbf( uiBlkIdx, TEXT_CHROMA_U ) || rpcTempCU->getCbf( uiBlkIdx, TEXT_CHROMA_V ) ) )
          {
            hasResidual = true;
            break;
          }
        }

        UInt uiTargetPartIdx;
        if ( pcPic->getCU( rpcTempCU->getAddr() )->getSliceSegmentStartCU(rpcTempCU->getZorderIdxInCU()) != pcSlice->getSliceSegmentCurStartCUAddr() )
        {
          uiTargetPartIdx = pcSlice->getSliceSegmentCurStartCUAddr() % pcPic->getNumPartInCU() - rpcTempCU->getZorderIdxInCU();
        }
        else
        {
          uiTargetPartIdx = 0;
        }
        if ( hasResidual )
        {
#if !RDO_WITHOUT_DQP_BITS
          m_pcEntropyCoder->resetBits();
          m_pcEntropyCoder->encodeQP( rpcTempCU, uiTargetPartIdx, false );
          rpcTempCU->getTotalBits() += m_pcEntropyCoder->getNumberOfWrittenBits(); // dQP bits
          rpcTempCU->getTotalBins() += ((TEncBinCABAC *)((TEncSbac*)m_pcEntropyCoder->m_pcEntropyCoderIf)->getEncBinIf())->getBinsCoded();
          rpcTempCU->getTotalCost()  = m_pcRdCost->calcRdCost( rpcTempCU->getTotalBits(), rpcTempCU->getTotalDistortion() );
#endif

          Bool foundNonZeroCbf = false;
          rpcTempCU->setQPSubCUs( rpcTempCU->getRefQP( uiTargetPartIdx ), rpcTempCU, 0, uiDepth, foundNonZeroCbf );
          assert( foundNonZeroCbf );
        }
        else
        {
          rpcTempCU->setQPSubParts( rpcTempCU->getRefQP( uiTargetPartIdx ), 0, uiDepth ); // set QP to default QP
        }
      }

      m_pppcRDSbacCoder[uhNextDepth][CI_NEXT_BEST]->store(m_pppcRDSbacCoder[uiDepth][CI_TEMP_BEST]);

      Bool isEndOfSlice        = rpcBestCU->getSlice()->getSliceMode()==FIXED_NUMBER_OF_BYTES
                                 && (rpcBestCU->getTotalBits()>rpcBestCU->getSlice()->getSliceArgument()<<3);
      Bool isEndOfSliceSegment = rpcBestCU->getSlice()->getSliceSegmentMode()==FIXED_NUMBER_OF_BYTES
                                 && (rpcBestCU->getTotalBits()>rpcBestCU->getSlice()->getSliceSegmentArgument()<<3);
      if(isEndOfSlice||isEndOfSliceSegment)
      {
        rpcBestCU->getTotalCost()=rpcTempCU->getTotalCost()+1;
      }
      xCheckBestMode( rpcBestCU, rpcTempCU, uiDepth);                                  // RD compare current larger prediction
    }                                                                                  // with sub partitioned prediction.
  }

  rpcBestCU->copyToPic(uiDepth);                                                     // Copy Best data to Picture for next partition prediction.

  xCopyYuv2Pic( rpcBestCU->getPic(), rpcBestCU->getAddr(), rpcBestCU->getZorderIdxInCU(), uiDepth, uiDepth, rpcBestCU, uiLPelX, uiTPelY );   // Copy Yuv data to picture Yuv
  if( bBoundary ||(bSliceEnd && bInsidePicture))
  {
    return;
  }

  // Assert if Best prediction mode is NONE
  // Selected mode's RD-cost must be not MAX_DOUBLE.
  assert( rpcBestCU->getPartitionSize ( 0 ) != SIZE_NONE  );
  assert( rpcBestCU->getPredictionMode( 0 ) != MODE_NONE  );
  assert( rpcBestCU->getTotalCost     (   ) != MAX_DOUBLE );
}