cuda.bindings._v2.driver.stream_wait_event#

cuda.bindings._v2.driver.stream_wait_event(
intptr_t h_stream,
intptr_t h_event,
unsigned int flags,
)#

Make a compute stream wait on an event.

Makes all future work submitted to h_stream wait for all work captured in h_event. See event_record() for details on what is captured by an event. The synchronization will be performed efficiently on the device when applicable. h_event may be from a different context or device than h_stream. flags include:.

  • CU_EVENT_WAIT_DEFAULT: Default event creation flag.

  • CU_EVENT_WAIT_EXTERNAL: Event is captured in the graph as an external event node when performing stream capture. This flag is invalid outside of stream capture.

Parameters:

  • h_stream (intptr_t) – Stream to wait.

  • h_event (intptr_t) – Event to wait on (may not be NULL).

  • flags (unsigned int) – See CUevent_capture_flags.

See also

cuStreamWaitEvent

On this page