If you are a researcher at SDU, you can now apply for HPC resources for the second half of 2023. Please submit your application on the 30th of April at the latest.
Remember that you can apply for resources on different types of National Systems. Notice that for the first time, you can also apply for GPU resources on the LUMI supercomputer.
Important Notification:
The SDU policy for accessing larger amount of HPC resources is changing starting from the next internal call, i.e. for resources to be consumed after the end of 2023. Applicants asking for larger amounts of HPC resources, either more than 50,000 core*hours for CPUs or more than 1000 GPU hours, will be required to: 1) apply for an equal or higher amount of national resources from DeiC and 2) re-use the same application form for the internal SDU call.
HPC Type1, Interactive HPC
Resources available to SDU for the second half of 2023: 2,000,000 CPU core hours and 100,000 GPU core hours.
Access the YouGene cluster hosted at the SDU eScience Center and the GPUs and Virtual Machine (VM) infrastructure at Aalborg University via UCloud by submitting a grant application for a research project as explained in the related documentation.
HPC Type 2 – Throughput HPC
No resources are available to SDU in this call.
Access the HPC Type 2 facilities by submitting an application form via our service desk. The hardware accessible to SDU users for a Type 2 HPC project is shown below. NB: there are no FAT or GPU nodes on Type 2.
| Computerome 2.0 | GenomeDK | Sophia |
| Xeon Gold 6230 Cascade Lake, 40 cores, 192 GB | AMD EPYC Rome 7452, 64 cores, 512 GB | AMD EPYC 7351, 32 cores, 128 GB |
HPC Type 3 – Large Memory HPC
Resources available to SDU for the second half of 2023: 600,000 core hours.
The application form for resources on one of the HPC Type 3 systems should also be submitted to our service desk. The user guide can be found via this link.
LUMI – European pre-exascale supercomputer
CPU resources available to SDU for the second half of 2023: 2,000,000 CPU core hours. GPU resources available to SDU in 2023: 250,000 GPU hours.
LUMI is an abbreviation for “Large Unified Modern Infrastructure”, and is located in CSC’s data center in Kajaani, Finland. LUMI is one of three European pre-exascale supercomputers part of the EuroHPC project.
For more information, check the official documentation here.
Researchers at SDU can apply for compute time on LUMI by submitting an application form via our service desk.
If you need help with/advice on how to write your application, please contact the representative from your faculty in the SDU eScience Center Operational Board:
- Associate Prof. Rocio Chongtay, rocio@sdu.dk(HUM)
- Prof. Hans Jørgen Aagaard Jensen hjj@sdu.dk (NAT)
- Prof. WSR Oliver Baumann oliv@sam.sdu.dk (SAMF)
- Associate Prof. Martin Jakob Larsen martin.larsen@rsyd.dk (SUND)
- Assistant Professor Parisa Niloofar parni@mmmi.sdu.dk (TEK)
