[x265] [PATCH] blockcopy_sp_4x2, optimized asm code according to modified C primitive

[praveen at multicorewareinc.com]

# HG changeset patch
# User Praveen Tiwari
# Date 1383901064 -19800
# Node ID ebbb72654464dd24814e68e40d9504d4ad662892
# Parent  94cba84de8dd754322cf62df71abd4af24b0b47d
blockcopy_sp_4x2, optimized asm code according to modified C primitive

diff -r 94cba84de8dd -r ebbb72654464 source/common/x86/blockcopy8.asm
--- a/source/common/x86/blockcopy8.asm	Fri Nov 08 02:01:52 2013 -0600
+++ b/source/common/x86/blockcopy8.asm	Fri Nov 08 14:27:44 2013 +0530
@@ -906,16 +906,14 @@
 
 add        r3,        r3
 
-mova       m0,        [tab_Vm]
+movh       m0,        [r2]
+movh       m1,        [r2 + r3]
 
-movh       m1,        [r2]
-movh       m2,        [r2 + r3]
+packuswb   m0,        m1
 
-pshufb     m1,        m0
-pshufb     m2,        m0
-
-movd       [r0],      m1
-movd       [r0 + r1], m2
+movd       [r0],      m0
+pshufd     m0,        m0,        2
+movd       [r0 + r1], m0
 
 RET