[x265] [PATCH] psyCost_pp: C code optimization, suitable for ASM conversion

[praveen at multicorewareinc.com]

# HG changeset patch
# User Praveen Tiwari
# Date 1418376812 -19800
# Node ID ca805794c7519ef698776d0f717fd66b0d3bc626
# Parent  b1c2ef980dfe59c486454a8838c2c1bb74bf4d32
psyCost_pp: C code optimization, suitable for ASM conversion

psy_sum_std_4x4, is combined version of satd_4x4 and sad<4, 4>, eliminating unnecessary load operations, extra arguments(zeroBuf and 0).
It also replaces SAD operation with low cost sum operation as the sencod pixel buffer is zero.

diff -r b1c2ef980dfe -r ca805794c751 source/common/pixel.cpp
--- a/source/common/pixel.cpp	Thu Dec 11 16:52:06 2014 -0600
+++ b/source/common/pixel.cpp	Fri Dec 12 15:03:32 2014 +0530
@@ -801,6 +801,38 @@
 #pragma warning(disable: 4127) // conditional expression is constant
 #endif
 
+int psy_sum_std_4x4(const pixel* pix1, intptr_t stride_pix1)
+{
+    sum2_t tmp[4][2];
+    sum2_t a0, a1, a2, a3, b0, b1;
+    sum2_t sum = 0;
+    int sum0 = 0;
+    uint32_t sum1 = 0;
+
+    for (int i = 0; i < 4; i++, pix1 += stride_pix1)
+    {
+        a0 = pix1[0];
+        a1 = pix1[1];
+        a2 = pix1[2];
+        a3 = pix1[3];
+        sum1 = sum1 + (a0 + a1 + a2 + a3);
+        b0 = (a0 + a1) + ((a0 - a1) << BITS_PER_SUM);
+        b1 = (a2 + a3) + ((a2 - a3) << BITS_PER_SUM);
+        tmp[i][0] = b0 + b1;
+        tmp[i][1] = b0 - b1;
+    }
+
+    for (int i = 0; i < 2; i++)
+    {
+        HADAMARD4(a0, a1, a2, a3, tmp[0][i], tmp[1][i], tmp[2][i], tmp[3][i]);
+        a0 = abs2(a0) + abs2(a1) + abs2(a2) + abs2(a3);
+        sum += ((sum_t)a0) + (a0 >> BITS_PER_SUM);
+    }
+
+    sum0 = (int)(sum >> 1);
+    return (int)(sum0 - (sum1 >> 2));
+}
+
 template<int size>
 int psyCost_pp(const pixel* source, intptr_t sstride, const pixel* recon, intptr_t rstride)
 {
@@ -828,8 +860,8 @@
     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);
+        int sourceEnergy = psy_sum_std_4x4(source, sstride);
+        int reconEnergy = psy_sum_std_4x4(recon, rstride);
         return abs(sourceEnergy - reconEnergy);
     }
 }