Merge pull request #1976 from alalek:ocl_multiple_command_queues

modules/core/include/opencv2/core/core.hpp

@@ -4821,6 +4821,32 @@ private:
     AutoLock& operator = (const AutoLock&);
 };
 
+class TLSDataContainer
+{
+private:
+    int key_;
+protected:
+    CV_EXPORTS TLSDataContainer();
+    CV_EXPORTS ~TLSDataContainer(); // virtual is not required
+public:
+    virtual void* createDataInstance() const = 0;
+    virtual void deleteDataInstance(void* data) const = 0;
+
+    CV_EXPORTS void* getData() const;
+};
+
+template <typename T>
+class TLSData : protected TLSDataContainer
+{
+public:
+    inline TLSData() {}
+    inline ~TLSData() {}
+    inline T* get() const { return (T*)getData(); }
+private:
+    virtual void* createDataInstance() const { return new T; }
+    virtual void deleteDataInstance(void* data) const { delete (T*)data; }
+};
+
 }
 
 #endif // __cplusplus

modules/core/src/system.cpp

@@ -806,24 +806,6 @@ cvGetModuleInfo( const char* name, const char **version, const char **plugin_lis
         *plugin_list = plugin_list_buf;
 }
 
-#if defined CVAPI_EXPORTS && defined WIN32 && !defined WINCE
-#ifdef HAVE_WINRT
-    #pragma warning(disable:4447) // Disable warning 'main' signature found without threading model
-#endif
-
-BOOL WINAPI DllMain( HINSTANCE, DWORD  fdwReason, LPVOID );
-
-BOOL WINAPI DllMain( HINSTANCE, DWORD  fdwReason, LPVOID )
-{
-    if( fdwReason == DLL_THREAD_DETACH || fdwReason == DLL_PROCESS_DETACH )
-    {
-        cv::deleteThreadAllocData();
-        cv::deleteThreadRNGData();
-    }
-    return TRUE;
-}
-#endif
-
 namespace cv
 {
 
@@ -941,6 +923,223 @@ void Mutex::lock() { impl->lock(); }
 void Mutex::unlock() { impl->unlock(); }
 bool Mutex::trylock() { return impl->trylock(); }
 
