[x265] [PATCH] asm: avx2 code for chroma sse_pp[16x32, 32x64] for i422

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy
# Date 1433482390 -19800
#      Fri Jun 05 11:03:10 2015 +0530
# Node ID bf9ddfe13ca034c59e20989765af647bf2f304d7
# Parent  62adf0ef875f9c310250bada6f9a699c9f8ff758
asm: avx2 code for chroma sse_pp[16x32, 32x64] for i422

sse2
[i422] sse_pp[16x32]  5.29x    1030.36         5446.27
[i422] sse_pp[32x64]  4.40x    4091.52         17994.55
avx2
[i422] sse_pp[16x32]  9.07x    599.30          5436.95
[i422] sse_pp[32x64]  9.07x    2009.39         18226.27

diff -r 62adf0ef875f -r bf9ddfe13ca0 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Thu Jun 04 15:25:47 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Fri Jun 05 11:03:10 2015 +0530
@@ -1364,6 +1364,8 @@
         p.cu[BLOCK_64x64].sse_pp = x265_pixel_ssd_64x64_avx2;
         p.chroma[X265_CSP_I420].cu[BLOCK_420_16x16].sse_pp = x265_pixel_ssd_16x16_avx2;
         p.chroma[X265_CSP_I420].cu[BLOCK_420_32x32].sse_pp = x265_pixel_ssd_32x32_avx2;
+        p.chroma[X265_CSP_I422].cu[BLOCK_422_16x32].sse_pp = (pixelcmp_t)x265_pixel_ssd_ss_16x32_avx2;
+        p.chroma[X265_CSP_I422].cu[BLOCK_422_32x64].sse_pp = (pixelcmp_t)x265_pixel_ssd_ss_32x64_avx2;
 
         p.quant = x265_quant_avx2;
         p.nquant = x265_nquant_avx2;
diff -r 62adf0ef875f -r bf9ddfe13ca0 source/common/x86/ssd-a.asm
--- a/source/common/x86/ssd-a.asm	Thu Jun 04 15:25:47 2015 +0530
+++ b/source/common/x86/ssd-a.asm	Fri Jun 05 11:03:10 2015 +0530
@@ -467,6 +467,8 @@
 SSD_ONE    16, 16
 SSD_ONE    32, 32
 SSD_ONE    64, 64
+SSD_ONE    16, 32
+SSD_ONE    32, 64
 %endif ; HIGH_BIT_DEPTH
 
 ;-----------------------------------------------------------------------------