extzstd 0.1.1 → 0.2

data/contrib/zstd/lib/common/pool.c

@@ -1,16 +1,16 @@
-/**
- * Copyright (c) 2016-present, Facebook, Inc.
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of this source tree. An additional grant
- * of patent rights can be found in the PATENTS file in the same directory.
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
  */
 
 
 /* ======   Dependencies   ======= */
 #include <stddef.h>  /* size_t */
-#include <stdlib.h>  /* malloc, calloc, free */
 #include "pool.h"
 
 /* ======   Compiler specifics   ====== */
@@ -25,13 +25,14 @@
 
 /* A job is a function and an opaque argument */
 typedef struct POOL_job_s {
-  POOL_function function;
-  void *opaque;
+    POOL_function function;
+    void *opaque;
 } POOL_job;
 
 struct POOL_ctx_s {
+    ZSTD_customMem customMem;
     /* Keep track of the threads */
-    pthread_t *threads;
+    ZSTD_pthread_t *threads;
     size_t numThreads;
 
     /* The queue is a circular buffer */
@@ -39,12 +40,18 @@ struct POOL_ctx_s {
     size_t queueHead;
     size_t queueTail;
     size_t queueSize;
+
+    /* The number of threads working on jobs */
+    size_t numThreadsBusy;
+    /* Indicates if the queue is empty */
+    int queueEmpty;
+
     /* The mutex protects the queue */
-    pthread_mutex_t queueMutex;
+    ZSTD_pthread_mutex_t queueMutex;
     /* Condition variable for pushers to wait on when the queue is full */
-    pthread_cond_t queuePushCond;
+    ZSTD_pthread_cond_t queuePushCond;
     /* Condition variables for poppers to wait on when the queue is empty */
-    pthread_cond_t queuePopCond;
+    ZSTD_pthread_cond_t queuePopCond;
     /* Indicates if the queue is shutting down */
     int shutdown;
 };
@@ -59,55 +66,73 @@ static void* POOL_thread(void* opaque) {
     if (!ctx) { return NULL; }
     for (;;) {
         /* Lock the mutex and wait for a non-empty queue or until shutdown */
-        pthread_mutex_lock(&ctx->queueMutex);
-        while (ctx->queueHead == ctx->queueTail && !ctx->shutdown) {
-            pthread_cond_wait(&ctx->queuePopCond, &ctx->queueMutex);
+        ZSTD_pthread_mutex_lock(&ctx->queueMutex);
+
+        while (ctx->queueEmpty && !ctx->shutdown) {
+            ZSTD_pthread_cond_wait(&ctx->queuePopCond, &ctx->queueMutex);
         }
         /* empty => shutting down: so stop */
-        if (ctx->queueHead == ctx->queueTail) {
-            pthread_mutex_unlock(&ctx->queueMutex);
+        if (ctx->queueEmpty) {
+            ZSTD_pthread_mutex_unlock(&ctx->queueMutex);
             return opaque;
         }
         /* Pop a job off the queue */
         {   POOL_job const job = ctx->queue[ctx->queueHead];
             ctx->queueHead = (ctx->queueHead + 1) % ctx->queueSize;
+            ctx->numThreadsBusy++;
+            ctx->queueEmpty = ctx->queueHead == ctx->queueTail;
             /* Unlock the mutex, signal a pusher, and run the job */
-            pthread_mutex_unlock(&ctx->queueMutex);
-            pthread_cond_signal(&ctx->queuePushCond);
+            ZSTD_pthread_mutex_unlock(&ctx->queueMutex);
+            ZSTD_pthread_cond_signal(&ctx->queuePushCond);
+
             job.function(job.opaque);
-        }
-    }
+
+            /* If the intended queue size was 0, signal after finishing job */
+            if (ctx->queueSize == 1) {
+                ZSTD_pthread_mutex_lock(&ctx->queueMutex);
+                ctx->numThreadsBusy--;
+                ZSTD_pthread_mutex_unlock(&ctx->queueMutex);
+                ZSTD_pthread_cond_signal(&ctx->queuePushCond);
+        }   }
+    }  /* for (;;) */
     /* Unreachable */
 }
 
