[x265] [PATCH] asm: avx2 code for sad_x4[64xN] for 10 bpp

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy
# Date 1432026003 -19800
#      Tue May 19 14:30:03 2015 +0530
# Node ID b3991a40f6a92a8fcfe7b24dcb02eeea7444178a
# Parent  179a50d8cc3efb9fef7b1d8f59b2d1d0f513e3ce
asm: avx2 code for sad_x4[64xN] for 10 bpp

sse2
sad_x4[64x16]  2.65x    11016.03        29192.78
sad_x4[64x32]  2.52x    22817.53        57604.71
sad_x4[64x48]  2.68x    32658.78        87513.64
sad_x4[64x64]  2.73x    47608.05        129783.16

avx2
sad_x4[64x16]  6.23x    4761.58         29662.72
sad_x4[64x32]  5.06x    11754.09        59433.72
sad_x4[64x48]  5.69x    15122.64        86068.27
sad_x4[64x64]  5.76x    20597.21        118573.05

diff -r 179a50d8cc3e -r b3991a40f6a9 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Tue May 19 12:54:14 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Tue May 19 14:30:03 2015 +0530
@@ -1357,6 +1357,10 @@
         p.pu[LUMA_32x24].sad_x4 = x265_pixel_sad_x4_32x24_avx2;
         p.pu[LUMA_32x32].sad_x4 = x265_pixel_sad_x4_32x32_avx2;
         p.pu[LUMA_32x64].sad_x4 = x265_pixel_sad_x4_32x64_avx2;
+        p.pu[LUMA_64x16].sad_x4 = x265_pixel_sad_x4_64x16_avx2;
+        p.pu[LUMA_64x32].sad_x4 = x265_pixel_sad_x4_64x32_avx2;
+        p.pu[LUMA_64x48].sad_x4 = x265_pixel_sad_x4_64x48_avx2;
+        p.pu[LUMA_64x64].sad_x4 = x265_pixel_sad_x4_64x64_avx2;
 
         p.pu[LUMA_16x4].convert_p2s = x265_filterPixelToShort_16x4_avx2;
         p.pu[LUMA_16x8].convert_p2s = x265_filterPixelToShort_16x8_avx2;
diff -r 179a50d8cc3e -r b3991a40f6a9 source/common/x86/sad16-a.asm
--- a/source/common/x86/sad16-a.asm	Tue May 19 12:54:14 2015 +0530
+++ b/source/common/x86/sad16-a.asm	Tue May 19 14:30:03 2015 +0530
@@ -1513,4 +1513,8 @@
 SAD_X 4, 32, 24
 SAD_X 4, 32, 32
 SAD_X 4, 32, 64
+SAD_X 4, 64, 16
+SAD_X 4, 64, 32
+SAD_X 4, 64, 48
+SAD_X 4, 64, 64