-
Notifications
You must be signed in to change notification settings - Fork 1
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
Add documentation #8
base: main
Are you sure you want to change the base?
Conversation
on: | ||
- push | ||
# push: | ||
# branches: | ||
# - main |
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.
Needs to be fixed before merging.
* [ETH Zurich]: Swiss Federal Institute of Technology Zurich | ||
* [PASC]: Platform for Advanced Scientific Computing | ||
|
||
<img height="50" src="./docs/images/logo-cscs.jpg"><img height="50" src="./docs/images/logo-eth.svg"><img height="50" src="./docs/images/logo-pasc.png"> |
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.
Require assets added in #6
Preliminary questions: |
There is a preview from my fork: https://rmeli.github.io/DLA-Future-Fortran
Not really... I'm open to suggestions. |
project: DLA-Future-Fortran | ||
summary: Fortan interface for DLA-Future | ||
project_github: https://github.com/eth-cscs/DLA-Future-Fortran | ||
author: Rocco Meli |
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.
Add everyone (or remove).
## Optimal parameters | ||
|
||
### Block size | ||
|
||
| Device | Block size | | ||
| :----: | :--------: | | ||
| CPU | 512 | | ||
| GPU | 1024 | | ||
|
||
### Ranks per node | ||
|
||
For CPU-only calculations it is recommended to use one rank per NUMA domain. For GPU calculations it is recommended to use one rank per GPU. |
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.
I wonder if this is something we could put in DLA-Future's documentation instead and link to it from here? Additionally, I'd add some sort of disclaimer for the block sizes that these are typically the best sizes, but YMMV etc. etc. i.e do your own tests if you want "optimal parameters".
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, adding this directly in DLA-Future's documentation would be ideal.
gh-pages
branchDocumentation Preview
The documentation is currently incomplete: only one function per algorithm is documented, plus the helper functions. It will be completed once the phrasing is agreed upon.