extlz4 0.2.5 → 0.3.4

data/contrib/lz4/lib/lz4.c

@@ -1,6 +1,6 @@
 /*
    LZ4 - Fast LZ compression algorithm
-   Copyright (C) 2011-2017, Yann Collet.
+   Copyright (C) 2011-2020, Yann Collet.
 
    BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
 
@@ -32,7 +32,6 @@
     - LZ4 source repository : https://github.com/lz4/lz4
 */
 
-
 /*-************************************
 *  Tuning parameters
 **************************************/
@@ -46,10 +45,16 @@
 #endif
 
 /*
- * ACCELERATION_DEFAULT :
+ * LZ4_ACCELERATION_DEFAULT :
  * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0
  */
-#define ACCELERATION_DEFAULT 1
+#define LZ4_ACCELERATION_DEFAULT 1
+/*
+ * LZ4_ACCELERATION_MAX :
+ * Any "acceleration" value higher than this threshold
+ * get treated as LZ4_ACCELERATION_MAX instead (fix #876)
+ */
+#define LZ4_ACCELERATION_MAX 65537
 
 
 /*-************************************
@@ -69,9 +74,11 @@
  * 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__) )
+#  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__)
+#  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)
 #    define LZ4_FORCE_MEMORY_ACCESS 1
 #  endif
 #endif
@@ -80,7 +87,8 @@
  * LZ4_FORCE_SW_BITCOUNT
  * 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 */
+#if defined(_MSC_VER) && defined(_WIN32_WCE)   /* Visual Studio for WinCE doesn't support Hardware bit count */
+#  undef  LZ4_FORCE_SW_BITCOUNT  /* avoid double def */
 #  define LZ4_FORCE_SW_BITCOUNT
 #endif
 
@@ -89,6 +97,23 @@
 /*-************************************
 *  Dependency
 **************************************/
+/*
+ * LZ4_SRC_INCLUDED:
+ * Amalgamation flag, whether lz4.c is included
+ */
+#ifndef LZ4_SRC_INCLUDED
+#  define LZ4_SRC_INCLUDED 1
+#endif
+
+#ifndef LZ4_STATIC_LINKING_ONLY
+#define LZ4_STATIC_LINKING_ONLY
+#endif
+
+#ifndef LZ4_DISABLE_DEPRECATE_WARNINGS
+#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
+#endif
+
+#define LZ4_STATIC_LINKING_ONLY  /* LZ4_DISTANCE_MAX */
 #include "lz4.h"
 /* see also "memory routines" below */
 
@@ -96,10 +121,10 @@
 /*-************************************
 *  Compiler Options
 **************************************/
-#ifdef _MSC_VER    /* Visual Studio */
-#  include <intrin.h>
-#  pragma warning(disable : 4127)        /* disable: C4127: conditional expression is constant */
-#  pragma warning(disable : 4293)        /* disable: C4293: too large shift (32-bits) */
+#if defined(_MSC_VER) && (_MSC_VER >= 1400)  /* Visual Studio 2005+ */
+#  include <intrin.h>               /* only present in VS2005+ */
+#  pragma warning(disable : 4127)   /* disable: C4127: conditional expression is constant */
+#  pragma warning(disable : 6237)   /* disable: C6237: conditional expression is always 0 */
 #endif  /* _MSC_VER */
 
 #ifndef LZ4_FORCE_INLINE
@@ -118,8 +143,8 @@
 #  endif  /* _MSC_VER */
 #endif /* LZ4_FORCE_INLINE */
 
-/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE
- * Gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy,
+/* LZ4_FORCE_O2 and LZ4_FORCE_INLINE
+ * gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy8,
  * together with a simple 8-byte copy loop as a fall-back path.
  * However, this optimization hurts the decompression speed by >30%,
  * because the execution does not go to the optimized loop
@@ -127,17 +152,17 @@
  * before going to the fall-back path become useless overhead.
  * This optimization happens only with the -O3 flag, and -O2 generates
  * a simple 8-byte copy loop.
- * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy
+ * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy8
  * functions are annotated with __attribute__((optimize("O2"))),
- * and also LZ4_wildCopy is forcibly inlined, so that the O2 attribute
- * of LZ4_wildCopy does not affect the compression speed.
+ * and also LZ4_wildCopy8 is forcibly inlined, so that the O2 attribute
+ * of LZ4_wildCopy8 does not affect the compression speed.
  */
-#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__)
-#  define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2")))
-#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE
+#if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__)
+#  define LZ4_FORCE_O2  __attribute__((optimize("O2")))
+#  undef LZ4_FORCE_INLINE
+#  define LZ4_FORCE_INLINE  static __inline __attribute__((optimize("O2"),always_inline))
 #else
-#  define LZ4_FORCE_O2_GCC_PPC64LE
-#  define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static
+#  define LZ4_FORCE_O2
 #endif
 
 #if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__)
@@ -146,23 +171,132 @@
 #  define expect(expr,value)    (expr)
 #endif
 
+#ifndef likely
 #define likely(expr)     expect((expr) != 0, 1)
+#endif
+#ifndef unlikely
 #define unlikely(expr)   expect((expr) != 0, 0)
+#endif
+
+/* Should the alignment test prove unreliable, for some reason,
+ * it can be disabled by setting LZ4_ALIGN_TEST to 0 */
+#ifndef LZ4_ALIGN_TEST  /* can be externally provided */
+# define LZ4_ALIGN_TEST 1
+#endif
 
 
 /*-************************************
 *  Memory routines
 **************************************/
-#include <stdlib.h>   /* malloc, calloc, free */
-#define ALLOCATOR(n,s) calloc(n,s)
-#define FREEMEM        free
-#include <string.h>   /* memset, memcpy */
-#define MEM_INIT       memset
+
+/*! LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION :
+ *  Disable relatively high-level LZ4/HC functions that use dynamic memory
+ *  allocation functions (malloc(), calloc(), free()).
+ *
+ *  Note that this is a compile-time switch. And since it disables
+ *  public/stable LZ4 v1 API functions, we don't recommend using this
+ *  symbol to generate a library for distribution.
+ *
+ *  The following public functions are removed when this symbol is defined.
+ *  - lz4   : LZ4_createStream, LZ4_freeStream,
+ *            LZ4_createStreamDecode, LZ4_freeStreamDecode, LZ4_create (deprecated)
+ *  - lz4hc : LZ4_createStreamHC, LZ4_freeStreamHC,
+ *            LZ4_createHC (deprecated), LZ4_freeHC  (deprecated)
+ *  - lz4frame, lz4file : All LZ4F_* functions
+ */
+#if defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
+#  define ALLOC(s)          lz4_error_memory_allocation_is_disabled
+#  define ALLOC_AND_ZERO(s) lz4_error_memory_allocation_is_disabled
+#  define FREEMEM(p)        lz4_error_memory_allocation_is_disabled
+#elif defined(LZ4_USER_MEMORY_FUNCTIONS)
+/* memory management functions can be customized by user project.
+ * Below functions must exist somewhere in the Project
+ * and be available at link time */
+void* LZ4_malloc(size_t s);
+void* LZ4_calloc(size_t n, size_t s);
+void  LZ4_free(void* p);
+# define ALLOC(s)          LZ4_malloc(s)
+# define ALLOC_AND_ZERO(s) LZ4_calloc(1,s)
+# define FREEMEM(p)        LZ4_free(p)
+#else
+# include <stdlib.h>   /* malloc, calloc, free */
+# define ALLOC(s)          malloc(s)
+# define ALLOC_AND_ZERO(s) calloc(1,s)
+# define FREEMEM(p)        free(p)
+#endif
+
+#if ! LZ4_FREESTANDING
+#  include <string.h>   /* memset, memcpy */
+#endif
+#if !defined(LZ4_memset)
+#  define LZ4_memset(p,v,s) memset((p),(v),(s))
+#endif
+#define MEM_INIT(p,v,s)   LZ4_memset((p),(v),(s))
+
+
+/*-************************************
+*  Common Constants
+**************************************/
+#define MINMATCH 4
+
+#define WILDCOPYLENGTH 8
+#define LASTLITERALS   5   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MFLIMIT       12   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MATCH_SAFEGUARD_DISTANCE  ((2*WILDCOPYLENGTH) - MINMATCH)   /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */
+#define FASTLOOP_SAFE_DISTANCE 64
+static const int LZ4_minLength = (MFLIMIT+1);
+
+#define KB *(1 <<10)
+#define MB *(1 <<20)
+#define GB *(1U<<30)
+
+#define LZ4_DISTANCE_ABSOLUTE_MAX 65535
+#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX)   /* max supported by LZ4 format */
+#  error "LZ4_DISTANCE_MAX is too big : must be <= 65535"
+#endif
+
+#define ML_BITS  4
+#define ML_MASK  ((1U<<ML_BITS)-1)
+#define RUN_BITS (8-ML_BITS)
+#define RUN_MASK ((1U<<RUN_BITS)-1)
+
+
+/*-************************************
+*  Error detection
+**************************************/
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)
+#  include <assert.h>
+#else
+#  ifndef assert
+#    define assert(condition) ((void)0)
+#  endif
+#endif
+
+#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use after variable declarations */
+
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
+#  include <stdio.h>
+   static int g_debuglog_enable = 1;
+#  define DEBUGLOG(l, ...) {                          \
+        if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) {  \
+            fprintf(stderr, __FILE__ ": ");           \
+            fprintf(stderr, __VA_ARGS__);             \
+            fprintf(stderr, " \n");                   \
+    }   }
+#else
+#  define DEBUGLOG(l, ...) {}    /* disabled */
+#endif
+
+static int LZ4_isAligned(const void* ptr, size_t alignment)
+{
+    return ((size_t)ptr & (alignment -1)) == 0;
+}
 
 
 /*-************************************
-*  Basic Types
+*  Types
 **************************************/
+#include <limits.h>
 #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
 # include <stdint.h>
   typedef  uint8_t BYTE;
@@ -172,6 +306,9 @@
   typedef uint64_t U64;
   typedef uintptr_t uptrval;
 #else
+# if UINT_MAX != 4294967295UL
+#   error "LZ4 code (when not C++ or C99) assumes that sizeof(int) == 4"
+# endif
   typedef unsigned char       BYTE;
   typedef unsigned short      U16;
   typedef unsigned int        U32;
@@ -186,9 +323,41 @@
   typedef size_t reg_t;   /* 32-bits in x32 mode */
 #endif
 
+typedef enum {
+    notLimited = 0,
+    limitedOutput = 1,
+    fillOutput = 2
+} limitedOutput_directive;
+
+
 /*-************************************
 *  Reading and writing into memory
 **************************************/
+
+/**
+ * LZ4 relies on memcpy with a constant size being inlined. In freestanding
+ * environments, the compiler can't assume the implementation of memcpy() is
+ * standard compliant, so it can't apply its specialized memcpy() inlining
+ * logic. When possible, use __builtin_memcpy() to tell the compiler to analyze
+ * memcpy() as if it were standard compliant, so it can inline it in freestanding
+ * environments. This is needed when decompressing the Linux Kernel, for example.
+ */
+#if !defined(LZ4_memcpy)
+#  if defined(__GNUC__) && (__GNUC__ >= 4)
+#    define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
+#  else
+#    define LZ4_memcpy(dst, src, size) memcpy(dst, src, size)
+#  endif
+#endif
+
+#if !defined(LZ4_memmove)
+#  if defined(__GNUC__) && (__GNUC__ >= 4)
+#    define LZ4_memmove __builtin_memmove
+#  else
+#    define LZ4_memmove memmove
+#  endif
+#endif
+
 static unsigned LZ4_isLittleEndian(void)
 {
     const union { U32 u; BYTE c[4]; } one = { 1 };   /* don't use static : performance detrimental */
@@ -210,40 +379,40 @@ static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
 
