annotate 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

/*
 * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
 * All rights reserved.
 *
 * This source code is licensed under both the BSD-style license (found in the
 * LICENSE file in the root directory of this source tree) and the GPLv2 (found
 * in the COPYING file in the root directory of this source tree).
 * You may select, at your option, one of the above-listed licenses.
 */

#ifndef ZSTD_COMPILER_H
#define ZSTD_COMPILER_H

/*-*******************************************************
*  Compiler specifics
*********************************************************/
/* force inlining */
#if defined (__GNUC__) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
#  define INLINE_KEYWORD inline
#else
#  define INLINE_KEYWORD
#endif

#if defined(__GNUC__)
#  define FORCE_INLINE_ATTR __attribute__((always_inline))
#elif defined(_MSC_VER)
#  define FORCE_INLINE_ATTR __forceinline
#else
#  define FORCE_INLINE_ATTR
#endif

/**
 * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
 * parameters. They must be inlined for the compiler to elimininate the constant
 * branches.
 */
#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
/**
 * HINT_INLINE is used to help the compiler generate better code. It is *not*
 * used for "templates", so it can be tweaked based on the compilers
 * performance.
 *
 * gcc-4.8 and gcc-4.9 have been shown to benefit from leaving off the
 * always_inline attribute.
 *
 * clang up to 5.0.0 (trunk) benefit tremendously from the always_inline
 * attribute.
 */
#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5
#  define HINT_INLINE static INLINE_KEYWORD
#else
#  define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR
#endif

/* force no inlining */
#ifdef _MSC_VER
#  define FORCE_NOINLINE static __declspec(noinline)
#else
#  ifdef __GNUC__
#    define FORCE_NOINLINE static __attribute__((__noinline__))
#  else
#    define FORCE_NOINLINE static
#  endif
#endif

/* target attribute */
#ifndef __has_attribute
  #define __has_attribute(x) 0  /* Compatibility with non-clang compilers. */
#endif
#if defined(__GNUC__)
#  define TARGET_ATTRIBUTE(target) __attribute__((__target__(target)))
#else
#  define TARGET_ATTRIBUTE(target)
#endif

/* 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 */
#  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
#  pragma warning(disable : 4204)        /* disable: C4204: non-constant aggregate initializer */
#  pragma warning(disable : 4214)        /* disable: C4214: non-int bitfields */
#  pragma warning(disable : 4324)        /* disable: C4324: padded structure */
#endif

#endif /* ZSTD_COMPILER_H */