Bug 1398021 - Update lz4 to version 1.8.0. r=froydnj, a=RyanVM

--HG--
extra : source : 9a4077eda5d80e2f7c7fe271035bee2e2d034cec
extra : histedit_source : 64eb1f6e9b2b08981644d7edccd22997d6463b4b%2C5619daf512a89b3a6bf84eca781190b56e8dea31

1 files changed, 956 insertions, 637 deletions

diff --git a/mfbt/lz4.c b/mfbt/lz4.c
index c416fe815a..5752b4d17b 100644
--- a/mfbt/lz4.c
+++ b/mfbt/lz4.c
@@ -1,6 +1,7 @@
 /*
    LZ4 - Fast LZ compression algorithm
-   Copyright (C) 2011-2014, Yann Collet.
+   Copyright (C) 2011-2017, 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
@@ -27,118 +28,96 @@
    OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
    You can contact the author at :
-   - LZ4 source repository : http://code.google.com/p/lz4/
-   - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c
+    - LZ4 homepage : http://www.lz4.org
+    - LZ4 source repository : https://github.com/lz4/lz4
 */
 
-/**************************************
-   Tuning parameters
+
+/*-************************************
+*  Tuning parameters
 **************************************/
 /*
- * HEAPMODE :
+ * LZ4_HEAPMODE :
  * Select how default compression functions will allocate memory for their hash table,
- * in memory stack (0:default, fastest), or in memory heap (1:requires memory allocation (malloc)).
+ * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()).
  */
-#define HEAPMODE 0
-
-
-/**************************************
-   CPU Feature Detection
-**************************************/
-/* 32 or 64 bits ? */
-#if (defined(__x86_64__) || defined(_M_X64) || defined(_WIN64) \
-  || defined(__powerpc64__) || defined(__powerpc64le__) \
-  || defined(__ppc64__) || defined(__ppc64le__) \
-  || defined(__PPC64__) || defined(__PPC64LE__) \
-  || defined(__ia64) || defined(__itanium__) || defined(_M_IA64) \
-  || (defined(__mips64) && defined(_ABI64)))   /* Detects 64 bits mode */
-#  define LZ4_ARCH64 1
-#else
-#  define LZ4_ARCH64 0
+#ifndef LZ4_HEAPMODE
+#  define LZ4_HEAPMODE 0
 #endif
 
 /*
- * Little Endian or Big Endian ?
- * Overwrite the #define below if you know your architecture endianess
+ * ACCELERATION_DEFAULT :
+ * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
  */
-#include <stdlib.h>   /* Apparently required to detect endianess */
-#if defined (__GLIBC__)
-#  include <endian.h>
-#  if (__BYTE_ORDER == __BIG_ENDIAN)
-#     define LZ4_BIG_ENDIAN 1
+#define ACCELERATION_DEFAULT 1
+
+
+/*-************************************
+*  CPU Feature Detection
+**************************************/
+/* LZ4_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 which assembly generation depends on alignment.
+ *            But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
+ * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.
+ * Prefer these methods in priority order (0 > 1 > 2)
+ */
+#ifndef LZ4_FORCE_MEMORY_ACCESS   /* can be defined externally */
+#  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 LZ4_FORCE_MEMORY_ACCESS 2
+#  elif defined(__INTEL_COMPILER) || defined(__GNUC__)
+#    define LZ4_FORCE_MEMORY_ACCESS 1
 #  endif
-#elif (defined(__BIG_ENDIAN__) || defined(__BIG_ENDIAN) || defined(_BIG_ENDIAN)) && !(defined(__LITTLE_ENDIAN__) || defined(__LITTLE_ENDIAN) || defined(_LITTLE_ENDIAN))
-#  define LZ4_BIG_ENDIAN 1
-#elif defined(__sparc) || defined(__sparc__) \
-   || defined(__powerpc__) || defined(__ppc__) || defined(__PPC__) \
-   || defined(__hpux)  || defined(__hppa) \
-   || defined(_MIPSEB) || defined(__s390__)
-#  define LZ4_BIG_ENDIAN 1
-#else
-/* Little Endian assumed. PDP Endian and other very rare endian format are unsupported. */
 #endif
 
 /*
- * Unaligned memory access is automatically enabled for "common" CPU, such as x86.
- * For others CPU, such as ARM, the compiler may be more cautious, inserting unnecessary extra code to ensure aligned access property
- * If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance
+ * LZ4_FORCE_SW_BITCOUNT
+ * Define this parameter if your target system or compiler does not support hardware bit count
  */
-#if defined(__ARM_FEATURE_UNALIGNED)
-#  define LZ4_FORCE_UNALIGNED_ACCESS 1
-#endif
-
-/* Define this parameter if your target system or compiler does not support hardware bit count */
 #if defined(_MSC_VER) && defined(_WIN32_WCE)   /* Visual Studio for Windows CE does not support Hardware bit count */
 #  define LZ4_FORCE_SW_BITCOUNT
 #endif
 
-/*
- * BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE :
- * This option may provide a small boost to performance for some big endian cpu, although probably modest.
- * You may set this option to 1 if data will remain within closed environment.
- * This option is useless on Little_Endian CPU (such as x86)
- */
 
-/* #define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1 */
+/*-************************************
+*  Dependency
+**************************************/
+#include "lz4.h"
+/* see also "memory routines" below */
 
 
-/**************************************
- Compiler Options
+/*-************************************
+*  Compiler Options
 **************************************/
-#if defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
-/* "restrict" is a known keyword */
-#else
-#  define restrict /* Disable restrict */
-#endif
-
 #ifdef _MSC_VER    /* Visual Studio */
-#  define FORCE_INLINE static __forceinline
-#  include <intrin.h>                    /* For Visual 2005 */
-#  if LZ4_ARCH64   /* 64-bits */
-#    pragma intrinsic(_BitScanForward64) /* For Visual 2005 */
-#    pragma intrinsic(_BitScanReverse64) /* For Visual 2005 */
-#  else            /* 32-bits */
-#    pragma intrinsic(_BitScanForward)   /* For Visual 2005 */
-#    pragma intrinsic(_BitScanReverse)   /* For Visual 2005 */
-#  endif
+#  include <intrin.h>
 #  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
-#else
-#  ifdef __GNUC__
-#    define FORCE_INLINE static inline __attribute__((always_inline))
-#  else
-#    define FORCE_INLINE static inline
-#  endif
-#endif
-
-#ifdef _MSC_VER  /* Visual Studio */
-#  define lz4_bswap16(x) _byteswap_ushort(x)
-#else
-#  define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)))
-#endif
-
-#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
+#  pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */
+#endif  /* _MSC_VER */
 
-#if (GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__)
+#ifndef FORCE_INLINE
+#  ifdef _MSC_VER    /* Visual Studio */
+#    define FORCE_INLINE static __forceinline
+#  else
+#    if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
+#      ifdef __GNUC__
+#        define FORCE_INLINE static inline __attribute__((always_inline))
+#      else
+#        define FORCE_INLINE static inline
+#      endif
+#    else
+#      define FORCE_INLINE static
+#    endif /* __STDC_VERSION__ */
+#  endif  /* _MSC_VER */
+#endif /* FORCE_INLINE */
+
+#if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__)
 #  define expect(expr,value)    (__builtin_expect ((expr),(value)) )
 #else
 #  define expect(expr,value)    (expr)
@@ -148,8 +127,8 @@
 #define unlikely(expr)   expect((expr) != 0, 0)
 
 
-/**************************************
-   Memory routines
+/*-************************************
+*  Memory routines
 **************************************/
 #include <stdlib.h>   /* malloc, calloc, free */
 #define ALLOCATOR(n,s) calloc(n,s)
@@ -158,84 +137,146 @@
 #define MEM_INIT       memset
 
 
-/**************************************
-   Includes
+/*-************************************
+*  Basic Types
 **************************************/
-#include "lz4.h"
-
-
-/**************************************
-   Basic Types
-**************************************/
-#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)   /* C99 */
+#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
 # include <stdint.h>
   typedef  uint8_t BYTE;
   typedef uint16_t U16;
   typedef uint32_t U32;
   typedef  int32_t S32;
   typedef uint64_t U64;
+  typedef uintptr_t uptrval;
 #else
   typedef unsigned char       BYTE;
   typedef unsigned short      U16;
   typedef unsigned int        U32;
   typedef   signed int        S32;
   typedef unsigned long long  U64;
+  typedef size_t              uptrval;   /* generally true, except OpenVMS-64 */
 #endif
 