 /* __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;
+typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) LZ4_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 U16 LZ4_read16(const void* ptr) { return ((const LZ4_unalign*)ptr)->u16; }
+static U32 LZ4_read32(const void* ptr) { return ((const LZ4_unalign*)ptr)->u32; }
+static reg_t LZ4_read_ARCH(const void* ptr) { return ((const LZ4_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; }
+static void LZ4_write16(void* memPtr, U16 value) { ((LZ4_unalign*)memPtr)->u16 = value; }
+static void LZ4_write32(void* memPtr, U32 value) { ((LZ4_unalign*)memPtr)->u32 = value; }
 
-#else  /* safe and portable access through memcpy() */
+#else  /* safe and portable access using memcpy() */
 
 static U16 LZ4_read16(const void* memPtr)
 {
-    U16 val; memcpy(&val, memPtr, sizeof(val)); return val;
+    U16 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
 }
 
 static U32 LZ4_read32(const void* memPtr)
 {
-    U32 val; memcpy(&val, memPtr, sizeof(val)); return val;
+    U32 val; LZ4_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;
+    reg_t val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val;
 }
 
 static void LZ4_write16(void* memPtr, U16 value)
 {
-    memcpy(memPtr, &value, sizeof(value));
+    LZ4_memcpy(memPtr, &value, sizeof(value));
 }
 
 static void LZ4_write32(void* memPtr, U32 value)
 {
-    memcpy(memPtr, &value, sizeof(value));
+    LZ4_memcpy(memPtr, &value, sizeof(value));
 }
 
 #endif /* LZ4_FORCE_MEMORY_ACCESS */
@@ -270,70 +439,116 @@ static void LZ4_writeLE16(void* memPtr, U16 value)
     }
 }
 
-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 */
-LZ4_FORCE_O2_INLINE_GCC_PPC64LE
-void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
+LZ4_FORCE_INLINE
+void LZ4_wildCopy8(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);
+    do { LZ4_memcpy(d,s,8); d+=8; s+=8; } while (d<e);
 }
 
+static const unsigned inc32table[8] = {0, 1, 2,  1,  0,  4, 4, 4};
+static const int      dec64table[8] = {0, 0, 0, -1, -4,  1, 2, 3};
 
-/*-************************************
-*  Common Constants
-**************************************/
-#define MINMATCH 4
 
-#define WILDCOPYLENGTH 8
-#define LASTLITERALS 5
-#define MFLIMIT (WILDCOPYLENGTH+MINMATCH)
-static const int LZ4_minLength = (MFLIMIT+1);
+#ifndef LZ4_FAST_DEC_LOOP
+#  if defined __i386__ || defined _M_IX86 || defined __x86_64__ || defined _M_X64
+#    define LZ4_FAST_DEC_LOOP 1
+#  elif defined(__aarch64__) && defined(__APPLE__)
+#    define LZ4_FAST_DEC_LOOP 1
+#  elif defined(__aarch64__) && !defined(__clang__)
+     /* On non-Apple aarch64, we disable this optimization for clang because
+      * on certain mobile chipsets, performance is reduced with clang. For
+      * more information refer to https://github.com/lz4/lz4/pull/707 */
+#    define LZ4_FAST_DEC_LOOP 1
+#  else
+#    define LZ4_FAST_DEC_LOOP 0
+#  endif
+#endif
 
-#define KB *(1 <<10)
-#define MB *(1 <<20)
-#define GB *(1U<<30)
+#if LZ4_FAST_DEC_LOOP
 
-#define MAXD_LOG 16
-#define MAX_DISTANCE ((1 << MAXD_LOG) - 1)
+LZ4_FORCE_INLINE void
+LZ4_memcpy_using_offset_base(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
+{
+    assert(srcPtr + offset == dstPtr);
+    if (offset < 8) {
+        LZ4_write32(dstPtr, 0);   /* silence an msan warning when offset==0 */
+        dstPtr[0] = srcPtr[0];
+        dstPtr[1] = srcPtr[1];
+        dstPtr[2] = srcPtr[2];
+        dstPtr[3] = srcPtr[3];
+        srcPtr += inc32table[offset];
+        LZ4_memcpy(dstPtr+4, srcPtr, 4);
+        srcPtr -= dec64table[offset];
+        dstPtr += 8;
+    } else {
+        LZ4_memcpy(dstPtr, srcPtr, 8);
+        dstPtr += 8;
+        srcPtr += 8;
+    }
 
-#define ML_BITS  4
-#define ML_MASK  ((1U<<ML_BITS)-1)
-#define RUN_BITS (8-ML_BITS)
-#define RUN_MASK ((1U<<RUN_BITS)-1)
+    LZ4_wildCopy8(dstPtr, srcPtr, dstEnd);
+}
 
+/* customized variant of memcpy, which can overwrite up to 32 bytes beyond dstEnd
+ * this version copies two times 16 bytes (instead of one time 32 bytes)
+ * because it must be compatible with offsets >= 16. */
+LZ4_FORCE_INLINE void
+LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd)
+{
+    BYTE* d = (BYTE*)dstPtr;
+    const BYTE* s = (const BYTE*)srcPtr;
+    BYTE* const e = (BYTE*)dstEnd;
 
-/*-************************************
-*  Error detection
-**************************************/
-#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)
-#  include <assert.h>
-#else
-#  ifndef assert
-#    define assert(condition) ((void)0)
-#  endif
-#endif
+    do { LZ4_memcpy(d,s,16); LZ4_memcpy(d+16,s+16,16); d+=32; s+=32; } while (d<e);
+}
+
+/* LZ4_memcpy_using_offset()  presumes :
+ * - dstEnd >= dstPtr + MINMATCH
+ * - there is at least 8 bytes available to write after dstEnd */
+LZ4_FORCE_INLINE void
+LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
+{
+    BYTE v[8];
 
-#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
+    assert(dstEnd >= dstPtr + MINMATCH);
 
-#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
-#  include <stdio.h>
-static int g_debuglog_enable = 1;
-#  define DEBUGLOG(l, ...) {                                  \
-                if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) {  \
-                    fprintf(stderr, __FILE__ ": ");           \
-                    fprintf(stderr, __VA_ARGS__);             \
-                    fprintf(stderr, " \n");                   \
-            }   }
-#else
-#  define DEBUGLOG(l, ...)      {}    /* disabled */
+    switch(offset) {
+    case 1:
+        MEM_INIT(v, *srcPtr, 8);
+        break;
+    case 2:
+        LZ4_memcpy(v, srcPtr, 2);
+        LZ4_memcpy(&v[2], srcPtr, 2);
+#if defined(_MSC_VER) && (_MSC_VER <= 1933) /* MSVC 2022 ver 17.3 or earlier */
+#  pragma warning(push)
+#  pragma warning(disable : 6385) /* warning C6385: Reading invalid data from 'v'. */
+#endif
+        LZ4_memcpy(&v[4], v, 4);
+#if defined(_MSC_VER) && (_MSC_VER <= 1933) /* MSVC 2022 ver 17.3 or earlier */
+#  pragma warning(pop)
+#endif
+        break;
+    case 4:
+        LZ4_memcpy(v, srcPtr, 4);
+        LZ4_memcpy(&v[4], srcPtr, 4);
+        break;
+    default:
+        LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset);
+        return;
+    }
+
+    LZ4_memcpy(dstPtr, v, 8);
+    dstPtr += 8;
+    while (dstPtr < dstEnd) {
+        LZ4_memcpy(dstPtr, v, 8);
+        dstPtr += 8;
+    }
+}
 #endif
 
 
@@ -342,75 +557,103 @@ static int g_debuglog_enable = 1;
 **************************************/
 static unsigned LZ4_NbCommonBytes (reg_t val)
 {
+    assert(val != 0);
     if (LZ4_isLittleEndian()) {
-        if (sizeof(val)==8) {
-#       if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+        if (sizeof(val) == 8) {
+#       if defined(_MSC_VER) && (_MSC_VER >= 1800) && (defined(_M_AMD64) && !defined(_M_ARM64EC)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+/*-*************************************************************************************************
+* ARM64EC is a Microsoft-designed ARM64 ABI compatible with AMD64 applications on ARM64 Windows 11.
+* The ARM64EC ABI does not support AVX/AVX2/AVX512 instructions, nor their relevant intrinsics
+* including _tzcnt_u64. Therefore, we need to neuter the _tzcnt_u64 code path for ARM64EC.
+****************************************************************************************************/
+#         if defined(__clang__) && (__clang_major__ < 10)
+            /* Avoid undefined clang-cl intrinsics issue.
+             * See https://github.com/lz4/lz4/pull/1017 for details. */
+            return (unsigned)__builtin_ia32_tzcnt_u64(val) >> 3;
+#         else
+            /* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */
+            return (unsigned)_tzcnt_u64(val) >> 3;
+#         endif
+#       elif 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);
+            _BitScanForward64(&r, (U64)val);
+            return (unsigned)r >> 3;
+#       elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+                                        !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__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];
+            const U64 m = 0x0101010101010101ULL;
+            val ^= val - 1;
+            return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56);
 #       endif
         } else /* 32 bits */ {
-#       if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT)
+#       if defined(_MSC_VER) && (_MSC_VER >= 1400) && !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);
+            _BitScanForward(&r, (U32)val);
+            return (unsigned)r >> 3;
+#       elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+                        !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__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];
+            const U32 m = 0x01010101;
+            return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24;
 #       endif
         }
     } else   /* Big Endian CPU */ {
-        if (sizeof(val)==8) {   /* 64-bits */
-#       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);
+        if (sizeof(val)==8) {
+#       if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+                        !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__builtin_clzll((U64)val) >> 3;
 #       else
+#if 1
+            /* this method is probably faster,
+             * but adds a 128 bytes lookup table */
+            static const unsigned char ctz7_tab[128] = {
+                7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+                5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+                6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+                5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+                4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0,
+            };
+            U64 const mask = 0x0101010101010101ULL;
+            U64 const t = (((val >> 8) - mask) | val) & mask;
+            return ctz7_tab[(t * 0x0080402010080402ULL) >> 57];
+#else
+            /* this method doesn't consume memory space like the previous one,
+             * but it contains several branches,
+             * that may end up slowing execution */
             static const U32 by32 = sizeof(val)*4;  /* 32 on 64 bits (goal), 16 on 32 bits.
-                Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.
-                Note that this code path is never triggered in 32-bits mode. */
+            Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.
+            Note that this code path is never triggered in 32-bits mode. */
             unsigned r;
             if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; }
             if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; }
             r += (!val);
             return r;
+#endif
 #       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);
+#       if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \
+                            ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \
+                                        !defined(LZ4_FORCE_SW_BITCOUNT)
+            return (unsigned)__builtin_clz((U32)val) >> 3;
 #       else
-            unsigned r;
-            if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
-            r += (!val);
-            return r;
+            val >>= 8;
+            val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) |
+              (val + 0x00FF0000)) >> 24;
+            return (unsigned)val ^ 3;
 #       endif
         }
     }
 }
 
+
 #define STEPSIZE sizeof(reg_t)
 LZ4_FORCE_INLINE
 unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit)
@@ -450,15 +693,34 @@ static const U32 LZ4_skipTrigger = 6;  /* Increase this value ==> compression ru
 /*-************************************
 *  Local Structures and types
 **************************************/
-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 { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;
+
+/**
+ * This enum distinguishes several different modes of accessing previous
+ * content in the stream.
+ *
+ * - noDict        : There is no preceding content.
+ * - withPrefix64k : Table entries up to ctx->dictSize before the current blob
+ *                   blob being compressed are valid and refer to the preceding
+ *                   content (of length ctx->dictSize), which is available
+ *                   contiguously preceding in memory the content currently
+ *                   being compressed.
+ * - usingExtDict  : Like withPrefix64k, but the preceding content is somewhere
+ *                   else in memory, starting at ctx->dictionary with length
+ *                   ctx->dictSize.
+ * - usingDictCtx  : Everything concerning the preceding content is
+ *                   in a separate context, pointed to by ctx->dictCtx.
+ *                   ctx->dictionary, ctx->dictSize, and table entries
+ *                   in the current context that refer to positions
+ *                   preceding the beginning of the current compression are
+ *                   ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx
+ *                   ->dictSize describe the location and size of the preceding
+ *                   content, and matches are found by looking in the ctx
+ *                   ->dictCtx->hashTable.
+ */
+typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive;
 typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
 
-typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
-typedef enum { full = 0, partial = 1 } earlyEnd_directive;
-
 
 /*-************************************
 *  Local Utils
@@ -466,13 +728,32 @@ typedef enum { full = 0, partial = 1 } earlyEnd_directive;
 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; }
+int LZ4_sizeofState(void) { return sizeof(LZ4_stream_t); }
+
 
+/*-****************************************
+*  Internal Definitions, used only in Tests
+*******************************************/
+#if defined (__cplusplus)
+extern "C" {
+#endif
+
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize);
+
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
+                                     int compressedSize, int maxOutputSize,
+                                     const void* dictStart, size_t dictSize);
+int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
+                                     int compressedSize, int targetOutputSize, int dstCapacity,
+                                     const void* dictStart, size_t dictSize);
+#if defined (__cplusplus)
+}
+#endif
 
 /*-******************************
 *  Compression functions
 ********************************/
-static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
+LZ4_FORCE_INLINE U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
 {
     if (tableType == byU16)
         return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
@@ -480,15 +761,16 @@ static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
         return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
 }
 
-static U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
+LZ4_FORCE_INLINE 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())
+    if (LZ4_isLittleEndian()) {
+        const U64 prime5bytes = 889523592379ULL;
         return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog));
-    else
+    } else {
+        const U64 prime8bytes = 11400714785074694791ULL;
         return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog));
+    }
 }
 
 LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
@@ -497,10 +779,37 @@ LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tab
     return LZ4_hash4(LZ4_read32(p), tableType);
 }
 
-static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase)
+LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType)
+{
+    switch (tableType)
+    {
+    default: /* fallthrough */
+    case clearedTable: { /* illegal! */ assert(0); return; }
+    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; }
+    }
+}
+
+LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
+{
+    switch (tableType)
+    {
+    default: /* fallthrough */
+    case clearedTable: /* fallthrough */
+    case byPtr: { /* illegal! */ assert(0); return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }
+    }
+}
+
+LZ4_FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h,
+                                  void* tableBase, tableType_t const tableType,
+                            const BYTE* srcBase)
 {
     switch (tableType)
     {
+    case clearedTable: { /* illegal! */ assert(0); return; }
     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; }
@@ -513,71 +822,163 @@ LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_
     LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
 }
 
-static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+/* LZ4_getIndexOnHash() :
+ * Index of match position registered in hash table.
+ * hash position must be calculated by using base+index, or dictBase+index.
+ * Assumption 1 : only valid if tableType == byU32 or byU16.
+ * Assumption 2 : h is presumed valid (within limits of hash table)
+ */
+LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
+{
+    LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
+    if (tableType == byU32) {
+        const U32* const hashTable = (const U32*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-2)));
+        return hashTable[h];
+    }
+    if (tableType == byU16) {
+        const U16* const hashTable = (const U16*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-1)));
+        return hashTable[h];
+    }
+    assert(0); return 0;  /* forbidden case */
+}
+
+static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase)
 {
-    if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }
-    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 */
+    if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; }
+    if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; }
+    { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
 }
 
-LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+LZ4_FORCE_INLINE const BYTE*
+LZ4_getPosition(const BYTE* p,
+                const void* tableBase, tableType_t tableType,
+                const BYTE* srcBase)
 {
     U32 const h = LZ4_hashPosition(p, tableType);
     return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
 }
 
+LZ4_FORCE_INLINE void
+LZ4_prepareTable(LZ4_stream_t_internal* const cctx,
+           const int inputSize,
+           const tableType_t tableType) {
+    /* If the table hasn't been used, it's guaranteed to be zeroed out, and is
+     * therefore safe to use no matter what mode we're in. Otherwise, we figure
+     * out if it's safe to leave as is or whether it needs to be reset.
+     */
+    if ((tableType_t)cctx->tableType != clearedTable) {
+        assert(inputSize >= 0);
+        if ((tableType_t)cctx->tableType != tableType
+          || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU)
+          || ((tableType == byU32) && cctx->currentOffset > 1 GB)
+          || tableType == byPtr
+          || inputSize >= 4 KB)
+        {
+            DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx);
+            MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
+            cctx->currentOffset = 0;
+            cctx->tableType = (U32)clearedTable;
+        } else {
+            DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");
+        }
+    }
+
+    /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back,
+     * is faster than compressing without a gap.
+     * However, compressing with currentOffset == 0 is faster still,
+     * so we preserve that case.
+     */
+    if (cctx->currentOffset != 0 && tableType == byU32) {
+        DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
+        cctx->currentOffset += 64 KB;
+    }
+
+    /* Finally, clear history */
+    cctx->dictCtx = NULL;
+    cctx->dictionary = NULL;
+    cctx->dictSize = 0;
+}
 
 /** LZ4_compress_generic() :
-    inlined, to ensure branches are decided at compilation time */
-LZ4_FORCE_INLINE int LZ4_compress_generic(
+ *  inlined, to ensure branches are decided at compilation time.
+ *  Presumed already validated at this stage:
+ *  - source != NULL
+ *  - inputSize > 0
+ */
+LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
                  LZ4_stream_t_internal* const cctx,
                  const char* const source,
                  char* const dest,
                  const int inputSize,
+                 int*  inputConsumed, /* only written when outputDirective == fillOutput */
                  const int maxOutputSize,
-                 const limitedOutput_directive outputLimited,
+                 const limitedOutput_directive outputDirective,
                  const tableType_t tableType,
-                 const dict_directive dict,
+                 const dict_directive dictDirective,
                  const dictIssue_directive dictIssue,
-                 const U32 acceleration)
+                 const int acceleration)
 {
+    int result;
     const BYTE* ip = (const BYTE*) source;
-    const BYTE* base;
+
+    U32 const startIndex = cctx->currentOffset;
+    const BYTE* base = (const BYTE*) source - startIndex;
     const BYTE* lowLimit;
-    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 LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;
+    const BYTE* const dictionary =
+        dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;
+    const U32 dictSize =
+        dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;
+    const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0;   /* make indexes in dictCtx comparable with index in current context */
+
+    int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);
+    U32 const prefixIdxLimit = startIndex - dictSize;   /* used when dictDirective == dictSmall */
+    const BYTE* const dictEnd = dictionary ? dictionary + dictSize : dictionary;
     const BYTE* anchor = (const BYTE*) source;
     const BYTE* const iend = ip + inputSize;
-    const BYTE* const mflimit = iend - MFLIMIT;
+    const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1;
     const BYTE* const matchlimit = iend - LASTLITERALS;
 
+    /* the dictCtx currentOffset is indexed on the start of the dictionary,
+     * while a dictionary in the current context precedes the currentOffset */
+    const BYTE* dictBase = (dictionary == NULL) ? NULL :
+                           (dictDirective == usingDictCtx) ?
+                            dictionary + dictSize - dictCtx->currentOffset :
+                            dictionary + dictSize - startIndex;
+
     BYTE* op = (BYTE*) dest;
     BYTE* const olimit = op + maxOutputSize;
 
+    U32 offset = 0;
     U32 forwardH;
 
-    /* Init conditions */
-    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;   /* Unsupported inputSize, too large (or negative) */
-    switch(dict)
-    {
-    case noDict:
-    default:
-        base = (const BYTE*)source;
-        lowLimit = (const BYTE*)source;
-        break;
-    case withPrefix64k:
-        base = (const BYTE*)source - cctx->currentOffset;
-        lowLimit = (const BYTE*)source - cctx->dictSize;
-        break;
-    case usingExtDict:
-        base = (const BYTE*)source - cctx->currentOffset;
-        lowLimit = (const BYTE*)source;
-        break;
+    DEBUGLOG(5, "LZ4_compress_generic_validated: srcSize=%i, tableType=%u", inputSize, tableType);
+    assert(ip != NULL);
+    /* If init conditions are not met, we don't have to mark stream
+     * as having dirty context, since no action was taken yet */
+    if (outputDirective == fillOutput && maxOutputSize < 1) { return 0; } /* Impossible to store anything */
+    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) { return 0; }  /* Size too large (not within 64K limit) */
+    if (tableType==byPtr) assert(dictDirective==noDict);      /* only supported use case with byPtr */
+    assert(acceleration >= 1);
+
+    lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0);
+
+    /* Update context state */
+    if (dictDirective == usingDictCtx) {
+        /* Subsequent linked blocks can't use the dictionary. */
+        /* Instead, they use the block we just compressed. */
+        cctx->dictCtx = NULL;
+        cctx->dictSize = (U32)inputSize;
+    } else {
+        cctx->dictSize += (U32)inputSize;
     }
-    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) */
+    cctx->currentOffset += (U32)inputSize;
+    cctx->tableType = (U32)tableType;
+
+    if (inputSize<LZ4_minLength) goto _last_literals;        /* Input too small, no compression (all literals) */
 
     /* First Byte */
     LZ4_putPosition(ip, cctx->hashTable, tableType, base);
@@ -585,50 +986,113 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
 
     /* Main Loop */
     for ( ; ; ) {
-        ptrdiff_t refDelta = 0;
         const BYTE* match;
         BYTE* token;
+        const BYTE* filledIp;
 
         /* Find a match */
-        {   const BYTE* forwardIp = ip;
-            unsigned step = 1;
-            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
+        if (tableType == byPtr) {
+            const BYTE* forwardIp = ip;
+            int step = 1;
+            int searchMatchNb = acceleration << LZ4_skipTrigger;
             do {
                 U32 const h = forwardH;
                 ip = forwardIp;
                 forwardIp += step;
                 step = (searchMatchNb++ >> LZ4_skipTrigger);
 
-                if (unlikely(forwardIp > mflimit)) goto _last_literals;
+                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+                assert(ip < mflimitPlusOne);
 
                 match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
-                if (dict==usingExtDict) {
-                    if (match < (const BYTE*)source) {
-                        refDelta = dictDelta;
+                forwardH = LZ4_hashPosition(forwardIp, tableType);
+                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
+
+            } while ( (match+LZ4_DISTANCE_MAX < ip)
+                   || (LZ4_read32(match) != LZ4_read32(ip)) );
+
+        } else {   /* byU32, byU16 */
+
+            const BYTE* forwardIp = ip;
+            int step = 1;
+            int searchMatchNb = acceleration << LZ4_skipTrigger;
+            do {
+                U32 const h = forwardH;
+                U32 const current = (U32)(forwardIp - base);
+                U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+                assert(matchIndex <= current);
+                assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));
+                ip = forwardIp;
+                forwardIp += step;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+                assert(ip < mflimitPlusOne);
+
+                if (dictDirective == usingDictCtx) {
+                    if (matchIndex < startIndex) {
+                        /* there was no match, try the dictionary */
+                        assert(tableType == byU32);
+                        matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                        match = dictBase + matchIndex;
+                        matchIndex += dictDelta;   /* make dictCtx index comparable with current context */
                         lowLimit = dictionary;
                     } else {
-                        refDelta = 0;
+                        match = base + matchIndex;
                         lowLimit = (const BYTE*)source;
-                }   }
+                    }
+                } else if (dictDirective == usingExtDict) {
+                    if (matchIndex < startIndex) {
+                        DEBUGLOG(7, "extDict candidate: matchIndex=%5u  <  startIndex=%5u", matchIndex, startIndex);
+                        assert(startIndex - matchIndex >= MINMATCH);
+                        assert(dictBase);
+                        match = dictBase + matchIndex;
+                        lowLimit = dictionary;
+                    } else {
+                        match = base + matchIndex;
+                        lowLimit = (const BYTE*)source;
+                    }
+                } else {   /* single continuous memory segment */
+                    match = base + matchIndex;
+                }
                 forwardH = LZ4_hashPosition(forwardIp, tableType);
-                LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
+                LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+
+                DEBUGLOG(7, "candidate at pos=%u  (offset=%u \n", matchIndex, current - matchIndex);
+                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; }    /* match outside of valid area */
+                assert(matchIndex < current);
+                if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX))
+                  && (matchIndex+LZ4_DISTANCE_MAX < current)) {
+                    continue;
+                } /* too far */
+                assert((current - matchIndex) <= LZ4_DISTANCE_MAX);  /* match now expected within distance */
+
+                if (LZ4_read32(match) == LZ4_read32(ip)) {
+                    if (maybe_extMem) offset = current - matchIndex;
+                    break;   /* match found */
+                }
 
