mirror of
https://github.com/Xevion/easy7zip.git
synced 2025-12-07 16:07:05 -06:00
58069903d0
- updated zstd to latest devel release - lz4, lz5 and zstd is included now - all three support threading
453 lines
14 KiB
C
453 lines
14 KiB
C
/* ******************************************************************
|
|
mem.h
|
|
low-level memory access routines
|
|
Copyright (C) 2013-2015, Yann Collet.
|
|
|
|
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
|
|
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions are
|
|
met:
|
|
|
|
* Redistributions of source code must retain the above copyright
|
|
notice, this list of conditions and the following disclaimer.
|
|
* Redistributions in binary form must reproduce the above
|
|
copyright notice, this list of conditions and the following disclaimer
|
|
in the documentation and/or other materials provided with the
|
|
distribution.
|
|
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
|
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
|
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
|
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
|
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
|
|
You can contact the author at :
|
|
- FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy
|
|
- Public forum : https://groups.google.com/forum/#!forum/lz4c
|
|
****************************************************************** */
|
|
#ifndef MEM_H_MODULE
|
|
#define MEM_H_MODULE
|
|
|
|
#if defined (__cplusplus)
|
|
extern "C" {
|
|
#endif
|
|
|
|
/******************************************
|
|
* Includes
|
|
******************************************/
|
|
#include <stddef.h> /* size_t, ptrdiff_t */
|
|
#include <string.h> /* memcpy */
|
|
|
|
|
|
|
|
/******************************************
|
|
* Compiler-specific
|
|
******************************************/
|
|
#if defined (__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
|
|
# define MEM_STATIC static inline
|
|
#elif defined(_MSC_VER)
|
|
# define MEM_STATIC static __inline
|
|
#elif defined(__GNUC__)
|
|
# define MEM_STATIC static __attribute__((unused))
|
|
#else
|
|
# define MEM_STATIC static /* this version may generate warnings for unused static functions; disable the relevant warning */
|
|
#endif
|
|
|
|
|
|
|
|
/****************************************************************
|
|
* Memory I/O
|
|
*****************************************************************/
|
|
/* MEM_FORCE_MEMORY_ACCESS
|
|
* By default, access to unaligned memory is controlled by `memcpy()`, which is safe and portable.
|
|
* Unfortunately, on some target/compiler combinations, the generated assembly is sub-optimal.
|
|
* The below switch allow to select different access method for improved performance.
|
|
* Method 0 (default) : use `memcpy()`. Safe and portable.
|
|
* Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable).
|
|
* This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.
|
|
* Method 2 : direct access. This method is portable but violate C standard.
|
|
* It can generate buggy code on targets generating assembly depending on alignment.
|
|
* But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
|
|
* See http://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.
|
|
* Prefer these methods in priority order (0 > 1 > 2)
|
|
*/
|
|
#ifndef MEM_FORCE_MEMORY_ACCESS /* can be defined externally, on command line for example */
|
|
# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
|
|
# define MEM_FORCE_MEMORY_ACCESS 2
|
|
# elif defined(__INTEL_COMPILER) || \
|
|
(defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) ))
|
|
# define MEM_FORCE_MEMORY_ACCESS 1
|
|
# endif
|
|
#endif
|
|
|
|
MEM_STATIC unsigned MEM_32bits(void) { return sizeof(void*)==4; }
|
|
MEM_STATIC unsigned MEM_64bits(void) { return sizeof(void*)==8; }
|
|
|
|
MEM_STATIC unsigned MEM_isLittleEndian(void)
|
|
{
|
|
const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */
|
|
return one.c[0];
|
|
}
|
|
|
|
#if defined(MEM_FORCE_MEMORY_ACCESS) && (MEM_FORCE_MEMORY_ACCESS==2)
|
|
|
|
/* violates C standard on structure alignment.