-#if defined(__GNUC__)  && !defined(LZ4_FORCE_UNALIGNED_ACCESS)
-#  define _PACKED __attribute__ ((packed))
+#if defined(__x86_64__)
+  typedef U64    reg_t;   /* 64-bits in x32 mode */
 #else
-#  define _PACKED
+  typedef size_t reg_t;   /* 32-bits in x32 mode */
 #endif
 
-#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-#  if defined(__IBMC__) || defined(__SUNPRO_C) || defined(__SUNPRO_CC)
-#    pragma pack(1)
-#  else
-#    pragma pack(push, 1)
-#  endif
-#endif
+/*-************************************
+*  Reading and writing into memory
+**************************************/
+static unsigned LZ4_isLittleEndian(void)
+{
+    const union { U32 u; BYTE c[4]; } one = { 1 };   /* don't use static : performance detrimental */
+    return one.c[0];
+}
 
-typedef struct { U16 v; }  _PACKED U16_S;
-typedef struct { U32 v; }  _PACKED U32_S;
-typedef struct { U64 v; }  _PACKED U64_S;
-typedef struct {size_t v;} _PACKED size_t_S;
 
-#if !defined(LZ4_FORCE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-#  if defined(__SUNPRO_C) || defined(__SUNPRO_CC)
-#    pragma pack(0)
-#  else
-#    pragma pack(pop)
-#  endif
-#endif
+#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2)
+/* lie to the compiler about data alignment; use with caution */
 
-#define A16(x)   (((U16_S *)(x))->v)
-#define A32(x)   (((U32_S *)(x))->v)
-#define A64(x)   (((U64_S *)(x))->v)
-#define AARCH(x) (((size_t_S *)(x))->v)
+static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; }
+static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; }
+static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; }
 
+static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; }
+static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
 
-/**************************************
-   Constants
-**************************************/
-#define LZ4_HASHLOG   (LZ4_MEMORY_USAGE-2)
-#define HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
-#define HASH_SIZE_U32 (1 << LZ4_HASHLOG)
+#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_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; reg_t uArch; } __attribute__((packed)) unalign;
+
+static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; }
+static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
+static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; }
+
+static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; }
+static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; }
+
+#else  /* safe and portable access through memcpy() */
 
+static U16 LZ4_read16(const void* memPtr)
+{
+    U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static U32 LZ4_read32(const void* memPtr)
+{
+    U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static reg_t LZ4_read_ARCH(const void* memPtr)
+{
+    reg_t val; memcpy(&val, memPtr, sizeof(val)); return val;
+}
+
+static void LZ4_write16(void* memPtr, U16 value)
+{
+    memcpy(memPtr, &value, sizeof(value));
+}
+
+static void LZ4_write32(void* memPtr, U32 value)
+{
+    memcpy(memPtr, &value, sizeof(value));
+}
+
+#endif /* LZ4_FORCE_MEMORY_ACCESS */
+
+
+static U16 LZ4_readLE16(const void* memPtr)
+{
+    if (LZ4_isLittleEndian()) {
+        return LZ4_read16(memPtr);
+    } else {
+        const BYTE* p = (const BYTE*)memPtr;
+        return (U16)((U16)p[0] + (p[1]<<8));
+    }
+}
+
+static void LZ4_writeLE16(void* memPtr, U16 value)
+{
+    if (LZ4_isLittleEndian()) {
+        LZ4_write16(memPtr, value);
+    } else {
+        BYTE* p = (BYTE*)memPtr;
+        p[0] = (BYTE) value;
+        p[1] = (BYTE)(value>>8);
+    }
+}
+
+static void LZ4_copy8(void* dst, const void* src)
+{
+    memcpy(dst,src,8);
+}
+
+/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */
+static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
+{
+    BYTE* d = (BYTE*)dstPtr;
+    const BYTE* s = (const BYTE*)srcPtr;
+    BYTE* const e = (BYTE*)dstEnd;
+
+    do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e);
+}
+
+
+/*-************************************
+*  Common Constants
+**************************************/
 #define MINMATCH 4
 
-#define COPYLENGTH 8
+#define WILDCOPYLENGTH 8
 #define LASTLITERALS 5
-#define MFLIMIT (COPYLENGTH+MINMATCH)
+#define MFLIMIT (WILDCOPYLENGTH+MINMATCH)
 static const int LZ4_minLength = (MFLIMIT+1);
 
-#define KB *(1U<<10)
-#define MB *(1U<<20)
+#define KB *(1 <<10)
+#define MB *(1 <<20)
 #define GB *(1U<<30)
 
-#define LZ4_64KLIMIT ((64 KB) + (MFLIMIT-1))
-#define SKIPSTRENGTH 6   /* Increasing this value will make the compression run slower on incompressible data */
-
 #define MAXD_LOG 16
 #define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
 
@@ -245,208 +286,213 @@ static const int LZ4_minLength = (MFLIMIT+1);
 #define RUN_MASK ((1U<<RUN_BITS)-1)
 
 
-/**************************************
-   Structures and local types
+/*-************************************
+*  Error detection
 **************************************/
-typedef struct {
-    U32  hashTable[HASH_SIZE_U32];
-    U32  currentOffset;
-    U32  initCheck;
-    const BYTE* dictionary;
-    const BYTE* bufferStart;
-    U32  dictSize;
-} LZ4_stream_t_internal;
+#define LZ4_STATIC_ASSERT(c)    { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
+
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
+#  include <stdio.h>
+#  define DEBUGLOG(l, ...) {                          \
+                if (l<=LZ4_DEBUG) {                   \
+                    fprintf(stderr, __FILE__ ": ");   \
+                    fprintf(stderr, __VA_ARGS__);     \
+                    fprintf(stderr, " \n");           \
+            }   }
+#else
+#  define DEBUGLOG(l, ...)      {}    /* disabled */
+#endif
 
-typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
-typedef enum { byPtr, byU32, byU16 } tableType_t;
 
-typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
-typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
+/*-************************************
+*  Common functions
+**************************************/
+static unsigned LZ4_NbCommonBytes (register reg_t val)
+{
+    if (LZ4_isLittleEndian()) {
+        if (sizeof(val)==8) {
+#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanForward64( &r, (U64)val );
+            return (int)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            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) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r;
+            _BitScanForward( &r, (U32)val );
+            return (int)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            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 (sizeof(val)==8) {
+#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanReverse64( &r, val );
+            return (unsigned)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (__builtin_clzll((U64)val) >> 3);
+#       else
+            unsigned r;
+            if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
+            if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
+            r += (!val);
+            return r;
+#       endif
+        } else /* 32 bits */ {
+#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            unsigned long r = 0;
+            _BitScanReverse( &r, (unsigned long)val );
+            return (unsigned)(r>>3);
+#       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            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
+        }
+    }
+}
 
-typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
-typedef enum { full = 0, partial = 1 } earlyEnd_directive;
+#define STEPSIZE sizeof(reg_t)
+static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
+{
+    const BYTE* const pStart = pIn;
 
+    while (likely(pIn<pInLimit-(STEPSIZE-1))) {
+        reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn);
+        if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; }
+        pIn += LZ4_NbCommonBytes(diff);
+        return (unsigned)(pIn - pStart);
+    }
 
-/**************************************
-   Architecture-specific macros
-**************************************/
-#define STEPSIZE                  sizeof(size_t)
-#define LZ4_COPYSTEP(d,s)         { AARCH(d) = AARCH(s); d+=STEPSIZE; s+=STEPSIZE; }
-#define LZ4_COPY8(d,s)            { LZ4_COPYSTEP(d,s); if (STEPSIZE<8) LZ4_COPYSTEP(d,s); }
-
-#if (defined(LZ4_BIG_ENDIAN) && !defined(BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE))
-#  define LZ4_READ_LITTLEENDIAN_16(d,s,p) { U16 v = A16(p); v = lz4_bswap16(v); d = (s) - v; }
-#  define LZ4_WRITE_LITTLEENDIAN_16(p,i)  { U16 v = (U16)(i); v = lz4_bswap16(v); A16(p) = v; p+=2; }
-#else      /* Little Endian */
-#  define LZ4_READ_LITTLEENDIAN_16(d,s,p) { d = (s) - A16(p); }
-#  define LZ4_WRITE_LITTLEENDIAN_16(p,v)  { A16(p) = v; p+=2; }
-#endif
+    if ((STEPSIZE==8) && (pIn<(pInLimit-3)) && (LZ4_read32(pMatch) == LZ4_read32(pIn))) { pIn+=4; pMatch+=4; }
+    if ((pIn<(pInLimit-1)) && (LZ4_read16(pMatch) == LZ4_read16(pIn))) { pIn+=2; pMatch+=2; }
+    if ((pIn<pInLimit) && (*pMatch == *pIn)) pIn++;
+    return (unsigned)(pIn - pStart);
+}
 
