cuda.core.experimental._event.Event¶

class cuda.core.experimental._event.Event(*args, **kwargs)¶

Represent a record at a specific point of execution within a CUDA stream.

Applications can asynchronously record events at any point in the program. An event keeps a record of all previous work within the last recorded stream.

Events can be used to monitor device’s progress, query completion of work up to event’s record, and help establish dependencies between GPU work submissions.

Directly creating an Event is not supported due to ambiguity, and they should instead be created through a Stream object.

Methods

__init__()¶

close()¶: Destroy the event.

sync()¶

Synchronize until the event completes.

If the event was created with busy_waited_sync, then the calling CPU thread will block until the event has been completed by the device. Otherwise the CPU thread will busy-wait until the event has been completed.

Attributes

property handle: cuda.bindings.driver.CUevent¶: Return the underlying CUevent object.

property is_done: bool¶: Return True if all captured works have been completed, otherwise False.

property is_ipc_supported: bool¶: Return True if this event can be used as an interprocess event, otherwise False.

property is_sync_busy_waited: bool¶: Return True if the event synchronization would keep the CPU busy-waiting, otherwise False.

property is_timing_disabled: bool¶: Return True if the event does not record timing data, otherwise False.