-POOL_ctx *POOL_create(size_t numThreads, size_t queueSize) {
-    POOL_ctx *ctx;
+POOL_ctx* POOL_create(size_t numThreads, size_t queueSize) {
+    return POOL_create_advanced(numThreads, queueSize, ZSTD_defaultCMem);
+}
+
+POOL_ctx* POOL_create_advanced(size_t numThreads, size_t queueSize, ZSTD_customMem customMem) {
+    POOL_ctx* ctx;
     /* Check the parameters */
-    if (!numThreads || !queueSize) { return NULL; }
+    if (!numThreads) { return NULL; }
     /* Allocate the context and zero initialize */
-    ctx = (POOL_ctx *)calloc(1, sizeof(POOL_ctx));
+    ctx = (POOL_ctx*)ZSTD_calloc(sizeof(POOL_ctx), customMem);
     if (!ctx) { return NULL; }
     /* Initialize the job queue.
      * It needs one extra space since one space is wasted to differentiate empty
      * and full queues.
      */
     ctx->queueSize = queueSize + 1;
-    ctx->queue = (POOL_job *)malloc(ctx->queueSize * sizeof(POOL_job));
+    ctx->queue = (POOL_job*)ZSTD_malloc(ctx->queueSize * sizeof(POOL_job), customMem);
     ctx->queueHead = 0;
     ctx->queueTail = 0;
-    pthread_mutex_init(&ctx->queueMutex, NULL);
-    pthread_cond_init(&ctx->queuePushCond, NULL);
-    pthread_cond_init(&ctx->queuePopCond, NULL);
+    ctx->numThreadsBusy = 0;
+    ctx->queueEmpty = 1;
+    (void)ZSTD_pthread_mutex_init(&ctx->queueMutex, NULL);
+    (void)ZSTD_pthread_cond_init(&ctx->queuePushCond, NULL);
+    (void)ZSTD_pthread_cond_init(&ctx->queuePopCond, NULL);
     ctx->shutdown = 0;
     /* Allocate space for the thread handles */
-    ctx->threads = (pthread_t *)malloc(numThreads * sizeof(pthread_t));
+    ctx->threads = (ZSTD_pthread_t*)ZSTD_malloc(numThreads * sizeof(ZSTD_pthread_t), customMem);
     ctx->numThreads = 0;
+    ctx->customMem = customMem;
     /* Check for errors */
     if (!ctx->threads || !ctx->queue) { POOL_free(ctx); return NULL; }
     /* Initialize the threads */
     {   size_t i;
         for (i = 0; i < numThreads; ++i) {
-            if (pthread_create(&ctx->threads[i], NULL, &POOL_thread, ctx)) {
+            if (ZSTD_pthread_create(&ctx->threads[i], NULL, &POOL_thread, ctx)) {
                 ctx->numThreads = i;
                 POOL_free(ctx);
                 return NULL;
@@ -120,52 +145,74 @@ POOL_ctx *POOL_create(size_t numThreads, size_t queueSize) {
 /*! POOL_join() :
     Shutdown the queue, wake any sleeping threads, and join all of the threads.
 */
-static void POOL_join(POOL_ctx *ctx) {
+static void POOL_join(POOL_ctx* ctx) {
     /* Shut down the queue */
-    pthread_mutex_lock(&ctx->queueMutex);
+    ZSTD_pthread_mutex_lock(&ctx->queueMutex);
     ctx->shutdown = 1;
-    pthread_mutex_unlock(&ctx->queueMutex);
+    ZSTD_pthread_mutex_unlock(&ctx->queueMutex);
     /* Wake up sleeping threads */
-    pthread_cond_broadcast(&ctx->queuePushCond);
-    pthread_cond_broadcast(&ctx->queuePopCond);
+    ZSTD_pthread_cond_broadcast(&ctx->queuePushCond);
+    ZSTD_pthread_cond_broadcast(&ctx->queuePopCond);
     /* Join all of the threads */
     {   size_t i;
         for (i = 0; i < ctx->numThreads; ++i) {
-            pthread_join(ctx->threads[i], NULL);
+            ZSTD_pthread_join(ctx->threads[i], NULL);
     }   }
 }
 