 
-/**************************************
-   Macros
+#ifndef LZ4_COMMONDEFS_ONLY
+/*-************************************
+*  Local Constants
 **************************************/
-#define LZ4_STATIC_ASSERT(c)    { enum { LZ4_static_assert = 1/(!!(c)) }; }   /* use only *after* variable declarations */
-#if LZ4_ARCH64 || !defined(__GNUC__)
-#  define LZ4_WILDCOPY(d,s,e)   { do { LZ4_COPY8(d,s) } while (d<e); }        /* at the end, d>=e; */
-#else
-#  define LZ4_WILDCOPY(d,s,e)   { if (likely(e-d <= 8)) LZ4_COPY8(d,s) else do { LZ4_COPY8(d,s) } while (d<e); }
-#endif
+static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));
+static const U32 LZ4_skipTrigger = 6;  /* Increase this value ==> compression run slower on incompressible data */
 
 
-/****************************
-   Private local functions
-****************************/
-#if LZ4_ARCH64
+/*-************************************
+*  Local Structures and types
+**************************************/
+typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
+typedef enum { byPtr, byU32, byU16 } tableType_t;
 
-int LZ4_NbCommonBytes (register U64 val)
-{
-# if defined(LZ4_BIG_ENDIAN)
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r = 0;
-    _BitScanReverse64( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_clzll(val) >> 3);
-#   else
-    int r;
-    if (!(val>>32)) { r=4; } else { r=0; val>>=32; }
-    if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
-    r += (!val);
-    return r;
-#   endif
-# else
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r = 0;
-    _BitScanForward64( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_ctzll(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
-# endif
-}
+typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
 
-#else
+typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
+typedef enum { full = 0, partial = 1 } earlyEnd_directive;
 
-int LZ4_NbCommonBytes (register U32 val)
-{
-# if defined(LZ4_BIG_ENDIAN)
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r = 0;
-    _BitScanReverse( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_clz(val) >> 3);
-#   else
-    int r;
-    if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
-    r += (!val);
-    return r;
-#   endif
-# else
-#   if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    unsigned long r;
-    _BitScanForward( &r, val );
-    return (int)(r>>3);
-#   elif defined(__GNUC__) && (GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT)
-    return (__builtin_ctz(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
-# endif
-}
 
-#endif
+/*-************************************
+*  Local Utils
+**************************************/
+int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
+const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; }
+int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }
+int LZ4_sizeofState() { return LZ4_STREAMSIZE; }
 
 
-/********************************
-   Compression functions
+/*-******************************
+*  Compression functions
 ********************************/
-int LZ4_compressBound(int isize)  { return LZ4_COMPRESSBOUND(isize); }
-
-static int LZ4_hashSequence(U32 sequence, tableType_t tableType)
+static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
 {
     if (tableType == byU16)
-        return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
+        return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
     else
-        return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
+        return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
 }
 
-static int LZ4_hashPosition(const BYTE* p, tableType_t tableType) { return LZ4_hashSequence(A32(p), tableType); }
+static U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
+{
+    static const U64 prime5bytes = 889523592379ULL;
+    static const U64 prime8bytes = 11400714785074694791ULL;
+    const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
+    if (LZ4_isLittleEndian())
+        return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
+    else
+        return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
+}
+
+FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
+{
+    if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);
+    return LZ4_hash4(LZ4_read32(p), tableType);
+}
 
-static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase)
 {
     switch (tableType)
     {
-    case byPtr: { const BYTE** hashTable = (const BYTE**) tableBase; hashTable[h] = p; break; }
-    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); break; }
-    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); break; }
+    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; }
     }
 }
 
-static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
 {
-    U32 h = LZ4_hashPosition(p, tableType);
+    U32 const h = LZ4_hashPosition(p, tableType);
     LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
 }
 
 static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
 {
     if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }
-    if (tableType == byU32) { U32* hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }
-    { U16* hashTable = (U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
+    if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }
+    { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
 }
 
-static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
 {
-    U32 h = LZ4_hashPosition(p, tableType);
+    U32 const h = LZ4_hashPosition(p, tableType);
     return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
 }
 
-static unsigned LZ4_count(const BYTE* pIn, const BYTE* pRef, const BYTE* pInLimit)
-{
-    const BYTE* const pStart = pIn;
-
-    while (likely(pIn<pInLimit-(STEPSIZE-1)))
-    {
-        size_t diff = AARCH(pRef) ^ AARCH(pIn);
-        if (!diff) { pIn+=STEPSIZE; pRef+=STEPSIZE; continue; }
-        pIn += LZ4_NbCommonBytes(diff);
-        return (unsigned)(pIn - pStart);
-    }
-    if (sizeof(void*)==8) if ((pIn<(pInLimit-3)) && (A32(pRef) == A32(pIn))) { pIn+=4; pRef+=4; }
-    if ((pIn<(pInLimit-1)) && (A16(pRef) == A16(pIn))) { pIn+=2; pRef+=2; }
-    if ((pIn<pInLimit) && (*pRef == *pIn)) pIn++;
-
-    return (unsigned)(pIn - pStart);
-}
-
 
-static int LZ4_compress_generic(
-                 void* ctx,
-                 const char* source,
-                 char* dest,
-                 int inputSize,
-                 int maxOutputSize,
-
-                 limitedOutput_directive outputLimited,
-                 tableType_t tableType,
-                 dict_directive dict,
-                 dictIssue_directive dictIssue)
+/** LZ4_compress_generic() :
+    inlined, to ensure branches are decided at compilation time */
+FORCE_INLINE int LZ4_compress_generic(
+                 LZ4_stream_t_internal* const cctx,
+                 const char* const source,
+                 char* const dest,
+                 const int inputSize,
+                 const int maxOutputSize,
+                 const limitedOutput_directive outputLimited,
+                 const tableType_t tableType,
+                 const dict_directive dict,
+                 const dictIssue_directive dictIssue,
+                 const U32 acceleration)
 {
-    LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx;
-
     const BYTE* ip = (const BYTE*) source;
     const BYTE* base;
     const BYTE* lowLimit;
-    const BYTE* const lowRefLimit = ip - dictPtr->dictSize;
-    const BYTE* const dictionary = dictPtr->dictionary;
-    const BYTE* const dictEnd = dictionary + dictPtr->dictSize;
-    const size_t dictDelta = dictEnd - (const BYTE*)source;
+    const BYTE* const lowRefLimit = ip - cctx->dictSize;
+    const BYTE* const dictionary = cctx->dictionary;
+    const BYTE* const dictEnd = dictionary + cctx->dictSize;
+    const ptrdiff_t dictDelta = dictEnd - (const BYTE*)source;
     const BYTE* anchor = (const BYTE*) source;
     const BYTE* const iend = ip + inputSize;
     const BYTE* const mflimit = iend - MFLIMIT;
@@ -455,12 +501,10 @@ static int LZ4_compress_generic(
     BYTE* op = (BYTE*) dest;
     BYTE* const olimit = op + maxOutputSize;
 
-    const int skipStrength = SKIPSTRENGTH;
     U32 forwardH;
-    size_t refDelta=0;
 
     /* Init conditions */
-    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;          /* Unsupported input size, too large (or negative) */
+    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;   /* Unsupported inputSize, too large (or negative) */
     switch(dict)
     {
     case noDict:
@@ -469,125 +513,118 @@ static int LZ4_compress_generic(
         lowLimit = (const BYTE*)source;
         break;
     case withPrefix64k:
-        base = (const BYTE*)source - dictPtr->currentOffset;
-        lowLimit = (const BYTE*)source - dictPtr->dictSize;
+        base = (const BYTE*)source - cctx->currentOffset;
+        lowLimit = (const BYTE*)source - cctx->dictSize;
         break;
     case usingExtDict:
-        base = (const BYTE*)source - dictPtr->currentOffset;
+        base = (const BYTE*)source - cctx->currentOffset;
         lowLimit = (const BYTE*)source;
         break;
     }
-    if ((tableType == byU16) && (inputSize>=(int)LZ4_64KLIMIT)) return 0;   /* Size too large (not within 64K limit) */
-    if (inputSize<LZ4_minLength) goto _last_literals;                       /* Input too small, no compression (all literals) */
+    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
+    if (inputSize<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */
 
