[x265] [PATCH] asm:intra_pred_ang4_2 improved by ~4% 134.99 -> 129.95 with nits and tweaks

[dtyx265 at gmail.com]

# HG changeset patch
# User David T Yuen <dtyx265 at gmail.com>
# Date 1427585923 25200
# Node ID 88b50a5f74d98018b1583761a6fc4c5c23f4d401
# Parent  36d70728acc2d9d6103af7530493176c08298ded
asm:intra_pred_ang4_2 improved by ~4% 134.99 -> 129.95 with nits and tweaks

Corrected parameter count
Changed r3m to r3d
Reduced xmm registers to 1

diff -r 36d70728acc2 -r 88b50a5f74d9 source/common/x86/intrapred8.asm
--- a/source/common/x86/intrapred8.asm	Fri Mar 27 13:16:28 2015 -0500
+++ b/source/common/x86/intrapred8.asm	Sat Mar 28 16:38:43 2015 -0700
@@ -1320,22 +1320,20 @@
 ; void intraPredAng4(pixel* dst, intptr_t dstStride, pixel* src, int dirMode, int bFilter)
 ;-----------------------------------------------------------------------------------------
 INIT_XMM sse2
-cglobal intra_pred_ang4_2, 3,5,3
+cglobal intra_pred_ang4_2, 4,5,1
     lea         r4, [r2 + 2]
     add         r2, 10
-    cmp         r3m, byte 34
+    cmp         r3d, byte 34
     cmove       r2, r4
 
     movh        m0, [r2]
     movd        [r0], m0
-    mova        m1, m0
-    psrldq      m1, 1
-    movd        [r0 + r1], m1
-    mova        m2, m0
-    psrldq      m2, 2
-    movd        [r0 + r1 * 2], m2
+    psrldq      m0, 1
+    movd        [r0 + r1], m0
+    psrldq      m0, 1
+    movd        [r0 + r1 * 2], m0
     lea         r1, [r1 * 3]
-    psrldq      m0, 3
+    psrldq      m0, 1
     movd        [r0 + r1], m0
     RET