 void POOL_free(POOL_ctx *ctx) {
     if (!ctx) { return; }
     POOL_join(ctx);
-    pthread_mutex_destroy(&ctx->queueMutex);
-    pthread_cond_destroy(&ctx->queuePushCond);
-    pthread_cond_destroy(&ctx->queuePopCond);
-    if (ctx->queue) free(ctx->queue);
-    if (ctx->threads) free(ctx->threads);
-    free(ctx);
+    ZSTD_pthread_mutex_destroy(&ctx->queueMutex);
+    ZSTD_pthread_cond_destroy(&ctx->queuePushCond);
+    ZSTD_pthread_cond_destroy(&ctx->queuePopCond);
+    ZSTD_free(ctx->queue, ctx->customMem);
+    ZSTD_free(ctx->threads, ctx->customMem);
+    ZSTD_free(ctx, ctx->customMem);
+}
+
+size_t POOL_sizeof(POOL_ctx *ctx) {
+    if (ctx==NULL) return 0;  /* supports sizeof NULL */
+    return sizeof(*ctx)
+        + ctx->queueSize * sizeof(POOL_job)
+        + ctx->numThreads * sizeof(ZSTD_pthread_t);
 }
 
-void POOL_add(void *ctxVoid, POOL_function function, void *opaque) {
-    POOL_ctx *ctx = (POOL_ctx *)ctxVoid;
+/**
+ * Returns 1 if the queue is full and 0 otherwise.
+ *
+ * If the queueSize is 1 (the pool was created with an intended queueSize of 0),
+ * then a queue is empty if there is a thread free and no job is waiting.
+ */
+static int isQueueFull(POOL_ctx const* ctx) {
+    if (ctx->queueSize > 1) {
+        return ctx->queueHead == ((ctx->queueTail + 1) % ctx->queueSize);
+    } else {
+        return ctx->numThreadsBusy == ctx->numThreads ||
+               !ctx->queueEmpty;
+    }
+}
+
+void POOL_add(void* ctxVoid, POOL_function function, void *opaque) {
+    POOL_ctx* const ctx = (POOL_ctx*)ctxVoid;
     if (!ctx) { return; }
 
-    pthread_mutex_lock(&ctx->queueMutex);
+    ZSTD_pthread_mutex_lock(&ctx->queueMutex);
     {   POOL_job const job = {function, opaque};
+
         /* Wait until there is space in the queue for the new job */
-        size_t newTail = (ctx->queueTail + 1) % ctx->queueSize;
-        while (ctx->queueHead == newTail && !ctx->shutdown) {
-          pthread_cond_wait(&ctx->queuePushCond, &ctx->queueMutex);
-          newTail = (ctx->queueTail + 1) % ctx->queueSize;
+        while (isQueueFull(ctx) && !ctx->shutdown) {
+          ZSTD_pthread_cond_wait(&ctx->queuePushCond, &ctx->queueMutex);
         }
         /* The queue is still going => there is space */
         if (!ctx->shutdown) {
+            ctx->queueEmpty = 0;
             ctx->queue[ctx->queueTail] = job;
-            ctx->queueTail = newTail;
+            ctx->queueTail = (ctx->queueTail + 1) % ctx->queueSize;
         }
     }
-    pthread_mutex_unlock(&ctx->queueMutex);
-    pthread_cond_signal(&ctx->queuePopCond);
+    ZSTD_pthread_mutex_unlock(&ctx->queueMutex);
+    ZSTD_pthread_cond_signal(&ctx->queuePopCond);
 }
 
