[x265] [PATCH] TComYuv::addClip, integrated luma_add_ps

[praveen at multicorewareinc.com]

# HG changeset patch
# User Praveen Tiwari
# Date 1385124193 -19800
# Node ID ecb4138b38572ad6c2c65082bfdcddf9acf39c84
# Parent  f2b8bcaf435c00d835cd4389063ed09d22e7be28
TComYuv::addClip, integrated luma_add_ps

diff -r f2b8bcaf435c -r ecb4138b3857 source/Lib/TLibCommon/TComYuv.cpp
--- a/source/Lib/TLibCommon/TComYuv.cpp	Fri Nov 22 16:34:26 2013 +0530
+++ b/source/Lib/TLibCommon/TComYuv.cpp	Fri Nov 22 18:13:13 2013 +0530
@@ -395,14 +395,14 @@
 
 void TComYuv::addClip(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize)
 {
-    addClipLuma(srcYuv0, srcYuv1, trUnitIdx, partSize);
+    int part = partitionFromSizes(partSize, partSize);
+
+    addClipLuma(srcYuv0, srcYuv1, trUnitIdx, partSize, part);
     addClipChroma(srcYuv0, srcYuv1, trUnitIdx, partSize >> m_hChromaShift);
 }
 
-void TComYuv::addClipLuma(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize)
+void TComYuv::addClipLuma(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize, uint32_t part)
 {
-    int x, y;
-
     Pel* src0 = srcYuv0->getLumaAddr(trUnitIdx, partSize);
     int16_t* src1 = srcYuv1->getLumaAddr(trUnitIdx, partSize);
     Pel* dst = getLumaAddr(trUnitIdx, partSize);
@@ -411,17 +411,7 @@
     uint32_t src1Stride = srcYuv1->m_width;
     uint32_t dststride  = getStride();
 
-    for (y = partSize - 1; y >= 0; y--)
-    {
-        for (x = partSize - 1; x >= 0; x--)
-        {
-            dst[x] = ClipY(static_cast<int16_t>(src0[x]) + src1[x]);
-        }
-
-        src0 += src0Stride;
-        src1 += src1Stride;
-        dst  += dststride;
-    }
+    primitives.luma_add_ps[part](dst, dststride, src0, src1, src0Stride, src1Stride);
 }
 
 void TComYuv::addClipChroma(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize)
diff -r f2b8bcaf435c -r ecb4138b3857 source/Lib/TLibCommon/TComYuv.h
--- a/source/Lib/TLibCommon/TComYuv.h	Fri Nov 22 16:34:26 2013 +0530
+++ b/source/Lib/TLibCommon/TComYuv.h	Fri Nov 22 18:13:13 2013 +0530
@@ -153,7 +153,7 @@
 
     //  Clip(srcYuv0 + srcYuv1) -> m_apiBuf
     void    addClip(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize);
-    void    addClipLuma(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize);
+    void    addClipLuma(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize, uint32_t part);
     void    addClipChroma(TComYuv* srcYuv0, TShortYUV* srcYuv1, uint32_t trUnitIdx, uint32_t partSize);
 
     //  srcYuv0 - srcYuv1 -> m_apiBuf