-            } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
-                || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
-                || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
+            } while(1);
         }
 
         /* Catch up */
-        while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
+        filledIp = ip;
+        while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
 
         /* Encode Literals */
         {   unsigned const litLength = (unsigned)(ip - anchor);
             token = op++;
-            if ((outputLimited) &&  /* Check output buffer overflow */
-                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
-                return 0;
+            if ((outputDirective == limitedOutput) &&  /* Check output buffer overflow */
+                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) {
+                return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+            }
+            if ((outputDirective == fillOutput) &&
+                (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) {
+                op--;
+                goto _last_literals;
+            }
             if (litLength >= RUN_MASK) {
-                int len = (int)litLength-RUN_MASK;
+                int len = (int)(litLength - RUN_MASK);
                 *token = (RUN_MASK<<ML_BITS);
                 for(; len >= 255 ; len-=255) *op++ = 255;
                 *op++ = (BYTE)len;
@@ -636,37 +1100,87 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
             else *token = (BYTE)(litLength<<ML_BITS);
 
             /* Copy Literals */
-            LZ4_wildCopy(op, anchor, op+litLength);
+            LZ4_wildCopy8(op, anchor, op+litLength);
             op+=litLength;
+            DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                        (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source));
         }
 
 _next_match:
+        /* at this stage, the following variables must be correctly set :
+         * - ip : at start of LZ operation
+         * - match : at start of previous pattern occurrence; can be within current prefix, or within extDict
+         * - offset : if maybe_ext_memSegment==1 (constant)
+         * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise
+         * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written
+         */
+
+        if ((outputDirective == fillOutput) &&
+            (op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) {
+            /* the match was too close to the end, rewind and go to last literals */
+            op = token;
+            goto _last_literals;
+        }
+
         /* Encode Offset */
-        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+        if (maybe_extMem) {   /* static test */
+            DEBUGLOG(6, "             with offset=%u  (ext if > %i)", offset, (int)(ip - (const BYTE*)source));
+            assert(offset <= LZ4_DISTANCE_MAX && offset > 0);
+            LZ4_writeLE16(op, (U16)offset); op+=2;
+        } else  {
+            DEBUGLOG(6, "             with offset=%u  (same segment)", (U32)(ip - match));
+            assert(ip-match <= LZ4_DISTANCE_MAX);
+            LZ4_writeLE16(op, (U16)(ip - match)); op+=2;
+        }
 
         /* Encode MatchLength */
         {   unsigned matchCode;
 
-            if ((dict==usingExtDict) && (lowLimit==dictionary)) {
-                const BYTE* limit;
-                match += refDelta;
-                limit = ip + (dictEnd-match);
+            if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)
+              && (lowLimit==dictionary) /* match within extDict */ ) {
+                const BYTE* limit = ip + (dictEnd-match);
+                assert(dictEnd > match);
                 if (limit > matchlimit) limit = matchlimit;
                 matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
-                ip += MINMATCH + matchCode;
+                ip += (size_t)matchCode + MINMATCH;
                 if (ip==limit) {
-                    unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+                    unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);
                     matchCode += more;
                     ip += more;
                 }
+                DEBUGLOG(6, "             with matchLength=%u starting in extDict", matchCode+MINMATCH);
             } else {
                 matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
-                ip += MINMATCH + matchCode;
+                ip += (size_t)matchCode + MINMATCH;
+                DEBUGLOG(6, "             with matchLength=%u", matchCode+MINMATCH);
             }
 
-            if ( outputLimited &&    /* Check output buffer overflow */
-                (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
-                return 0;
+            if ((outputDirective) &&    /* Check output buffer overflow */
+                (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) {
+                if (outputDirective == fillOutput) {
+                    /* Match description too long : reduce it */
+                    U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255;
+                    ip -= matchCode - newMatchCode;
+                    assert(newMatchCode < matchCode);
+                    matchCode = newMatchCode;
+                    if (unlikely(ip <= filledIp)) {
+                        /* We have already filled up to filledIp so if ip ends up less than filledIp
+                         * we have positions in the hash table beyond the current position. This is
+                         * a problem if we reuse the hash table. So we have to remove these positions
+                         * from the hash table.
+                         */
+                        const BYTE* ptr;
+                        DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip));
+                        for (ptr = ip; ptr <= filledIp; ++ptr) {
+                            U32 const h = LZ4_hashPosition(ptr, tableType);
+                            LZ4_clearHash(h, cctx->hashTable, tableType);
+                        }
+                    }
+                } else {
+                    assert(outputDirective == limitedOutput);
+                    return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+                }
+            }
             if (matchCode >= ML_MASK) {
                 *token += ML_MASK;
                 matchCode -= ML_MASK;
@@ -681,41 +1195,90 @@ _next_match:
             } else
                 *token += (BYTE)(matchCode);
         }
+        /* Ensure we have enough space for the last literals. */
+        assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit));
 
         anchor = ip;
 
         /* Test end of chunk */
-        if (ip > mflimit) break;
+        if (ip >= mflimitPlusOne) break;
 
         /* Fill table */
         LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
 
         /* Test next position */
-        match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
-        if (dict==usingExtDict) {
-            if (match < (const BYTE*)source) {
-                refDelta = dictDelta;
-                lowLimit = dictionary;
-            } else {
-                refDelta = 0;
-                lowLimit = (const BYTE*)source;
-        }   }
-        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; }
+        if (tableType == byPtr) {
+
+            match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
+            LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+            if ( (match+LZ4_DISTANCE_MAX >= ip)
+              && (LZ4_read32(match) == LZ4_read32(ip)) )
+            { token=op++; *token=0; goto _next_match; }
+
+        } else {   /* byU32, byU16 */
+
+            U32 const h = LZ4_hashPosition(ip, tableType);
+            U32 const current = (U32)(ip-base);
+            U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+            assert(matchIndex < current);
+            if (dictDirective == usingDictCtx) {
+                if (matchIndex < startIndex) {
+                    /* there was no match, try the dictionary */
+                    matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                    matchIndex += dictDelta;
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;  /* required for match length counter */
+                }
+            } else if (dictDirective==usingExtDict) {
+                if (matchIndex < startIndex) {
+                    assert(dictBase);
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;   /* required for match length counter */
+                }
+            } else {   /* single memory segment */
+                match = base + matchIndex;
+            }
+            LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+            assert(matchIndex < current);
+            if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
+              && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current))
+              && (LZ4_read32(match) == LZ4_read32(ip)) ) {
+                token=op++;
+                *token=0;
+                if (maybe_extMem) offset = current - matchIndex;
+                DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                            (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
+                goto _next_match;
+            }
+        }
 
         /* Prepare next loop */
         forwardH = LZ4_hashPosition(++ip, tableType);
+
     }
 
 _last_literals:
     /* Encode Last Literals */
-    {   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;
+    {   size_t lastRun = (size_t)(iend - anchor);
+        if ( (outputDirective) &&  /* Check output buffer overflow */
+            (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) {
+            if (outputDirective == fillOutput) {
+                /* adapt lastRun to fill 'dst' */
+                assert(olimit >= op);
+                lastRun  = (size_t)(olimit-op) - 1/*token*/;
+                lastRun -= (lastRun + 256 - RUN_MASK) / 256;  /*additional length tokens*/
+            } else {
+                assert(outputDirective == limitedOutput);
+                return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
+            }
+        }
+        DEBUGLOG(6, "Final literal run : %i literals", (int)lastRun);
         if (lastRun >= RUN_MASK) {
             size_t accumulator = lastRun - RUN_MASK;
             *op++ = RUN_MASK << ML_BITS;
@@ -724,45 +1287,143 @@ _last_literals:
         } else {
             *op++ = (BYTE)(lastRun<<ML_BITS);
         }
-        memcpy(op, anchor, lastRun);
+        LZ4_memcpy(op, anchor, lastRun);
+        ip = anchor + lastRun;
         op += lastRun;
     }
 
-    /* End */
-    return (int) (((char*)op)-dest);
+    if (outputDirective == fillOutput) {
+        *inputConsumed = (int) (((const char*)ip)-source);
+    }
+    result = (int)(((char*)op) - dest);
+    assert(result > 0);
+    DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, result);
+    return result;
 }
 
-
-int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+/** LZ4_compress_generic() :
+ *  inlined, to ensure branches are decided at compilation time;
+ *  takes care of src == (NULL, 0)
+ *  and forward the rest to LZ4_compress_generic_validated */
+LZ4_FORCE_INLINE int LZ4_compress_generic(
+                 LZ4_stream_t_internal* const cctx,
+                 const char* const src,
+                 char* const dst,
+                 const int srcSize,
+                 int *inputConsumed, /* only written when outputDirective == fillOutput */
+                 const int dstCapacity,
+                 const limitedOutput_directive outputDirective,
+                 const tableType_t tableType,
+                 const dict_directive dictDirective,
+                 const dictIssue_directive dictIssue,
+                 const int acceleration)
 {
-    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);
+    DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, dstCapacity=%i",
+                srcSize, dstCapacity);
+
+    if ((U32)srcSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; }  /* Unsupported srcSize, too large (or negative) */
+    if (srcSize == 0) {   /* src == NULL supported if srcSize == 0 */
+        if (outputDirective != notLimited && dstCapacity <= 0) return 0;  /* no output, can't write anything */
+        DEBUGLOG(5, "Generating an empty block");
+        assert(outputDirective == notLimited || dstCapacity >= 1);
+        assert(dst != NULL);
+        dst[0] = 0;
+        if (outputDirective == fillOutput) {
+            assert (inputConsumed != NULL);
+            *inputConsumed = 0;
+        }
+        return 1;
+    }
+    assert(src != NULL);
+
+    return LZ4_compress_generic_validated(cctx, src, dst, srcSize,
+                inputConsumed, /* only written into if outputDirective == fillOutput */
+                dstCapacity, outputDirective,
+                tableType, dictDirective, dictIssue, acceleration);
+}
+
+
+int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+{
+    LZ4_stream_t_internal* const ctx = & LZ4_initStream(state, sizeof(LZ4_stream_t)) -> internal_donotuse;
+    assert(ctx != NULL);
+    if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
+    if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
+    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
+        if (inputSize < LZ4_64Klimit) {
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+        }
+    } else {
+        if (inputSize < LZ4_64Klimit) {
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+        }
+    }
+}
+
+/**
+ * LZ4_compress_fast_extState_fastReset() :
+ * A variant of LZ4_compress_fast_extState().
+ *
+ * Using this variant avoids an expensive initialization step. It is only safe
+ * to call if the state buffer is known to be correctly initialized already
+ * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of
+ * "correctly initialized").
+ */
+int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration)
+{
+    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
+    if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
+    if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
+
+    if (dstCapacity >= LZ4_compressBound(srcSize)) {
+        if (srcSize < LZ4_64Klimit) {
+            const tableType_t tableType = byU16;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            if (ctx->currentOffset) {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration);
+            } else {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+            }
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+        }
+    } else {
+        if (srcSize < LZ4_64Klimit) {
+            const tableType_t tableType = byU16;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            if (ctx->currentOffset) {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration);
+            } else {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+            }
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+        }
     }
 }
 
 
 int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
+    int result;
 #if (LZ4_HEAPMODE)
-    void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    LZ4_stream_t* ctxPtr = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    if (ctxPtr == NULL) return 0;
 #else
     LZ4_stream_t ctx;
-    void* const ctxPtr = &ctx;
+    LZ4_stream_t* const ctxPtr = &ctx;
 #endif
-
-    int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
+    result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
 