 #else  /* ZSTD_MULTITHREAD  not defined */
@@ -173,22 +220,35 @@ void POOL_add(void *ctxVoid, POOL_function function, void *opaque) {
 
 /* We don't need any data, but if it is empty malloc() might return NULL. */
 struct POOL_ctx_s {
-  int data;
+    int dummy;
 };
+static POOL_ctx g_ctx;
 
-POOL_ctx *POOL_create(size_t numThreads, size_t queueSize) {
-  (void)numThreads;
-  (void)queueSize;
-  return (POOL_ctx *)malloc(sizeof(POOL_ctx));
+POOL_ctx* POOL_create(size_t numThreads, size_t queueSize) {
+    return POOL_create_advanced(numThreads, queueSize, ZSTD_defaultCMem);
 }
 
-void POOL_free(POOL_ctx *ctx) {
-  if (ctx) free(ctx);
+POOL_ctx* POOL_create_advanced(size_t numThreads, size_t queueSize, ZSTD_customMem customMem) {
+    (void)numThreads;
+    (void)queueSize;
+    (void)customMem;
+    return &g_ctx;
+}
+
+void POOL_free(POOL_ctx* ctx) {
+    assert(!ctx || ctx == &g_ctx);
+    (void)ctx;
+}
+
+void POOL_add(void* ctx, POOL_function function, void* opaque) {
+    (void)ctx;
+    function(opaque);
 }
 
-void POOL_add(void *ctx, POOL_function function, void *opaque) {
-  (void)ctx;
-  function(opaque);
+size_t POOL_sizeof(POOL_ctx* ctx) {
+    if (ctx==NULL) return 0;  /* supports sizeof NULL */
+    assert(ctx == &g_ctx);
+    return sizeof(*ctx);
 }
 
 #endif  /* ZSTD_MULTITHREAD */

data/contrib/zstd/lib/common/pool.h

@@ -1,11 +1,13 @@
-/**
- * Copyright (c) 2016-present, Facebook, Inc.
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of this source tree. An additional grant
- * of patent rights can be found in the PATENTS file in the same directory.
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
  */
+
 #ifndef POOL_H
 #define POOL_H
 
@@ -15,23 +17,30 @@ extern "C" {
 
 
 #include <stddef.h>   /* size_t */
+#include "zstd_internal.h"   /* ZSTD_customMem */
 
 typedef struct POOL_ctx_s POOL_ctx;
 
 /*! POOL_create() :
-    Create a thread pool with at most `numThreads` threads.
-    `numThreads` must be at least 1.
-    The maximum number of queued jobs before blocking is `queueSize`.
-    `queueSize` must be at least 1.
-    @return : The POOL_ctx pointer on success else NULL.
+ *  Create a thread pool with at most `numThreads` threads.
+ * `numThreads` must be at least 1.
+ *  The maximum number of queued jobs before blocking is `queueSize`.
+ * @return : POOL_ctx pointer on success, else NULL.
 */
 POOL_ctx *POOL_create(size_t numThreads, size_t queueSize);
 
+POOL_ctx *POOL_create_advanced(size_t numThreads, size_t queueSize, ZSTD_customMem customMem);
+
 /*! POOL_free() :
     Free a thread pool returned by POOL_create().
 */
 void POOL_free(POOL_ctx *ctx);
 
