[x265] [PATCH 1 of 2] fix crash in pixel_var_16x16_internal, because RateControl::acEnergyCu() call it with unalignment pointer

[Min Chen]

# HG changeset patch
# User Min Chen <chenm003 at 163.com>
# Date 1387248448 -28800
# Node ID eff0c2abda8ec2c091688a4312d3c6e65288fe22
# Parent  517eadc29cf6f7c90810b4f997fb3e762895aa6e
fix crash in pixel_var_16x16_internal, because RateControl::acEnergyCu() call it with unalignment pointer

diff -r 517eadc29cf6 -r eff0c2abda8e source/common/x86/pixel-util8.asm
--- a/source/common/x86/pixel-util8.asm	Tue Dec 17 10:50:03 2013 +0530
+++ b/source/common/x86/pixel-util8.asm	Tue Dec 17 10:47:28 2013 +0800
@@ -4452,39 +4452,39 @@
     VAR_END 8, 8
 
 cglobal pixel_var_16x16_internal
-    mova      m0,    [r0]
-    mova      m3,    [r0 + r1]
+    movu      m0,    [r0]
+    movu      m3,    [r0 + r1]
     DEINTB    1, 0, 4, 3, 7
     VAR_CORE
-    mova      m0,    [r0 + 2 * r1]
-    mova      m3,    [r0 + r2]
+    movu      m0,    [r0 + 2 * r1]
+    movu      m3,    [r0 + r2]
     DEINTB    1, 0, 4, 3, 7
     lea       r0,    [r0 + r1 * 4]
     VAR_CORE
-    mova      m0,    [r0]
-    mova      m3,    [r0 + r1]
+    movu      m0,    [r0]
+    movu      m3,    [r0 + r1]
     DEINTB    1, 0, 4, 3, 7
     VAR_CORE
-    mova      m0,    [r0 + 2 * r1]
-    mova      m3,    [r0 + r2]
+    movu      m0,    [r0 + 2 * r1]
+    movu      m3,    [r0 + r2]
     DEINTB    1, 0, 4, 3, 7
     lea       r0,    [r0 + r1 * 4]
     VAR_CORE
-    mova      m0,    [r0]
-    mova      m3,    [r0 + r1]
+    movu      m0,    [r0]
+    movu      m3,    [r0 + r1]
     DEINTB    1, 0, 4, 3, 7
     VAR_CORE
-    mova      m0,    [r0 + 2 * r1]
-    mova      m3,    [r0 + r2]
+    movu      m0,    [r0 + 2 * r1]
+    movu      m3,    [r0 + r2]
     DEINTB    1, 0, 4, 3, 7
     lea       r0,    [r0 + r1 * 4]
     VAR_CORE
-    mova      m0,    [r0]
-    mova      m3,    [r0 + r1]
+    movu      m0,    [r0]
+    movu      m3,    [r0 + r1]
     DEINTB    1, 0, 4, 3, 7
     VAR_CORE
-    mova      m0,    [r0 + 2 * r1]
-    mova      m3,    [r0 + r2]
+    movu      m0,    [r0 + 2 * r1]
+    movu      m3,    [r0 + r2]
     DEINTB    1, 0, 4, 3, 7
     VAR_CORE
     ret