sk4px the rest of the easy xfermodes.

src/core/Sk4px.h

 /*
  * Copyright 2015 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #ifndef Sk4px_DEFINED
 #define Sk4px_DEFINED
 
@@ skipping 47 matching lines @@
     };
 
     Wide widenLo() const;               // ARGB -> 0A 0R 0G 0B
     Wide widenHi() const;               // ARGB -> A0 R0 G0 B0
     Wide mulWiden(const Sk16b&) const;  // 8-bit x 8-bit -> 16-bit components.
     Wide mul255Widen() const {
         // TODO: x*255 = x*256-x, so something like this->widenHi() - this->widenLo()?
         return this->mulWiden(Sk16b(255));
     }
 
+    // Generally faster than this->mulWiden(other).div255RoundNarrow().
+    // May be incorrect by +-1, but is always exactly correct when *this or other is 0 or 255.
+    Sk4px fastMulDiv255Round(const Sk16b& other) const {
+        // (x*y + x) / 256 meets these criteria.  (As of course does (x*y + y) / 256 by symmetry.)
+        Sk4px::Wide  x = this->widenLo(),
+                    xy = this->mulWiden(other);
+        return x.addNarrowHi(xy);
+    }
+
     // A generic driver that maps fn over a src array into a dst array.
     // fn should take an Sk4px (4 src pixels) and return an Sk4px (4 dst pixels).
     template <typename Fn>
     static void MapSrc(int count, SkPMColor* dst, const SkPMColor* src, Fn fn) {
         // This looks a bit odd, but it helps loop-invariant hoisting across different calls to fn.
         // Basically, we need to make sure we keep things inside a single loop.
         while (count > 0) {
             if (count >= 8) {
                 Sk4px dst0 = fn(Load4(src+0)),
                       dst4 = fn(Load4(src+4));
@@ skipping 90 matching lines @@
     #if SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2
         #include "../opts/Sk4px_SSE2.h"
     #elif defined(SK_ARM_HAS_NEON)
         #include "../opts/Sk4px_NEON.h"
     #else
         #include "../opts/Sk4px_none.h"
     #endif
 #endif
 
 #endif//Sk4px_DEFINED