-
Notifications
You must be signed in to change notification settings - Fork 310
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Fix stream synchronization in MTMG graph construction #4275
Fix stream synchronization in MTMG graph construction #4275
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
* @param device_buffer_size Number of edges to store in each device buffer | ||
* @param use_weight Whether or not the edgelist will have weights | ||
* @param use_edge_id Whether or not the edgelist will have edge ids | ||
* @param use_edge_type Whether or not the edgelist will have edge types | ||
*/ | ||
per_device_edgelist_t(cugraph::mtmg::handle_t const& handle, | ||
per_device_edgelist_t(rmm::cuda_stream_view stream_view, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Something tedious, but I guess our convention is to pass the handle as the first input argument and stream_view as the last input argument. Should we better keep this convention?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, I should have caught that. I will make that change.
/merge |
Restructure to pass stream instead of handle and synchronize appropriately.
Closes #4236