     /* First Byte */
-    LZ4_putPosition(ip, ctx, tableType, base);
+    LZ4_putPosition(ip, cctx->hashTable, tableType, base);
     ip++; forwardH = LZ4_hashPosition(ip, tableType);
 
     /* Main Loop */
-    for ( ; ; )
-    {
-        const BYTE* ref;
+    for ( ; ; ) {
+        ptrdiff_t refDelta = 0;
+        const BYTE* match;
         BYTE* token;
-        {
-            const BYTE* forwardIp = ip;
-            unsigned step=1;
-            unsigned searchMatchNb = (1U << skipStrength);
 
-            /* Find a match */
+        /* Find a match */
+        {   const BYTE* forwardIp = ip;
+            unsigned step = 1;
+            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
             do {
-                U32 h = forwardH;
+                U32 const h = forwardH;
                 ip = forwardIp;
                 forwardIp += step;
-                step = searchMatchNb++ >> skipStrength;
-                //if (step>8) step=8;   // required for valid forwardIp ; slows down uncompressible data a bit
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
 
                 if (unlikely(forwardIp > mflimit)) goto _last_literals;
 
-                ref = LZ4_getPositionOnHash(h, ctx, tableType, base);
-                if (dict==usingExtDict)
-                {
-                    if (ref<(const BYTE*)source)
-                    {
+                match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
+                if (dict==usingExtDict) {
+                    if (match < (const BYTE*)source) {
                         refDelta = dictDelta;
                         lowLimit = dictionary;
-                    }
-                    else
-                    {
+                    } else {
                         refDelta = 0;
                         lowLimit = (const BYTE*)source;
-                    }
-                }
+                }   }
                 forwardH = LZ4_hashPosition(forwardIp, tableType);
-                LZ4_putPositionOnHash(ip, h, ctx, tableType, base);
+                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
 
-            } while ( ((dictIssue==dictSmall) ? (ref < lowRefLimit) : 0)
-                || ((tableType==byU16) ? 0 : (ref + MAX_DISTANCE < ip))
-                || (A32(ref+refDelta) != A32(ip)) );
+            } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
+                || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
+                || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
         }
 
         /* Catch up */
-        while ((ip>anchor) && (ref+refDelta > lowLimit) && (unlikely(ip[-1]==ref[refDelta-1]))) { ip--; ref--; }
+        while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
 
-        {
-            /* Encode Literal length */
-            unsigned litLength = (unsigned)(ip - anchor);
+        /* Encode Literals */
+        {   unsigned const litLength = (unsigned)(ip - anchor);
             token = op++;
-            if ((outputLimited) && (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
-                return 0;   /* Check output limit */
-            if (litLength>=RUN_MASK)
-            {
+            if ((outputLimited) &&  /* Check output buffer overflow */
+                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
+                return 0;
+            if (litLength >= RUN_MASK) {
                 int len = (int)litLength-RUN_MASK;
-                *token=(RUN_MASK<<ML_BITS);
+                *token = (RUN_MASK<<ML_BITS);
                 for(; len >= 255 ; len-=255) *op++ = 255;
                 *op++ = (BYTE)len;
             }
             else *token = (BYTE)(litLength<<ML_BITS);
 
             /* Copy Literals */
-            { BYTE* end = op+litLength; LZ4_WILDCOPY(op,anchor,end); op=end; }
+            LZ4_wildCopy(op, anchor, op+litLength);
+            op+=litLength;
         }
 
 _next_match:
         /* Encode Offset */
-        LZ4_WRITE_LITTLEENDIAN_16(op, (U16)(ip-ref));
+        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
 
         /* Encode MatchLength */
-        {
-            unsigned matchLength;
+        {   unsigned matchCode;
 
-            if ((dict==usingExtDict) && (lowLimit==dictionary))
-            {
+            if ((dict==usingExtDict) && (lowLimit==dictionary)) {
                 const BYTE* limit;
-                ref += refDelta;
-                limit = ip + (dictEnd-ref);
+                match += refDelta;
+                limit = ip + (dictEnd-match);
                 if (limit > matchlimit) limit = matchlimit;
-                matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, limit);
-                ip += MINMATCH + matchLength;
-                if (ip==limit)
-                {
-                    unsigned more = LZ4_count(ip, (const BYTE*)source, matchlimit);
-                    matchLength += more;
+                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
+                ip += MINMATCH + matchCode;
+                if (ip==limit) {
+                    unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+                    matchCode += more;
                     ip += more;
                 }
-            }
-            else
-            {
-                matchLength = LZ4_count(ip+MINMATCH, ref+MINMATCH, matchlimit);
-                ip += MINMATCH + matchLength;
+            } else {
+                matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
+                ip += MINMATCH + matchCode;
             }
 
-            if (matchLength>=ML_MASK)
-            {
-                if ((outputLimited) && (unlikely(op + (1 + LASTLITERALS) + (matchLength>>8) > olimit)))
-                    return 0;    /* Check output limit */
+            if ( outputLimited &&    /* Check output buffer overflow */
+                (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
+                return 0;
+            if (matchCode >= ML_MASK) {
                 *token += ML_MASK;
-                matchLength -= ML_MASK;
-                for (; matchLength >= 510 ; matchLength-=510) { *op++ = 255; *op++ = 255; }
-                if (matchLength >= 255) { matchLength-=255; *op++ = 255; }
-                *op++ = (BYTE)matchLength;
-            }
-            else *token += (BYTE)(matchLength);
+                matchCode -= ML_MASK;
+                LZ4_write32(op, 0xFFFFFFFF);
+                while (matchCode >= 4*255) {
+                    op+=4;
+                    LZ4_write32(op, 0xFFFFFFFF);
+                    matchCode -= 4*255;
+                }
+                op += matchCode / 255;
+                *op++ = (BYTE)(matchCode % 255);
+            } else
+                *token += (BYTE)(matchCode);
         }
 
         anchor = ip;
@@ -596,27 +633,22 @@ _next_match:
         if (ip > mflimit) break;
 
         /* Fill table */
-        LZ4_putPosition(ip-2, ctx, tableType, base);
+        LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
 
         /* Test next position */
-        ref = LZ4_getPosition(ip, ctx, tableType, base);
-        if (dict==usingExtDict)
-        {
-            if (ref<(const BYTE*)source)
-            {
+        match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
+        if (dict==usingExtDict) {
+            if (match < (const BYTE*)source) {
                 refDelta = dictDelta;
                 lowLimit = dictionary;
-            }
-            else
-            {
+            } else {
                 refDelta = 0;
                 lowLimit = (const BYTE*)source;
-            }
-        }
-        LZ4_putPosition(ip, ctx, tableType, base);
-        if ( ((dictIssue==dictSmall) ? (ref>=lowRefLimit) : 1)
-            && (ref+MAX_DISTANCE>=ip)
-            && (A32(ref+refDelta)==A32(ip)) )
+        }   }
+        LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+        if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
+            && (match+MAX_DISTANCE>=ip)
+            && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
         { token=op++; *token=0; goto _next_match; }
 
         /* Prepare next loop */
@@ -625,14 +657,20 @@ _next_match:
 
 _last_literals:
     /* Encode Last Literals */
-    {
-        int lastRun = (int)(iend - anchor);
-        if ((outputLimited) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize))
-            return 0;   /* Check output limit */
-        if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK<<ML_BITS); lastRun-=RUN_MASK; for(; lastRun >= 255 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; }
-        else *op++ = (BYTE)(lastRun<<ML_BITS);
-        memcpy(op, anchor, iend - anchor);
-        op += iend-anchor;
+    {   size_t const lastRun = (size_t)(iend - anchor);
+        if ( (outputLimited) &&  /* Check output buffer overflow */
+            ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
+            return 0;
+        if (lastRun >= RUN_MASK) {
+            size_t accumulator = lastRun - RUN_MASK;
+            *op++ = RUN_MASK << ML_BITS;
+            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+            *op++ = (BYTE) accumulator;
+        } else {
+            *op++ = (BYTE)(lastRun<<ML_BITS);
+        }
+        memcpy(op, anchor, lastRun);
+        op += lastRun;
     }
 
