[x265] [PATCH 3 of 3] vbv: calculate cuSatdCost, rowSatdCost from lowresCus

[aarthi at multicorewareinc.com]

# HG changeset patch
# User Aarthi Thirumalai<aarthi at multicorewareinc.com>
# Date 1392576377 -19800
#      Mon Feb 17 00:16:17 2014 +0530
# Node ID 85a6960bef867b3bfdf363e3a52a035106776c9d
# Parent  e7e527d13d2fdd9b08915b3245a248332df29882
vbv: calculate cuSatdCost, rowSatdCost from lowresCus.

diff -r e7e527d13d2f -r 85a6960bef86 source/encoder/frameencoder.cpp
--- a/source/encoder/frameencoder.cpp	Sun Feb 16 23:31:39 2014 +0530
+++ b/source/encoder/frameencoder.cpp	Mon Feb 17 00:16:17 2014 +0530
@@ -1056,6 +1056,7 @@
     CTURow& codeRow = m_rows[m_cfg->param.bEnableWavefront ? row : 0];
     const uint32_t numCols = m_pic->getPicSym()->getFrameWidthInCU();
     const uint32_t lineStartCUAddr = row * numCols;
+    double qpBase = m_pic->m_avgQpRc;
     for (uint32_t col = curRow.m_completed; col < numCols; col++)
     {
         const uint32_t cuAddr = lineStartCUAddr + col;
@@ -1066,14 +1067,16 @@
         codeRow.m_entropyCoder.resetEntropy();
 
         TEncSbac *bufSbac = (m_cfg->param.bEnableWavefront && col == 0 && row > 0) ? &m_rows[row - 1].m_bufferSbacCoder : NULL;
-        if (m_cfg->param.rc.aqMode)
+
+        if (m_cfg->param.rc.aqMode || (m_cfg->param.rc.vbvBufferSize >0 && m_cfg->param.rc.vbvMaxBitrate > 0))
         {
-            int qp = calcQpForCu(m_pic, cuAddr);
+            int qp = calcQpForCu(m_pic, cuAddr , qpBase);
             setLambda(qp, row);
-            if (qp > MAX_QP)
-                qp = MAX_QP;
-            cu->setQP(0, (char)qp);
+            qp = X265_MIN(qp, MAX_QP);
+            cu->setQP(0,char(qp));
+            cu->m_baseQp = qpBase;
         }
+
         codeRow.processCU(cu, m_pic->getSlice(), bufSbac, m_cfg->param.bEnableWavefront && col == 1);
 
         // TODO: Keep atomic running totals for rate control?
@@ -1127,34 +1130,40 @@
     curRow.m_busy = false;
 }
 
-int FrameEncoder::calcQpForCu(TComPic *pic, uint32_t cuAddr)
+int FrameEncoder::calcQpForCu(TComPic *pic, uint32_t cuAddr, double baseQp)
 {
     x265_emms();
-    double qp = pic->getSlice()->m_avgQpRc;
-    if (m_cfg->param.rc.aqMode)
+    double qp = baseQp;
+
+    /* Derive qpOffet for each CU by averaging offsets for all 16x16 blocks in the cu. */
+    double qp_offset = 0;
+    int maxBlockCols = (pic->getPicYuvOrg()->getWidth() + (16 - 1)) / 16;
+    int maxBlockRows = (pic->getPicYuvOrg()->getHeight() + (16 - 1)) / 16;
+    int noOfBlocks = g_maxCUWidth / 16;
+    int block_y = (cuAddr / pic->getPicSym()->getFrameWidthInCU()) * noOfBlocks;
+    int block_x = (cuAddr * noOfBlocks) - block_y * pic->getPicSym()->getFrameWidthInCU();
+
+    double *qpoffs = (pic->getSlice()->isReferenced() && m_cfg->param.rc.cuTree) ? pic->m_lowres.qpOffset : pic->m_lowres.qpAqOffset;
+    int cnt = 0, idx =0;
+    for (int h = 0; h < noOfBlocks && block_y < maxBlockRows; h++, block_y++)
     {
-        /* Derive qpOffet for each CU by averaging offsets for all 16x16 blocks in the cu. */
-        double qp_offset = 0;
-        int maxBlockCols = (pic->getPicYuvOrg()->getWidth() + (16 - 1)) / 16;
-        int maxBlockRows = (pic->getPicYuvOrg()->getHeight() + (16 - 1)) / 16;
-        int noOfBlocks = g_maxCUWidth / 16;
-        int block_y = (cuAddr / pic->getPicSym()->getFrameWidthInCU()) * noOfBlocks;
-        int block_x = (cuAddr * noOfBlocks) - block_y * pic->getPicSym()->getFrameWidthInCU();
+        for (int w = 0; w < noOfBlocks && (block_x + w) < maxBlockCols; w++)
+        {
+            idx = block_x + w + (block_y * maxBlockCols);
+            if (m_cfg->param.rc.aqMode)
+                qp_offset += qpoffs[idx];
 
