Support Float32 output from SkColorSpaceXform

src/opts/SkNx_neon.h

Index: src/opts/SkNx_neon.h
diff --git a/src/opts/SkNx_neon.h b/src/opts/SkNx_neon.h
index a511243219e3157b5094584cabab51840a7415d3..a6c905d9ee7273eafa200351a49615dde8962fae 100644
--- a/src/opts/SkNx_neon.h
+++ b/src/opts/SkNx_neon.h
@@ -523,7 +523,7 @@ static inline void Sk4h_load4(const void* ptr, Sk4h* r, Sk4h* g, Sk4h* b, Sk4h*
     *a = rgba.val[3];
 }
 
-static inline void Sk4h_store4(void* dst, const Sk4h& r, const Sk4h& g, const Sk4h& b,
+static inline void Sk4f_store4(void* dst, const Sk4h& r, const Sk4h& g, const Sk4h& b,

[Brian Osman, 2016/09/14 20:46:53]

This looks like it should still be Sk4h_store4 ? And the one below is meant to
be Sk4f_store4?

[msarett, 2016/09/14 21:09:43]

Yes :).  Done.

                                const Sk4h& a) {
     uint16x4x4_t rgba = {{
         r.fVec,
@@ -534,4 +534,23 @@ static inline void Sk4h_store4(void* dst, const Sk4h& r, const Sk4h& g, const Sk
     vst4_u16((uint16_t*) dst, rgba);
 }
 
+static inline void Sk4f_load4(const void* ptr, Sk4f* r, Sk4f* g, Sk4f* b, Sk4f* a) {
+    uint16x4x4_t rgba = vld4q_f32((const float*) ptr);

[Brian Osman, 2016/09/14 20:46:53]

float32x4x4_t ?

[msarett, 2016/09/14 21:09:43]

Done.

+    *r = rgba.val[0];
+    *g = rgba.val[1];
+    *b = rgba.val[2];
+    *a = rgba.val[3];
+}
+
+static inline void Sk4h_store4(void* dst, const Sk4f& r, const Sk4f& g, const Sk4f& b,
+                               const Sk4f& a) {
+    float32x4x4_t rgba = {{
+        r.fVec,
+        g.fVec,
+        b.fVec,
+        a.fVec,
+    }};
+    vst4q_f32((float*) dst, rgba);
+}
+
 #endif//SkNx_neon_DEFINED