Split rsqrt into rsqrt{0,1,2}, with increasing cost and precision on ARM

src/effects/gradients/SkRadialGradient.cpp

 
 /*
  * Copyright 2012 Google Inc.
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #include "SkRadialGradient.h"
 #include "SkRadialGradient_Table.h"
@@ skipping 359 matching lines @@
                 *dstC++ = cache[toggle + (sqrt_table[fi] >>
                     SkGradientShaderBase::kSqrt32Shift)];
                 toggle = next_dither_toggle(toggle);
                 fx += dx;
                 fy += dy;
             } while (--count != 0);
         }
     }
 }
 
-// TODO: can we get away with 0th approximatino of inverse-sqrt (i.e. faster than rsqrt)?
-//       seems like ~10bits is more than enough for our use, since we want a byte-index
 static inline Sk4f fast_sqrt(const Sk4f& R) {
-    return R * R.rsqrt();
+    // R * R.rsqrt0() is much faster, but it's non-monotonic, which isn't so pretty for gradients.
+    return R * R.rsqrt1();
 }
 
 static inline Sk4f sum_squares(const Sk4f& a, const Sk4f& b) {
     return a * a + b * b;
 }
 
 void shadeSpan_radial_clamp2(SkScalar sfx, SkScalar sdx, SkScalar sfy, SkScalar sdy,
                              SkPMColor* SK_RESTRICT dstC, const SkPMColor* SK_RESTRICT cache,
                              int count, int toggle) {
     if (radial_completely_pinned(sfx, sdx, sfy, sdy)) {
@@ skipping 294 matching lines @@
     str->appendScalar(fCenter.fY);
     str->append(") radius: ");
     str->appendScalar(fRadius);
     str->append(" ");
 
     this->INHERITED::toString(str);
 
     str->append(")");
 }
 #endif