+
+//////////////////////////////// thread-local storage ////////////////////////////////
+
+class TLSStorage
+{
+    std::vector<void*> tlsData_;
+public:
+    TLSStorage() { tlsData_.reserve(16); }
+    ~TLSStorage();
+    inline void* getData(int key) const
+    {
+        CV_DbgAssert(key >= 0);
+        return (key < (int)tlsData_.size()) ? tlsData_[key] : NULL;
+    }
+    inline void setData(int key, void* data)
+    {
+        CV_DbgAssert(key >= 0);
+        if (key >= (int)tlsData_.size())
+        {
+            tlsData_.resize(key + 1, NULL);
+        }
+        tlsData_[key] = data;
+    }
+
+    inline static TLSStorage* get();
+};
+
+#ifdef WIN32
+#pragma warning(disable:4505) // unreferenced local function has been removed
+
+#ifdef HAVE_WINRT
+    // using C++11 thread attribute for local thread data
+    static __declspec( thread ) TLSStorage* g_tlsdata = NULL;
+
+    static void deleteThreadData()
+    {
+        if (g_tlsdata)
+        {
+            delete g_tlsdata;
+            g_tlsdata = NULL;
+        }
+    }
+
+    inline TLSStorage* TLSStorage::get()
+    {
+        if (!g_tlsdata)
+        {
+            g_tlsdata = new TLSStorage;
+        }
+        return g_tlsdata;
+    }
+#else
+#ifdef WINCE
+#   define TLS_OUT_OF_INDEXES ((DWORD)0xFFFFFFFF)
+#endif
+    static DWORD tlsKey = TLS_OUT_OF_INDEXES;
+
+    static void deleteThreadData()
+    {
+        if(tlsKey != TLS_OUT_OF_INDEXES)
+        {
+            delete (TLSStorage*)TlsGetValue(tlsKey);
+            TlsSetValue(tlsKey, NULL);
+        }
+    }
+
+    inline TLSStorage* TLSStorage::get()
+    {
+        if (tlsKey == TLS_OUT_OF_INDEXES)
+        {
+            tlsKey = TlsAlloc();
+            CV_Assert(tlsKey != TLS_OUT_OF_INDEXES);
+        }
+        TLSStorage* d = (TLSStorage*)TlsGetValue(tlsKey);
+        if (!d)
+        {
+            d = new TLSStorage;
+            TlsSetValue(tlsKey, d);
+        }
+        return d;
+    }
+#endif //HAVE_WINRT
+
+#if defined CVAPI_EXPORTS && defined WIN32 && !defined WINCE
+#ifdef HAVE_WINRT
+    #pragma warning(disable:4447) // Disable warning 'main' signature found without threading model
+#endif
+
+BOOL WINAPI DllMain(HINSTANCE, DWORD fdwReason, LPVOID);
+
+BOOL WINAPI DllMain(HINSTANCE, DWORD fdwReason, LPVOID)
+{
+    if (fdwReason == DLL_THREAD_DETACH || fdwReason == DLL_PROCESS_DETACH)
+    {
+        cv::deleteThreadAllocData();
+        cv::deleteThreadRNGData();
+        cv::deleteThreadData();
+    }
+    return TRUE;
+}
+#endif
+
+#else
+    static pthread_key_t tlsKey = 0;
+    static pthread_once_t tlsKeyOnce = PTHREAD_ONCE_INIT;
+
+    static void deleteTLSStorage(void* data)
+    {
+        delete (TLSStorage*)data;
+    }
+
+    static void makeKey()
+    {
+        int errcode = pthread_key_create(&tlsKey, deleteTLSStorage);
+        CV_Assert(errcode == 0);
+    }
+
+    inline TLSStorage* TLSStorage::get()
+    {
+        pthread_once(&tlsKeyOnce, makeKey);
+        TLSStorage* d = (TLSStorage*)pthread_getspecific(tlsKey);
+        if( !d )
+        {
+            d = new TLSStorage;
+            pthread_setspecific(tlsKey, d);
+        }
+        return d;
+    }
+#endif
+
+class TLSContainerStorage
+{
+    cv::Mutex mutex_;
+    std::vector<TLSDataContainer*> tlsContainers_;
+public:
+    TLSContainerStorage() { }
+    ~TLSContainerStorage()
+    {
+        for (size_t i = 0; i < tlsContainers_.size(); i++)
+        {
+            CV_DbgAssert(tlsContainers_[i] == NULL); // not all keys released
+            tlsContainers_[i] = NULL;
+        }
+    }
+
+    int allocateKey(TLSDataContainer* pContainer)
+    {
+        cv::AutoLock lock(mutex_);
+        tlsContainers_.push_back(pContainer);
+        return (int)tlsContainers_.size() - 1;
+    }
+    void releaseKey(int id, TLSDataContainer* pContainer)
+    {
+        cv::AutoLock lock(mutex_);
+        CV_Assert(tlsContainers_[id] == pContainer);
+        tlsContainers_[id] = NULL;
+        // currently, we don't go into thread's TLSData and release data for this key
+    }
+
+    void destroyData(int key, void* data)
+    {
+        cv::AutoLock lock(mutex_);
+        TLSDataContainer* k = tlsContainers_[key];
+        if (!k)
+            return;
+        try
+        {
+            k->deleteDataInstance(data);
+        }
+        catch (...)
+        {
+            CV_DbgAssert(k == NULL); // Debug this!
+        }
+    }
+};
+static TLSContainerStorage tlsContainerStorage;
+
+TLSDataContainer::TLSDataContainer()
+    : key_(-1)
+{
+    key_ = tlsContainerStorage.allocateKey(this);
 }
 
+TLSDataContainer::~TLSDataContainer()
+{
+    tlsContainerStorage.releaseKey(key_, this);
+    key_ = -1;
+}
+
+void* TLSDataContainer::getData() const
+{
+    CV_Assert(key_ >= 0);
+    TLSStorage* tlsData = TLSStorage::get();
+    void* data = tlsData->getData(key_);
+    if (!data)
+    {
+        data = this->createDataInstance();
+        CV_DbgAssert(data != NULL);
+        tlsData->setData(key_, data);
+    }
+    return data;
+}
+
+TLSStorage::~TLSStorage()
+{
+    for (int i = 0; i < (int)tlsData_.size(); i++)
+    {
+        void*& data = tlsData_[i];
+        if (data)
+        {
+            tlsContainerStorage.destroyData(i, data);
+            data = NULL;
+        }
+    }
+    tlsData_.clear();
+}
+
+} // namespace cv
+
 /* End of file. */

modules/ocl/src/cl_context.cpp

@@ -57,6 +57,10 @@
 namespace cv {
 namespace ocl {
 
+#if defined(WIN32)
+static bool __termination = false;
+#endif
+
 struct __Module
 {
     __Module();
@@ -494,6 +498,38 @@ PlatformInfo::PlatformInfo()
     // nothing
 }
 
