[x265] [PATCH] asm: avx2 code for sad_x4[32xN] for 10 bpp

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy
# Date 1432020254 -19800
#      Tue May 19 12:54:14 2015 +0530
# Node ID 179a50d8cc3efb9fef7b1d8f59b2d1d0f513e3ce
# Parent  7423bf9989d3def6f009a2dc813ac245d9789100
asm: avx2 code for sad_x4[32xN] for 10 bpp

sse2
sad_x4[ 32x8]  2.77x    3007.23         8338.03
sad_x4[32x16]  2.92x    5716.42         16685.54
sad_x4[32x24]  2.66x    9305.07         24790.30
sad_x4[32x32]  2.68x    12034.66        32295.28
sad_x4[32x64]  2.73x    23399.44        63928.18

avx2
sad_x4[ 32x8]  5.82x    1441.76         8388.88
sad_x4[32x16]  6.23x    2692.36         16771.69
sad_x4[32x24]  5.29x    4622.78         24452.15
sad_x4[32x32]  6.14x    5767.10         35437.46
sad_x4[32x64]  5.65x    11114.55        62818.39

diff -r 7423bf9989d3 -r 179a50d8cc3e source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Tue May 19 12:31:11 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Tue May 19 12:54:14 2015 +0530
@@ -1352,6 +1352,11 @@
         p.pu[LUMA_16x16].sad_x4 = x265_pixel_sad_x4_16x16_avx2;
         p.pu[LUMA_16x32].sad_x4 = x265_pixel_sad_x4_16x32_avx2;
         p.pu[LUMA_16x64].sad_x4 = x265_pixel_sad_x4_16x64_avx2;
+        p.pu[LUMA_32x8].sad_x4 = x265_pixel_sad_x4_32x8_avx2;
+        p.pu[LUMA_32x16].sad_x4 = x265_pixel_sad_x4_32x16_avx2;
+        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_16x4].convert_p2s = x265_filterPixelToShort_16x4_avx2;
         p.pu[LUMA_16x8].convert_p2s = x265_filterPixelToShort_16x8_avx2;
diff -r 7423bf9989d3 -r 179a50d8cc3e source/common/x86/sad16-a.asm
--- a/source/common/x86/sad16-a.asm	Tue May 19 12:31:11 2015 +0530
+++ b/source/common/x86/sad16-a.asm	Tue May 19 12:54:14 2015 +0530
@@ -1508,4 +1508,9 @@
 SAD_X 4, 16,  16
 SAD_X 4, 16,  32
 SAD_X 4, 16,  64
+SAD_X 4, 32,  8
+SAD_X 4, 32, 16
+SAD_X 4, 32, 24
+SAD_X 4, 32, 32
+SAD_X 4, 32, 64