+/*! POOL_sizeof() :
+    return memory usage of pool returned by POOL_create().
+*/
+size_t POOL_sizeof(POOL_ctx *ctx);
+
 /*! POOL_function :
     The function type that can be added to a thread pool.
 */

data/contrib/zstd/lib/common/threading.c

@@ -1,11 +1,10 @@
-
 /**
  * Copyright (c) 2016 Tino Reichardt
  * All rights reserved.
  *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of this source tree. An additional grant
- * of patent rights can be found in the PATENTS file in the same directory.
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
  *
  * You can contact the author at:
  * - zstdmt source repository: https://github.com/mcmilk/zstdmt
@@ -15,12 +14,8 @@
  * This file will hold wrapper for systems, which do not support pthreads
  */
 
-/* When ZSTD_MULTITHREAD is not defined, this file would become an empty translation unit.
-* Include some ISO C header code to prevent this and portably avoid related warnings.
-* (Visual C++: C4206 / GCC: -Wpedantic / Clang: -Wempty-translation-unit)
-*/
-#include <stddef.h>
-
+/* create fake symbol to avoid empty trnaslation unit warning */
+int g_ZSTD_threading_useles_symbol;
 
 #if defined(ZSTD_MULTITHREAD) && defined(_WIN32)
 
@@ -40,12 +35,12 @@
 
 static unsigned __stdcall worker(void *arg)
 {
-    pthread_t* const thread = (pthread_t*) arg;
+    ZSTD_pthread_t* const thread = (ZSTD_pthread_t*) arg;
     thread->arg = thread->start_routine(thread->arg);
     return 0;
 }
 
-int pthread_create(pthread_t* thread, const void* unused,
+int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused,
             void* (*start_routine) (void*), void* arg)
 {
     (void)unused;
@@ -59,16 +54,16 @@ int pthread_create(pthread_t* thread, const void* unused,
         return 0;
 }
 
-int _pthread_join(pthread_t * thread, void **value_ptr)
+int ZSTD_pthread_join(ZSTD_pthread_t thread, void **value_ptr)
 {
     DWORD result;
 
-    if (!thread->handle) return 0;
+    if (!thread.handle) return 0;
 
-    result = WaitForSingleObject(thread->handle, INFINITE);
+    result = WaitForSingleObject(thread.handle, INFINITE);
     switch (result) {
     case WAIT_OBJECT_0:
-        if (value_ptr) *value_ptr = thread->arg;
+        if (value_ptr) *value_ptr = thread.arg;
         return 0;
     case WAIT_ABANDONED:
         return EINVAL;

data/contrib/zstd/lib/common/threading.h

@@ -1,11 +1,10 @@
-
 /**
  * Copyright (c) 2016 Tino Reichardt
  * All rights reserved.
  *
- * This source code is licensed under the BSD-style license found in the
- * LICENSE file in the root directory of this source tree. An additional grant
- * of patent rights can be found in the PATENTS file in the same directory.
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
  *
  * You can contact the author at:
  * - zstdmt source repository: https://github.com/mcmilk/zstdmt
@@ -38,35 +37,38 @@ extern "C" {
 #  define WIN32_LEAN_AND_MEAN
 #endif
 
+#undef ERROR   /* reported already defined on VS 2015 (Rich Geldreich) */
 #include <windows.h>
+#undef ERROR
+#define ERROR(name) ZSTD_ERROR(name)
+
 
 /* mutex */
-#define pthread_mutex_t           CRITICAL_SECTION
-#define pthread_mutex_init(a,b)   InitializeCriticalSection((a))
-#define pthread_mutex_destroy(a)  DeleteCriticalSection((a))
-#define pthread_mutex_lock(a)     EnterCriticalSection((a))
-#define pthread_mutex_unlock(a)   LeaveCriticalSection((a))
+#define ZSTD_pthread_mutex_t           CRITICAL_SECTION
+#define ZSTD_pthread_mutex_init(a, b)  (InitializeCriticalSection((a)), 0)
+#define ZSTD_pthread_mutex_destroy(a)  DeleteCriticalSection((a))
+#define ZSTD_pthread_mutex_lock(a)     EnterCriticalSection((a))
+#define ZSTD_pthread_mutex_unlock(a)   LeaveCriticalSection((a))
 
