Use switch operator[](int) to kth<int>() so we can use vget_lane.

src/opts/SkNx_sse.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 SkNx_sse_DEFINED
 #define SkNx_sse_DEFINED
 
@@ skipping 69 matching lines @@
 
     static SkNf Min(const SkNf& l, const SkNf& r) { return _mm_min_ps(l.fVec, r.fVec); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return _mm_max_ps(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return _mm_sqrt_ps (fVec);  }
     SkNf rsqrt() const { return _mm_rsqrt_ps(fVec); }
 
     SkNf       invert() const { return SkNf(1) / *this; }
     SkNf approxInvert() const { return _mm_rcp_ps(fVec); }
 
-    float operator[] (int k) const {
+    template <int k> float kth() const {
         SkASSERT(0 <= k && k < 2);
         union { __m128 v; float fs[4]; } pun = {fVec};
-        return pun.fs[k];
+        return pun.fs[k&1];
     }
 
 private:
     __m128 fVec;
 };
 
 template <>
 class SkNf<2, double> {
     typedef SkNi<2, int64_t> Ni;
 public:
@@ skipping 20 matching lines @@
 
     static SkNf Min(const SkNf& l, const SkNf& r) { return _mm_min_pd(l.fVec, r.fVec); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return _mm_max_pd(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return _mm_sqrt_pd(fVec);  }
     SkNf rsqrt() const { return _mm_cvtps_pd(_mm_rsqrt_ps(_mm_cvtpd_ps(fVec))); }
 
     SkNf       invert() const { return SkNf(1) / *this; }
     SkNf approxInvert() const { return _mm_cvtps_pd(_mm_rcp_ps(_mm_cvtpd_ps(fVec))); }
 
-    double operator[] (int k) const {
+    template <int k> double kth() const {
         SkASSERT(0 <= k && k < 2);
         union { __m128d v; double ds[2]; } pun = {fVec};
-        return pun.ds[k];
+        return pun.ds[k&1];
     }
 
 private:
     __m128d fVec;
 };
 
 template <>
 class SkNf<4, float> {
     typedef SkNi<4, int32_t> Ni;
 public:
@@ skipping 21 matching lines @@
 
     static SkNf Min(const SkNf& l, const SkNf& r) { return _mm_min_ps(l.fVec, r.fVec); }
     static SkNf Max(const SkNf& l, const SkNf& r) { return _mm_max_ps(l.fVec, r.fVec); }
 
     SkNf  sqrt() const { return _mm_sqrt_ps (fVec);  }
     SkNf rsqrt() const { return _mm_rsqrt_ps(fVec); }
 
     SkNf       invert() const { return SkNf(1) / *this; }
     SkNf approxInvert() const { return _mm_rcp_ps(fVec); }
 
-    float operator[] (int k) const {
+    template <int k> float kth() const {
         SkASSERT(0 <= k && k < 4);
         union { __m128 v; float fs[4]; } pun = {fVec};
-        return pun.fs[k];
+        return pun.fs[k&3];
     }
 
 private:
     __m128 fVec;
 };
 
 
 #endif//SkNx_sse_DEFINED