Port S32A_opaque blit row to SkOpts.

src/opts/SkOpts_sse41.cpp

Index: src/opts/SkOpts_sse41.cpp
diff --git a/src/opts/SkOpts_sse41.cpp b/src/opts/SkOpts_sse41.cpp
index 7a76081e7a62cf33253f63d3ad655d65555cbbc8..34b078c2cafd4a3353d1d6ff0cbe634c099834b2 100644
--- a/src/opts/SkOpts_sse41.cpp
+++ b/src/opts/SkOpts_sse41.cpp
@@ -9,10 +9,11 @@
 
 #define SK_OPTS_NS sk_sse41
 #include "SkBlurImageFilter_opts.h"
+#include "SkBlitRow_opts.h"
 
 #ifndef SK_SUPPORT_LEGACY_X86_BLITS
 
-namespace sk_sse41 {
+namespace sk_sse41_new {

[djsollen, 2016/03/22 17:12:42]

why do we need to add _new?

[mtklein, 2016/03/22 17:39:28]

This is sort of dumb.

You know how the new SkBlitRow_opts.h code has a lot of
   // TODO: this math is bad and you should feel bad.
?  I started trying to fix some of those math problems a few months ago, and
that's the code here in this file.  The blit_row_color32 and blit_mask_d32_a8 in
this file should have correct math.

SkBlitRow_opts.h also has an older blit_row_color32.  Now that I'm mixing the
two files, I end up with two sk_sse41::blit_row_color32 functions, one older,
slower and incorrect, one newer faster and correct.  I've been dragging my heels
a little to rebase Blink and remove the old code.

 
 // An SSE register holding at most 64 bits of useful data in the low lanes.
 struct m64i {
@@ -211,7 +212,7 @@ static void blit_mask_d32_a8(SkPMColor* dst,     size_t dstRB,
     }
 }
 
-}  // namespace sk_sse41
+}  // namespace sk_sse41_new
 
 #endif
 
@@ -222,8 +223,9 @@ namespace SkOpts {
         box_blur_yx = sk_sse41::box_blur_yx;
 
     #ifndef SK_SUPPORT_LEGACY_X86_BLITS
-        blit_row_color32 = sk_sse41::blit_row_color32;
-        blit_mask_d32_a8 = sk_sse41::blit_mask_d32_a8;
+        blit_row_color32 = sk_sse41_new::blit_row_color32;
+        blit_mask_d32_a8 = sk_sse41_new::blit_mask_d32_a8;
     #endif
+        blit_row_s32a_opaque = sk_sse41::blit_row_s32a_opaque;
     }
 }