 /* condition variable */
-#define pthread_cond_t             CONDITION_VARIABLE
-#define pthread_cond_init(a, b)    InitializeConditionVariable((a))
-#define pthread_cond_destroy(a)    /* No delete */
-#define pthread_cond_wait(a, b)    SleepConditionVariableCS((a), (b), INFINITE)
-#define pthread_cond_signal(a)     WakeConditionVariable((a))
-#define pthread_cond_broadcast(a)  WakeAllConditionVariable((a))
-
-/* pthread_create() and pthread_join() */
+#define ZSTD_pthread_cond_t             CONDITION_VARIABLE
+#define ZSTD_pthread_cond_init(a, b)    (InitializeConditionVariable((a)), 0)
+#define ZSTD_pthread_cond_destroy(a)    /* No delete */
+#define ZSTD_pthread_cond_wait(a, b)    SleepConditionVariableCS((a), (b), INFINITE)
+#define ZSTD_pthread_cond_signal(a)     WakeConditionVariable((a))
+#define ZSTD_pthread_cond_broadcast(a)  WakeAllConditionVariable((a))
+
+/* ZSTD_pthread_create() and ZSTD_pthread_join() */
 typedef struct {
     HANDLE handle;
     void* (*start_routine)(void*);
     void* arg;
-} pthread_t;
+} ZSTD_pthread_t;
 
-int pthread_create(pthread_t* thread, const void* unused,
+int ZSTD_pthread_create(ZSTD_pthread_t* thread, const void* unused,
                    void* (*start_routine) (void*), void* arg);
 
-#define pthread_join(a, b) _pthread_join(&(a), (b))
-int _pthread_join(pthread_t* thread, void** value_ptr);
+int ZSTD_pthread_join(ZSTD_pthread_t thread, void** value_ptr);
 
 /**
  * add here more wrappers as required
@@ -77,23 +79,40 @@ int _pthread_join(pthread_t* thread, void** value_ptr);
 /* ===   POSIX Systems   === */
 #  include <pthread.h>
 
+#define ZSTD_pthread_mutex_t            pthread_mutex_t
+#define ZSTD_pthread_mutex_init(a, b)   pthread_mutex_init((a), (b))
+#define ZSTD_pthread_mutex_destroy(a)   pthread_mutex_destroy((a))
+#define ZSTD_pthread_mutex_lock(a)      pthread_mutex_lock((a))
+#define ZSTD_pthread_mutex_unlock(a)    pthread_mutex_unlock((a))
+
+#define ZSTD_pthread_cond_t             pthread_cond_t
+#define ZSTD_pthread_cond_init(a, b)    pthread_cond_init((a), (b))
+#define ZSTD_pthread_cond_destroy(a)    pthread_cond_destroy((a))
+#define ZSTD_pthread_cond_wait(a, b)    pthread_cond_wait((a), (b))
+#define ZSTD_pthread_cond_signal(a)     pthread_cond_signal((a))
+#define ZSTD_pthread_cond_broadcast(a)  pthread_cond_broadcast((a))
+
+#define ZSTD_pthread_t                  pthread_t
+#define ZSTD_pthread_create(a, b, c, d) pthread_create((a), (b), (c), (d))
+#define ZSTD_pthread_join(a, b)         pthread_join((a),(b))
+
 #else  /* ZSTD_MULTITHREAD not defined */
 /* No multithreading support */
 
-#define pthread_mutex_t int   /* #define rather than typedef, as sometimes pthread support is implicit, resulting in duplicated symbols */
-#define pthread_mutex_init(a,b)
-#define pthread_mutex_destroy(a)
-#define pthread_mutex_lock(a)
-#define pthread_mutex_unlock(a)
+typedef int ZSTD_pthread_mutex_t;
+#define ZSTD_pthread_mutex_init(a, b)   ((void)a, 0)
+#define ZSTD_pthread_mutex_destroy(a)
+#define ZSTD_pthread_mutex_lock(a)
+#define ZSTD_pthread_mutex_unlock(a)
 
