cuda::event_t Class Reference

Wrapper class for a CUDA event. More...

#include <event.hpp>

Public Member Functions
device::id_t	device_id () const noexcept
	The raw CUDA ID for the device w.r.t. which the event is defined.
context::handle_t	context_handle () const noexcept
	The raw CUDA handle for the context in which the represented stream is defined.
event::handle_t	handle () const noexcept
	The raw CUDA handle for this event.
bool	is_owning () const noexcept
	True if this wrapper is responsible for telling CUDA to destroy the event upon the wrapper's own destruction.
bool	holds_primary_context_reference () const noexcept
	True if this wrapper has been associated with an increase of the device's primary context's reference count.
device_t	device () const
	The device w.r.t. which the event is defined.
context_t	context () const
	The context in which this stream was defined.
bool	has_occurred () const
	Has this event already occurred, or is it still pending on a stream? More...
bool	query () const
	An alias for {event_t::has_occurred()} - to conform to how the CUDA runtime API names this functionality.
void	record () const
	Schedule a specified event to occur (= to fire) when all activities already scheduled on the event's device's default stream have concluded. More...
void	record (const stream_t &stream) const
	Schedule a specified event to occur (= to fire) when all activities already scheduled on the stream have concluded. More...
void	fire (const stream_t &stream) const
	Records the event and ensures it has occurred before returning (by synchronizing the stream). More...
void	synchronize () const
	Have the calling thread wait - either busy-waiting or blocking - and return only after this event has occurred (see has_occurred() ).
	event_t (const event_t &other) noexcept
	event_t (event_t &&other) noexcept
event_t &	operator= (const event_t &)=delete
event_t &	operator= (event_t &&other) noexcept

Friends
event_t	event::wrap (device::id_t device, context::handle_t context_handle, event::handle_t event_handle, bool take_ownership, bool hold_pc_refcount_unit) noexcept

Detailed Description

Wrapper class for a CUDA event.

Use this class - built around an event handle - to perform almost, if not all, event-related operations the CUDA Runtime API is capable of.

Note

By default this class has RAII semantics, i.e. it has the runtime create an event on construction and destroy it on destruction, and isn't merely an ephemeral wrapper one could apply and discard; but this second kind of semantics is also (sort of) supported, through the event_t::owning field.

this is one of the three main classes in the Runtime API wrapper library, together with cuda::device_t and cuda::stream_t

This class is a "reference type", not a "value type". Therefore, making changes to the event is a const-respecting operation on this class.

Member Function Documentation

fire()

void cuda::event_t::fire ( const stream_t &  stream ) const

inline

Records the event and ensures it has occurred before returning (by synchronizing the stream).

Note

No protection against repeated calls.

has_occurred()

bool cuda::event_t::has_occurred ( ) const

inline

Has this event already occurred, or is it still pending on a stream?

Note

an event can occur multiple times, but in the context of this method, it only has two states: pending (on a stream) and has_occured.

Returns

if all work on the stream with which the event was recorded has been completed, returns true; if there is pending work on that stream before the point of recording, returns false; if the event has not been recorded at all, returns true.

record() [1/2]

void cuda::event_t::record ( ) const

inline

Schedule a specified event to occur (= to fire) when all activities already scheduled on the event's device's default stream have concluded.

Note

No protection against repeated calls.

record() [2/2]

void cuda::event_t::record ( const stream_t &  stream ) const

inline

Schedule a specified event to occur (= to fire) when all activities already scheduled on the stream have concluded.

Note

No protection against repeated calls.

---

The documentation for this class was generated from the following file:

• src/cuda/api/event.hpp