[x265] [PATCH] pixel-sse41.cpp: Modified PROCESS_SSE_SS4x1 macro with faster intrinsics

[dnyaneshwar at multicorewareinc.com]

# HG changeset patch
# User Dnyaneshwar Gorade <dnyaneshwar at multicorewareinc.com>
# Date 1381826069 -19800
#      Tue Oct 15 14:04:29 2013 +0530
# Node ID 3cd533917aa110f7231abf6e0186e99b22dd4dcf
# Parent  1a85d8814346efdb984ea9eae24d1b06b973e9a8
pixel-sse41.cpp: Modified PROCESS_SSE_SS4x1 macro with faster intrinsics.

diff -r 1a85d8814346 -r 3cd533917aa1 source/common/vec/pixel-sse41.cpp
--- a/source/common/vec/pixel-sse41.cpp	Tue Oct 15 12:45:58 2013 +0530
+++ b/source/common/vec/pixel-sse41.cpp	Tue Oct 15 14:04:29 2013 +0530
@@ -5331,10 +5331,8 @@
 #define PROCESS_SSE_SS4x1(BASE)\
     m1 = _mm_loadu_si128((__m128i const*)(fenc + BASE)); \
     n1 = _mm_loadu_si128((__m128i const*)(fref + BASE)); \
-    sign1 = _mm_srai_epi16(m1, 15); \
-    tmp1 = _mm_unpacklo_epi16(m1, sign1); \
-    sign2 = _mm_srai_epi16(n1, 15); \
-    tmp2 = _mm_unpacklo_epi16(n1, sign2); \
+    tmp1= _mm_cvtepi16_epi32(m1); \
+    tmp2= _mm_cvtepi16_epi32(n1); \
     diff = _mm_sub_epi32(tmp1, tmp2); \
     diff = _mm_mullo_epi32(diff, diff); \
     sum = _mm_add_epi32(sum, diff)