2.12. Event Management
This section describes the event management functions of the low-level CUDA driver application programming interface.
Functions
- CUresult cuEventCreate ( CUevent* phEvent, unsigned int Flags )
- Creates an event.
- CUresult cuEventDestroy ( CUevent hEvent )
- Destroys an event.
- CUresult cuEventElapsedTime ( float* pMilliseconds, CUevent hStart, CUevent hEnd )
- Computes the elapsed time between two events.
- CUresult cuEventQuery ( CUevent hEvent )
- Queries an event's status.
- CUresult cuEventRecord ( CUevent hEvent, CUstream hStream )
- Records an event.
- CUresult cuEventSynchronize ( CUevent hEvent )
- Waits for an event to complete.
Functions
- CUresult cuEventCreate ( CUevent* phEvent, unsigned int Flags )
-
Creates an event. Creates an event *phEvent with the flags specified via Flags. Valid flags include:
-
CU_EVENT_DEFAULT: Default event creation flag.
-
CU_EVENT_BLOCKING_SYNC: Specifies that the created event should use blocking synchronization. A CPU thread that uses cuEventSynchronize() to wait on an event created with this flag will block until the event has actually been recorded.
-
CU_EVENT_DISABLE_TIMING: Specifies that the created event does not need to record timing data. Events created with this flag specified and the CU_EVENT_BLOCKING_SYNC flag not specified will provide the best performance when used with cuStreamWaitEvent() and cuEventQuery().
-
CU_EVENT_INTERPROCESS: Specifies that the created event may be used as an interprocess event by cuIpcGetEventHandle(). CU_EVENT_INTERPROCESS must be specified along with CU_EVENT_DISABLE_TIMING.
Note:Note that this function may also return error codes from previous, asynchronous launches.
See also:
cuEventRecord, cuEventQuery, cuEventSynchronize, cuEventDestroy, cuEventElapsedTime
Parameters
- phEvent
- - Returns newly created event
- Flags
- - Event creation flags
-
- CUresult cuEventDestroy ( CUevent hEvent )
-
Destroys an event. Destroys the event specified by hEvent.
In the case that hEvent has been recorded but has not yet been completed when cuEventDestroy() is called, the function will return immediately and the resources associated with hEvent will be released automatically once the device has completed hEvent.
Note:Note that this function may also return error codes from previous, asynchronous launches.
See also:
cuEventCreate, cuEventRecord, cuEventQuery, cuEventSynchronize, cuEventElapsedTime
Parameters
- hEvent
- - Event to destroy
- CUresult cuEventElapsedTime ( float* pMilliseconds, CUevent hStart, CUevent hEnd )
-
Computes the elapsed time between two events. Computes the elapsed time between two events (in milliseconds with a resolution of around 0.5 microseconds).
If either event was last recorded in a non-NULL stream, the resulting time may be greater than expected (even if both used the same stream handle). This happens because the cuEventRecord() operation takes place asynchronously and there is no guarantee that the measured latency is actually just between the two events. Any number of other different stream operations could execute in between the two measured events, thus altering the timing in a significant way.
If cuEventRecord() has not been called on either event then CUDA_ERROR_INVALID_HANDLE is returned. If cuEventRecord() has been called on both events but one or both of them has not yet been completed (that is, cuEventQuery() would return CUDA_ERROR_NOT_READY on at least one of the events), CUDA_ERROR_NOT_READY is returned. If either event was created with the CU_EVENT_DISABLE_TIMING flag, then this function will return CUDA_ERROR_INVALID_HANDLE.
Note:Note that this function may also return error codes from previous, asynchronous launches.
See also:
cuEventCreate, cuEventRecord, cuEventQuery, cuEventSynchronize, cuEventDestroy
Parameters
- pMilliseconds
- - Time between hStart and hEnd in ms
- hStart
- - Starting event
- hEnd
- - Ending event
- CUresult cuEventQuery ( CUevent hEvent )
-
Queries an event's status. Query the status of all device work preceding the most recent call to cuEventRecord() (in the appropriate compute streams, as specified by the arguments to cuEventRecord()).
If this work has successfully been completed by the device, or if cuEventRecord() has not been called on hEvent, then CUDA_SUCCESS is returned. If this work has not yet been completed by the device then CUDA_ERROR_NOT_READY is returned.
Note:Note that this function may also return error codes from previous, asynchronous launches.
See also:
cuEventCreate, cuEventRecord, cuEventSynchronize, cuEventDestroy, cuEventElapsedTime
Parameters
- hEvent
- - Event to query
- CUresult cuEventRecord ( CUevent hEvent, CUstream hStream )
-
Records an event. Records an event. If hStream is non-zero, the event is recorded after all preceding operations in hStream have been completed; otherwise, it is recorded after all preceding operations in the CUDA context have been completed. Since operation is asynchronous, cuEventQuery and/or cuEventSynchronize() must be used to determine when the event has actually been recorded.
If cuEventRecord() has previously been called on hEvent, then this call will overwrite any existing state in hEvent. Any subsequent calls which examine the status of hEvent will only examine the completion of this most recent call to cuEventRecord().
It is necessary that hEvent and hStream be created on the same context.
Note:Note that this function may also return error codes from previous, asynchronous launches.
See also:
cuEventCreate, cuEventQuery, cuEventSynchronize, cuStreamWaitEvent, cuEventDestroy, cuEventElapsedTime
Parameters
- hEvent
- - Event to record
- hStream
- - Stream to record event for
- CUresult cuEventSynchronize ( CUevent hEvent )
-
Waits for an event to complete. Wait until the completion of all device work preceding the most recent call to cuEventRecord() (in the appropriate compute streams, as specified by the arguments to cuEventRecord()).
If cuEventRecord() has not been called on hEvent, CUDA_SUCCESS is returned immediately.
Waiting for an event that was created with the CU_EVENT_BLOCKING_SYNC flag will cause the calling CPU thread to block until the event has been completed by the device. If the CU_EVENT_BLOCKING_SYNC flag has not been set, then the CPU thread will busy-wait until the event has been completed by the device.
Note:Note that this function may also return error codes from previous, asynchronous launches.
See also:
cuEventCreate, cuEventRecord, cuEventQuery, cuEventDestroy, cuEventElapsedTime
Parameters
- hEvent
- - Event to wait for