Add sqrt() and rsqrt() to Sk4f.

src/core/Sk4x_sse.h

 // It is important _not_ to put header guards here.
 // This file will be intentionally included three times.
 
 // Useful reading:
 //   https://software.intel.com/sites/landingpage/IntrinsicsGuide/
 
 #if defined(SK4X_PREAMBLE)
     // Code in this file may assume SSE and SSE2.
     #include <emmintrin.h>
 
@@ skipping 81 matching lines @@
 
 // We're going to try a little experiment here and skip allTrue(), anyTrue(), and bit-manipulators
 // for Sk4f.  Code that calls them probably does so accidentally.
 // Ask mtklein to fill these in if you really need them.
 
 M(Sk4f) add     (const Sk4f& o) const { return _mm_add_ps(fVec, o.fVec); }
 M(Sk4f) subtract(const Sk4f& o) const { return _mm_sub_ps(fVec, o.fVec); }
 M(Sk4f) multiply(const Sk4f& o) const { return _mm_mul_ps(fVec, o.fVec); }
 M(Sk4f) divide  (const Sk4f& o) const { return _mm_div_ps(fVec, o.fVec); }
 
+M(Sk4f) rsqrt() const { return _mm_rsqrt_ps(fVec); }
+M(Sk4f)  sqrt() const { return _mm_sqrt_ps( fVec); }
+
 M(Sk4i) equal           (const Sk4f& o) const { return _mm_cmpeq_ps (fVec, o.fVec); }
 M(Sk4i) notEqual        (const Sk4f& o) const { return _mm_cmpneq_ps(fVec, o.fVec); }
 M(Sk4i) lessThan        (const Sk4f& o) const { return _mm_cmplt_ps (fVec, o.fVec); }
 M(Sk4i) greaterThan     (const Sk4f& o) const { return _mm_cmpgt_ps (fVec, o.fVec); }
 M(Sk4i) lessThanEqual   (const Sk4f& o) const { return _mm_cmple_ps (fVec, o.fVec); }
 M(Sk4i) greaterThanEqual(const Sk4f& o) const { return _mm_cmpge_ps (fVec, o.fVec); }
 
 M(Sk4f) Min(const Sk4f& a, const Sk4f& b) { return _mm_min_ps(a.fVec, b.fVec); }
 M(Sk4f) Max(const Sk4f& a, const Sk4f& b) { return _mm_max_ps(a.fVec, b.fVec); }
 
@@ skipping 58 matching lines @@
     }
     M(Sk4i) Max(const Sk4i& a, const Sk4i& b) {
         Sk4i less = a.lessThan(b);
         return b.bitAnd(less).bitOr(a.andNot(less));
     }
 #endif
 
 #undef M
 
 #endif//Method definitions.