linear -> sRGB: use fast approximate sqrt()

src/core/SkXfermode4f.cpp

 /*
  * Copyright 2016 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #include "SkPM4fPriv.h"
 #include "SkUtils.h"
 #include "SkXfermode.h"
@@ skipping 50 matching lines @@
     p.r *= p.r;
     p.g *= p.g;
     p.b *= p.b;
 
     return p;
 }
 
 // Store an Sk4x4f back to 4 interlaced 8888 sRGB pixels.
 static void store_4_srgb(void* ptr, const Sk4x4f& p) {
     // Convert back to sRGB and [0,255], again approximating sRGB as gamma == 2.
-    auto r = p.r.sqrt() * 255.0f + 0.5f,
-         g = p.g.sqrt() * 255.0f + 0.5f,
-         b = p.b.sqrt() * 255.0f + 0.5f,
-         a = p.a        * 255.0f + 0.5f;
+    auto r = p.r.rsqrt().invert() * 255.0f + 0.5f,
+         g = p.g.rsqrt().invert() * 255.0f + 0.5f,
+         b = p.b.rsqrt().invert() * 255.0f + 0.5f,
+         a = p.a                  * 255.0f + 0.5f;
     Sk4x4f{r,g,b,a}.transpose((uint8_t*)ptr);
 }
 
 ///////////////////////////////////////////////////////////////////////////////////////////////////
 
 template <DstType D> void general_1(const SkXfermode* xfer, uint32_t dst[],
                                     const SkPM4f* src, int count, const SkAlpha aa[]) {
     const SkPM4f s = rgba_to_pmcolor_order(*src);
     SkXfermodeProc4f proc = xfer->getProc4f();
     SkPM4f d;
@@ skipping 433 matching lines @@
 
     const LCD32Proc procs[] = {
         srcover_n_lcd<kSRGB_Dst>,   src_n_lcd<kSRGB_Dst>,
         srcover_1_lcd<kSRGB_Dst>,   src_1_lcd<kSRGB_Dst>,
 
         srcover_n_lcd<kLinear_Dst>, src_n_lcd<kLinear_Dst>,
         srcover_1_lcd<kLinear_Dst>, src_1_lcd<kLinear_Dst>,
     };
     return procs[flags];
 }