Skip to content
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

problem with BFS topdown algorithm #53

Open
samuelecancellieri opened this issue May 2, 2020 · 2 comments
Open

problem with BFS topdown algorithm #53

samuelecancellieri opened this issue May 2, 2020 · 2 comments

Comments

@samuelecancellieri
Copy link

Hi,

I'm trying to implement an algorithm based on the top down BFS integrated in hornet,
but I obtained different results every time I execute the BFS.

For example, I fix the root for the BFS, I start the algorithm and in the end I check the distance array.
Every time the distances of the same vertices are different in the results array, how is that possible?

I thought about some compatibility problem, but I tested with cuda 9 and cuda 10 and I have always this problem.

Thanks for the help.

@ogreen
Copy link
Collaborator

ogreen commented May 4, 2020

Are you using TopDown or TopDown2? I would recommend using TopDown2. TopDown using a unique optimization that allows for "over-queuing" elements while improving overall performance.

Also, I would suggest moving this discussion to:
https://github.com/rapidsai/cuhornet
We have made a lot of modifications to Hornet in the last year that have not been applied to this framework.

@samuelecancellieri
Copy link
Author

Thanks.
I will download the new repository and try the alternative topdown BFS.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants