Fix ArrowDeviceArray interface to pass address of event
Description
the sync_event member of ArrowDeviceArray needs to be a pointer to a cudaEvent_t, currently we're returning the cudaEvent_t directly. We need to be passing the address of the event. Thankfully this is a single line change, plus adding a test to confirm.
Checklist
- [x] I am familiar with the Contributing Guidelines.
- [x] New or existing tests cover these changes.
- [x] The documentation is up to date with these changes.
This pull request requires additional validation before any workflows can run on NVIDIA's runners.
Pull request vetters can view their responsibilities here.
Contributors can view more details about this message here.
CC @vyasr
/ok to test
Added calls to cudaEventSynchronize
/ok to test
@vyasr anything else needed for this to get merged?
/merge