[x265] [PATCH] pixel-sse41.cpp: Modified sse_ss8 function using faster macro PROCESS_SSE_SS4x1

[dnyaneshwar at multicorewareinc.com]

# HG changeset patch
# User Dnyaneshwar Gorade <dnyaneshwar at multicorewareinc.com>
# Date 1381826441 -19800
#      Tue Oct 15 14:10:41 2013 +0530
# Node ID e00905521f015292f9ccc1ae83b1476c3c433310
# Parent  1019dc55ec1b7f6b4ba7d15126d96167998c4031
pixel-sse41.cpp: Modified sse_ss8 function using faster macro PROCESS_SSE_SS4x1.

diff -r 1019dc55ec1b -r e00905521f01 source/common/vec/pixel-sse41.cpp
--- a/source/common/vec/pixel-sse41.cpp	Tue Oct 15 14:07:36 2013 +0530
+++ b/source/common/vec/pixel-sse41.cpp	Tue Oct 15 14:10:41 2013 +0530
@@ -5361,14 +5361,16 @@
 {
     int rows = ly;
     __m128i sum  = _mm_setzero_si128();
-    __m128i m1, n1, diff, sign1, sign2, tmp1, tmp2;
+    __m128i m1, n1, diff, sign, tmp1, tmp2;
 
     for (; rows != 0; rows--)
     {
         PROCESS_SSE_SS4x1(0);
 
-        m1 = _mm_unpackhi_epi16(m1, sign1);
-        n1 = _mm_unpackhi_epi16(n1, sign2);
+        sign = _mm_srai_epi16(m1, 15);
+        m1 = _mm_unpackhi_epi16(m1, sign);
+        sign = _mm_srai_epi16(n1, 15);
+        n1 = _mm_unpackhi_epi16(n1, sign);
         diff = _mm_sub_epi32(m1, n1);
         diff = _mm_mullo_epi32(diff, diff);
         sum = _mm_add_epi32(sum, diff);