[x265] [PATCH 6 of 7] asm: intra_pred_ang4_8_sse2 improved ~5% 609.99 -> 577.50 with nits and tweaks

[dtyx265 at gmail.com]

# HG changeset patch
# User David T Yuen <dtyx265 at gmail.com>
# Date 1427913679 25200
# Node ID 0b47c12cc9acc1d7b417f909eccf03275ecdcedb
# Parent  a71fadb79b45978dc86fbcbb923f3d2d90ebaa21
asm: intra_pred_ang4_8_sse2 improved ~5% 609.99 -> 577.50 with nits and tweaks

Changed r3 and r4 to r3d and r4d
tweaked unpacking for performance

diff -r a71fadb79b45 -r 0b47c12cc9ac source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Wed Apr 01 11:36:57 2015 -0700
+++ b/source/common/x86/intrapred8.asm	Wed Apr 01 11:41:19 2015 -0700
@@ -1505,16 +1505,15 @@
     jmp         mangle(private_prefix %+ _ %+ intra_pred_ang4_3 %+ SUFFIX %+ .do_filter4x4)
 
 cglobal intra_pred_ang4_8, 3,5,8
-    xor         r4, r4
-    inc         r4
+    xor         r4d, r4d
+    inc         r4d
     cmp         r3m, byte 28
-    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
-    psrldq      m1, 1           ; [x 8 7 6 5 4 3 2]
-    punpcklbw   m0, m1          ; [x 8 8 7 7 6 6 5 5 4 4 3 3 2 2 1]
+    punpcklbw   m0, m0
+    psrldq      m0, 1
     punpcklqdq  m0, m0
     mova        m2, m0