update memset16/32 inlining heuristics

include/core/SkUtils.h

 /*
  * Copyright 2006 The Android Open Source Project
  *
  * Use of this source code is governed by a BSD-style license that can be
  * found in the LICENSE file.
  */
 
 #ifndef SkUtils_DEFINED
 #define SkUtils_DEFINED
 
 #include "SkTypes.h"
 
 namespace SkOpts {
     extern void (*memset16)(uint16_t[], uint16_t, int);
     extern void (*memset32)(uint32_t[], uint32_t, int);
 }
 
 ///////////////////////////////////////////////////////////////////////////////
 
-// The inlining heuristics below were determined using bench/MemsetBench.cpp
-// on a x86 desktop, a Nexus 7 with and without NEON, and a Nexus 9:
-//   - on x86, inlining was never faster,
-//   - on ARMv7, inlining was faster for N<=10.  Putting this check inside the NEON
-//     code was not helpful; it's got to be here outside.
-//   - NEON code generation for ARMv8 with GCC 4.9 is terrible,
-//     making the NEON code ~8x slower that just a serial loop.
+// 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; }

[Noel Gordon, 2015/11/25 02:02:25]

while (count --> 0)

I suppose it compiles, but maybe 

while (count-- > 0)

might be idiomatic here?

   

 
 /** 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(SK_CPU_ARM64)
-    while (count --> 0) { *buffer++ = value; } return;
-#elif defined(SK_CPU_ARM32)
-    if (count <= 10) { while (count --> 0) { *buffer++ = value; } return; }
+#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);
 }
 
 /** Similar to memset(), but it assigns a 32bit value into the buffer.
     @param buffer   The memory to have value copied into it
     @param value    The 32bit value to be copied into buffer
     @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; }
+#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);
 }
 
+#undef INLINE_IF
 
 ///////////////////////////////////////////////////////////////////////////////
 
 #define kMaxBytesInUTF8Sequence     4
 
 #ifdef SK_DEBUG
     int SkUTF8_LeadByteToCount(unsigned c);
 #else
     #define SkUTF8_LeadByteToCount(c)   ((((0xE5 << 24) >> ((unsigned)c >> 4 << 1)) & 3) + 1)
 #endif
@@ skipping 58 matching lines @@
     }
     ~SkAutoTrace() {
         SkDebugf("--- trace: %s Leave\n", fLabel);
     }
 private:
     const char* fLabel;
 };
 #define SkAutoTrace(...) SK_REQUIRE_LOCAL_VAR(SkAutoTrace)
 
 #endif