|
|
Only use if no other choice to achieve best performance on target platform */
|
|
MEM_STATIC U16 MEM_read16(const void* memPtr) { return *(const U16*) memPtr; }
|
|
MEM_STATIC U32 MEM_read32(const void* memPtr) { return *(const U32*) memPtr; }
|
|
MEM_STATIC U64 MEM_read64(const void* memPtr) { return *(const U64*) memPtr; }
|
|
|
|
MEM_STATIC void MEM_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; }
|
|
MEM_STATIC void MEM_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
|
|
MEM_STATIC void MEM_write64(void* memPtr, U64 value) { *(U64*)memPtr = value; }
|
|
|
|
#elif defined(MEM_FORCE_MEMORY_ACCESS) && (MEM_FORCE_MEMORY_ACCESS==1)
|
|
|
|
/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
|
|
/* currently only defined for gcc and icc */
|
|
typedef union { U16 u16; U32 u32; U64 u64; } __attribute__((packed)) unalign;
|
|
|
|
MEM_STATIC U16 MEM_read16(const void* ptr) { return ((const unalign*)ptr)->u16; }
|
|
MEM_STATIC U32 MEM_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
|
|
MEM_STATIC U64 MEM_read64(const void* ptr) { return ((const unalign*)ptr)->u64; }
|
|
|
|
MEM_STATIC void MEM_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; }
|
|
MEM_STATIC void MEM_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; }
|
|
MEM_STATIC void MEM_write64(void* memPtr, U64 value) { ((unalign*)memPtr)->u64 = value; }
|
|
|
|
#else
|
|
|
|
/* default method, safe and standard.
|
|
can sometimes prove slower */
|
|
|
|
MEM_STATIC U16 MEM_read16(const void* memPtr)
|
|
{
|
|
U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
|
|
}
|
|
|
|
MEM_STATIC U32 MEM_read32(const void* memPtr)
|
|
{
|
|
U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
|
|
}
|
|
|
|
MEM_STATIC U64 MEM_read64(const void* memPtr)
|
|
{
|
|
U64 val; memcpy(&val, memPtr, sizeof(val)); return val;
|
|
}
|
|
|
|
MEM_STATIC void MEM_write16(void* memPtr, U16 value)
|
|
{
|
|
memcpy(memPtr, &value, sizeof(value));
|
|
}
|
|
|
|
MEM_STATIC void MEM_write32(void* memPtr, U32 value)
|
|
{
|
|
memcpy(memPtr, &value, sizeof(value));
|
|
}
|
|
|
|
MEM_STATIC void MEM_write64(void* memPtr, U64 value)
|
|
{
|
|
memcpy(memPtr, &value, sizeof(value));
|
|
}
|
|
|
|
#endif // MEM_FORCE_MEMORY_ACCESS
|
|
|
|
|
|
MEM_STATIC U16 MEM_readLE16(const void* memPtr)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
return MEM_read16(memPtr);
|
|
else
|
|
{
|
|
const BYTE* p = (const BYTE*)memPtr;
|
|
return (U16)(p[0] + (p[1]<<8));
|
|
}
|
|
}
|
|
|
|
MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
{
|
|
MEM_write16(memPtr, val);
|
|
}
|
|
else
|
|
{
|
|
BYTE* p = (BYTE*)memPtr;
|
|
p[0] = (BYTE)val;
|
|
p[1] = (BYTE)(val>>8);
|
|
}
|
|
}
|
|
|
|
MEM_STATIC U32 MEM_readLE24(const void* memPtr)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
{
|
|
U32 val32 = 0;
|
|
memcpy(&val32, memPtr, 3);
|
|
return val32;
|
|
}
|
|
else
|
|
{
|
|
const BYTE* p = (const BYTE*)memPtr;
|
|
return (U32)(p[0] + (p[1]<<8) + (p[2]<<16));
|
|
}
|
|
}
|
|
|
|
MEM_STATIC void MEM_writeLE24(void* memPtr, U32 value)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
{
|
|
memcpy(memPtr, &value, 3);
|
|
}
|
|
else
|
|
{
|
|
BYTE* p = (BYTE*)memPtr;
|
|
p[0] = (BYTE) value;
|
|