 #if (LZ4_HEAPMODE)
     FREEMEM(ctxPtr);
@@ -771,205 +1432,37 @@ int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutp
 }
 
 
-int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize)
-{
-    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)
+int LZ4_compress_default(const char* src, char* dst, int srcSize, int maxOutputSize)
 {
-    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);
+    return LZ4_compress_fast(src, dst, srcSize, maxOutputSize, 1);
 }
 
 
+/* Note!: This function leaves the stream in an unclean/broken state!
+ * It is not safe to subsequently use the same state with a _fastReset() or
+ * _continue() call without resetting it. */
 static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
 {
-    LZ4_resetStream(state);
+    void* const s = LZ4_initStream(state, sizeof (*state));
+    assert(s != NULL); (void)s;
 
     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);
-    }
+        if (*srcSizePtr < LZ4_64Klimit) {
+            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1);
+        } else {
+            tableType_t const addrMode = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
+            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, 1);
+    }   }
 }
 
 
 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 */
+    LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    if (ctx == NULL) return 0;
 #else
     LZ4_stream_t ctxBody;
     LZ4_stream_t* ctx = &ctxBody;
@@ -989,69 +1482,142 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe
 *  Streaming functions
 ********************************/
 
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
 LZ4_stream_t* LZ4_createStream(void)
 {
-    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);
+    LZ4_stream_t* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
+    LZ4_STATIC_ASSERT(sizeof(LZ4_stream_t) >= sizeof(LZ4_stream_t_internal));
+    DEBUGLOG(4, "LZ4_createStream %p", lz4s);
+    if (lz4s == NULL) return NULL;
+    LZ4_initStream(lz4s, sizeof(*lz4s));
     return lz4s;
 }
+#endif
 
+static size_t LZ4_stream_t_alignment(void)
+{
+#if LZ4_ALIGN_TEST
+    typedef struct { char c; LZ4_stream_t t; } t_a;
+    return sizeof(t_a) - sizeof(LZ4_stream_t);
+#else
+    return 1;  /* effectively disabled */
+#endif
+}
+
+LZ4_stream_t* LZ4_initStream (void* buffer, size_t size)
+{
+    DEBUGLOG(5, "LZ4_initStream");
+    if (buffer == NULL) { return NULL; }
+    if (size < sizeof(LZ4_stream_t)) { return NULL; }
+    if (!LZ4_isAligned(buffer, LZ4_stream_t_alignment())) return NULL;
+    MEM_INIT(buffer, 0, sizeof(LZ4_stream_t_internal));
+    return (LZ4_stream_t*)buffer;
+}
+
+/* resetStream is now deprecated,
+ * prefer initStream() which is more general */
 void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
 {
-    DEBUGLOG(4, "LZ4_resetStream");
-    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
+    DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream);
+    MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t_internal));
 }
 
+void LZ4_resetStream_fast(LZ4_stream_t* ctx) {
+    LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
+}
+
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
 int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
 {
     if (!LZ4_stream) return 0;   /* support free on NULL */
+    DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream);
     FREEMEM(LZ4_stream);
     return (0);
 }
+#endif
 
 
 #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_dict->internal_donotuse;
+    const tableType_t tableType = byU32;
     const BYTE* p = (const BYTE*)dictionary;
     const BYTE* const dictEnd = p + dictSize;
     const BYTE* base;
 
-    if ((dict->initCheck) || (dict->currentOffset > 1 GB))  /* Uninitialized structure, or reuse overflow */
-        LZ4_resetStream(LZ4_dict);
+    DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict);
+
+    /* It's necessary to reset the context,
+     * and not just continue it with prepareTable()
+     * to avoid any risk of generating overflowing matchIndex
+     * when compressing using this dictionary */
+    LZ4_resetStream(LZ4_dict);
+
+    /* We always increment the offset by 64 KB, since, if the dict is longer,
+     * we truncate it to the last 64k, and if it's shorter, we still want to
+     * advance by a whole window length so we can provide the guarantee that
+     * there are only valid offsets in the window, which allows an optimization
+     * in LZ4_compress_fast_continue() where it uses noDictIssue even when the
+     * dictionary isn't a full 64k. */
+    dict->currentOffset += 64 KB;
 
     if (dictSize < (int)HASH_UNIT) {
-        dict->dictionary = NULL;
-        dict->dictSize = 0;
         return 0;
     }
 
     if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
-    dict->currentOffset += 64 KB;
-    base = p - dict->currentOffset;
+    base = dictEnd - dict->currentOffset;
     dict->dictionary = p;
     dict->dictSize = (U32)(dictEnd - p);
-    dict->currentOffset += dict->dictSize;
+    dict->tableType = (U32)tableType;
 
     while (p <= dictEnd-HASH_UNIT) {
-        LZ4_putPosition(p, dict->hashTable, byU32, base);
+        LZ4_putPosition(p, dict->hashTable, tableType, base);
         p+=3;
     }
 
-    return dict->dictSize;
+    return (int)dict->dictSize;
+}
+
+void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream)
+{
+    const LZ4_stream_t_internal* dictCtx = (dictionaryStream == NULL) ? NULL :
+        &(dictionaryStream->internal_donotuse);
+
+    DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)",
+             workingStream, dictionaryStream,
+             dictCtx != NULL ? dictCtx->dictSize : 0);
+
+    if (dictCtx != NULL) {
+        /* If the current offset is zero, we will never look in the
+         * external dictionary context, since there is no value a table
+         * entry can take that indicate a miss. In that case, we need
+         * to bump the offset to something non-zero.
+         */
+        if (workingStream->internal_donotuse.currentOffset == 0) {
+            workingStream->internal_donotuse.currentOffset = 64 KB;
+        }
+
+        /* Don't actually attach an empty dictionary.
+         */
+        if (dictCtx->dictSize == 0) {
+            dictCtx = NULL;
+        }
+    }
+    workingStream->internal_donotuse.dictCtx = dictCtx;
 }
 
 
-static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
+static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize)
 {
-    if ((LZ4_dict->currentOffset > 0x80000000) ||
-        ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) {   /* address space overflow */
+    assert(nextSize >= 0);
+    if (LZ4_dict->currentOffset + (unsigned)nextSize > 0x80000000) {   /* potential ptrdiff_t overflow (32-bits mode) */
         /* rescale hash table */
         U32 const delta = LZ4_dict->currentOffset - 64 KB;
         const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
         int i;
+        DEBUGLOG(4, "LZ4_renormDictT");
         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;
@@ -1063,69 +1629,101 @@ static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
 }
 
 
-int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
+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->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;
+    const tableType_t tableType = byU32;
+    LZ4_stream_t_internal* const streamPtr = &LZ4_stream->internal_donotuse;
+    const char* dictEnd = streamPtr->dictSize ? (const char*)streamPtr->dictionary + streamPtr->dictSize : NULL;
+
+    DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i, dictSize=%u)", inputSize, streamPtr->dictSize);
+
+    LZ4_renormDictT(streamPtr, inputSize);   /* fix index overflow */
+    if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
+    if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
+
+    /* invalidate tiny dictionaries */
+    if ( (streamPtr->dictSize < 4)     /* tiny dictionary : not enough for a hash */
+      && (dictEnd != source)           /* prefix mode */
+      && (inputSize > 0)               /* tolerance : don't lose history, in case next invocation would use prefix mode */
+      && (streamPtr->dictCtx == NULL)  /* usingDictCtx */
+      ) {
+        DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary);
+        /* remove dictionary existence from history, to employ faster prefix mode */
+        streamPtr->dictSize = 0;
+        streamPtr->dictionary = (const BYTE*)source;
+        dictEnd = source;
+    }
 
     /* Check overlapping input/dictionary space */
-    {   const BYTE* sourceEnd = (const BYTE*) source + inputSize;
-        if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) {
+    {   const char* const sourceEnd = source + inputSize;
+        if ((sourceEnd > (const char*)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;
-            streamPtr->dictionary = dictEnd - streamPtr->dictSize;
+            streamPtr->dictionary = (const BYTE*)dictEnd - streamPtr->dictSize;
         }
     }
 
     /* prefix mode : source data follows dictionary */
-    if (dictEnd == (const BYTE*)source) {
-        int result;
+    if (dictEnd == source) {
         if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration);
+            return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
         else
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration);
-        streamPtr->dictSize += (U32)inputSize;
-        streamPtr->currentOffset += (U32)inputSize;
-        return result;
+            return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration);
     }
 
     /* external dictionary mode */
     {   int result;
-        if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration);
-        else
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration);
+        if (streamPtr->dictCtx) {
+            /* We depend here on the fact that dictCtx'es (produced by
+             * LZ4_loadDict) guarantee that their tables contain no references
+             * to offsets between dictCtx->currentOffset - 64 KB and
+             * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe
+             * to use noDictIssue even when the dict isn't a full 64 KB.
+             */
+            if (inputSize > 4 KB) {
+                /* For compressing large blobs, it is faster to pay the setup
+                 * cost to copy the dictionary's tables into the active context,
+                 * so that the compression loop is only looking into one table.
+                 */
+                LZ4_memcpy(streamPtr, streamPtr->dictCtx, sizeof(*streamPtr));
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
+            } else {
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
+            }
+        } else {  /* small data <= 4 KB */
+            if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
+            } else {
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
+            }
+        }
         streamPtr->dictionary = (const BYTE*)source;
         streamPtr->dictSize = (U32)inputSize;
-        streamPtr->currentOffset += (U32)inputSize;
         return result;
     }
 }
 
 
-/* Hidden debug function, to force external dictionary mode */
-int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
+/* Hidden debug function, to force-test external dictionary mode */
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize)
 {
     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(streamPtr, smallest);
+    LZ4_renormDictT(streamPtr, srcSize);
 
-    result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+    if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
+        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
+    } else {
+        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+    }
 
     streamPtr->dictionary = (const BYTE*)source;
-    streamPtr->dictSize = (U32)inputSize;
-    streamPtr->currentOffset += (U32)inputSize;
+    streamPtr->dictSize = (U32)srcSize;
 
     return result;
 }
@@ -1134,19 +1732,25 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char*
 /*! 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.
+ *  Note : no need to call LZ4_loadDict() afterwards, dictionary is immediately usable,
+ *         one can therefore call LZ4_compress_fast_continue() right after.
+ * @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* 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;
+    DEBUGLOG(5, "LZ4_saveDict : dictSize=%i, safeBuffer=%p", dictSize, safeBuffer);
+
+    if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */
+    if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; }
 
-    memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
+    if (safeBuffer == NULL) assert(dictSize == 0);
+    if (dictSize > 0) {
+        const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
+        assert(dict->dictionary);
+        LZ4_memmove(safeBuffer, previousDictEnd - dictSize, (size_t)dictSize);
+    }
 
     dict->dictionary = (const BYTE*)safeBuffer;
     dict->dictSize = (U32)dictSize;
@@ -1156,245 +1760,759 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
 
 
 
