You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* Now properly setting the batch memory operation parameters for flush-remote-writes
* Now supporting the memory barrier batch-memory-operation (as an single operation, not in an actual batch)
* Now properly setting the batch memory operation parameters for flush-remote-writes
* Now supporting the memory barrier batch-memory-operation (as an single operation, not in an actual batch)
* Now properly setting the batch memory operation parameters for flush-remote-writes
* Now supporting the memory barrier batch-memory-operation (as an single operation, not in an actual batch)
* Now properly setting the batch memory operation parameters for flush-remote-writes
* Now supporting the memory barrier batch-memory-operation (as an single operation, not in an actual batch)
Here is the current list of "batch memory operations" one can enqueue on a CUDA stream:
these are described in this section of the CUDA driver API manual.
We already support all of these - except for the barrier operation. Let's add support for it.
The text was updated successfully, but these errors were encountered: