[x265] [PATCH 1 of 7] asm:intra_pred_ang4_3_sse2 improved ~4.5% 684.95 -> 654.99 with nits and tweaks

[dtyx265 at gmail.com]

# HG changeset patch
# User David T Yuen <dtyx265 at gmail.com>
# Date 1427891624 25200
# Node ID 529c6056ccfbce57cd845abec59a2af02812cd57
# Parent  89bc6238d4a2e3f117f0127e406c6dfbf093868b
asm:intra_pred_ang4_3_sse2 improved ~4.5% 684.95 -> 654.99 with nits and tweaks

Changed r3 and r4 to r3d and r4d
Removed unnecessary pxor's
changed pshufd to psrldq

diff -r 89bc6238d4a2 -r 529c6056ccfb source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Tue Mar 31 10:44:43 2015 -0700
+++ b/source/common/x86/intrapred8.asm	Wed Apr 01 05:33:44 2015 -0700
@@ -1339,10 +1339,10 @@
 
 INIT_XMM sse2
 cglobal intra_pred_ang4_3, 3,5,8
-    mov         r4, 1
+    mov         r4d, 1
     cmp         r3m, byte 33
-    mov         r3, 9
-    cmove       r3, r4
+    mov         r3d, 9
+    cmove       r3d, r4d
 
     movh        m0, [r2 + r3]   ; [8 7 6 5 4 3 2 1]
     mova        m1, m0
@@ -1368,7 +1368,6 @@
 ALIGN 16
 .do_filter4x4:
     pxor        m1, m1
-    pxor        m3, m3
     punpckhbw   m3, m0
     psrlw       m3, 8
     pmaddwd     m3, m5
@@ -1377,7 +1376,6 @@
     packssdw    m0, m3
     paddw       m0, [pw_16]
     psraw       m0, 5
-    pxor        m3, m3
     punpckhbw   m3, m2
     psrlw       m3, 8
     pmaddwd     m3, m7
@@ -1404,12 +1402,12 @@
 .store:
     packuswb    m0, m2
     movd        [r0], m0
-    pshufd      m0, m0, 0x39
+    psrldq      m0, 4
     movd        [r0 + r1], m0
-    pshufd      m0, m0, 0x39
+    psrldq      m0, 4
     movd        [r0 + r1 * 2], m0
     lea         r1, [r1 * 3]
-    pshufd      m0, m0, 0x39
+    psrldq      m0, 4
     movd        [r0 + r1], m0
     RET