try plain-old code for sk_memset16/32 now that NEON is compile-time

include/core/SkUtils.h

Index: include/core/SkUtils.h
diff --git a/include/core/SkUtils.h b/include/core/SkUtils.h
index 2b390f04e5270b1ed64c1bfaaffe0f5be91b69bd..b5674eceadebb9516223b7875c73bb84c97928d1 100644
--- a/include/core/SkUtils.h
+++ b/include/core/SkUtils.h
@@ -10,36 +10,15 @@
 
 #include "SkTypes.h"
 
-namespace SkOpts {
-    extern void (*memset16)(uint16_t[], uint16_t, int);
-    extern void (*memset32)(uint32_t[], uint32_t, int);
-}
-
-///////////////////////////////////////////////////////////////////////////////
-
-// Inlining heuristics were determined by using perf.skia.org and bench/MemsetBench.cpp.
-// When using MSVC, inline is better >= 1K and worse <= 100.  The Nexus Player was the opposite.
-// Otherwise, when NEON or SSE is available to GCC or Clang, they can handle it best.
-// See https://code.google.com/p/chromium/issues/detail?id=516426#c15 for more details.
-// See also skia:4316; it might be a good idea to use rep stosw/stosd here.
-#define INLINE_IF(cond) if (cond) { while (count --> 0) { *buffer++ = value; } return; }
-
 /** Similar to memset(), but it assigns a 16bit value into the buffer.
     @param buffer   The memory to have value copied into it
     @param value    The 16bit value to be copied into buffer
     @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(_MSC_VER)
-    INLINE_IF(count > 300)
-#elif defined(SK_BUILD_FOR_ANDROID) && defined(SK_CPU_X86)
-    INLINE_IF(count < 300)
-#elif defined(SK_ARM_HAS_NEON) || SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2
-    INLINE_IF(true)
-#else
-    INLINE_IF(count <= 10)
-#endif
-    SkOpts::memset16(buffer, value, count);
+    for (int i = 0; i < count; i++) {
+        buffer[i] = value;
+    }
 }
 
 /** Similar to memset(), but it assigns a 32bit value into the buffer.
@@ -48,20 +27,11 @@ 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(_MSC_VER)
-    INLINE_IF(count > 300)
-#elif defined(SK_BUILD_FOR_ANDROID) && defined(SK_CPU_X86)
-    INLINE_IF(count < 300)
-#elif defined(SK_ARM_HAS_NEON) || SK_CPU_SSE_LEVEL >= SK_CPU_SSE_LEVEL_SSE2
-    INLINE_IF(true)
-#else
-    INLINE_IF(count <= 10)
-#endif
-    SkOpts::memset32(buffer, value, count);
+    for (int i = 0; i < count; i++) {
+        buffer[i] = value;
+    }
 }
 
-#undef INLINE_IF
-
 ///////////////////////////////////////////////////////////////////////////////
 
 #define kMaxBytesInUTF8Sequence     4