     /* End */
@@ -640,109 +678,325 @@ _last_literals:
 }
 
 
-int LZ4_compress(const char* source, char* dest, int inputSize)
+int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
-#if (HEAPMODE)
-    void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4);   /* Aligned on 4-bytes boundaries */
+    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
+    LZ4_resetStream((LZ4_stream_t*)state);
+    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
+
+    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
+        if (inputSize < LZ4_64Klimit)
+            return LZ4_compress_generic(ctx, source, dest, inputSize,             0,    notLimited,                        byU16, noDict, noDictIssue, acceleration);
+        else
+            return LZ4_compress_generic(ctx, source, dest, inputSize,             0,    notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+    } else {
+        if (inputSize < LZ4_64Klimit)
+            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput,                        byU16, noDict, noDictIssue, acceleration);
+        else
+            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+    }
+}
+
+
+int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+#if (LZ4_HEAPMODE)
+    void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
 #else
-    U32 ctx[LZ4_STREAMSIZE_U32] = {0};      /* Ensure data is aligned on 4-bytes boundaries */
+    LZ4_stream_t ctx;
+    void* const ctxPtr = &ctx;
 #endif
-    int result;
 
-    if (inputSize < (int)LZ4_64KLIMIT)
-        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue);
-    else
-        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue);
+    int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
 
-#if (HEAPMODE)
-    FREEMEM(ctx);
+#if (LZ4_HEAPMODE)
+    FREEMEM(ctxPtr);
 #endif
     return result;
 }
 
-int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
+
+int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize)
 {
-#if (HEAPMODE)
-    void* ctx = ALLOCATOR(LZ4_STREAMSIZE_U32, 4);   /* Aligned on 4-bytes boundaries */
+    return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1);
+}
+
+
+/* hidden debug function */
+/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */
+int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+    LZ4_stream_t ctx;
+    LZ4_resetStream(&ctx);
+
+    if (inputSize < LZ4_64Klimit)
+        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16,                        noDict, noDictIssue, acceleration);
+    else
+        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+}
+
+
+/*-******************************
+*  *_destSize() variant
+********************************/
+
+static int LZ4_compress_destSize_generic(
+                       LZ4_stream_t_internal* const ctx,
+                 const char* const src,
+                       char* const dst,
+                       int*  const srcSizePtr,
+                 const int targetDstSize,
+                 const tableType_t tableType)
+{
+    const BYTE* ip = (const BYTE*) src;
+    const BYTE* base = (const BYTE*) src;
+    const BYTE* lowLimit = (const BYTE*) src;
+    const BYTE* anchor = ip;
+    const BYTE* const iend = ip + *srcSizePtr;
+    const BYTE* const mflimit = iend - MFLIMIT;
+    const BYTE* const matchlimit = iend - LASTLITERALS;
+
+    BYTE* op = (BYTE*) dst;
+    BYTE* const oend = op + targetDstSize;
+    BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */;
+    BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */);
+    BYTE* const oMaxSeq = oMaxLit - 1 /* token */;
+
+    U32 forwardH;
+
+
+    /* Init conditions */
+    if (targetDstSize < 1) return 0;                                     /* Impossible to store anything */
+    if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0;            /* Unsupported input size, too large (or negative) */
+    if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
+    if (*srcSizePtr<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */
+
+    /* First Byte */
+    *srcSizePtr = 0;
+    LZ4_putPosition(ip, ctx->hashTable, tableType, base);
+    ip++; forwardH = LZ4_hashPosition(ip, tableType);
+
+    /* Main Loop */
+    for ( ; ; ) {
+        const BYTE* match;
+        BYTE* token;
+
+        /* Find a match */
+        {   const BYTE* forwardIp = ip;
+            unsigned step = 1;
+            unsigned searchMatchNb = 1 << LZ4_skipTrigger;
+
+            do {
+                U32 h = forwardH;
+                ip = forwardIp;
+                forwardIp += step;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+                if (unlikely(forwardIp > mflimit)) goto _last_literals;
+
+                match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base);
+                forwardH = LZ4_hashPosition(forwardIp, tableType);
+                LZ4_putPositionOnHash(ip, h, ctx->hashTable, tableType, base);
+
+            } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
+                || (LZ4_read32(match) != LZ4_read32(ip)) );
+        }
+
+        /* Catch up */
+        while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
+
+        /* Encode Literal length */
+        {   unsigned litLength = (unsigned)(ip - anchor);
+            token = op++;
+            if (op + ((litLength+240)/255) + litLength > oMaxLit) {
+                /* Not enough space for a last match */
+                op--;
+                goto _last_literals;
+            }
+            if (litLength>=RUN_MASK) {
+                unsigned len = litLength - RUN_MASK;
+                *token=(RUN_MASK<<ML_BITS);
+                for(; len >= 255 ; len-=255) *op++ = 255;
+                *op++ = (BYTE)len;
+            }
+            else *token = (BYTE)(litLength<<ML_BITS);
+
+            /* Copy Literals */
+            LZ4_wildCopy(op, anchor, op+litLength);
+            op += litLength;
+        }
+
+_next_match:
+        /* Encode Offset */
+        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+
+        /* Encode MatchLength */
+        {   size_t matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
+
+            if (op + ((matchLength+240)/255) > oMaxMatch) {
+                /* Match description too long : reduce it */
+                matchLength = (15-1) + (oMaxMatch-op) * 255;
+            }
+            ip += MINMATCH + matchLength;
+
+            if (matchLength>=ML_MASK) {
+                *token += ML_MASK;
+                matchLength -= ML_MASK;
+                while (matchLength >= 255) { matchLength-=255; *op++ = 255; }
+                *op++ = (BYTE)matchLength;
+            }
+            else *token += (BYTE)(matchLength);
+        }
+
+        anchor = ip;
+
+        /* Test end of block */
+        if (ip > mflimit) break;
+        if (op > oMaxSeq) break;
+
+        /* Fill table */
+        LZ4_putPosition(ip-2, ctx->hashTable, tableType, base);
+
+        /* Test next position */
+        match = LZ4_getPosition(ip, ctx->hashTable, tableType, base);
+        LZ4_putPosition(ip, ctx->hashTable, tableType, base);
+        if ( (match+MAX_DISTANCE>=ip)
+            && (LZ4_read32(match)==LZ4_read32(ip)) )
+        { token=op++; *token=0; goto _next_match; }
+
+        /* Prepare next loop */
+        forwardH = LZ4_hashPosition(++ip, tableType);
+    }
+
+_last_literals:
+    /* Encode Last Literals */
+    {   size_t lastRunSize = (size_t)(iend - anchor);
+        if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) {
+            /* adapt lastRunSize to fill 'dst' */
+            lastRunSize  = (oend-op) - 1;
+            lastRunSize -= (lastRunSize+240)/255;
+        }
+        ip = anchor + lastRunSize;
+
+        if (lastRunSize >= RUN_MASK) {
+            size_t accumulator = lastRunSize - RUN_MASK;
+            *op++ = RUN_MASK << ML_BITS;
+            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
+            *op++ = (BYTE) accumulator;
+        } else {
+            *op++ = (BYTE)(lastRunSize<<ML_BITS);
+        }
+        memcpy(op, anchor, lastRunSize);
+        op += lastRunSize;
+    }
+
+    /* End */
+    *srcSizePtr = (int) (((const char*)ip)-src);
+    return (int) (((char*)op)-dst);
+}
+
+
+static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
+{
+    LZ4_resetStream(state);
+
+    if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) {  /* compression success is guaranteed */
+        return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
+    } else {
+        if (*srcSizePtr < LZ4_64Klimit)
+            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16);
+        else
+            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr);
+    }
+}
+
+
+int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
+{
+#if (LZ4_HEAPMODE)
+    LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOCATOR(1, sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
 #else
-    U32 ctx[LZ4_STREAMSIZE_U32] = {0};      /* Ensure data is aligned on 4-bytes boundaries */
+    LZ4_stream_t ctxBody;
+    LZ4_stream_t* ctx = &ctxBody;
 #endif
-    int result;
 
-    if (inputSize < (int)LZ4_64KLIMIT)
-        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue);
-    else
-        result = LZ4_compress_generic((void*)ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue);
+    int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize);
 
