Luma fetch 4 pixels

BUG=267
TEST=Luma*
R=ryanpetrie@google.com

Review URL: https://webrtc-codereview.appspot.com/3079004

git-svn-id: http://libyuv.googlecode.com/svn/trunk@831 16f28f9a-4ce2-e073-06de-1de4eb20be90

README.chromium

 Name: libyuv
 URL: http://code.google.com/p/libyuv/
-Version: 830
+Version: 831
 License: BSD
 License File: LICENSE
 

include/libyuv/version.h

@@ -11,6 +11,6 @@
 #ifndef INCLUDE_LIBYUV_VERSION_H_  // NOLINT
 #define INCLUDE_LIBYUV_VERSION_H_
 
-#define LIBYUV_VERSION 830
+#define LIBYUV_VERSION 831
 
 #endif  // INCLUDE_LIBYUV_VERSION_H_  NOLINT

source/row_posix.cc

@@ -6378,7 +6378,7 @@ void ARGBLumaColorTableRow_SSSE3(const uint8* src_argb,
     // 4 pixel loop.
     ".p2align  4                               \n"
   "1:                                          \n"
-    "movq      (%2),%%xmm0                     \n"
+    "movdqu    (%2),%%xmm0                     \n"
     "pmaddubsw %%xmm3,%%xmm0                   \n"
     "phaddw    %%xmm0,%%xmm0                   \n"
     "pand      %%xmm4,%%xmm0                   \n"

source/row_win.cc

@@ -7161,7 +7161,7 @@ void ARGBLumaColorTableRow_SSSE3(const uint8* src_argb,
     // 4 pixel loop.
     align      4
   convertloop:
-    movq       xmm0, qword ptr [eax]      // generate luma ptr
+    movdqu     xmm0, qword ptr [eax]      // generate luma ptr
     pmaddubsw  xmm0, xmm3
     phaddw     xmm0, xmm0
     pand       xmm0, xmm4  // mask out low bits