-/*-*****************************
-*  Decompression functions
-*******************************/
+/*-*******************************
+ *  Decompression functions
+ ********************************/
+
+typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
+
+#undef MIN
+#define MIN(a,b)    ( (a) < (b) ? (a) : (b) )
+
+
+/* variant for decompress_unsafe()
+ * does not know end of input
+ * presumes input is well formed
+ * note : will consume at least one byte */
+size_t read_long_length_no_check(const BYTE** pp)
+{
+    size_t b, l = 0;
+    do { b = **pp; (*pp)++; l += b; } while (b==255);
+    DEBUGLOG(6, "read_long_length_no_check: +length=%zu using %zu input bytes", l, l/255 + 1)
+    return l;
+}
+
+/* core decoder variant for LZ4_decompress_fast*()
+ * for legacy support only : these entry points are deprecated.
+ * - Presumes input is correctly formed (no defense vs malformed inputs)
+ * - Does not know input size (presume input buffer is "large enough")
+ * - Decompress a full block (only)
+ * @return : nb of bytes read from input.
+ * Note : this variant is not optimized for speed, just for maintenance.
+ *        the goal is to remove support of decompress_fast*() variants by v2.0
+**/
+LZ4_FORCE_INLINE int
+LZ4_decompress_unsafe_generic(
+                 const BYTE* const istart,
+                 BYTE* const ostart,
+                 int decompressedSize,
+
+                 size_t prefixSize,
+                 const BYTE* const dictStart,  /* only if dict==usingExtDict */
+                 const size_t dictSize         /* note: =0 if dictStart==NULL */
+                 )
+{
+    const BYTE* ip = istart;
+    BYTE* op = (BYTE*)ostart;
+    BYTE* const oend = ostart + decompressedSize;
+    const BYTE* const prefixStart = ostart - prefixSize;
+
+    DEBUGLOG(5, "LZ4_decompress_unsafe_generic");
+    if (dictStart == NULL) assert(dictSize == 0);
+
+    while (1) {
+        /* start new sequence */
+        unsigned token = *ip++;
+
+        /* literals */
+        {   size_t ll = token >> ML_BITS;
+            if (ll==15) {
+                /* long literal length */
+                ll += read_long_length_no_check(&ip);
+            }
+            if ((size_t)(oend-op) < ll) return -1; /* output buffer overflow */
+            LZ4_memmove(op, ip, ll); /* support in-place decompression */
+            op += ll;
+            ip += ll;
+            if ((size_t)(oend-op) < MFLIMIT) {
+                if (op==oend) break;  /* end of block */
+                DEBUGLOG(5, "invalid: literals end at distance %zi from end of block", oend-op);
+                /* incorrect end of block :
+                 * last match must start at least MFLIMIT==12 bytes before end of output block */
+                return -1;
+        }   }
+
+        /* match */
+        {   size_t ml = token & 15;
+            size_t const offset = LZ4_readLE16(ip);
+            ip+=2;
+
+            if (ml==15) {
+                /* long literal length */
+                ml += read_long_length_no_check(&ip);
+            }
+            ml += MINMATCH;
+
+            if ((size_t)(oend-op) < ml) return -1; /* output buffer overflow */
+
+            {   const BYTE* match = op - offset;
+
+                /* out of range */
+                if (offset > (size_t)(op - prefixStart) + dictSize) {
+                    DEBUGLOG(6, "offset out of range");
+                    return -1;
+                }
+
+                /* check special case : extDict */
+                if (offset > (size_t)(op - prefixStart)) {
+                    /* extDict scenario */
+                    const BYTE* const dictEnd = dictStart + dictSize;
+                    const BYTE* extMatch = dictEnd - (offset - (size_t)(op-prefixStart));
+                    size_t const extml = (size_t)(dictEnd - extMatch);
+                    if (extml > ml) {
+                        /* match entirely within extDict */
+                        LZ4_memmove(op, extMatch, ml);
+                        op += ml;
+                        ml = 0;
+                    } else {
+                        /* match split between extDict & prefix */
+                        LZ4_memmove(op, extMatch, extml);
+                        op += extml;
+                        ml -= extml;
+                    }
+                    match = prefixStart;
+                }
+
+                /* match copy - slow variant, supporting overlap copy */
+                {   size_t u;
+                    for (u=0; u<ml; u++) {
+                        op[u] = match[u];
+            }   }   }
+            op += ml;
+            if ((size_t)(oend-op) < LASTLITERALS) {
+                DEBUGLOG(5, "invalid: match ends at distance %zi from end of block", oend-op);
+                /* incorrect end of block :
+                 * last match must stop at least LASTLITERALS==5 bytes before end of output block */
+                return -1;
+            }
+        } /* match */
+    } /* main loop */
+    return (int)(ip - istart);
+}
+
+
+/* Read the variable-length literal or match length.
+ *
+ * @ip : input pointer
+ * @ilimit : position after which if length is not decoded, the input is necessarily corrupted.
+ * @initial_check - check ip >= ipmax before start of loop.  Returns initial_error if so.
+ * @error (output) - error code.  Must be set to 0 before call.
+**/
+typedef size_t Rvl_t;
+static const Rvl_t rvl_error = (Rvl_t)(-1);
+LZ4_FORCE_INLINE Rvl_t
+read_variable_length(const BYTE** ip, const BYTE* ilimit,
+                     int initial_check)
+{
+    Rvl_t s, length = 0;
+    assert(ip != NULL);
+    assert(*ip !=  NULL);
+    assert(ilimit != NULL);
+    if (initial_check && unlikely((*ip) >= ilimit)) {    /* read limit reached */
+        return rvl_error;
+    }
+    do {
+        s = **ip;
+        (*ip)++;
+        length += s;
+        if (unlikely((*ip) > ilimit)) {    /* read limit reached */
+            return rvl_error;
+        }
+        /* accumulator overflow detection (32-bit mode only) */
+        if ((sizeof(length)<8) && unlikely(length > ((Rvl_t)(-1)/2)) ) {
+            return rvl_error;
+        }
+    } while (s==255);
+
+    return length;
+}
+
 /*! LZ4_decompress_generic() :
  *  This generic decompression function covers all use cases.
  *  It shall be instantiated several times, using different sets of directives.
  *  Note that it is important for performance that this function really get inlined,
  *  in order to remove useless branches during compilation optimization.
  */
-LZ4_FORCE_O2_GCC_PPC64LE
-LZ4_FORCE_INLINE int LZ4_decompress_generic(
+LZ4_FORCE_INLINE int
+LZ4_decompress_generic(
                  const char* const src,
                  char* const dst,
                  int srcSize,
                  int outputSize,         /* If endOnInput==endOnInputSize, this value is `dstCapacity` */
 
-                 int endOnInput,         /* endOnOutputSize, endOnInputSize */
-                 int partialDecoding,    /* full, partial */
-                 int targetOutputSize,   /* only used if partialDecoding==partial */
-                 int dict,               /* noDict, withPrefix64k, usingExtDict */
+                 earlyEnd_directive partialDecoding,  /* full, partial */
+                 dict_directive dict,                 /* noDict, withPrefix64k, usingExtDict */
                  const BYTE* const lowPrefix,  /* always <= dst, == dst when no prefix */
                  const BYTE* const dictStart,  /* only if dict==usingExtDict */
                  const size_t dictSize         /* note : = 0 if noDict */
                  )
 {
-    const BYTE* ip = (const BYTE*) src;
-    const BYTE* const iend = ip + srcSize;
+    if ((src == NULL) || (outputSize < 0)) { return -1; }
 
-    BYTE* op = (BYTE*) dst;
-    BYTE* const oend = op + outputSize;
-    BYTE* cpy;
-    BYTE* oexit = op + targetOutputSize;
+    {   const BYTE* ip = (const BYTE*) src;
+        const BYTE* const iend = ip + srcSize;
 
-    const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
-    const unsigned inc32table[8] = {0, 1, 2,  1,  0,  4, 4, 4};
-    const int      dec64table[8] = {0, 0, 0, -1, -4,  1, 2, 3};
+        BYTE* op = (BYTE*) dst;
+        BYTE* const oend = op + outputSize;
+        BYTE* cpy;
 
-    const int safeDecode = (endOnInput==endOnInputSize);
-    const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
+        const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize;
 
+        const int checkOffset = (dictSize < (int)(64 KB));
 
-    /* Special cases */
-    if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT;                      /* targetOutputSize too high => just decode everything */
-    if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
-    if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1);
 
-    /* Main Loop : decode sequences */
-    while (1) {
-        size_t length;
+        /* Set up the "end" pointers for the shortcut. */
+        const BYTE* const shortiend = iend - 14 /*maxLL*/ - 2 /*offset*/;
+        const BYTE* const shortoend = oend - 14 /*maxLL*/ - 18 /*maxML*/;
+
         const BYTE* match;
         size_t offset;
+        unsigned token;
+        size_t length;
+
+
+        DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize);
+
+        /* Special cases */
+        assert(lowPrefix <= op);
+        if (unlikely(outputSize==0)) {
+            /* Empty output buffer */
+            if (partialDecoding) return 0;
+            return ((srcSize==1) && (*ip==0)) ? 0 : -1;
+        }
+        if (unlikely(srcSize==0)) { return -1; }
+
+    /* LZ4_FAST_DEC_LOOP:
+     * designed for modern OoO performance cpus,
+     * where copying reliably 32-bytes is preferable to an unpredictable branch.
+     * note : fast loop may show a regression for some client arm chips. */
+#if LZ4_FAST_DEC_LOOP
+        if ((oend - op) < FASTLOOP_SAFE_DISTANCE) {
+            DEBUGLOG(6, "skip fast decode loop");
+            goto safe_decode;
+        }
+
+        /* Fast loop : decode sequences as long as output < oend-FASTLOOP_SAFE_DISTANCE */
+        while (1) {
+            /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */
+            assert(oend - op >= FASTLOOP_SAFE_DISTANCE);
+            assert(ip < iend);
+            token = *ip++;
+            length = token >> ML_BITS;  /* literal length */
+
+            /* decode literal length */
+            if (length == RUN_MASK) {
+                size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1);
+                if (addl == rvl_error) { goto _output_error; }
+                length += addl;
+                if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+                if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+
+                /* copy literals */
+                cpy = op+length;
+                LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+                if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
+                LZ4_wildCopy32(op, ip, cpy);
+                ip += length; op = cpy;
+            } else {
+                cpy = op+length;
+                DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
+                /* We don't need to check oend, since we check it once for each loop below */
+                if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
+                /* Literals can only be <= 14, but hope compilers optimize better when copy by a register size */
+                LZ4_memcpy(op, ip, 16);
+                ip += length; op = cpy;
+            }
+
+            /* get offset */
+            offset = LZ4_readLE16(ip); ip+=2;
+            match = op - offset;
+            assert(match <= op);  /* overflow check */
+
+            /* get matchlength */
+            length = token & ML_MASK;
+
+            if (length == ML_MASK) {
+                size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0);
+                if (addl == rvl_error) { goto _output_error; }
+                length += addl;
+                length += MINMATCH;
+                if (unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
+                if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
+                if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
+                    goto safe_match_copy;
+                }
+            } else {
+                length += MINMATCH;
+                if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
+                    goto safe_match_copy;
+                }
 
-        unsigned const token = *ip++;
-
-        /* shortcut for common case :
-         * in most circumstances, we expect to decode small matches (<= 18 bytes) separated by few literals (<= 14 bytes).
-         * this shortcut was tested on x86 and x64, where it improves decoding speed.
-         * it has not yet been benchmarked on ARM, Power, mips, etc. */
-        if (((ip + 14 /*maxLL*/ + 2 /*offset*/ <= iend)
-          & (op + 14 /*maxLL*/ + 18 /*maxML*/ <= oend))
-          & ((token < (15<<ML_BITS)) & ((token & ML_MASK) != 15)) ) {
-            size_t const ll = token >> ML_BITS;
-            size_t const off = LZ4_readLE16(ip+ll);
-            const BYTE* const matchPtr = op + ll - off;  /* pointer underflow risk ? */
-            if ((off >= 18) /* do not deal with overlapping matches */ & (matchPtr >= lowPrefix)) {
-                size_t const ml = (token & ML_MASK) + MINMATCH;
-                memcpy(op, ip, 16); op += ll; ip += ll + 2 /*offset*/;
-                memcpy(op, matchPtr, 18); op += ml;
+                /* Fastpath check: skip LZ4_wildCopy32 when true */
+                if ((dict == withPrefix64k) || (match >= lowPrefix)) {
+                    if (offset >= 8) {
+                        assert(match >= lowPrefix);
+                        assert(match <= op);
+                        assert(op + 18 <= oend);
+
+                        LZ4_memcpy(op, match, 8);
+                        LZ4_memcpy(op+8, match+8, 8);
+                        LZ4_memcpy(op+16, match+16, 2);
+                        op += length;
+                        continue;
+            }   }   }
+
+            if (checkOffset && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
+            /* match starting within external dictionary */
+            if ((dict==usingExtDict) && (match < lowPrefix)) {
+                assert(dictEnd != NULL);
+                if (unlikely(op+length > oend-LASTLITERALS)) {
+                    if (partialDecoding) {
+                        DEBUGLOG(7, "partialDecoding: dictionary match, close to dstEnd");
+                        length = MIN(length, (size_t)(oend-op));
+                    } else {
+                        goto _output_error;  /* end-of-block condition violated */
+                }   }
+
+                if (length <= (size_t)(lowPrefix-match)) {
+                    /* match fits entirely within external dictionary : just copy */
+                    LZ4_memmove(op, dictEnd - (lowPrefix-match), length);
+                    op += length;
+                } else {
+                    /* match stretches into both external dictionary and current block */
+                    size_t const copySize = (size_t)(lowPrefix - match);
+                    size_t const restSize = length - copySize;
+                    LZ4_memcpy(op, dictEnd - copySize, 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 {
+                        LZ4_memcpy(op, lowPrefix, restSize);
+                        op += restSize;
+                }   }
                 continue;
             }
-        }
 
