div255(x) as ((x+128)*257)>>16 with SSE

src/opts/Sk4px_none.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.
  */
 
 #include "SkUtils.h"
 
 namespace { // See Sk4px.h
@@ skipping 44 matching lines @@
 }
 
 inline Sk4px Sk4px::Wide::addNarrowHi(const Sk16h& other) const {
     Sk4px::Wide r = (*this + other) >> 8;
     return Sk16b(r.kth< 0>(), r.kth< 1>(), r.kth< 2>(), r.kth< 3>(),
                  r.kth< 4>(), r.kth< 5>(), r.kth< 6>(), r.kth< 7>(),
                  r.kth< 8>(), r.kth< 9>(), r.kth<10>(), r.kth<11>(),
                  r.kth<12>(), r.kth<13>(), r.kth<14>(), r.kth<15>());
 }
 
+inline Sk4px Sk4px::Wide::div255() const {
+    // Calculated as ((x+128) + ((x+128)>>8)) >> 8.
+    auto v = *this + Sk16h(128);
+    return v.addNarrowHi(v>>8);
+}
+
 inline Sk4px Sk4px::alphas() const {
     static_assert(SK_A32_SHIFT == 24, "This method assumes little-endian.");
     return Sk16b(this->kth< 3>(), this->kth< 3>(), this->kth< 3>(), this->kth< 3>(),
                  this->kth< 7>(), this->kth< 7>(), this->kth< 7>(), this->kth< 7>(),
                  this->kth<11>(), this->kth<11>(), this->kth<11>(), this->kth<11>(),
                  this->kth<15>(), this->kth<15>(), this->kth<15>(), this->kth<15>());
 }
 
 inline Sk4px Sk4px::Load4Alphas(const SkAlpha a[4]) {
     return Sk16b(a[0], a[0], a[0], a[0],
@@ skipping 50 matching lines @@
     this->store2(dst32);
     for (int i = 0; i < 2; i++) { dst[i] = SkPixel32ToPixel16(dst32[i]); }
 }
 inline void Sk4px::store1(SkPMColor16 dst[1]) const {
     SkPMColor dst32;
     this->store1(&dst32);
     dst[0] = SkPixel32ToPixel16(dst32);
 }
 
 }  // namespace