-#define pthread_cond_t int
-#define pthread_cond_init(a,b)
-#define pthread_cond_destroy(a)
-#define pthread_cond_wait(a,b)
-#define pthread_cond_signal(a)
-#define pthread_cond_broadcast(a)
+typedef int ZSTD_pthread_cond_t;
+#define ZSTD_pthread_cond_init(a, b)    ((void)a, 0)
+#define ZSTD_pthread_cond_destroy(a)
+#define ZSTD_pthread_cond_wait(a, b)
+#define ZSTD_pthread_cond_signal(a)
+#define ZSTD_pthread_cond_broadcast(a)
 
-/* do not use pthread_t */
+/* do not use ZSTD_pthread_t */
 
 #endif /* ZSTD_MULTITHREAD */
 

data/contrib/zstd/lib/common/xxhash.c

@@ -113,19 +113,25 @@ static void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcp
 /* *************************************
 *  Compiler Specific Options
 ***************************************/
-#ifdef _MSC_VER    /* Visual Studio */
-#  pragma warning(disable : 4127)      /* disable: C4127: conditional expression is constant */
-#  define FORCE_INLINE static __forceinline
+#if defined (__GNUC__) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
+#  define INLINE_KEYWORD inline
 #else
-#  if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   /* C99 */
-#    ifdef __GNUC__
-#      define FORCE_INLINE static inline __attribute__((always_inline))
-#    else
-#      define FORCE_INLINE static inline
-#    endif
-#  else
-#    define FORCE_INLINE static
-#  endif /* __STDC_VERSION__ */
+#  define INLINE_KEYWORD
+#endif
+
+#if defined(__GNUC__)
+#  define FORCE_INLINE_ATTR __attribute__((always_inline))
+#elif defined(_MSC_VER)
+#  define FORCE_INLINE_ATTR __forceinline
+#else
+#  define FORCE_INLINE_ATTR
+#endif
+
+#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
+
+
+#ifdef _MSC_VER
+#  pragma warning(disable : 4127)      /* disable: C4127: conditional expression is constant */
 #endif
 
 
@@ -248,7 +254,7 @@ typedef enum { XXH_bigEndian=0, XXH_littleEndian=1 } XXH_endianess;
 *****************************/
 typedef enum { XXH_aligned, XXH_unaligned } XXH_alignment;
 
-FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
+FORCE_INLINE_TEMPLATE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
 {
     if (align==XXH_unaligned)
         return endian==XXH_littleEndian ? XXH_read32(ptr) : XXH_swap32(XXH_read32(ptr));
@@ -256,7 +262,7 @@ FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian, XXH_a
         return endian==XXH_littleEndian ? *(const U32*)ptr : XXH_swap32(*(const U32*)ptr);
 }
 
-FORCE_INLINE U32 XXH_readLE32(const void* ptr, XXH_endianess endian)
+FORCE_INLINE_TEMPLATE U32 XXH_readLE32(const void* ptr, XXH_endianess endian)
 {
     return XXH_readLE32_align(ptr, endian, XXH_unaligned);
 }
@@ -266,7 +272,7 @@ static U32 XXH_readBE32(const void* ptr)
     return XXH_CPU_LITTLE_ENDIAN ? XXH_swap32(XXH_read32(ptr)) : XXH_read32(ptr);
 }
 
-FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
+FORCE_INLINE_TEMPLATE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_alignment align)
 {
     if (align==XXH_unaligned)
         return endian==XXH_littleEndian ? XXH_read64(ptr) : XXH_swap64(XXH_read64(ptr));
@@ -274,7 +280,7 @@ FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian, XXH_a
         return endian==XXH_littleEndian ? *(const U64*)ptr : XXH_swap64(*(const U64*)ptr);
 }
 
