[x265] [PATCH 1 of 5] asm: avx2 code sse_pp[32x32] and sse_pp[64x64] for 8 bpp

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy
# Date 1427260761 -19800
#      Wed Mar 25 10:49:21 2015 +0530
# Node ID 49d9c978601618ab2588b2a6f11eeeb59fb57450
# Parent  e637273e2ae6391d43a037d9a4298a8be8e178ad
asm: avx2 code sse_pp[32x32] and sse_pp[64x64] for 8 bpp

sse3
sse_pp[32x32]  6.39x    2497.86         15957.98
sse_pp[64x64]  5.01x    12520.95        62749.02

avx2
sse_pp[32x32]  13.02x   1246.36         16225.92
sse_pp[64x64]  11.79x   5189.50         61170.29

diff -r e637273e2ae6 -r 49d9c9786016 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Tue Mar 24 15:31:05 2015 -0500
+++ b/source/common/x86/asm-primitives.cpp	Wed Mar 25 10:49:21 2015 +0530
@@ -1534,6 +1534,8 @@
         p.pu[LUMA_16x32].sad_x4 = x265_pixel_sad_x4_16x32_avx2;
 
         p.cu[BLOCK_16x16].sse_pp = x265_pixel_ssd_16x16_avx2;
+        p.cu[BLOCK_32x32].sse_pp = x265_pixel_ssd_32x32_avx2;
+        p.cu[BLOCK_64x64].sse_pp = x265_pixel_ssd_64x64_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;
diff -r e637273e2ae6 -r 49d9c9786016 source/common/x86/ssd-a.asm
--- a/source/common/x86/ssd-a.asm	Tue Mar 24 15:31:05 2015 -0500
+++ b/source/common/x86/ssd-a.asm	Wed Mar 25 10:49:21 2015 +0530
@@ -1094,6 +1094,8 @@
 INIT_YMM avx2
 SSD 16, 16
 SSD 16,  8
+SSD 32, 32
+SSD 64, 64
 %assign function_align 16
 %endif ; !HIGH_BIT_DEPTH