p[1] = (BYTE)(value>>8);
|
|
p[2] = (BYTE)(value>>16);
|
|
}
|
|
}
|
|
|
|
|
|
MEM_STATIC U32 MEM_readLE32(const void* memPtr)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
return MEM_read32(memPtr);
|
|
else
|
|
{
|
|
const BYTE* p = (const BYTE*)memPtr;
|
|
return (U32)((U32)p[0] + ((U32)p[1]<<8) + ((U32)p[2]<<16) + ((U32)p[3]<<24));
|
|
}
|
|
}
|
|
|
|
MEM_STATIC void MEM_writeLE32(void* memPtr, U32 val32)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
{
|
|
MEM_write32(memPtr, val32);
|
|
}
|
|
else
|
|
{
|
|
BYTE* p = (BYTE*)memPtr;
|
|
p[0] = (BYTE)val32;
|
|
p[1] = (BYTE)(val32>>8);
|
|
p[2] = (BYTE)(val32>>16);
|
|
p[3] = (BYTE)(val32>>24);
|
|
}
|
|
}
|
|
|
|
MEM_STATIC U64 MEM_readLE64(const void* memPtr)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
return MEM_read64(memPtr);
|
|
else
|
|
{
|
|
const BYTE* p = (const BYTE*)memPtr;
|
|
return (U64)((U64)p[0] + ((U64)p[1]<<8) + ((U64)p[2]<<16) + ((U64)p[3]<<24)
|
|
+ ((U64)p[4]<<32) + ((U64)p[5]<<40) + ((U64)p[6]<<48) + ((U64)p[7]<<56));
|
|
}
|
|
}
|
|
|
|
MEM_STATIC void MEM_writeLE64(void* memPtr, U64 val64)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
{
|
|
MEM_write64(memPtr, val64);
|
|
}
|
|
else
|
|
{
|
|
BYTE* p = (BYTE*)memPtr;
|
|
p[0] = (BYTE)val64;
|
|
p[1] = (BYTE)(val64>>8);
|
|
p[2] = (BYTE)(val64>>16);
|
|
p[3] = (BYTE)(val64>>24);
|
|
p[4] = (BYTE)(val64>>32);
|
|
p[5] = (BYTE)(val64>>40);
|
|
p[6] = (BYTE)(val64>>48);
|
|
p[7] = (BYTE)(val64>>56);
|
|
}
|
|
}
|
|
|
|
MEM_STATIC size_t MEM_readLEST(const void* memPtr)
|
|
{
|
|
if (MEM_32bits())
|
|
return (size_t)MEM_readLE32(memPtr);
|
|
else
|
|
return (size_t)MEM_readLE64(memPtr);
|
|
}
|
|
|
|
MEM_STATIC void MEM_writeLEST(void* memPtr, size_t val)
|
|
{
|
|
if (MEM_32bits())
|
|
MEM_writeLE32(memPtr, (U32)val);
|
|
else
|
|
MEM_writeLE64(memPtr, (U64)val);
|
|
}
|
|
|
|
|
|
#if MINMATCH == 3
|
|
#define MEM_read24(ptr) (U32)(MEM_read32(ptr)<<8)
|
|
#else
|
|
#define MEM_read24(ptr) (U32)(MEM_read32(ptr))
|
|
#endif
|
|
|
|
|
|
/* **************************************
|
|
* Function body to include for inlining
|
|
****************************************/
|
|
static size_t MEM_read_ARCH(const void* p) { size_t r; memcpy(&r, p, sizeof(r)); return r; }
|
|
|
|
#define MIN(a,b) ((a)<(b) ? (a) : (b))
|
|
|
|
|
|
/*static unsigned MEM_highbit(U32 val)
|
|
{
|
|
# if defined(_MSC_VER) // Visual
|
|
unsigned long r=0;
|
|
_BitScanReverse(&r, val);
|
|
return (unsigned)r;
|
|
# elif defined(__GNUC__) && (__GNUC__ >= 3) // GCC Intrinsic
|
|
return 31 - __builtin_clz(val);
|
|
# else // Software version
|
|
static const int DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 };
|
|
U32 v = val;
|
|
int r;
|
|
v |= v >> 1;
|
|
v |= v >> 2;
|
|
v |= v >> 4;
|
|
v |= v >> 8;
|
|
v |= v >> 16;
|
|
r = DeBruijnClz[(U32)(v * 0x07C4ACDDU) >> 27];
|
|
return r;
|
|
# endif
|
|
}*/
|
|
|
|
|
|
MEM_STATIC unsigned MEM_NbCommonBytes (register size_t val)
|
|
{
|
|
if (MEM_isLittleEndian())
|
|
{
|
|
if (MEM_64bits())
|
|
{
|
|
# if defined(_MSC_VER) && defined(_WIN64)
|
|
unsigned long r = 0;
|
|
_BitScanForward64( &r, (U64)val );
|
|
return (int)(r>>3);
|
|
# elif defined(__GNUC__) && (__GNUC__ >= 3)
|
|
