Apply for access to compute services

Several institutions have organised direct access to national compute facilities for their researchers. They provide access to SURF compute and data services via a Research Capacity Computing Service (RCCS) contract. This way you will be able to speed up your analyses up to 1.000 times or include many more parameters than you normally could.

Researchers from these institutions already have direct and easy access to compute power and data services via their IT department or research support office:

• VU Amsterdam (helpdesk@surfsara.nl)
• UvA (helpdesk@surfsara.nl)
• Tilburg University (ITsupport@tilburguniversity.edu)
• Erasmus University Rotterdam (datasupport@ubib.eur.nl)
• Utrecht University (research.engineering@uu.nl)
• Eindhoven University of Technology (hpcsupport@tue.nl)
• and a number of faculties of Delft University of Technology (TBM & CITG)

More and more institutions are offering Research Drive via their RDM/research support or IT department. Is the use of Research Drive desirable for your small request for computing time (so-called pilot grant), and possible via your institution? SURF will ensure that you, as a researcher, can make use of it when you are awarded a grant.

You can submit the following pilot applications for the use of calculation systems, storage and support:

• up to 1,000,000 CPU or GPU SBU (standard billing units) of cluster computing on Snellius Supercomputer (including max. 200GB directory storage, 4 hours of support, if required max. 50TB offline tape storage, if required max. 50TB project space storage, Research Drive - via SURF max. 5TB or via institution).
• Up to 50,000 CPU core hours of cloud computing on HPC Cloud (via Research Cloud portal) (including max. 2TB storage, 4 hours of support, if required max. 50TB offline tape storage, Research Drive - via SURF max. 5TB or via institution).
• up to 10,000 GPU hours of cloud computing on HPC Cloud (via Research Cloud portal) (including max. 2TB storage, 4 hours of support, if required max. 50TB offline tape storage, Research Drive - via SURF (max. 5TB) or via institution).
• up to 1,000,000 CPU core hours of data processing on Grid/Spider (including up to 200TB disk storage, 300TB tape storage, Research Drive (via SURF max. 5TB or via institution) and expertise to be determined in consultation for setting up the infrastructure).
• up to 10,000 GPU hours of data processing on Grid/Spider (including up to 200TB disk storage, 300TB tape storage, Research Drive - via SURF (up to 5TB) or via institution, and expertise to be determined in consultation for setting up the infrastructure).
• maximum 100,000 CPU core hours Custom Cloud Solutions (MS4/Kubernetes), max. 2TB storage, support in consultation, if necessary max. 50TB offline tape storage, Research Drive (via SURF max. 5 TB or via institution).
• up to 10,000 GPU hours of Custom Cloud Solutions (MS4/Kubernetes), max. 2TB storage, amount of support in consultation, if necessary max. 50TB offline tape storage, Research Drive - via SURF (max. 5 TB) or via institution.

The Computing Time on National Computer Facilities programme finances access to national computer facilities. Both the so-called pilot applications for limited amounts of computing time, storage and support that you apply for directly from SURF and the large-scale applications that go through NWO are subject to the terms and conditions of this call. More information about this call can be found on the NWO website.

The available budget for 2023 concerns both large applications via NWO and small pilot applications via SURF: 

• 1656 million SBU computing time
• 59,256 TB of data storage. 

Of which: 

• Supercomputer: 1485 million SBU on Snellius (1253 million SBU CPU nodes, 126 million SBU GPU nodes, 97 million SBU CPU fat nodes, 9 million SBU CPU high‐memory nodes), with 9,956 TB Snellius project space and 15,000 TB Data Archive (offline tape storage).
• Data Processing (Grid on/of Spider): 145,3 million CPU core‐hour and 0,3 million GPU hour, with 22,272 TB online storage and 10,995 TB Data Archive (offline tape storage).
• HPC Cloud: 21,9 million CPU core‐hour en 0,8 million GPU hour, with 640 TB online storage.
• Custom Cloud Solutions: 2,2 million CPU core‐hour, with 193 TB online storage.
• 200 TB storage Research Drive.

Note: 

• Improved interchangeability between systems offers extra possibilities in capacity.
• For all grants, the use of a Research Drive account is possible for storing and sharing data with others. If available, this will be offered through your institution.

Researchers from the following knowledge institutions may submit applications:

• Universities located in the Kingdom of the Netherlands
• University medical centres
• KNAW and NWO institutes
• Dutch universities of applied sciences
• the Netherlands Cancer Institute
• the Max Planck Institute for Psycholinguistics in Nijmegen
• the Dutch-Belgian beamline at ESRF in Grenoble
• NCB Naturalis
• Princess Máxima Center
• the institutions participating in SURF Cooperative: KNMI, RIVM, TNO, National Archives, Royal Library, University for Humanistics, Police Academy
• IHE
• All TO2 institutes: TNO, NLR, Marin, Deltares, and WUR/DLO

If the applicant does not have a permanent, but a temporary employment contract with the institution, the application must be signed digitally by a responsible academic supervisor with a permanent appointment. By doing so, the supervisor declares that he or she stands guarantee for the justification of the allocated computing time, storage and support. This scientific supervisor may act as guarantor for several applicants.

Within 1 to 2 weeks after submitting your application, you can have access to our systems.

As long as the application is within the limits set by the compute service, it may be raised.

Example: applicant has a pilot allocation of 350,000 core hours on Snellius. If it turns out that the applicant needs an additional 150,000 core hours during the period of use, then an increase is possible within the same allocation.

1 year. After that, a one-time extension of 6 months is possible.

Each applicant may submit one application per type of pilot per calendar year.

Example: in 2021, a researcher can apply for 50,000 core hours on HPC Cloud and 500,000 core hours on Cartesius/Snellius.

Example: if a researcher works for 2 research projects, both of which require HPC Cloud, this researcher can only submit a pilot application for HPC Cloud for 1 of these projects. For the other project, someone else must submit the application.

SURF Data Archive can be used for the storage of research data for the duration of the pilot grant. Contact SURF at the end of the grant period to discuss the possibilities of long-term archiving with your institution.

SURF and an increasing number of institutions also offer the Research Drive service so that you can share with others during the award period. If your institution offers SURF Research Drive, you can make use of it. This improves the link with your institution's data services.

EUR
Fontys
Hanze 
HAN
HHS
HU
HvA
HZ
Inholland
OU
Radiant (pabo's)
Saxion
TUe
Leiden University
UvA
VU

You can include this in the data management plan to be drawn up in consultation with the RDM support of your knowledge institution (see NWO website).

You can also use our services as a researcher in industry and (as yet) ineligible institutions. Please contact us for more information about the possibilities.

Yes, on the NWO website. NWO publishes all granted large NWO applications via news items. At the bottom of these announcements there is an appendix with all pilot awards via SURF.

Do you need technical support with the use of our services? Check out our consultancy service.