Add SSE4 optimization of S32A_Opaque_Blitrow

gyp/opts.gyp

 # Gyp file for opts projects
 {
   '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
@@ skipping 28 matching lines @@
               'cflags': [
                 '-msse2',
               ],
             }],
           ],
           'include_dirs': [
             '../include/utils',
           ],
           'dependencies': [
             'opts_ssse3',
+            'opts_sse4',
           ],
           'sources': [
             '../src/opts/opts_check_x86.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',
@@ skipping 128 matching lines @@
           ],
         }],
         # (Mac has -mssse3 globally.)
         [ 'skia_arch_type == "x86"', {
           'sources': [
             '../src/opts/SkBitmapProcState_opts_SSSE3.cpp',
           ],
         }],
       ],
     },
+    # For the same lame reasons as what is done for skia_opts, we also have to
+    # create another target specifically for SSE4 code as we would not want
+    # to compile the SSE2 code with -msse4 which would potentially allow
+    # gcc to generate SSE4 code.
+    {
+      'target_name': 'opts_sse4',
+      'product_name': 'skia_opts_sse4',
+      'type': 'static_library',
+      'standalone_static_library': 1,
+      'dependencies': [
+        'core.gyp:*',
+        'effects.gyp:*'
+      ],
+      'include_dirs': [
+        '../src/core',
+      ],
+      'conditions': [
+        [ 'skia_os in ["linux", "freebsd", "openbsd", "solaris", "nacl", "chromeos", "android", "mac"] \
+           and not skia_android_framework', {
+          'cflags': [
+            '-msse4',
+          ],
+        }],
+        [ 'skia_arch_width == 64 and skia_arch_type == "x86"', {
+          'sources': [
+            '../src/opts/SkBlitRow_opts_SSE4_x64_asm.S',
+          ],
+        }],
+        [ 'skia_arch_width == 32 and skia_arch_type == "x86"', {
+          'sources': [
+            '../src/opts/SkBlitRow_opts_SSE4_asm.S',
+          ],
+       }],
+      ],
+    },
     # NEON code must be compiled with -mfpu=neon which also affects scalar
     # code. To support dynamic NEON code paths, we need to build all
     # NEON-specific sources in a separate static library. The situation
-    # is very similar to the SSSE3 one.
+    # is very similar to the SSSE3 and SSE4 one.
     {
       'target_name': 'opts_neon',
       'product_name': 'skia_opts_neon',
       'type': 'static_library',
       'standalone_static_library': 1,
       'dependencies': [
         'core.gyp:*',
         'effects.gyp:*'
       ],
       'include_dirs': [
@@ skipping 26 matching lines @@
         '../src/opts/SkBitmapProcState_matrix_neon.h',
         '../src/opts/SkBlitMask_opts_arm_neon.cpp',
         '../src/opts/SkBlitRow_opts_arm_neon.cpp',
         '../src/opts/SkBlurImage_opts_neon.cpp',
         '../src/opts/SkMorphology_opts_neon.cpp',
         '../src/opts/SkXfermode_opts_arm_neon.cpp',
       ],
     },
   ],
 }