-#if (HEAPMODE)
+#if (LZ4_HEAPMODE)
     FREEMEM(ctx);
 #endif
     return result;
 }
 
 
-/*****************************************
-   Experimental : Streaming functions
-*****************************************/
 
-void* LZ4_createStream()
+/*-******************************
+*  Streaming functions
+********************************/
+
+LZ4_stream_t* LZ4_createStream(void)
 {
-    void* lz4s = ALLOCATOR(4, LZ4_STREAMSIZE_U32);
-    MEM_INIT(lz4s, 0, LZ4_STREAMSIZE);
+    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64);
+    LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal));    /* A compilation error here means LZ4_STREAMSIZE is not large enough */
+    LZ4_resetStream(lz4s);
     return lz4s;
 }
 
-int LZ4_free (void* LZ4_stream)
+void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
+{
+    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
+}
+
+int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
 {
+    if (!LZ4_stream) return 0;   /* support free on NULL */
     FREEMEM(LZ4_stream);
     return (0);
 }
 
 
-int LZ4_loadDict (void* LZ4_dict, const char* dictionary, int dictSize)
+#define HASH_UNIT sizeof(reg_t)
+int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
 {
-    LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
+    LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse;
     const BYTE* p = (const BYTE*)dictionary;
     const BYTE* const dictEnd = p + dictSize;
     const BYTE* base;
 
-    LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal));      /* A compilation error here means LZ4_STREAMSIZE is not large enough */
-    if (dict->initCheck) MEM_INIT(dict, 0, sizeof(LZ4_stream_t_internal));   /* Uninitialized structure detected */
+    if ((dict->initCheck) || (dict->currentOffset > 1 GB))  /* Uninitialized structure, or reuse overflow */
+        LZ4_resetStream(LZ4_dict);
 
-    if (dictSize < MINMATCH)
-    {
+    if (dictSize < (int)HASH_UNIT) {
         dict->dictionary = NULL;
         dict->dictSize = 0;
-        return 1;
+        return 0;
     }
 
-    if (p <= dictEnd - 64 KB) p = dictEnd - 64 KB;
+    if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
+    dict->currentOffset += 64 KB;
     base = p - dict->currentOffset;
     dict->dictionary = p;
     dict->dictSize = (U32)(dictEnd - p);
     dict->currentOffset += dict->dictSize;
 
-    while (p <= dictEnd-MINMATCH)
-    {
-        LZ4_putPosition(p, dict, byU32, base);
+    while (p <= dictEnd-HASH_UNIT) {
+        LZ4_putPosition(p, dict->hashTable, byU32, base);
         p+=3;
     }
 
-    return 1;
+    return dict->dictSize;
 }
 
 
-void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
+static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
 {
     if ((LZ4_dict->currentOffset > 0x80000000) ||
-        ((size_t)LZ4_dict->currentOffset > (size_t)src))   /* address space overflow */
-    {
+        ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) {   /* address space overflow */
         /* rescale hash table */
-        U32 delta = LZ4_dict->currentOffset - 64 KB;
+        U32 const delta = LZ4_dict->currentOffset - 64 KB;
         const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
         int i;
-        for (i=0; i<HASH_SIZE_U32; i++)
-        {
+        for (i=0; i<LZ4_HASH_SIZE_U32; i++) {
             if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
             else LZ4_dict->hashTable[i] -= delta;
         }
@@ -753,22 +1007,20 @@ void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
 }
 
 
-FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* source, char* dest, int inputSize,
-                                                int maxOutputSize, limitedOutput_directive limit)
+int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
-    LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_stream;
+    LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse;
     const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
 
     const BYTE* smallest = (const BYTE*) source;
     if (streamPtr->initCheck) return 0;   /* Uninitialized structure detected */
     if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd;
     LZ4_renormDictT(streamPtr, smallest);
+    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
 
     /* Check overlapping input/dictionary space */
-    {
-        const BYTE* sourceEnd = (const BYTE*) source + inputSize;
-        if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd))
-        {
+    {   const BYTE* sourceEnd = (const BYTE*) source + inputSize;
+        if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) {
             streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
             if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
             if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
@@ -777,25 +1029,23 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so
     }
 
     /* prefix mode : source data follows dictionary */
-    if (dictEnd == (const BYTE*)source)
-    {
+    if (dictEnd == (const BYTE*)source) {
         int result;
         if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
-            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, dictSmall);
+            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration);
         else
-            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, withPrefix64k, noDictIssue);
+            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration);
         streamPtr->dictSize += (U32)inputSize;
         streamPtr->currentOffset += (U32)inputSize;
         return result;
     }
 
     /* external dictionary mode */
-    {
-        int result;
+    {   int result;
         if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
-            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, dictSmall);
+            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration);
         else
-            result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limit, byU32, usingExtDict, noDictIssue);
+            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration);
         streamPtr->dictionary = (const BYTE*)source;
         streamPtr->dictSize = (U32)inputSize;
         streamPtr->currentOffset += (U32)inputSize;
@@ -804,29 +1054,18 @@ FORCE_INLINE int LZ4_compress_continue_generic (void* LZ4_stream, const char* so
 }
 
 
-int LZ4_compress_continue (void* LZ4_stream, const char* source, char* dest, int inputSize)
-{
-    return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, 0, notLimited);
-}
-
-int LZ4_compress_limitedOutput_continue (void* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize)
-{
-    return LZ4_compress_continue_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput);
-}
-
-
-// Hidden debug function, to force separate dictionary mode
+/* Hidden debug function, to force external dictionary mode */
 int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
 {
-    LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_dict;
+    LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse;
     int result;
     const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
 
     const BYTE* smallest = dictEnd;
     if (smallest > (const BYTE*) source) smallest = (const BYTE*) source;
-    LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest);
+    LZ4_renormDictT(streamPtr, smallest);
 
-    result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue);
+    result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
 
     streamPtr->dictionary = (const BYTE*)source;
     streamPtr->dictSize = (U32)inputSize;
@@ -836,36 +1075,43 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char*
 }
 
 
-int LZ4_saveDict (void* LZ4_dict, char* safeBuffer, int dictSize)
+/*! LZ4_saveDict() :
+ *  If previously compressed data block is not guaranteed to remain available at its memory location,
+ *  save it into a safer place (char* safeBuffer).
+ *  Note : you don't need to call LZ4_loadDict() afterwards,
+ *         dictionary is immediately usable, you can therefore call LZ4_compress_fast_continue().
+ *  Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
+ */
+int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
 {
-    LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict;
-    const BYTE* previousDictEnd = dict->dictionary + dict->dictSize;
+    LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
+    const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
 
     if ((U32)dictSize > 64 KB) dictSize = 64 KB;   /* useless to define a dictionary > 64 KB */
     if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize;
 
-    memcpy(safeBuffer, previousDictEnd - dictSize, dictSize);
+    memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
 
     dict->dictionary = (const BYTE*)safeBuffer;
     dict->dictSize = (U32)dictSize;
 
-    return 1;
+    return dictSize;
 }
 
 
 
-/****************************
-   Decompression functions
-****************************/
-/*
- * This generic decompression function cover all use cases.
- * It shall be instanciated several times, using different sets of directives
- * Note that it is essential this generic function is really inlined,
- * in order to remove useless branches during compilation optimisation.
+/*-*****************************
+*  Decompression functions
+*******************************/
+/*! LZ4_decompress_generic() :
+ *  This generic decompression function cover all use cases.
+ *  It shall be instantiated several times, using different sets of directives
+ *  Note that it is important this generic function is really inlined,
+ *  in order to remove useless branches during compilation optimization.
  */
 FORCE_INLINE int LZ4_decompress_generic(
-                 const char* source,
-                 char* dest,
+                 const char* const source,
+                 char* const dest,
                  int inputSize,
                  int outputSize,         /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */
 
@@ -873,162 +1119,143 @@ FORCE_INLINE int LZ4_decompress_generic(
                  int partialDecoding,    /* full, partial */
                  int targetOutputSize,   /* only used if partialDecoding==partial */
                  int dict,               /* noDict, withPrefix64k, usingExtDict */
-                 const char* dictStart,  /* only if dict==usingExtDict */
-                 int dictSize            /* note : = 0 if noDict */
+                 const BYTE* const lowPrefix,  /* == dest when no prefix */
+                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
+                 const size_t dictSize         /* note : = 0 if noDict */
                  )
 {
     /* Local Variables */
-    const BYTE* restrict ip = (const BYTE*) source;
-    const BYTE* ref;
+    const BYTE* ip = (const BYTE*) source;
     const BYTE* const iend = ip + inputSize;
 
