SSE2 implementation of RGBA box blurs. This yields ~2X perf improvement on

gyp/opts.gyp

 {
   'targets': [
     # Due to an unfortunate intersection of lameness between gcc and gyp,
     # we have to build the *_SSE2.cpp files in a separate target.  The
     # gcc lameness is that, in order to compile SSE2 intrinsics code, it
     # must be passed the -msse2 flag.  However, with this flag, it may
     # emit SSE2 instructions even for scalar code, such as the CPUID
     # test used to test for the presence of SSE2.  So that, and all other
     # code must be compiled *without* -msse2.  The gyp lameness is that it
     # does not allow file-specific CFLAGS, so we must create this extra
@@ skipping 33 matching lines @@
           ],
           'dependencies': [
             'opts_ssse3',
           ],
           'sources': [
             '../src/opts/opts_check_SSE2.cpp',
             '../src/opts/SkBitmapProcState_opts_SSE2.cpp',
             '../src/opts/SkBitmapFilter_opts_SSE2.cpp',
             '../src/opts/SkBlitRow_opts_SSE2.cpp',
             '../src/opts/SkBlitRect_opts_SSE2.cpp',
+            '../src/opts/SkBlurImage_opts_SSE2.cpp',
             '../src/opts/SkMorphology_opts_SSE2.cpp',
             '../src/opts/SkUtils_opts_SSE2.cpp',
             '../src/opts/SkXfermode_opts_none.cpp',
           ],
         }],
         [ 'skia_arch_type == "arm" and arm_version >= 7', {
           # The assembly uses the frame pointer register (r7 in Thumb/r11 in
           # ARM), the compiler doesn't like that.
           'cflags!': [
             '-fno-omit-frame-pointer',
             '-mapcs-frame',
             '-mapcs',
           ],
           'cflags': [
             '-fomit-frame-pointer',
             '-mno-apcs-frame',
           ],
           'variables': {
             'arm_neon_optional%': '<(arm_neon_optional>',
           },
           'sources': [
             '../src/opts/opts_check_arm.cpp',
             '../src/opts/memset.arm.S',
             '../src/opts/SkBitmapProcState_opts_arm.cpp',
             '../src/opts/SkBlitMask_opts_arm.cpp',
             '../src/opts/SkBlitRow_opts_arm.cpp',
             '../src/opts/SkBlitRow_opts_arm.h',
+            '../src/opts/SkBlurImage_opts_none.cpp',
             '../src/opts/SkMorphology_opts_none.cpp',
             '../src/opts/SkXfermode_opts_arm.cpp',
           ],
           'conditions': [
             [ 'arm_neon == 1 or arm_neon_optional == 1', {
               'dependencies': [
                 'opts_neon',
               ]
             }],
             [ 'skia_os == "ios"', {
               'sources!': [
                 # these fail to compile under xcode for ios
                 '../src/opts/memset.arm.S',
                 '../src/opts/SkBitmapProcState_opts_arm.cpp',
                 '../src/opts/SkBlitRow_opts_arm.cpp',
               ],
             }],
           ],
         }],
         [ '(skia_arch_type == "arm" and arm_version < 7) or (skia_os == "ios")', {
           'sources': [
             '../src/opts/SkBitmapProcState_opts_none.cpp',
             '../src/opts/SkBlitMask_opts_none.cpp',
             '../src/opts/SkBlitRow_opts_none.cpp',
+            '../src/opts/SkBlurImage_opts_none.cpp',
             '../src/opts/SkMorphology_opts_none.cpp',
             '../src/opts/SkUtils_opts_none.cpp',
             '../src/opts/SkXfermode_opts_none.cpp',
           ],
         }],
       ],
     },
     # For the same lame reasons as what is done for skia_opts, we have to
     # create another target specifically for SSSE3 code as we would not want
     # to compile the SSE2 code with -mssse3 which would potentially allow
@@ skipping 65 matching lines @@
       ],
     },
   ],
 }
 
 # Local Variables:
 # tab-width:2
 # indent-tabs-mode:nil
 # End:
 # vim: set expandtab tabstop=2 shiftwidth=2: