[x265] [PATCH] asm: intra_pred_ang4_6_sse2 improved ~2% 622.50 -> 609.99 with nits and tweaks

[dtyx265 at gmail.com]

# HG changeset patch
# User David T Yuen <dtyx265 at gmail.com>
# Date 1427985292 25200
# Node ID 77318f83cca5c86c21f3ea050878eca3f1ba33a0
# Parent  c55ff3e7f4842c5bc9ce5fb45b6de2a1bdabcd4c
asm: intra_pred_ang4_6_sse2 improved ~2% 622.50 -> 609.99 with nits and tweaks

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

diff -r c55ff3e7f484 -r 77318f83cca5 source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Sat Mar 28 14:06:53 2015 -0700
+++ b/source/common/x86/intrapred8.asm	Thu Apr 02 07:34:52 2015 -0700
@@ -1462,18 +1462,17 @@
     jmp         mangle(private_prefix %+ _ %+ intra_pred_ang4_3 %+ SUFFIX %+ .do_filter4x4)
 
 cglobal intra_pred_ang4_6, 3,5,8
-    xor         r4, r4
-    inc         r4
+    xor         r4d, r4d
+    inc         r4d
     cmp         r3m, byte 30
-    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           ; [x 8 8 7 7 6 6 5 5 4 4 3 3 2 2 1]
     mova        m2, m0
-    psrldq      m2, 2           ; [x x x x x x x x 6 5 5 4 4 3 3 2]
+    psrldq      m2, 2           ; [x x x 8 8 7 7 6 6 5 5 4 4 3 3 2]
     punpcklqdq  m0, m0
     punpcklqdq  m2, m2