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

Tkurth/cuda disco reduce scatter #39

Closed
wants to merge 43 commits into from

Conversation

azrael417
Copy link
Collaborator

this PR fixes a potential issue with memory ordering in the distributed transpose. Furthermore, it adds support for reduce scatter in the distributed disco convolution.

azrael417 and others added 13 commits August 19, 2024 08:35
* attempt to make disco distributed

* working distributed convolutions

* fixing distributed conv

* working distributed disco

* removing irrelevant extra argument
* initial working commit with new convention of counting collocation points across the diameter instead of across the radius

* fixed a bug in the computation of the even kernels

* changing heuristic for computing theta_cutoff

* Fixing unittest

* Readability improvements
* cleaned up normalization code in convolution

* formatting changes in distributed convolution

* Fixing default theta_cutoff to be the same in distributed and local case

* fixed distributed convolution to support the same normalization as non-distributed one

* readability improvements
@azrael417 azrael417 force-pushed the tkurth/cuda-disco-reduce-scatter branch from 92d1a6d to b9fac9b Compare August 19, 2024 15:35
@azrael417 azrael417 closed this Aug 19, 2024
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

Successfully merging this pull request may close these issues.

2 participants