+class ContextImpl;
+
+struct CommandQueue
+{
+    ContextImpl* context_;
+    cl_command_queue clQueue_;
+
+    CommandQueue() : context_(NULL), clQueue_(NULL) { }
+    ~CommandQueue() { release(); }
+
+    void create(ContextImpl* context_);
+    void release()
+    {
+#ifdef WIN32
+        // if process is on termination stage (ExitProcess was called and other threads were terminated)
+        // then disable command queue release because it may cause program hang
+        if (!__termination)
+#endif
+        {
+            if(clQueue_)
+            {
+                openCLSafeCall(clReleaseCommandQueue(clQueue_)); // some cleanup problems are here
+            }
+
+        }
+        clQueue_ = NULL;
+        context_ = NULL;
+    }
+};
+
+cv::TLSData<CommandQueue> commandQueueTLSData;
+
 //////////////////////////////// OpenCL context ////////////////////////
 //This is a global singleton class used to represent a OpenCL context.
 class ContextImpl : public Context
@@ -501,12 +537,11 @@ class ContextImpl : public Context
 public:
     const cl_device_id clDeviceID;
     cl_context clContext;
-    cl_command_queue clCmdQueue;
     const DeviceInfo& deviceInfo;
 
 protected:
     ContextImpl(const DeviceInfo& deviceInfo, cl_device_id clDeviceID)
-        : clDeviceID(clDeviceID), clContext(NULL), clCmdQueue(NULL), deviceInfo(deviceInfo)
+        : clDeviceID(clDeviceID), clContext(NULL), deviceInfo(deviceInfo)
     {
         // nothing
     }
@@ -581,7 +616,13 @@ const void* Context::getOpenCLContextPtr() const
 
 const void* Context::getOpenCLCommandQueuePtr() const
 {
-    return &(((ContextImpl*)this)->clCmdQueue);
+    ContextImpl* pThis = (ContextImpl*)this;
+    CommandQueue* commandQueue = commandQueueTLSData.get();
+    if (commandQueue->context_ != pThis)
+    {
+        commandQueue->create(pThis);
+    }
+    return &commandQueue->clQueue_;
 }
 
 const void* Context::getOpenCLDeviceIDPtr() const
@@ -607,10 +648,6 @@ bool ContextImpl::supportsFeature(FEATURE_TYPE featureType) const
     return false;
 }
 
-#if defined(WIN32)
-static bool __termination = false;
-#endif
-
 ContextImpl::~ContextImpl()
 {
 #ifdef WIN32
@@ -619,17 +656,11 @@ ContextImpl::~ContextImpl()
     if (!__termination)
 #endif
     {
-        if(clCmdQueue)
-        {
-            openCLSafeCall(clReleaseCommandQueue(clCmdQueue)); // some cleanup problems are here
-        }
-
         if(clContext)
         {
             openCLSafeCall(clReleaseContext(clContext));
         }
     }
-    clCmdQueue = NULL;
     clContext = NULL;
 }
 
@@ -667,12 +698,8 @@ void ContextImpl::setContext(const DeviceInfo* deviceInfo)
     cl_context_properties cps[3] = { CL_CONTEXT_PLATFORM, (cl_context_properties)(infoImpl.platform_id), 0 };
     cl_context clContext = clCreateContext(cps, 1, &infoImpl.device_id, NULL, NULL, &status);
     openCLVerifyCall(status);
-    // TODO add CL_QUEUE_PROFILING_ENABLE
-    cl_command_queue clCmdQueue = clCreateCommandQueue(clContext, infoImpl.device_id, 0, &status);
-    openCLVerifyCall(status);
 
     ContextImpl* ctx = new ContextImpl(infoImpl.info, infoImpl.device_id);
-    ctx->clCmdQueue = clCmdQueue;
     ctx->clContext = clContext;
 
     ContextImpl* old = NULL;
@@ -687,6 +714,17 @@ void ContextImpl::setContext(const DeviceInfo* deviceInfo)
     }
 }
 
+void CommandQueue::create(ContextImpl* context)
+{
+    release();
+    cl_int status = 0;
+    // TODO add CL_QUEUE_PROFILING_ENABLE
+    cl_command_queue clCmdQueue = clCreateCommandQueue(context->clContext, context->clDeviceID, 0, &status);
+    openCLVerifyCall(status);
+    context_ = context;
+    clQueue_ = clCmdQueue;
+}
+
 int getOpenCLPlatforms(PlatformsInfo& platforms)
 {
     if (!__initialized)