Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
139 changes: 75 additions & 64 deletions bitstream.h
Original file line number Diff line number Diff line change
Expand Up @@ -80,9 +80,9 @@ extern "C" {
* bitStream encoding API (write forward)
********************************************/
/* bitStream can mix input from multiple sources.
* A critical property of these streams is that they encode and decode in **reverse** direction.
* So the first bit sequence you add will be the last to be read, like a LIFO stack.
*/
* A critical property of these streams is that they encode and decode in **reverse** direction.
* So the first bit sequence you add will be the last to be read, like a LIFO stack.
*/
typedef struct
{
size_t bitContainer;
Expand Down Expand Up @@ -167,43 +167,49 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits);
/*-**************************************************************
* Internal functions
****************************************************************/
MEM_STATIC unsigned BIT_highbit32 (register U32 val)
MEM_STATIC unsigned BIT_highbit32 (U32 val)
{
assert(val != 0);
{
# if defined(_MSC_VER) /* Visual */
unsigned long r=0;
_BitScanReverse ( &r, val );
return (unsigned) r;
unsigned long r=0;
_BitScanReverse ( &r, val );
return (unsigned) r;
# elif defined(__GNUC__) && (__GNUC__ >= 3) /* Use GCC Intrinsic */
return 31 - __builtin_clz (val);
return 31 - __builtin_clz (val);
# else /* Software version */
static const unsigned 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;
v |= v >> 1;
v |= v >> 2;
v |= v >> 4;
v |= v >> 8;
v |= v >> 16;
return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27];
static const unsigned 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;
v |= v >> 1;
v |= v >> 2;
v |= v >> 4;
v |= v >> 8;
v |= v >> 16;
return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27];
# endif
}
}

/*===== Local Constants =====*/
static const unsigned BIT_mask[] = { 0, 1, 3, 7, 0xF, 0x1F, 0x3F, 0x7F,
0xFF, 0x1FF, 0x3FF, 0x7FF, 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF,
0xFFFF, 0x1FFFF, 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF,
0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF }; /* up to 26 bits */

static const unsigned BIT_mask[] = {
0, 1, 3, 7, 0xF, 0x1F,
0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF,
0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF,
0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF,
0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF,
0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */
#define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0]))

/*-**************************************************************
* bitStream encoding
****************************************************************/
/*! BIT_initCStream() :
* `dstCapacity` must be > sizeof(size_t)
* @return : 0 if success,
otherwise an error code (can be tested using ERR_isError() ) */
* otherwise an error code (can be tested using ERR_isError()) */
MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
void* startPtr, size_t dstCapacity)
{
Expand All @@ -217,11 +223,14 @@ MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC,
}

/*! BIT_addBits() :
can add up to 26 bits into `bitC`.
Does not check for register overflow ! */
* can add up to 31 bits into `bitC`.
* Note : does not check for register overflow ! */
MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC,
size_t value, unsigned nbBits)
{
MEM_STATIC_ASSERT(BIT_MASK_SIZE == 32);
assert(nbBits < BIT_MASK_SIZE);
assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos;
bitC->bitPos += nbBits;
}
Expand All @@ -232,6 +241,7 @@ MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
size_t value, unsigned nbBits)
{
assert((value>>nbBits) == 0);
assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8);
bitC->bitContainer |= value << bitC->bitPos;
bitC->bitPos += nbBits;
}
Expand All @@ -242,7 +252,7 @@ MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC,
MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC)
{
size_t const nbBytes = bitC->bitPos >> 3;
assert( bitC->bitPos <= (sizeof(bitC->bitContainer)*8) );
assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8);
MEM_writeLEST(bitC->ptr, bitC->bitContainer);
bitC->ptr += nbBytes;
assert(bitC->ptr <= bitC->endPtr);
Expand All @@ -258,7 +268,7 @@ MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC)
MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC)
{
size_t const nbBytes = bitC->bitPos >> 3;
assert( bitC->bitPos <= (sizeof(bitC->bitContainer)*8) );
assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8);
MEM_writeLEST(bitC->ptr, bitC->bitContainer);
bitC->ptr += nbBytes;
if (bitC->ptr > bitC->endPtr) bitC->ptr = bitC->endPtr;
Expand All @@ -268,7 +278,7 @@ MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC)

/*! BIT_closeCStream() :
* @return : size of CStream, in bytes,
or 0 if it could not fit into dstBuffer */
* or 0 if it could not fit into dstBuffer */
MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)
{
BIT_addBitsFast(bitC, 1, 1); /* endMark */
Expand All @@ -279,14 +289,14 @@ MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC)