-FORCE_INLINE U64 XXH_readLE64(const void* ptr, XXH_endianess endian)
+FORCE_INLINE_TEMPLATE U64 XXH_readLE64(const void* ptr, XXH_endianess endian)
 {
     return XXH_readLE64_align(ptr, endian, XXH_unaligned);
 }
@@ -335,7 +341,7 @@ static U32 XXH32_round(U32 seed, U32 input)
     return seed;
 }
 
-FORCE_INLINE U32 XXH32_endian_align(const void* input, size_t len, U32 seed, XXH_endianess endian, XXH_alignment align)
+FORCE_INLINE_TEMPLATE U32 XXH32_endian_align(const void* input, size_t len, U32 seed, XXH_endianess endian, XXH_alignment align)
 {
     const BYTE* p = (const BYTE*)input;
     const BYTE* bEnd = p + len;
@@ -435,7 +441,7 @@ static U64 XXH64_mergeRound(U64 acc, U64 val)
     return acc;
 }
 
-FORCE_INLINE U64 XXH64_endian_align(const void* input, size_t len, U64 seed, XXH_endianess endian, XXH_alignment align)
+FORCE_INLINE_TEMPLATE U64 XXH64_endian_align(const void* input, size_t len, U64 seed, XXH_endianess endian, XXH_alignment align)
 {
     const BYTE* p = (const BYTE*)input;
     const BYTE* const bEnd = p + len;
@@ -584,7 +590,7 @@ XXH_PUBLIC_API XXH_errorcode XXH64_reset(XXH64_state_t* statePtr, unsigned long
 }
 
 
-FORCE_INLINE XXH_errorcode XXH32_update_endian (XXH32_state_t* state, const void* input, size_t len, XXH_endianess endian)
+FORCE_INLINE_TEMPLATE XXH_errorcode XXH32_update_endian (XXH32_state_t* state, const void* input, size_t len, XXH_endianess endian)
 {
     const BYTE* p = (const BYTE*)input;
     const BYTE* const bEnd = p + len;
@@ -654,7 +660,7 @@ XXH_PUBLIC_API XXH_errorcode XXH32_update (XXH32_state_t* state_in, const void*
 
 
 
-FORCE_INLINE U32 XXH32_digest_endian (const XXH32_state_t* state, XXH_endianess endian)
+FORCE_INLINE_TEMPLATE U32 XXH32_digest_endian (const XXH32_state_t* state, XXH_endianess endian)
 {
     const BYTE * p = (const BYTE*)state->mem32;
     const BYTE* const bEnd = (const BYTE*)(state->mem32) + state->memsize;
@@ -704,7 +710,7 @@ XXH_PUBLIC_API unsigned int XXH32_digest (const XXH32_state_t* state_in)
 
 /* **** XXH64 **** */
 
-FORCE_INLINE XXH_errorcode XXH64_update_endian (XXH64_state_t* state, const void* input, size_t len, XXH_endianess endian)
+FORCE_INLINE_TEMPLATE XXH_errorcode XXH64_update_endian (XXH64_state_t* state, const void* input, size_t len, XXH_endianess endian)
 {
     const BYTE* p = (const BYTE*)input;
     const BYTE* const bEnd = p + len;
@@ -771,7 +777,7 @@ XXH_PUBLIC_API XXH_errorcode XXH64_update (XXH64_state_t* state_in, const void*
 
 
 
-FORCE_INLINE U64 XXH64_digest_endian (const XXH64_state_t* state, XXH_endianess endian)
+FORCE_INLINE_TEMPLATE U64 XXH64_digest_endian (const XXH64_state_t* state, XXH_endianess endian)
 {
     const BYTE * p = (const BYTE*)state->mem64;
     const BYTE* const bEnd = (const BYTE*)state->mem64 + state->memsize;