[x265] [PATCH] asm: avx2 code for ssd_s[16x16] for 10 bpp (336 -> 221)

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy
# Date 1432271370 -19800
#      Fri May 22 10:39:30 2015 +0530
# Node ID 2d8f8053ef1fd1daf5c175143d373c5ded6f17da
# Parent  234bc93bd51698801fad77cc861177ed019f5113
asm: avx2 code for ssd_s[16x16] for 10 bpp (336 -> 221)

sse2
ssd_s[16x16]  6.47x    336.95          2179.88

avx2
ssd_s[16x16]  9.85x    221.43          2181.85

diff -r 234bc93bd516 -r 2d8f8053ef1f source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Thu May 21 16:34:48 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Fri May 22 10:39:30 2015 +0530
@@ -1257,7 +1257,9 @@
         p.pu[LUMA_16x32].satd = x265_pixel_satd_16x32_avx2;
         p.pu[LUMA_16x64].satd = x265_pixel_satd_16x64_avx2;
 
+        p.cu[BLOCK_16x16].ssd_s = x265_pixel_ssd_s_16_avx2;
         p.cu[BLOCK_32x32].ssd_s = x265_pixel_ssd_s_32_avx2;
+
         p.cu[BLOCK_16x16].sse_ss = x265_pixel_ssd_ss_16x16_avx2;
         p.cu[BLOCK_32x32].sse_ss = x265_pixel_ssd_ss_32x32_avx2;
         p.cu[BLOCK_64x64].sse_ss = x265_pixel_ssd_ss_64x64_avx2;