--- a/contrib/python-zstandard/zstd/common/compiler.h	Tue Sep 25 20:55:03 2018 +0900
+++ b/contrib/python-zstandard/zstd/common/compiler.h	Mon Oct 08 16:27:40 2018 -0700
@@ -77,9 +77,9 @@
  * Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default.
  */
 #ifndef DYNAMIC_BMI2
-  #if (defined(__clang__) && __has_attribute(__target__)) \
+  #if ((defined(__clang__) && __has_attribute(__target__)) \
       || (defined(__GNUC__) \
-          && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8))) \
+          && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \
       && (defined(__x86_64__) || defined(_M_X86)) \
       && !defined(__BMI2__)
   #  define DYNAMIC_BMI2 1
@@ -88,15 +88,37 @@
   #endif
 #endif
 
-/* prefetch */
-#if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86))  /* _mm_prefetch() is not defined outside of x86/x64 */
-#  include <mmintrin.h>   /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
-#  define PREFETCH(ptr)   _mm_prefetch((const char*)ptr, _MM_HINT_T0)
-#elif defined(__GNUC__)
-#  define PREFETCH(ptr)   __builtin_prefetch(ptr, 0, 0)
+/* prefetch
+ * can be disabled, by declaring NO_PREFETCH macro
+ * All prefetch invocations use a single default locality 2,
+ * generating instruction prefetcht1,
+ * which, according to Intel, means "load data into L2 cache".
+ * This is a good enough "middle ground" for the time being,
+ * though in theory, it would be better to specialize locality depending on data being prefetched.
+ * Tests could not determine any sensible difference based on locality value. */
+#if defined(NO_PREFETCH)
+#  define PREFETCH(ptr)     (void)(ptr)  /* disabled */
 #else
-#  define PREFETCH(ptr)   /* disabled */
-#endif
+#  if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_I86))  /* _mm_prefetch() is not defined outside of x86/x64 */
+#    include <mmintrin.h>   /* https://msdn.microsoft.com/fr-fr/library/84szxsww(v=vs.90).aspx */
+#    define PREFETCH(ptr)   _mm_prefetch((const char*)(ptr), _MM_HINT_T1)
+#  elif defined(__GNUC__) && ( (__GNUC__ >= 4) || ( (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1) ) )
+#    define PREFETCH(ptr)   __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */)
+#  else
+#    define PREFETCH(ptr)   (void)(ptr)  /* disabled */
+#  endif
+#endif  /* NO_PREFETCH */
+
+#define CACHELINE_SIZE 64
+
+#define PREFETCH_AREA(p, s)  {            \
+    const char* const _ptr = (const char*)(p);  \
+    size_t const _size = (size_t)(s);     \
+    size_t _pos;                          \
+    for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) {  \
+        PREFETCH(_ptr + _pos);            \
+    }                                     \
+}
 
 /* disable warnings */
 #ifdef _MSC_VER    /* Visual Studio */