-        /* decode literal length */
-        if ((length=(token>>ML_BITS)) == RUN_MASK) {
-            unsigned s;
-            do {
-                s = *ip++;
-                length += s;
-            } 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 match within block */
+            cpy = op + length;
 
-        /* copy literals */
-        cpy = op+length;
-        if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) )
-            || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
-        {
-            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 */
+            assert((op <= oend) && (oend-op >= 32));
+            if (unlikely(offset<16)) {
+                LZ4_memcpy_using_offset(op, match, cpy, offset);
             } 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 */
+                LZ4_wildCopy32(op, match, cpy);
             }
-            memcpy(op, ip, length);
-            ip += length;
-            op += length;
-            break;     /* Necessarily EOF, due to parsing restrictions */
-        }
-        LZ4_wildCopy(op, ip, cpy);
-        ip += length; op = cpy;
-
-        /* get offset */
-        offset = LZ4_readLE16(ip); ip+=2;
-        match = op - offset;
-        if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
-        LZ4_write32(op, (U32)offset);   /* costs ~1%; silence an msan warning when offset==0 */
-
-        /* get matchlength */
-        length = token & ML_MASK;
-        if (length == ML_MASK) {
-            unsigned s;
-            do {
-                s = *ip++;
-                if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
-                length += s;
-            } while (s==255);
-            if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
+
+            op = cpy;   /* wildcopy correction */
         }
-        length += MINMATCH;
+    safe_decode:
+#endif
+
+        /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */
+        while (1) {
+            assert(ip < iend);
+            token = *ip++;
+            length = token >> ML_BITS;  /* literal length */
+
+            /* A two-stage shortcut for the most common case:
+             * 1) If the literal length is 0..14, and there is enough space,
+             * enter the shortcut and copy 16 bytes on behalf of the literals
+             * (in the fast mode, only 8 bytes can be safely copied this way).
+             * 2) Further if the match length is 4..18, copy 18 bytes in a similar
+             * manner; but we ensure that there's enough space in the output for
+             * those 18 bytes earlier, upon entering the shortcut (in other words,
+             * there is a combined check for both stages).
+             */
+            if ( (length != RUN_MASK)
+                /* strictly "less than" on input, to re-enter the loop with at least one byte */
+              && likely((ip < shortiend) & (op <= shortoend)) ) {
+                /* Copy the literals */
+                LZ4_memcpy(op, ip, 16);
+                op += length; ip += length;
+
+                /* The second stage: prepare for match copying, decode full info.
+                 * If it doesn't work out, the info won't be wasted. */
+                length = token & ML_MASK; /* match length */
+                offset = LZ4_readLE16(ip); ip += 2;
+                match = op - offset;
+                assert(match <= op); /* check overflow */
+
+                /* Do not deal with overlapping matches. */
+                if ( (length != ML_MASK)
+                  && (offset >= 8)
+                  && (dict==withPrefix64k || match >= lowPrefix) ) {
+                    /* Copy the match. */
+                    LZ4_memcpy(op + 0, match + 0, 8);
+                    LZ4_memcpy(op + 8, match + 8, 8);
+                    LZ4_memcpy(op +16, match +16, 2);
+                    op += length + MINMATCH;
+                    /* Both stages worked, load the next token. */
+                    continue;
+                }
+
+                /* The second stage didn't work out, but the info is ready.
+                 * Propel it right to the point of match copying. */
+                goto _copy_match;
+            }
 
-        /* check external dictionary */
-        if ((dict==usingExtDict) && (match < lowPrefix)) {
-            if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error;   /* doesn't respect parsing restriction */
+            /* decode literal length */
+            if (length == RUN_MASK) {
+                size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1);
+                if (addl == rvl_error) { goto _output_error; }
+                length += addl;
+                if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+                if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+            }
 
-            if (length <= (size_t)(lowPrefix-match)) {
-                /* match can be copied as a single segment from external dictionary */
-                memmove(op, dictEnd - (lowPrefix-match), length);
+            /* copy literals */
+            cpy = op+length;
+#if LZ4_FAST_DEC_LOOP
+        safe_literal_copy:
+#endif
+            LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
+            if ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) {
+                /* We've either hit the input parsing restriction or the output parsing restriction.
+                 * In the normal scenario, decoding a full block, it must be the last sequence,
+                 * otherwise it's an error (invalid input or dimensions).
+                 * In partialDecoding scenario, it's necessary to ensure there is no buffer overflow.
+                 */
+                if (partialDecoding) {
+                    /* Since we are partial decoding we may be in this block because of the output parsing
+                     * restriction, which is not valid since the output buffer is allowed to be undersized.
+                     */
+                    DEBUGLOG(7, "partialDecoding: copying literals, close to input or output end")
+                    DEBUGLOG(7, "partialDecoding: literal length = %u", (unsigned)length);
+                    DEBUGLOG(7, "partialDecoding: remaining space in dstBuffer : %i", (int)(oend - op));
+                    DEBUGLOG(7, "partialDecoding: remaining space in srcBuffer : %i", (int)(iend - ip));
+                    /* Finishing in the middle of a literals segment,
+                     * due to lack of input.
+                     */
+                    if (ip+length > iend) {
+                        length = (size_t)(iend-ip);
+                        cpy = op + length;
+                    }
+                    /* Finishing in the middle of a literals segment,
+                     * due to lack of output space.
+                     */
+                    if (cpy > oend) {
+                        cpy = oend;
+                        assert(op<=oend);
+                        length = (size_t)(oend-op);
+                    }
+                } else {
+                     /* We must be on the last sequence (or invalid) because of the parsing limitations
+                      * so check that we exactly consume the input and don't overrun the output buffer.
+                      */
+                    if ((ip+length != iend) || (cpy > oend)) {
+                        DEBUGLOG(6, "should have been last run of literals")
+                        DEBUGLOG(6, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend);
+                        DEBUGLOG(6, "or cpy(%p) > oend(%p)", cpy, oend);
+                        goto _output_error;
+                    }
+                }
+                LZ4_memmove(op, ip, length);  /* supports overlapping memory regions, for in-place decompression scenarios */
+                ip += length;
                 op += length;
+                /* Necessarily EOF when !partialDecoding.
+                 * When partialDecoding, it is EOF if we've either
+                 * filled the output buffer or
+                 * can't proceed with reading an offset for following match.
+                 */
+                if (!partialDecoding || (cpy == oend) || (ip >= (iend-2))) {
+                    break;
+                }
             } 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;
-                if (restSize > (size_t)(op-lowPrefix)) {  /* overlap copy */
-                    BYTE* const endOfMatch = op + restSize;
-                    const BYTE* copyFrom = lowPrefix;
-                    while (op < endOfMatch) *op++ = *copyFrom++;
+                LZ4_wildCopy8(op, ip, cpy);   /* can overwrite up to 8 bytes beyond cpy */
+                ip += length; op = cpy;
+            }
+
+            /* get offset */
+            offset = LZ4_readLE16(ip); ip+=2;
+            match = op - offset;
+
+            /* get matchlength */
+            length = token & ML_MASK;
+
+    _copy_match:
+            if (length == ML_MASK) {
+                size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0);
+                if (addl == rvl_error) { goto _output_error; }
+                length += addl;
+                if (unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
+            }
+            length += MINMATCH;
+
+#if LZ4_FAST_DEC_LOOP
+        safe_match_copy:
+#endif
+            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
+            /* match starting within external dictionary */
+            if ((dict==usingExtDict) && (match < lowPrefix)) {
+                assert(dictEnd != NULL);
+                if (unlikely(op+length > oend-LASTLITERALS)) {
+                    if (partialDecoding) length = MIN(length, (size_t)(oend-op));
+                    else goto _output_error;   /* doesn't respect parsing restriction */
+                }
+
+                if (length <= (size_t)(lowPrefix-match)) {
+                    /* match fits entirely within external dictionary : just copy */
+                    LZ4_memmove(op, dictEnd - (lowPrefix-match), length);
+                    op += length;
                 } else {
-                    memcpy(op, lowPrefix, restSize);
-                    op += restSize;
-            }   }
-            continue;
-        }
+                    /* match stretches into both external dictionary and current block */
+                    size_t const copySize = (size_t)(lowPrefix - match);
+                    size_t const restSize = length - copySize;
+                    LZ4_memcpy(op, dictEnd - copySize, 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 {
+                        LZ4_memcpy(op, lowPrefix, restSize);
+                        op += restSize;
+                }   }
+                continue;
+            }
+            assert(match >= lowPrefix);
+
+            /* copy match within block */
+            cpy = op + length;
+
+            /* partialDecoding : may end anywhere within the block */
+            assert(op<=oend);
+            if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
+                size_t const mlen = MIN(length, (size_t)(oend-op));
+                const BYTE* const matchEnd = match + mlen;
+                BYTE* const copyEnd = op + mlen;
+                if (matchEnd > op) {   /* overlap copy */
+                    while (op < copyEnd) { *op++ = *match++; }
+                } else {
+                    LZ4_memcpy(op, match, mlen);
+                }
+                op = copyEnd;
+                if (op == oend) { break; }
+                continue;
+            }
 
-        /* copy match within block */
-        cpy = op + length;
-        if (unlikely(offset<8)) {
-            op[0] = match[0];
-            op[1] = match[1];
-            op[2] = match[2];
-            op[3] = match[3];
-            match += inc32table[offset];
-            memcpy(op+4, match, 4);
-            match -= dec64table[offset];
-        } 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;
+            if (unlikely(offset<8)) {
+                LZ4_write32(op, 0);   /* silence msan warning when offset==0 */
+                op[0] = match[0];
+                op[1] = match[1];
+                op[2] = match[2];
+                op[3] = match[3];
+                match += inc32table[offset];
+                LZ4_memcpy(op+4, match, 4);
+                match -= dec64table[offset];
+            } else {
+                LZ4_memcpy(op, match, 8);
+                match += 8;
             }
-            while (op<cpy) *op++ = *match++;
-        } else {
-            LZ4_copy8(op, match);
-            if (length>16) LZ4_wildCopy(op+8, match+8, cpy);
+            op += 8;
+
+            if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
+                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_wildCopy8(op, match, oCopyLimit);
+                    match += oCopyLimit - op;
+                    op = oCopyLimit;
+                }
+                while (op < cpy) { *op++ = *match++; }
+            } else {
+                LZ4_memcpy(op, match, 8);
+                if (length > 16)  { LZ4_wildCopy8(op+8, match+8, cpy); }
+            }
+            op = cpy;   /* wildcopy correction */
         }
-        op = cpy;   /* correction */
-    }
 
-    /* end of decoding */
-    if (endOnInput)
-       return (int) (((char*)op)-dst);     /* Nb of output bytes decoded */
-    else
-       return (int) (((const char*)ip)-src);   /* Nb of input bytes read */
+        /* end of decoding */
+        DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst));
+        return (int) (((char*)op)-dst);     /* Nb of output bytes decoded */
 