/*-********************************************************
* bitStream decoding
* bitStream decoding
**********************************************************/
/*! BIT_initDStream() :
* Initialize a BIT_DStream_t.
* `bitD` : a pointer to an already allocated BIT_DStream_t structure.
* `srcSize` must be the *exact* size of the bitStream, in bytes.
* @return : size of stream (== srcSize) or an errorCode if a problem is detected
*/
* Initialize a BIT_DStream_t.
* `bitD` : a pointer to an already allocated BIT_DStream_t structure.
* `srcSize` must be the *exact* size of the bitStream, in bytes.
* @return : size of stream (== srcSize), or an errorCode if a problem is detected
*/
MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize)
{
if (srcSize < 1) { memset(bitD, 0, sizeof(*bitD)); return ERROR(srcSize_wrong); }
Expand All @@ -305,29 +315,30 @@ MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, si
bitD->bitContainer = *(const BYTE*)(bitD->start);
switch(srcSize)
{
case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
/* fall-through */
case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16);
/* fall-through */

case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
/* fall-through */
case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24);
/* fall-through */

case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
/* fall-through */
case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32);
/* fall-through */

case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
/* fall-through */
case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24;
/* fall-through */

case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
/* fall-through */
case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16;
/* fall-through */

case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
/* fall-through */
case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8;
/* fall-through */

default: break;
default: break;
}
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
if (lastByte == 0) return ERROR(corruption_detected); /* endMark not present */
}
{ BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1];
bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0;
if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ }
bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize)*8;
}

Expand All @@ -349,12 +360,14 @@ MEM_STATIC size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 co
# endif
return _bextr_u32(bitContainer, start, nbBits);
#else
assert(nbBits < BIT_MASK_SIZE);
return (bitContainer >> start) & BIT_mask[nbBits];
#endif
}

MEM_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
{
assert(nbBits < BIT_MASK_SIZE);
return bitContainer & BIT_mask[nbBits];
}

Expand All @@ -363,9 +376,8 @@ MEM_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
* local register is not modified.
* On 32-bits, maxNbBits==24.
* On 64-bits, maxNbBits==56.
* @return : value extracted
*/
MEM_STATIC size_t BIT_lookBits(const BIT_DStream_t* bitD, U32 nbBits)
* @return : value extracted */
MEM_STATIC size_t BIT_lookBits(const BIT_DStream_t* bitD, U32 nbBits)
{
#if defined(__BMI__) && defined(__GNUC__) /* experimental; fails if bitD->bitsConsumed + nbBits > sizeof(bitD->bitContainer)*8 */
return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits);
Expand All @@ -392,8 +404,7 @@ MEM_STATIC void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits)
/*! BIT_readBits() :
* Read (consume) next n bits from local register and update.
* Pay attention to not read more than nbBits contained into local register.
* @return : extracted value.
*/
* @return : extracted value. */
MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, U32 nbBits)
{
size_t const value = BIT_lookBits(bitD, nbBits);
Expand All @@ -402,7 +413,7 @@ MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, U32 nbBits)
}

/*! BIT_readBitsFast() :
* unsafe version; only works only if nbBits >= 1 */
* unsafe version; only works only if nbBits >= 1 */
MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits)
{
size_t const value = BIT_lookBitsFast(bitD, nbBits);
Expand All @@ -412,10 +423,10 @@ MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, U32 nbBits)
}

/*! BIT_reloadDStream() :
* Refill `bitD` from buffer previously set in BIT_initDStream() .
* This function is safe, it guarantees it will not read beyond src buffer.
* @return : status of `BIT_DStream_t` internal register.
if status == BIT_DStream_unfinished, internal register is filled with >= (sizeof(bitD->bitContainer)*8 - 7) bits */
* Refill `bitD` from buffer previously set in BIT_initDStream() .
* This function is safe, it guarantees it will not read beyond src buffer.
* @return : status of `BIT_DStream_t` internal register.
* when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */
MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
{
if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* overflow detected, like end of stream */
Expand Down Expand Up @@ -446,8 +457,8 @@ MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD)
}

/*! BIT_endOfDStream() :
* @return Tells if DStream has exactly reached its end (all bits consumed).
*/
* @return : 1 if DStream has _exactly_ reached its end (all bits consumed).
*/
MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream)
{
return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8));
Expand Down
86 changes: 86 additions & 0 deletions compiler.h
Original file line number Diff line number Diff line change
@@ -0,0 +1,86 @@
/*
* 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

/* 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 */
# 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 */
Loading