     BYTE* op = (BYTE*) dest;
     BYTE* const oend = op + outputSize;
     BYTE* cpy;
     BYTE* oexit = op + targetOutputSize;
-    const BYTE* const lowLimit = (const BYTE*)dest - dictSize;
+    const BYTE* const lowLimit = lowPrefix - dictSize;
 
     const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
-//#define OLD
-#ifdef OLD
-    const size_t dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0};   /* static reduces speed for LZ4_decompress_safe() on GCC64 */
-#else
-    const size_t dec32table[] = {4-0, 4-3, 4-2, 4-3, 4-0, 4-0, 4-0, 4-0};   /* static reduces speed for LZ4_decompress_safe() on GCC64 */
-#endif
-    static const size_t dec64table[] = {0, 0, 0, (size_t)-1, 0, 1, 2, 3};
+    const unsigned dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4};
+    const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3};
 
-    const int checkOffset = (endOnInput) && (dictSize < (int)(64 KB));
+    const int safeDecode = (endOnInput==endOnInputSize);
+    const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
 
 
     /* Special cases */
-    if ((partialDecoding) && (oexit> oend-MFLIMIT)) oexit = oend-MFLIMIT;                        /* targetOutputSize too high => decode everything */
-    if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1;   /* Empty output buffer */
+    if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT;                        /* targetOutputSize too high => decode everything */
+    if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
     if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);
 
-
-    /* Main Loop */
-    while (1)
-    {
-        unsigned token;
+    /* Main Loop : decode sequences */
+    while (1) {
         size_t length;
+        const BYTE* match;
+        size_t offset;
 
-        /* get runlength */
-        token = *ip++;
-        if ((length=(token>>ML_BITS)) == RUN_MASK)
-        {
+        /* get literal length */
+        unsigned const token = *ip++;
+        if ((length=(token>>ML_BITS)) == RUN_MASK) {
             unsigned s;
-            do
-            {
+            do {
                 s = *ip++;
                 length += s;
-            }
-            while (likely((endOnInput)?ip<iend-RUN_MASK:1) && (s==255));
-            //if ((sizeof(void*)==4) && unlikely(length>LZ4_MAX_INPUT_SIZE)) goto _output_error;   /* overflow detection */
-            if ((sizeof(void*)==4) && unlikely((size_t)(op+length)<(size_t)(op))) goto _output_error;   /* quickfix issue 134 */
-            if ((endOnInput) && (sizeof(void*)==4) && unlikely((size_t)(ip+length)<(size_t)(ip))) goto _output_error;   /* quickfix issue 134 */
+            } while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) & (s==255) );
+            if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error;   /* overflow detection */
+            if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error;   /* overflow detection */
         }
 
         /* copy literals */
         cpy = op+length;
-        if (((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
-            || ((!endOnInput) && (cpy>oend-COPYLENGTH)))
+        if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
+            || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
         {
-            if (partialDecoding)
-            {
+            if (partialDecoding) {
                 if (cpy > oend) goto _output_error;                           /* Error : write attempt beyond end of output buffer */
                 if ((endOnInput) && (ip+length > iend)) goto _output_error;   /* Error : read attempt beyond end of input buffer */
-            }
-            else
-            {
+            } else {
                 if ((!endOnInput) && (cpy != oend)) goto _output_error;       /* Error : block decoding must stop exactly there */
                 if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error;   /* Error : input must be consumed */
             }
             memcpy(op, ip, length);
             ip += length;
             op += length;
-            break;                                       /* Necessarily EOF, due to parsing restrictions */
+            break;     /* Necessarily EOF, due to parsing restrictions */
         }
-        LZ4_WILDCOPY(op, ip, cpy); ip -= (op-cpy); op = cpy;
+        LZ4_wildCopy(op, ip, cpy);
+        ip += length; op = cpy;
 
         /* get offset */
-        LZ4_READ_LITTLEENDIAN_16(ref,cpy,ip); ip+=2;
-        if ((checkOffset) && (unlikely(ref < lowLimit))) goto _output_error;   /* Error : offset outside destination buffer */
+        offset = LZ4_readLE16(ip); ip+=2;
+        match = op - offset;
+        if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error;   /* Error : offset outside buffers */
+        LZ4_write32(op, (U32)offset);   /* costs ~1%; silence an msan warning when offset==0 */
 
         /* get matchlength */
-        if ((length=(token&ML_MASK)) == ML_MASK)
-        {
+        length = token & ML_MASK;
+        if (length == ML_MASK) {
             unsigned s;
-            do
-            {
-                if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
+            do {
                 s = *ip++;
+                if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
                 length += s;
             } while (s==255);
-            //if ((sizeof(void*)==4) && unlikely(length>LZ4_MAX_INPUT_SIZE)) goto _output_error;   /* overflow detection */
-            if ((sizeof(void*)==4) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error;   /* quickfix issue 134 */
+            if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
         }
+        length += MINMATCH;
 
         /* check external dictionary */
-        if ((dict==usingExtDict) && (ref < (BYTE* const)dest))
-        {
-            if (unlikely(op+length+MINMATCH > oend-LASTLITERALS)) goto _output_error;
-
-            if (length+MINMATCH <= (size_t)(dest-(char*)ref))
-            {
-                ref = dictEnd - (dest-(char*)ref);
-                memcpy(op, ref, length+MINMATCH);
-                op += length+MINMATCH;
-            }
-            else
-            {
-                size_t copySize = (size_t)(dest-(char*)ref);
+        if ((dict==usingExtDict) && (match < lowPrefix)) {
+            if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */
+
+            if (length <= (size_t)(lowPrefix-match)) {
+                /* match can be copied as a single segment from external dictionary */
+                memmove(op, dictEnd - (lowPrefix-match), length);
+                op += length;
+            } else {
+                /* match encompass external dictionary and current block */
+                size_t const copySize = (size_t)(lowPrefix-match);
+                size_t const restSize = length - copySize;
                 memcpy(op, dictEnd - copySize, copySize);
                 op += copySize;
-                copySize = length+MINMATCH - copySize;
-                if (copySize > (size_t)((char*)op-dest))   /* overlap */
-                {
-                    BYTE* const cpy = op + copySize;
-                    const BYTE* ref = (BYTE*)dest;
-                    while (op < cpy) *op++ = *ref++;
-                }
-                else
-                {
-                    memcpy(op, dest, copySize);
-                    op += copySize;
-                }
-            }
+                if (restSize > (size_t)(op-lowPrefix)) {  /* overlap copy */
+                    BYTE* const endOfMatch = op + restSize;
+                    const BYTE* copyFrom = lowPrefix;
+                    while (op < endOfMatch) *op++ = *copyFrom++;
+                } else {
+                    memcpy(op, lowPrefix, restSize);
+                    op += restSize;
+            }   }
             continue;
         }
 
-        /* copy repeated sequence */
-        if (unlikely((op-ref)<(int)STEPSIZE))
-        {
-            const size_t dec64 = dec64table[(sizeof(void*)==4) ? 0 : op-ref];
-            op[0] = ref[0];
-            op[1] = ref[1];
-            op[2] = ref[2];
-            op[3] = ref[3];
-#ifdef OLD
-            op += 4, ref += 4; ref -= dec32table[op-ref];
-            A32(op) = A32(ref);
-            op += STEPSIZE-4; ref -= dec64;
-#else
-            ref += dec32table[op-ref];
-            A32(op+4) = A32(ref);
-            op += STEPSIZE; ref -= dec64;
-#endif
-        } else { LZ4_COPYSTEP(op,ref); }
-        cpy = op + length - (STEPSIZE-4);
-
-        if (unlikely(cpy>oend-COPYLENGTH-(STEPSIZE-4)))
-        {
-            if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last 5 bytes must be literals */
-            if (op<oend-COPYLENGTH) LZ4_WILDCOPY(op, ref, (oend-COPYLENGTH));
-            while(op<cpy) *op++=*ref++;
-            op=cpy;
-            continue;
+        /* copy match within block */
+        cpy = op + length;
+        if (unlikely(offset<8)) {
+            const int dec64 = dec64table[offset];
+            op[0] = match[0];
+            op[1] = match[1];
+            op[2] = match[2];
+            op[3] = match[3];
+            match += dec32table[offset];
+            memcpy(op+4, match, 4);
+            match -= dec64;
+        } else { LZ4_copy8(op, match); match+=8; }
+        op += 8;
+
+        if (unlikely(cpy>oend-12)) {
+            BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
+            if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
+            if (op < oCopyLimit) {
+                LZ4_wildCopy(op, match, oCopyLimit);
+                match += oCopyLimit - op;
+                op = oCopyLimit;
+            }
+            while (op<cpy) *op++ = *match++;
+        } else {
+            LZ4_copy8(op, match);
+            if (length>16) LZ4_wildCopy(op+8, match+8, cpy);
         }
-        LZ4_WILDCOPY(op, ref, cpy);
         op=cpy;   /* correction */
     }
 