-        double *qpoffs = (pic->getSlice()->isReferenced() && m_cfg->param.rc.cuTree) ? pic->m_lowres.qpOffset : pic->m_lowres.qpAqOffset;
-        int cnt = 0;
-        for (int h = 0; h < noOfBlocks && block_y < maxBlockRows; h++, block_y++)
-        {
-            for (int w = 0; w < noOfBlocks && (block_x + w) < maxBlockCols; w++)
-            {
-                qp_offset += qpoffs[block_x + w + (block_y * maxBlockCols)];
-                cnt++;
-            }
+            if (m_cfg->param.rc.vbvBufferSize > 0 && m_cfg->param.rc.vbvMaxBitrate > 0)
+                m_pic->m_cuCostsForVbv[cuAddr] += m_pic->m_lowres.lowresCostForRc[idx];
+
+            cnt++;
         }
+    }
 
-        qp_offset /= cnt;
-        qp += qp_offset;
-    }
+    qp_offset /= cnt;
+    qp += qp_offset;
+
+
     return Clip3(MIN_QP, MAX_MAX_QP, (int)(qp + 0.5));
 }
 
diff -r e7e527d13d2f -r 85a6960bef86 source/encoder/frameencoder.h
--- a/source/encoder/frameencoder.h	Sun Feb 16 23:31:39 2014 +0530
+++ b/source/encoder/frameencoder.h	Mon Feb 17 00:16:17 2014 +0530
@@ -173,7 +173,7 @@
 protected:
 
     void determineSliceBounds();
-    int calcQpForCu(TComPic *pic, uint32_t cuAddr);
+    int calcQpForCu (TComPic *pic, uint32_t cuAddr, double baseQp);
     Encoder*                 m_top;
     TEncCfg*                 m_cfg;
 
diff -r e7e527d13d2f -r 85a6960bef86 source/encoder/slicetype.cpp
--- a/source/encoder/slicetype.cpp	Sun Feb 16 23:31:39 2014 +0530
+++ b/source/encoder/slicetype.cpp	Mon Feb 17 00:16:17 2014 +0530
@@ -178,6 +178,26 @@
         pic->m_lowres.satdCost = pic->m_lowres.costEstAq[b - p0][p1 - b];
     else
         pic->m_lowres.satdCost = pic->m_lowres.costEst[b - p0][p1 - b];
+
+    if (cfg->param.rc.vbvBufferSize > 0 && cfg->param.rc.vbvMaxBitrate > 0)
+    {
+        pic->m_lowres.lowresCostForRc = pic->m_lowres.lowresCosts[b - p0][p1 - b];
+        uint32_t maxBlockRows = (pic->getPicYuvOrg()->getHeight() + (16 - 1)) / 16;
+        uint32_t lowresRow = 0;
+        int lowresCol = 0;
+        for (uint32_t row = 0; row < pic->getFrameHeightInCU(); row++)
+        {
+            lowresRow = row * maxBlockRows;
+            for (uint32_t cnt = 0; cnt < maxBlockRows && lowresRow < (uint32_t)heightInCU; cnt++, lowresRow++)
+            {
+                lowresCol = lowresRow * widthInCU;
+                for (; lowresCol < widthInCU; lowresCol++)
+                {
+                    pic->m_rowSatdForVbv[row] +=  pic->m_lowres.lowresCostForRc[lowresCol];
+                }
+            }
+        }
+    }
     return pic->m_lowres.satdCost;
 }