[x265] [PATCH] pixel_add_pp: 4x8, 4x16, merged movd and pmovzxbw instructions

[praveen at multicorewareinc.com]

# HG changeset patch
# User Praveen Tiwari
# Date 1384953332 -19800
# Node ID ce1c38cd5e4373a6fe2d8df5bacd97536c7574c5
# Parent  1044e71e42ad08d9961e3c3106609eda58f099f4
pixel_add_pp: 4x8, 4x16, merged movd and pmovzxbw instructions

diff -r 1044e71e42ad -r ce1c38cd5e43 source/common/x86/pixeladd8.asm
--- a/source/common/x86/pixeladd8.asm	Wed Nov 20 18:40:59 2013 +0530
+++ b/source/common/x86/pixeladd8.asm	Wed Nov 20 18:45:32 2013 +0530
@@ -113,8 +113,7 @@
 mov         r6d,           %2/4
 
 .loop
-      movd        m0,            [r2]
-      pmovzxbw    m0,            m0
+      pmovzxbw    m0,            [r2]
       movh        m1,            [r3]
 
       paddw       m0,            m1
@@ -122,8 +121,7 @@
 
       movd        [r0],          m0
 
-      movd        m0,            [r2 + r4]
-      pmovzxbw    m0,            m0
+      pmovzxbw    m0,            [r2 + r4]
       movh        m1,            [r3 + r5]
 
       paddw       m0,            m1
@@ -131,8 +129,7 @@
 
       movd        [r0 + r1],     m0
 
-      movd        m0,            [r2 + 2 * r4]
-      pmovzxbw    m0,            m0
+      pmovzxbw    m0,            [r2 + 2 * r4]
       movh        m1,            [r3 + 2 * r5]
 
       paddw       m0,            m1
@@ -144,8 +141,7 @@
       lea         r2,            [r2 + 2 * r4]
       lea         r3,            [r3 + 2 * r5]
 
-      movd        m0,            [r2 + r4]
-      pmovzxbw    m0,            m0
+      pmovzxbw    m0,            [r2 + r4]
       movh        m1,            [r3 + r5]
 
       paddw       m0,            m1