-    /* Overflow error detected */
-_output_error:
-    return (int) (-(((const char*)ip)-src))-1;
+        /* Overflow error detected */
+    _output_error:
+        return (int) (-(((const char*)ip)-src))-1;
+    }
 }
 
 
-LZ4_FORCE_O2_GCC_PPC64LE
+/*===== Instantiate the API decoding functions. =====*/
+
+LZ4_FORCE_O2
 int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
 {
-    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
+                                  decode_full_block, noDict,
+                                  (BYTE*)dest, NULL, 0);
 }
 
-LZ4_FORCE_O2_GCC_PPC64LE
-int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
+LZ4_FORCE_O2
+int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity)
 {
-    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0);
+    dstCapacity = MIN(targetOutputSize, dstCapacity);
+    return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
+                                  partial_decode,
+                                  noDict, (BYTE*)dst, NULL, 0);
 }
 
-LZ4_FORCE_O2_GCC_PPC64LE
+LZ4_FORCE_O2
 int LZ4_decompress_fast(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);
+    DEBUGLOG(5, "LZ4_decompress_fast");
+    return LZ4_decompress_unsafe_generic(
+                (const BYTE*)source, (BYTE*)dest, originalSize,
+                0, NULL, 0);
+}
+
+/*===== Instantiate a few more decoding cases, used more than once. =====*/
+
+LZ4_FORCE_O2 /* Exported, an obsolete API function. */
+int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  decode_full_block, withPrefix64k,
+                                  (BYTE*)dest - 64 KB, NULL, 0);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_safe_partial_withPrefix64k(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity)
+{
+    dstCapacity = MIN(targetOutputSize, dstCapacity);
+    return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
+                                  partial_decode, withPrefix64k,
+                                  (BYTE*)dest - 64 KB, NULL, 0);
+}
+
+/* Another obsolete API function, paired with the previous one. */
+int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
+{
+    return LZ4_decompress_unsafe_generic(
+                (const BYTE*)source, (BYTE*)dest, originalSize,
+                64 KB, NULL, 0);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize,
+                                               size_t prefixSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  decode_full_block, noDict,
+                                  (BYTE*)dest-prefixSize, NULL, 0);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_safe_partial_withSmallPrefix(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity,
+                                               size_t prefixSize)
+{
+    dstCapacity = MIN(targetOutputSize, dstCapacity);
+    return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
+                                  partial_decode, noDict,
+                                  (BYTE*)dest-prefixSize, NULL, 0);
+}
+
+LZ4_FORCE_O2
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
+                                     int compressedSize, int maxOutputSize,
+                                     const void* dictStart, size_t dictSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  decode_full_block, usingExtDict,
+                                  (BYTE*)dest, (const BYTE*)dictStart, dictSize);
 }
 
+LZ4_FORCE_O2
+int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
+                                     int compressedSize, int targetOutputSize, int dstCapacity,
+                                     const void* dictStart, size_t dictSize)
+{
+    dstCapacity = MIN(targetOutputSize, dstCapacity);
+    return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
+                                  partial_decode, usingExtDict,
+                                  (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize,
+                                       const void* dictStart, size_t dictSize)
+{
+    return LZ4_decompress_unsafe_generic(
+                (const BYTE*)source, (BYTE*)dest, originalSize,
+                0, (const BYTE*)dictStart, dictSize);
+}
+
+/* The "double dictionary" mode, for use with e.g. ring buffers: the first part
+ * of the dictionary is passed as prefix, and the second via dictStart + dictSize.
+ * These routines are used only once, in LZ4_decompress_*_continue().
+ */
+LZ4_FORCE_INLINE
+int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize,
+                                   size_t prefixSize, const void* dictStart, size_t dictSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  decode_full_block, usingExtDict,
+                                  (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
+}
 
 /*===== streaming decompression functions =====*/
 
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
 LZ4_streamDecode_t* LZ4_createStreamDecode(void)
 {
-    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t));
-    return lz4s;
+    LZ4_STATIC_ASSERT(sizeof(LZ4_streamDecode_t) >= sizeof(LZ4_streamDecode_t_internal));
+    return (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
 }
 
 int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
 {
-    if (!LZ4_stream) return 0;   /* support free on NULL */
+    if (LZ4_stream == NULL) { return 0; }  /* support free on NULL */
     FREEMEM(LZ4_stream);
     return 0;
 }
+#endif
 
-/*!
- * 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
+/*! 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_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
 {
     LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
-    lz4sd->prefixSize = (size_t) dictSize;
-    lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
+    lz4sd->prefixSize = (size_t)dictSize;
+    if (dictSize) {
+        assert(dictionary != NULL);
+        lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
+    } else {
+        lz4sd->prefixEnd = (const BYTE*) dictionary;
+    }
     lz4sd->externalDict = NULL;
     lz4sd->extDictSize  = 0;
     return 1;
 }
 
+/*! LZ4_decoderRingBufferSize() :
+ *  when setting a ring buffer for streaming decompression (optional scenario),
+ *  provides the minimum size of this ring buffer
+ *  to be compatible with any source respecting maxBlockSize condition.
+ *  Note : in a ring buffer scenario,
+ *  blocks are presumed decompressed next to each other.
+ *  When not enough space remains for next block (remainingSize < maxBlockSize),
+ *  decoding resumes from beginning of ring buffer.
+ * @return : minimum ring buffer size,
+ *           or 0 if there is an error (invalid maxBlockSize).
+ */
+int LZ4_decoderRingBufferSize(int maxBlockSize)
+{
+    if (maxBlockSize < 0) return 0;
+    if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0;
+    if (maxBlockSize < 16) maxBlockSize = 16;
+    return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize);
+}
+
 /*
 *_continue() :
     These decoding functions allow decompression of multiple blocks in "streaming" mode.
@@ -1402,54 +2520,81 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti
     If it's not possible, save the relevant part of decoded data into a safe buffer,
     and indicate where it stands using LZ4_setStreamDecode()
 */
-LZ4_FORCE_O2_GCC_PPC64LE
+LZ4_FORCE_O2
 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->internal_donotuse;
     int 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 (lz4sd->prefixSize == 0) {
+        /* The first call, no dictionary yet. */
+        assert(lz4sd->extDictSize == 0);
+        result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
         if (result <= 0) return result;
-        lz4sd->prefixSize += result;
+        lz4sd->prefixSize = (size_t)result;
+        lz4sd->prefixEnd = (BYTE*)dest + result;
+    } else if (lz4sd->prefixEnd == (BYTE*)dest) {
+        /* They're rolling the current segment. */
+        if (lz4sd->prefixSize >= 64 KB - 1)
+            result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
+        else if (lz4sd->extDictSize == 0)
+            result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize,
+                                                         lz4sd->prefixSize);
+        else
+            result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize,
+                                                    lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize += (size_t)result;
         lz4sd->prefixEnd  += result;
     } else {
+        /* The buffer wraps around, or they're switching to another buffer. */
         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);
+        result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize,
+                                                  lz4sd->externalDict, lz4sd->extDictSize);
         if (result <= 0) return result;
-        lz4sd->prefixSize = result;
+        lz4sd->prefixSize = (size_t)result;
         lz4sd->prefixEnd  = (BYTE*)dest + result;
     }
 
     return result;
 }
 
-LZ4_FORCE_O2_GCC_PPC64LE
-int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
+LZ4_FORCE_O2 int
+LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode,
+                        const char* source, char* dest, int originalSize)
 {
-    LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
+    LZ4_streamDecode_t_internal* const lz4sd =
+        (assert(LZ4_streamDecode!=NULL), &LZ4_streamDecode->internal_donotuse);
     int 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);
+    DEBUGLOG(5, "LZ4_decompress_fast_continue (toDecodeSize=%i)", originalSize);
+    assert(originalSize >= 0);
+
+    if (lz4sd->prefixSize == 0) {
+        DEBUGLOG(5, "first invocation : no prefix nor extDict");
+        assert(lz4sd->extDictSize == 0);
+        result = LZ4_decompress_fast(source, dest, originalSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize = (size_t)originalSize;
+        lz4sd->prefixEnd = (BYTE*)dest + originalSize;
+    } else if (lz4sd->prefixEnd == (BYTE*)dest) {
+        DEBUGLOG(5, "continue using existing prefix");
+        result = LZ4_decompress_unsafe_generic(
+                        (const BYTE*)source, (BYTE*)dest, originalSize,
+                        lz4sd->prefixSize,
+                        lz4sd->externalDict, lz4sd->extDictSize);
         if (result <= 0) return result;
-        lz4sd->prefixSize += originalSize;
+        lz4sd->prefixSize += (size_t)originalSize;
         lz4sd->prefixEnd  += originalSize;
     } else {
+        DEBUGLOG(5, "prefix becomes extDict");
         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);
+        result = LZ4_decompress_fast_extDict(source, dest, originalSize,
+                                             lz4sd->externalDict, lz4sd->extDictSize);
         if (result <= 0) return result;
-        lz4sd->prefixSize = originalSize;
+        lz4sd->prefixSize = (size_t)originalSize;
         lz4sd->prefixEnd  = (BYTE*)dest + originalSize;
     }
 
@@ -1464,36 +2609,44 @@ Advanced decoding functions :
     the dictionary must be explicitly provided within parameters
 */
 
-LZ4_FORCE_O2_GCC_PPC64LE
-LZ4_FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
+int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
 {
     if (dictSize==0)
-        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
+        return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
     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);
+        if (dictSize >= 64 KB - 1) {
+            return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
+        }
+        assert(dictSize >= 0);
+        return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize);
     }
-    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+    assert(dictSize >= 0);
+    return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize);
 }
 
-LZ4_FORCE_O2_GCC_PPC64LE
-int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
+int LZ4_decompress_safe_partial_usingDict(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, const char* dictStart, int dictSize)
 {
-    return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
+    if (dictSize==0)
+        return LZ4_decompress_safe_partial(source, dest, compressedSize, targetOutputSize, dstCapacity);
+    if (dictStart+dictSize == dest) {
+        if (dictSize >= 64 KB - 1) {
+            return LZ4_decompress_safe_partial_withPrefix64k(source, dest, compressedSize, targetOutputSize, dstCapacity);
+        }
+        assert(dictSize >= 0);
+        return LZ4_decompress_safe_partial_withSmallPrefix(source, dest, compressedSize, targetOutputSize, dstCapacity, (size_t)dictSize);
+    }
+    assert(dictSize >= 0);
+    return LZ4_decompress_safe_partial_forceExtDict(source, dest, compressedSize, targetOutputSize, dstCapacity, dictStart, (size_t)dictSize);
 }
 
-LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
 {
-    return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
-}
-
-/* debug function */
-LZ4_FORCE_O2_GCC_PPC64LE
-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);
+    if (dictSize==0 || dictStart+dictSize == dest)
+        return LZ4_decompress_unsafe_generic(
+                        (const BYTE*)source, (BYTE*)dest, originalSize,
+                        (size_t)dictSize, NULL, 0);
+    assert(dictSize >= 0);
+    return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize);
 }
 
 
@@ -1501,64 +2654,69 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compres
 *  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); }
+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* src, char* dest, int srcSize)
+{
+    return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize));
+}
+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 dstCapacity)
+{
+    return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 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.
+These decompression functions 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); }
-
+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_sizeofStreamState(void) { return sizeof(LZ4_stream_t); }
 
 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);
+    (void)inputBuffer;
+    LZ4_resetStream((LZ4_stream_t*)state);
     return 0;
 }
 
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
 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);
+    (void)inputBuffer;
+    return LZ4_createStream();
 }
+#endif
 
-int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
+char* LZ4_slideInputBuffer (void* state)
 {
-    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
+    /* avoid const char * -> char * conversion warning */
+    return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary;
 }
 
 #endif   /* LZ4_COMMONDEFS_ONLY */