HPCE/gitea-pages
HPCE/gitea-pages
0
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Activity
gitea-pages/pages/CSCS/index.md

2.7 KiB
Raw Blame History

title, last_updated, sidebar, permalink
title last_updated sidebar permalink
PSI HPC@CSCS 3 May 2024 CSCS_sidebar /CSCS/index.html

PSI HPC@CSCS

PSI has a long standing collaboration with CSCS for offering high end HPC resources to PSI projects. PSI had co-invested in CSCS' initial Cray XT3 supercomputer Horizon in 2005 and we continue to procure a share on the CSCS flagship systems.

The share is mainly intended for projects that cannot profit from applying for regular CSCS user lab allocation schemes.. We can also help PSI groups to procure additional resources based on the PSI conditions - please contact us in such a case.

Capacity of PSI resources at CSCS

For 2024 PSI we have a share of 400'000 NH (Node Hours) on Piz Daint, and 65 TB of storage.

CSCS plans to decommission Piz Daint during 2024. All allocations will be converted to allocations on the new user lab on the CSCS Alps infrastructure. Users will be informed about the migration process.

How to request a PSI project

A survey is sent out to subscribed users once per year, usually in the third quarter. It serves for collecting the CSCS resources requests for the upcoming year.

Users registered in the PSI HPC@CSCS mailing list psi-hpc-at-cscs@lists.psi.ch will be contacted to take part in the yearly survey. Please subscribe to the list if you are interested.

Users need to specify in the survey the total resources they intend to use next year and also how this is to be split over the 4 quarters (e.g. 25%, 25%, 25%, 25%), since CSCS allocates recources on a quarterly basis. We provide the possibility to adapt the distribution over the course of the active year or shift unused resources to other projects (contact us on the mailing list).

By default allocated nodes are on the CPU partition of PizDaint (36 cores per node). However, allocations to the GPU partition are also possible (1 x NVIDIA P100 and 12 cores per node).

CSCS Systems reference information

Contact information