[x265] [PATCH] asm: avx2 code for sad_x3[64xN] for 10 bpp

[sumalatha at multicorewareinc.com]

# HG changeset patch
# User Sumalatha Polureddy
# Date 1431932524 -19800
#      Mon May 18 12:32:04 2015 +0530
# Node ID d9dce07e5564e656ebbb7d8abe6afc85523d8de4
# Parent  3a1112791e4ed15239908e18f2f004ba8ddc2186
asm: avx2 code for sad_x3[64xN] for 10 bpp

sse2
sad_x3[64x16]  2.78x    8370.09         23242.03
sad_x3[64x32]  2.67x    17362.56        46289.12
sad_x3[64x48]  2.72x    25053.33        68260.15
sad_x3[64x64]  2.47x    35227.60        87136.18

avx2
sad_x3[64x16]  6.45x    3664.96         23624.50
sad_x3[64x32]  5.74x    8741.48         50144.03
sad_x3[64x48]  6.07x    11401.75        69182.98
sad_x3[64x64]  6.38x    16092.67        102696.92

diff -r 3a1112791e4e -r d9dce07e5564 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Mon May 18 12:13:37 2015 +0530
+++ b/source/common/x86/asm-primitives.cpp	Mon May 18 12:32:04 2015 +0530
@@ -1340,6 +1340,10 @@
         p.pu[LUMA_32x24].sad_x3 = x265_pixel_sad_x3_32x24_avx2;
         p.pu[LUMA_32x32].sad_x3 = x265_pixel_sad_x3_32x32_avx2;
         p.pu[LUMA_32x64].sad_x3 = x265_pixel_sad_x3_32x64_avx2;
+        p.pu[LUMA_64x16].sad_x3 = x265_pixel_sad_x3_64x16_avx2;
+        p.pu[LUMA_64x32].sad_x3 = x265_pixel_sad_x3_64x32_avx2;
+        p.pu[LUMA_64x48].sad_x3 = x265_pixel_sad_x3_64x48_avx2;
+        p.pu[LUMA_64x64].sad_x3 = x265_pixel_sad_x3_64x64_avx2;
 
         p.pu[LUMA_16x4].convert_p2s = x265_filterPixelToShort_16x4_avx2;
         p.pu[LUMA_16x8].convert_p2s = x265_filterPixelToShort_16x8_avx2;
diff -r 3a1112791e4e -r d9dce07e5564 source/common/x86/sad16-a.asm
--- a/source/common/x86/sad16-a.asm	Mon May 18 12:13:37 2015 +0530
+++ b/source/common/x86/sad16-a.asm	Mon May 18 12:32:04 2015 +0530
@@ -1496,6 +1496,10 @@
 SAD_X 3, 32, 24
 SAD_X 3, 32, 32
 SAD_X 3, 32, 64
+SAD_X 3, 64, 16
+SAD_X 3, 64, 32
+SAD_X 3, 64, 48
+SAD_X 3, 64, 64
 %define XMM_REGS 9
 SAD_X 4, 16, 16
 SAD_X 4, 16,  8