Skip to content

Minor fixes #243

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.

Sign up for GitHub

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

Merged
merged 4 commits into from
Aug 27, 2025
Merged

Minor fixes #243

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
03d2c3c
Fix missing period
msimberg Aug 25, 2025
ebaf3eb
Rename CP2K hpc platform subsection
msimberg Aug 25, 2025
702bb4b
Add missing backticks in cp2k docs
msimberg Aug 25, 2025
dbb23ed
More consistency
msimberg Aug 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/platforms/mlp/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ The Machine Learning Platform (MLP) provides compute, storage and expertise to t
### Getting access

Project administrators (PIs and deputy PIs) of projects on the MLP can to invite users to join their project, before they can use the project's resources on Alps.
This is performed using the [project management tool][ref-account-waldur]
This is performed using the [project management tool][ref-account-waldur].

Once invited to a project, you will receive an email, which you need to create an account and configure [multi-factor authentication][ref-mfa] (MFA).

Expand Down
4 changes: 2 additions & 2 deletions docs/software/sciapps/cp2k.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ On our systems, CP2K is built with the following dependencies:

## Running CP2K

### Running on the HPC platform
### Running on GH200 nodes
Copy link
Collaborator Author

@msimberg msimberg Aug 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We could call this Running on Daint as well? I left the heading further down as Running on Eiger, so it's a bit inconsistent like this. Open to better suggestions.

Motivation to change it: HPC platform includes both daint and eiger. Note to self, change the later mentions of "HPC platform" as well in this section...

Copy link
Member

@bcumming bcumming Aug 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Running on Daint: CP2K is deployed on the HPC platform only, and users on that platform might be familiar with Daint, but not ght200.

Copy link
Member

@bcumming bcumming Aug 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe the first sentence could say something like: Daint nodes have 4 grace-hopper GPUs that have to be configured properly to get the best performance.?

Copy link
Collaborator

@abussy abussy Aug 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I agree, Running on Daint is both the most consistent option, and one that non-experts will understand.

As @bcumming suggests, it is probably a good idea to briefly remind users of the architecture of Daint (which was kinda self-contained in the GH200 title, but for expert users only)

Copy link
Collaborator Author

@msimberg msimberg Aug 25, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks both for having a look. I've updated this to "Running on daint", and a few other places to match hopefully.


To start a job, two bash scripts are potentially required: a [Slurm] submission script, and a wrapper to start the [CUDA
MPS] daemon so that multiple MPI ranks can use the same GPU.
Expand Down Expand Up @@ -348,7 +348,7 @@ srun --cpu-bind=socket cp2k.psmp -i <CP2K_INPUT> -o <CP2K_OUTPUT>
for good performance. With [Intel MKL], this is not necessary and one can set `OMP_NUM_THREADS` to
`SLURM_CPUS_PER_TASK`.

* Change <ACCOUNT> to your project account name
* Change `<ACCOUNT>` to your project account name
* Change `<CP2K_UENV>` to the name (or path) of the actual CP2K uenv you want to use
* Change `<PATH_TO_CP2K_DATA_DIR>` to the actual path to the CP2K data directory
* Change `<CP2K_INPUT>` and `<CP2K_OUTPUT>` to the actual input and output files
Expand Down