[x265] [PATCH] asm: avx code for chroma copy_ss 32x64, reused luma code (2616 -> 1313)

sumalatha at multicorewareinc.com sumalatha at multicorewareinc.com
Tue Apr 14 13:13:03 CEST 2015


# HG changeset patch
# User Sumalatha Polureddy
# Date 1429006919 -19800
#      Tue Apr 14 15:51:59 2015 +0530
# Node ID ad2cab40df66aa1b2c2f5bc36d61a5f06dbbf176
# Parent  dd456de98c239b86e29bf349881854a699056240
asm: avx code for chroma copy_ss 32x64, reused luma code (2616 -> 1313)

sse2
[i422] copy_ss[32x64]  8.36x    2616.62         21881.62

avx
[i422] copy_ss[32x64]  16.80x   1313.77         22065.42

diff -r dd456de98c23 -r ad2cab40df66 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp	Tue Apr 14 13:41:40 2015 +0800
+++ b/source/common/x86/asm-primitives.cpp	Tue Apr 14 15:51:59 2015 +0530
@@ -1516,6 +1516,7 @@
         p.chroma[X265_CSP_I420].cu[CHROMA_420_16x16].copy_ss = x265_blockcopy_ss_16x16_avx;
         p.chroma[X265_CSP_I420].cu[CHROMA_420_32x32].copy_ss = x265_blockcopy_ss_32x32_avx;
         p.chroma[X265_CSP_I422].cu[CHROMA_422_16x32].copy_ss = x265_blockcopy_ss_16x32_avx;
+        p.chroma[X265_CSP_I422].cu[CHROMA_422_32x64].copy_ss = x265_blockcopy_ss_32x64_avx;
 
         p.chroma[X265_CSP_I420].pu[CHROMA_420_32x8].copy_pp = x265_blockcopy_pp_32x8_avx;
         p.pu[LUMA_32x8].copy_pp = x265_blockcopy_pp_32x8_avx;


More information about the x265-devel mailing list