try simplest code: inline whenever vaguely sensible

include/core/SkUtils.h

Index: include/core/SkUtils.h
diff --git a/include/core/SkUtils.h b/include/core/SkUtils.h
index 4e24bd0883555e641515c8a35e0029086f4b22b6..d34975523406547f98c12f6c1180a7adb2abc614 100644
--- a/include/core/SkUtils.h
+++ b/include/core/SkUtils.h
@@ -31,12 +31,11 @@ namespace SkOpts {
     @param count    The number of times value should be copied into the buffer.
 */
 static inline void sk_memset16(uint16_t buffer[], uint16_t value, int count) {
-#if defined(SK_CPU_ARM64)
-    while (count --> 0) { *buffer++ = value; } return;
-#elif defined(SK_CPU_ARM32)
-    if (count <= 10) { while (count --> 0) { *buffer++ = value; } return; }
-#endif
+#if defined(SK_ARM_HAS_NEON) || SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2
+    while (count --> 0) { *buffer++ = value; }
+#else
     SkOpts::memset16(buffer, value, count);
+#endif
 }
 
 /** Similar to memset(), but it assigns a 32bit value into the buffer.
@@ -45,12 +44,11 @@ static inline void sk_memset16(uint16_t buffer[], uint16_t value, int count) {
     @param count    The number of times value should be copied into the buffer.
 */
 static inline void sk_memset32(uint32_t buffer[], uint32_t value, int count) {
-#if defined(SK_CPU_ARM64)
-    while (count --> 0) { *buffer++ = value; } return;
-#elif defined(SK_CPU_ARM32)
-    if (count <= 10) { while (count --> 0) { *buffer++ = value; } return; }
-#endif
+#if defined(SK_ARM_HAS_NEON) || SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2
+    while (count --> 0) { *buffer++ = value; }
+#else
     SkOpts::memset32(buffer, value, count);
+#endif
 }