comparison contrib/python-zstandard/zstd/common/compiler.h @ 40121:73fef626dae3

zstandard: vendor python-zstandard 0.10.1

This was just released.

The upstream source distribution from PyPI was extracted. Unwanted
files were removed.

The clang-format ignore list was updated to reflect the new source
of files.

setup.py was updated to pass a new argument to python-zstandard's
function for returning an Extension instance. Upstream had to change
to use relative paths because Python 3.7's packaging doesn't
seem to like absolute paths when defining sources, includes, etc.
The default relative path calculation is relative to setup_zstd.py
which is different from the directory of Mercurial's setup.py.

The project contains a vendored copy of zstandard 1.3.6. The old
version was 1.3.4.

The API should be backwards compatible and nothing in core should
need adjusted. However, there is a new "chunker" API that we
may find useful in places where we want to emit compressed chunks
of a fixed size.

There are a pair of bug fixes in 0.10.0 with regards to
compressobj() and decompressobj() when block flushing is used. I
actually found these bugs when introducing these APIs in Mercurial!
But existing Mercurial code is not affected because we don't
perform block flushing.

# no-check-commit because 3rd party code has different style guidelines

Differential Revision: https://phab.mercurial-scm.org/D4911

40120:89742f1fa6cb

/* Enable runtime BMI2 dispatch based on the CPU.
 * Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default.
 */
#ifndef DYNAMIC_BMI2
  #if (defined(__clang__) && __has_attribute(__target__)) \
      || (defined(__GNUC__) \
          && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8))) \
      && (defined(__x86_64__) || defined(_M_X86)) \
      && !defined(__BMI2__)
  #  define DYNAMIC_BMI2 1
  #else
  #  define DYNAMIC_BMI2 0
  #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)
#else
#  define PREFETCH(ptr)   /* disabled */
#endif

/* disable warnings */
#ifdef _MSC_VER    /* Visual Studio */
#  include <intrin.h>                    /* For Visual 2005 */
#  pragma warning(disable : 4100)        /* disable: C4100: unreferenced formal parameter */

40121:73fef626dae3

/* Enable runtime BMI2 dispatch based on the CPU.
 * Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default.
 */
#ifndef DYNAMIC_BMI2
  #if ((defined(__clang__) && __has_attribute(__target__)) \
      || (defined(__GNUC__) \
          && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \
      && (defined(__x86_64__) || defined(_M_X86)) \
      && !defined(__BMI2__)
  #  define DYNAMIC_BMI2 1
  #else
  #  define DYNAMIC_BMI2 0
  #endif
#endif

/* 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
#  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 */
#  include <intrin.h>                    /* For Visual 2005 */
#  pragma warning(disable : 4100)        /* disable: C4100: unreferenced formal parameter */