return (__builtin_ctzll((U64)val) >> 3);
|
|
# else
|
|
static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 };
|
|
return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58];
|
|
# endif
|
|
}
|
|
else /* 32 bits */
|
|
{
|
|
# if defined(_MSC_VER)
|
|
unsigned long r=0;
|
|
_BitScanForward( &r, (U32)val );
|
|
return (int)(r>>3);
|
|
# elif defined(__GNUC__) && (__GNUC__ >= 3)
|
|
return (__builtin_ctz((U32)val) >> 3);
|
|
# else
|
|
static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 };
|
|
return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27];
|
|
# endif
|
|
}
|
|
}
|
|
else /* Big Endian CPU */
|
|
{
|
|
if (MEM_32bits())
|
|
{
|
|
# if defined(_MSC_VER) && defined(_WIN64)
|
|
unsigned long r = 0;
|
|
_BitScanReverse64( &r, val );
|
|
return (unsigned)(r>>3);
|
|
# elif defined(__GNUC__) && (__GNUC__ >= 3)
|
|
return (__builtin_clzll(val) >> 3);
|
|
# else
|
|
unsigned r;
|
|
const unsigned n32 = sizeof(size_t)*4; /* calculate this way due to compiler complaining in 32-bits mode */
|
|
if (!(val>>n32)) { r=4; } else { r=0; val>>=n32; }
|
|
if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
|
|
r += (!val);
|
|
return r;
|
|
# endif
|
|
}
|
|
else /* 32 bits */
|
|
{
|
|
# if defined(_MSC_VER)
|
|
unsigned long r = 0;
|
|
_BitScanReverse( &r, (unsigned long)val );
|
|
return (unsigned)(r>>3);
|
|
# elif defined(__GNUC__) && (__GNUC__ >= 3)
|
|
return (__builtin_clz((U32)val) >> 3);
|
|
# else
|
|
unsigned r;
|
|
if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
|
|
r += (!val);
|
|
return r;
|
|
# endif
|
|
}
|
|
}
|
|
}
|
|
|
|
|
|
MEM_STATIC size_t MEM_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
|
|
{
|
|
const BYTE* const pStart = pIn;
|
|
|
|
while ((pIn<pInLimit-(sizeof(size_t)-1)))
|
|
{
|
|
size_t diff = MEM_read_ARCH(pMatch) ^ MEM_read_ARCH(pIn);
|
|
if (!diff) { pIn+=sizeof(size_t); pMatch+=sizeof(size_t); continue; }
|
|
pIn += MEM_NbCommonBytes(diff);
|
|
return (size_t)(pIn - pStart);
|
|
}
|
|
|
|
if (MEM_64bits()) if ((pIn<(pInLimit-3)) && (MEM_read32(pMatch) == MEM_read32(pIn))) { pIn+=4; pMatch+=4; }
|
|
if ((pIn<(pInLimit-1)) && (MEM_read16(pMatch) == MEM_read16(pIn))) { pIn+=2; pMatch+=2; }
|
|
if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
|
|
return (size_t)(pIn - pStart);
|
|
}
|
|
|
|
|
|
static void MEM_copy8(void* dst, const void* src) { memcpy(dst, src, 8); }
|
|
|
|
#define COPY8(d,s) { MEM_copy8(d,s); d+=8; s+=8; }
|
|
|
|
|
|
/*! MEM_wildcopy : custom version of memcpy(), can copy up to 7-8 bytes too many */
|
|
/*static void MEM_wildcopy(void* dst, const void* src, size_t length)
|
|
{
|
|
const BYTE* ip = (const BYTE*)src;
|
|
BYTE* op = (BYTE*)dst;
|
|
BYTE* const oend = op + length;
|
|
do
|
|
COPY8(op, ip)
|
|
while (op < oend);
|
|
} */
|
|
|
|
/* customized variant of memcpy, which can overwrite up to 7 bytes beyond dstEnd */
|
|
static void MEM_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
|
|
{
|
|
BYTE* d = (BYTE*)dstPtr;
|
|
const BYTE* s = (const BYTE*)srcPtr;
|
|
BYTE* const e = (BYTE*)dstEnd;
|
|
|
|
do { MEM_copy8(d,s); d+=8; s+=8; } while (d<e);
|
|
}
|
|
|
|
#if defined (__cplusplus)
|
|
}
|
|
#endif
|
|
|
|
#endif /* MEM_H_MODULE */
|
|
|