Add Sk4h_load4 for loading F16.

src/opts/SkNx_neon.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_neon_DEFINED
 #define SkNx_neon_DEFINED
 
@@ skipping 465 matching lines @@
 }
 
 template<> inline Sk4h SkNx_cast<uint16_t, int>(const Sk4i& src) {
     return vmovn_u32(vreinterpretq_u32_s32(src.fVec));
 }
 
 static inline Sk4i Sk4f_round(const Sk4f& x) {
     return vcvtq_s32_f32((x + 0.5f).fVec);
 }
 
+static inline void Sk4h_load4(const void* ptr, Sk4h* r, Sk4h* g, Sk4h* b, Sk4h* a) {
+    uint16x4x4_t rgba = vld4_u16((const uint16_t*)ptr);
+    *r = rgba.val[0];
+    *g = rgba.val[1];
+    *b = rgba.val[2];
+    *a = rgba.val[3];
+}
+
 static inline void Sk4h_store4(void* dst, const Sk4h& r, const Sk4h& g, const Sk4h& b,
                                const Sk4h& a) {
     uint16x4x4_t rgba = {{
         r.fVec,
         g.fVec,
         b.fVec,
         a.fVec,
     }};
     vst4_u16((uint16_t*) dst, rgba);
 }
 
 #endif//SkNx_neon_DEFINED