update PSI@CSCS for 2026 survey

pages/CSCS/index.md

@@ -2,7 +2,7 @@
 title: PSI HPC@CSCS 
 #tags:
 #keywords:
-last_updated: 3 May 2024
+last_updated: 20 Nov 2025
 #summary: ""
 sidebar: CSCS_sidebar
 permalink: /CSCS/index.html
@@ -15,42 +15,38 @@ 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.](https://www.cscs.ch/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.
+The share is intended for projects that by their nature cannot profit
+from applying for regular [CSCS user lab allocation
+schemes.](https://www.cscs.ch/user-lab/allocation-schemes).
 
-### Capacity of PSI resources at CSCS
+We can also help PSI groups to procure additional resources based on
+the PSI conditions - please contact us in such a case.
 
-For 2024 PSI we have a share of 400'000 NH (Node Hours) on [Piz Daint](https://www.cscs.ch/computers/piz-daint), and 65 TB of storage.
+### Yearly survey for requesting a project on the PSI share
 
-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.
+At the end of each year we prepare a survey process and notify all subscribed users of the specialized **PSI HPC@CSCS mailing list** ([subscription link](https://psilists.ethz.ch/sympa/subscribe/psi-hpc-at-cscs)) and the merlin cluster lists, to enter their next year resource requests. Projects receive resources in the form of allocations over the four quarters of the following year.
 
-### How to request a PSI project
+The projects requests get reviewed and requests may get adapted to fit into the available capacity.
 
-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.
+The survey is done through ServiceNow, please navigate to [Home > Service Catalog > Research Computing > Apply for computing resources at CSCS](https://psi.service-now.com/psisp?id=psi_new_sc_cat_item&sys_id=8d14bd1e4f9c7b407f7660fe0310c7e9) and submit the form.
 
-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](https://psilists.ethz.ch/sympa/subscribe/psi-hpc-at-cscs) 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).
+#### Instructions for filling out the 2026 survey
 
-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).
+* We have a budget of 100 kCHF for this 2026, which translates to 435'000 multicore node hours or 35'600 node hours on the GPU Grace Hopper nodes. The minimum allocation is 10'000 node hours for multicore projects, an average project allocation would amount to 30'000 node hours
+* You need to specify the total resource request for your project in node hours, and how you would like to split the resources over the 4 quarters. For the allocations per quarter year, please enter the number in percent (e.g. 25%, 25%, 25%, 25%). If you indicate nothing, a 25% per quarter will be assumed.
+* We currently have a total of 65 TB of storage for all projects. Additional storage
+  can be obtained, but large storage assignments are not in scope for these projects.
 
 ### CSCS Systems reference information
 
+For 2025 we can offer access to [CSCS Alps](https://www.cscs.ch/computers/alps) Eiger (CPU multicore) and Daint (GPU) systems.
+
 * [CSCS User Portal](https://user.cscs.ch/)
-* [Piz Daint Information](https://www.cscs.ch/computers/piz-daint/)
-* [Piz Daint: One of the most powerful supercomputers in the world](https://www.cscs.ch/publications/news/2017/piz-daint-one-of-the-most-powerful-supercomputers-in-the-world)
+* Documentation
+   * [Eiger CPU multicore cluster](https://docs.cscs.ch/clusters/eiger/)
+   * [Daint GPU cluster](https://docs.cscs.ch/clusters/daint/)
 
 ## Contact information