stream.hpp File Reference

A proxy class for CUDA streams, providing access to all Runtime API calls involving their use and management. More...

#include "current_context.hpp"
#include "current_device.hpp"
#include "error.hpp"
#include "kernel_launch.hpp"
#include "memory.hpp"
#include "miscellany.hpp"
#include "types.hpp"
#include <string>
#include <memory>
#include <utility>
#include <tuple>
#include <algorithm>

Include dependency graph for stream.hpp:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	cuda::stream_t
	Proxy class for a CUDA stream. More...
class	cuda::stream_t::enqueue_t
	A gadget through which commands are enqueued on the stream. More...

Namespaces
	cuda
	Definitions and functionality wrapping CUDA APIs.
	cuda::memory
	Representation, allocation and manipulation of CUDA-related memory, of different.
	cuda::stream
	Definitions and functionality related to CUDA streams (not including the device wrapper type stream_t itself)

Enumerations
enum	: bool {   implicitly_synchronizes_with_default_stream = true,   no_implicit_synchronization_with_default_stream = false,   sync = implicitly_synchronizes_with_default_stream,   async = no_implicit_synchronization_with_default_stream,   blocking = sync,   nonblocking = async }
enum	cuda::stream::wait_condition_t : unsigned {   greater_or_equal_to = CU_STREAM_WAIT_VALUE_GEQ,   geq = CU_STREAM_WAIT_VALUE_GEQ,   equality = CU_STREAM_WAIT_VALUE_EQ,   equals = CU_STREAM_WAIT_VALUE_EQ,   nonzero_after_applying_bitmask = CU_STREAM_WAIT_VALUE_AND,   one_bits_overlap = CU_STREAM_WAIT_VALUE_AND,   bitwise_and = CU_STREAM_WAIT_VALUE_AND,   zero_bits_overlap = CU_STREAM_WAIT_VALUE_NOR,   bitwise_nor = CU_STREAM_WAIT_VALUE_NOR }
	Kinds of conditions to apply to a value in GPU global memory when waiting on that value, i.e. More...

Functions
stream_t	cuda::stream::wrap (device::id_t device_id, context::handle_t context_handle, handle_t stream_handle, bool take_ownership=false, bool hold_pc_refcount_unit=false) noexcept
	Wrap an existing stream in a stream_t instance. More...
void	cuda::synchronize (const stream_t &stream)
	Waits for all previously-scheduled tasks on a given stream to conclude, before returning. More...
stream_t	cuda::stream::create (const device_t &device, bool synchronizes_with_default_stream, priority_t priority=stream::default_priority)
	Create a new stream (= queue) in the primary execution context of a CUDA device. More...
stream_t	cuda::stream::create (const context_t &context, bool synchronizes_with_default_stream, priority_t priority=stream::default_priority, bool hold_pc_refcount_unit=false)
	Create a new stream (= queue) in a CUDA execution context. More...

Detailed Description

A proxy class for CUDA streams, providing access to all Runtime API calls involving their use and management.

Note

: Missing functionality: Stream attributes; stream capturing.