@@ -1036,64 +1263,59 @@ FORCE_INLINE int LZ4_decompress_generic(
     if (endOnInput)
        return (int) (((char*)op)-dest);     /* Nb of output bytes decoded */
     else
-       return (int) (((char*)ip)-source);   /* Nb of input bytes read */
+       return (int) (((const char*)ip)-source);   /* Nb of input bytes read */
 
     /* Overflow error detected */
 _output_error:
-    return (int) (-(((char*)ip)-source))-1;
+    return (int) (-(((const char*)ip)-source))-1;
 }
 
 
-int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxOutputSize)
+int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
 {
-    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, noDict, NULL, 0);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0);
 }
 
-int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxOutputSize)
+int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
 {
-    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, partial, targetOutputSize, noDict, NULL, 0);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0);
 }
 
 int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
 {
-    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, NULL, 0);
+    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
 }
 
-/* streaming decompression functions */
 
-//#define LZ4_STREAMDECODESIZE_U32 4
-//#define LZ4_STREAMDECODESIZE     (LZ4_STREAMDECODESIZE_U32 * sizeof(unsigned int))
-//typedef struct { unsigned int table[LZ4_STREAMDECODESIZE_U32]; } LZ4_streamDecode_t;
-typedef struct
-{
-    const char* dictionary;
-    int dictSize;
-} LZ4_streamDecode_t_internal;
+/*===== streaming decompression functions =====*/
 
-/*
- * If you prefer dynamic allocation methods,
- * LZ4_createStreamDecode()
- * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure.
- */
-void* LZ4_createStreamDecode()
+LZ4_streamDecode_t* LZ4_createStreamDecode(void)
 {
-    void* lz4s = ALLOCATOR(sizeof(U32), LZ4_STREAMDECODESIZE_U32);
-    MEM_INIT(lz4s, 0, LZ4_STREAMDECODESIZE);
+    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t));
     return lz4s;
 }
 
-/*
- * LZ4_setDictDecode
- * Use this function to instruct where to find the dictionary
+int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
+{
+    if (!LZ4_stream) return 0;   /* support free on NULL */
+    FREEMEM(LZ4_stream);
+    return 0;
+}
+
+/*!
+ * LZ4_setStreamDecode() :
+ * Use this function to instruct where to find the dictionary.
  * This function is not necessary if previous data is still available where it was decoded.
  * Loading a size of 0 is allowed (same effect as no dictionary).
  * Return : 1 if OK, 0 if error
  */
-int LZ4_setDictDecode (void* LZ4_streamDecode, const char* dictionary, int dictSize)
+int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
 {
-    LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
-    lz4sd->dictionary = dictionary;
-    lz4sd->dictSize = dictSize;
+    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
+    lz4sd->prefixSize = (size_t) dictSize;
+    lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
+    lz4sd->externalDict = NULL;
+    lz4sd->extDictSize  = 0;
     return 1;
 }
 
@@ -1102,43 +1324,55 @@ int LZ4_setDictDecode (void* LZ4_streamDecode, const char* dictionary, int dictS
     These decoding functions allow decompression of multiple blocks in "streaming" mode.
     Previously decoded blocks must still be available at the memory position where they were decoded.
     If it's not possible, save the relevant part of decoded data into a safe buffer,
-    and indicate where it stands using LZ4_setDictDecode()
+    and indicate where it stands using LZ4_setStreamDecode()
 */
-int LZ4_decompress_safe_continue (void* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
+int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
 {
-    LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
     int result;
 
-    result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, lz4sd->dictionary, lz4sd->dictSize);
-    if (result <= 0) return result;
-    if (lz4sd->dictionary + lz4sd->dictSize == dest)
-    {
-        lz4sd->dictSize += result;
-    }
-    else
-    {
-        lz4sd->dictionary = dest;
-        lz4sd->dictSize = result;
+    if (lz4sd->prefixEnd == (BYTE*)dest) {
+        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                        endOnInputSize, full, 0,
+                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize += result;
+        lz4sd->prefixEnd  += result;
+    } else {
+        lz4sd->extDictSize = lz4sd->prefixSize;
+        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                        endOnInputSize, full, 0,
+                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize = result;
+        lz4sd->prefixEnd  = (BYTE*)dest + result;
     }
 
     return result;
 }
 
-int LZ4_decompress_fast_continue (void* LZ4_streamDecode, const char* source, char* dest, int originalSize)
+int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
 {
-    LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode;
+    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
     int result;
 
-    result = LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, lz4sd->dictionary, lz4sd->dictSize);
-    if (result <= 0) return result;
-    if (lz4sd->dictionary + lz4sd->dictSize == dest)
-    {
-        lz4sd->dictSize += result;
-    }
-    else
-    {
-        lz4sd->dictionary = dest;
-        lz4sd->dictSize = result;
+    if (lz4sd->prefixEnd == (BYTE*)dest) {
+        result = LZ4_decompress_generic(source, dest, 0, originalSize,
+                                        endOnOutputSize, full, 0,
+                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize += originalSize;
+        lz4sd->prefixEnd  += originalSize;
+    } else {
+        lz4sd->extDictSize = lz4sd->prefixSize;
+        lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
+        result = LZ4_decompress_generic(source, dest, 0, originalSize,
+                                        endOnOutputSize, full, 0,
+                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize = originalSize;
+        lz4sd->prefixEnd  = (BYTE*)dest + originalSize;
     }
 
     return result;
@@ -1152,12 +1386,97 @@ Advanced decoding functions :
     the dictionary must be explicitly provided within parameters
 */
 
+FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
+{
+    if (dictSize==0)
+        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
+    if (dictStart+dictSize == dest) {
+        if (dictSize >= (int)(64 KB - 1))
+            return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0);
+        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0);
+    }
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
 int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
 {
-    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, dictStart, dictSize);
+    return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
 }
 
 int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
 {
-    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, usingExtDict, dictStart, dictSize);
+    return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
+}
+
+/* debug function */
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
 }
+
+
+/*=*************************************************
+*  Obsolete Functions
+***************************************************/
+/* obsolete compression functions */
+int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); }
+int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); }
+int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); }
+int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); }
+int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); }
+int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); }
+
+/*
+These function names are deprecated and should no longer be used.
+They are only provided here for compatibility with older user programs.
+- LZ4_uncompress is totally equivalent to LZ4_decompress_fast
+- LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
+*/
+int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
+int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }
+
+
+/* Obsolete Streaming functions */
+
+int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }
+
+static void LZ4_init(LZ4_stream_t* lz4ds, BYTE* base)
+{
+    MEM_INIT(lz4ds, 0, sizeof(LZ4_stream_t));
+    lz4ds->internal_donotuse.bufferStart = base;
+}
+
+int LZ4_resetStreamState(void* state, char* inputBuffer)
+{
+    if ((((uptrval)state) & 3) != 0) return 1;   /* Error : pointer is not aligned on 4-bytes boundary */
+    LZ4_init((LZ4_stream_t*)state, (BYTE*)inputBuffer);
+    return 0;
+}
+
+void* LZ4_create (char* inputBuffer)
+{
+    LZ4_stream_t* lz4ds = (LZ4_stream_t*)ALLOCATOR(8, sizeof(LZ4_stream_t));
+    LZ4_init (lz4ds, (BYTE*)inputBuffer);
+    return lz4ds;
+}
+
+char* LZ4_slideInputBuffer (void* LZ4_Data)
+{
+    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)LZ4_Data)->internal_donotuse;
+    int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB);
+    return (char*)(ctx->bufferStart + dictSize);
+}
+
+/* Obsolete streaming decompression functions */
+
+int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
+}
+
+int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
+{
+    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
+}
+
+#endif   /* LZ4_COMMONDEFS_ONLY */