cv::cuda::Stream クラス

This class encapsulates a queue of asynchronous calls. [詳解]

#include <cuda.hpp>

公開型
typedef void(*	StreamCallback) (int status, void *userData)

公開メンバ関数
CV_WRAP	Stream ()
	creates a new asynchronous stream
CV_WRAP	Stream (const Ptr< GpuMat::Allocator > &allocator)
	creates a new asynchronous stream with custom allocator
CV_WRAP	Stream (const size_t cudaFlags)
	creates a new Stream using the cudaFlags argument to determine the behaviors of the stream [詳解]
CV_WRAP bool	queryIfComplete () const
	Returns true if the current stream queue is finished. Otherwise, it returns false.
CV_WRAP void	waitForCompletion ()
	Blocks the current CPU thread until all operations in the stream are complete.
CV_WRAP void	waitEvent (const Event &event)
	Makes a compute stream wait on an event.
void	enqueueHostCallback (StreamCallback callback, void *userData)
	Adds a callback to be called on the host after all currently enqueued items in the stream have completed. [詳解]
	operator bool_type () const
	returns true if stream object is not default (!= 0)
CV_WRAP void *	cudaPtr () const
	return Pointer to CUDA stream

静的公開メンバ関数
static CV_WRAP Stream &	Null ()
	return Stream object for default CUDA stream

フレンド
struct	StreamAccessor
class	BufferPool
class	DefaultDeviceInitializer

詳解

This class encapsulates a queue of asynchronous calls.

覚え書き

Currently, you may face problems if an operation is enqueued twice with different data. Some functions use the constant GPU memory, and next call may update the memory before the previous one has been finished. But calling different operations asynchronously is safe because each operation has its own constant buffer. Memory copy/upload/download/set operations to the buffers you hold are also safe.

The Stream class is not thread-safe. Please use different Stream objects for different CPU threads.

void thread1()
{
    cv::cuda::Stream stream1;
    cv::cuda::func1(..., stream1);
}
 
void thread2()
{
    cv::cuda::Stream stream2;
    cv::cuda::func2(..., stream2);
}

覚え書き

By default all CUDA routines are launched in Stream::Null() object, if the stream is not specified by user. In multi-threading environment the stream objects must be passed explicitly (see previous note).

構築子と解体子

Stream()

CV_WRAP cv::cuda::Stream::Stream

(

const size_t

cudaFlags

)

creates a new Stream using the cudaFlags argument to determine the behaviors of the stream

覚え書き

The cudaFlags parameter is passed to the underlying api cudaStreamCreateWithFlags() and supports the same parameter values.

// creates an OpenCV cuda::Stream that manages an asynchronous, non-blocking,
// non-default CUDA stream
cv::cuda::Stream cvStream(cudaStreamNonBlocking);

関数詳解

enqueueHostCallback()

void cv::cuda::Stream::enqueueHostCallback	(	StreamCallback	callback,
		void *	userData
	)

Adds a callback to be called on the host after all currently enqueued items in the stream have completed.

覚え書き

Callbacks must not make any CUDA API calls. Callbacks must not perform any synchronization that may depend on outstanding device work or other callbacks that are not mandated to run earlier. Callbacks without a mandated order (in independent streams) execute in undefined order and may be serialized.

---

このクラス詳解は次のファイルから抽出されました:

• core/cuda.hpp