[x265] [PATCH] asm: primitives of sse_ss for 12x16, 24x32, 48x64 and 64xN blocks

murugan at multicorewareinc.com murugan at multicorewareinc.com
Thu Dec 5 10:50:42 CET 2013


# HG changeset patch
# User Murugan Vairavel <murugan at multicorewareinc.com>
# Date 1386237030 -19800
#      Thu Dec 05 15:20:30 2013 +0530
# Node ID 589f43958b63b96c3192967494555e5af9c2cde6
# Parent  dbfde5222782eec2ba414d473fd4ba2494c6f333
asm: primitives of sse_ss for 12x16, 24x32, 48x64 and 64xN blocks

diff -r dbfde5222782 -r 589f43958b63 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Thu Dec 05 13:29:02 2013 +0530
+++ b/source/common/x86/asm-primitives.cpp	Thu Dec 05 15:20:30 2013 +0530
@@ -516,17 +516,24 @@
         p.sse_ss[LUMA_8x8] = x265_pixel_ssd_ss_8x8_sse2;
         p.sse_ss[LUMA_8x16] = x265_pixel_ssd_ss_8x16_sse2;
         p.sse_ss[LUMA_8x32] = x265_pixel_ssd_ss_8x32_sse2;
+        p.sse_ss[LUMA_12x16] = x265_pixel_ssd_ss_12x16_sse2;
         p.sse_ss[LUMA_16x4] = x265_pixel_ssd_ss_16x4_sse2;
         p.sse_ss[LUMA_16x8] = x265_pixel_ssd_ss_16x8_sse2;
         p.sse_ss[LUMA_16x12] = x265_pixel_ssd_ss_16x12_sse2;
         p.sse_ss[LUMA_16x16] = x265_pixel_ssd_ss_16x16_sse2;
         p.sse_ss[LUMA_16x32] = x265_pixel_ssd_ss_16x32_sse2;
         p.sse_ss[LUMA_16x64] = x265_pixel_ssd_ss_16x64_sse2;
+        p.sse_ss[LUMA_24x32] = x265_pixel_ssd_ss_24x32_sse2;
         p.sse_ss[LUMA_32x8] = x265_pixel_ssd_ss_32x8_sse2;
         p.sse_ss[LUMA_32x16] = x265_pixel_ssd_ss_32x16_sse2;
         p.sse_ss[LUMA_32x24] = x265_pixel_ssd_ss_32x24_sse2;
         p.sse_ss[LUMA_32x32] = x265_pixel_ssd_ss_32x32_sse2;
         p.sse_ss[LUMA_32x64] = x265_pixel_ssd_ss_32x64_sse2;
+        p.sse_ss[LUMA_48x64] = x265_pixel_ssd_ss_48x64_sse2;
+        p.sse_ss[LUMA_64x16] = x265_pixel_ssd_ss_64x16_sse2;
+        p.sse_ss[LUMA_64x32] = x265_pixel_ssd_ss_64x32_sse2;
+        p.sse_ss[LUMA_64x48] = x265_pixel_ssd_ss_64x48_sse2;
+        p.sse_ss[LUMA_64x64] = x265_pixel_ssd_ss_64x64_sse2;
 
         p.transpose[BLOCK_4x4] = x265_transpose4_sse2;
         p.transpose[BLOCK_8x8] = x265_transpose8_sse2;


More information about the x265-devel mailing list