Extremely large resources

If the standard computing or storage resources offered by CSC are not sufficient for your needs, there are other options to turn to.

LUMI Extreme Scale Access

LUMI, one of the EuroHPC flagship supercomputers and leading platforms for AI for science, is located at CSC’s data center in Kajaani, Finland.

A part of LUMI resources are allocated by the EuroHPC Joint Undertaking. These resources are available to users from EU member states and the countries associated to Horizon 2020. In addition, users in LUMI consortium countries can apply for resources from national quotas. Read more about applying for LUMI resources from the EuroHPC and country-specific quotas on the LUMI website.

Finnish users can access LUMI in four different access modes: Regular, Benchmark, Development, or Extreme Scale.

LUMI Extreme Scale Access is aimed at high-impact, high-gain innovative research, open to all fields of science justifying the need for extremely large allocations in terms of computing time (especially GPU) and data storage. The call for the Finnish Extreme Scale Access projects is organized by CSC, and it is open for researchers in Finnish higher education and research institutions. The awarded resources are part of Finland’s share of LUMI.

Other access modes (e.g. Regular Access) are reserved for lower resource needs. These access modes are described in the Users in Finland section on the LUMI website.

Applying for LUMI Extreme Scale Access

Applicants of the Extreme Scale calls need to:

  1. Demonstrate that the research requires the use of extremely large allocations to reach the objectives.
  2. Demonstrate that the methods, software and tools are technically adapted to LUMI-G architecture and its next-generation AMD GPUs. This can be shown by technical data collected from GPU systems currently available (Mahti GPU, Puhti GPU, or other large accelerated systems).
  3. Provide a project plan with adequate schedule of the expected resource consumption during the lifetime of the project.

Please note:

  • Codes that are already GPU-enabled may be ported to LUMI-G. For example, codes using CUDA can typically be converted to use HIP with modest effort and good performance. GPU offloading with OpenMP or OpenACC is also supported to certain extent.
  • The Extreme Scale projects are awarded resources in GPU hours, CPU core-hours, and storage hours. These are limited between 0.5–3 million GPU hours and max. 16 million CPU core-hours. The awarded resources have to be consumed within a year.
  • The proposals will go through a technical review and a scientific evaluation. The scientific evaluation will be done by an international panel.
  • The link to fill in the project application will be separate for each call and announced on the LUMI website.
  • LUMI resources are not awarded in billing units as for other CSC services.

For more information, please visit:

CSC Grand Challenge calls

CSC Grand Challenge calls are aimed at cutting-edge research projects that require computational resources exceeding CSC’s standard project resources. The maximum amount of resources awarded is 50 million BUs (~50 million core-h) for Mahti, or 1.0 million GPUh and 12 million core-h per project for LUMI. Grand Challenge projects also have a possibility to ask for higher priority.

The computational resources allocated to Grand challenge projects have to be consumed within a year. Access to other resources may be used depending on the needs. The proposals will go through a technical and a scientific evaluation. The scientific evaluation will be done by CSC’s Scientific Customer Panel. CSC will assign a project coordinator to each project.

There is a special application process for obtaining Grand Challenge rights. The proposal link will be separate for each call. Since also partial grants can come into question, please indicate what would be the minimum requested resources, and in that case, what part of the project could be left out.

Evaluation criteria

Grand Challenge applications are assessed on the basis of the following criteria:

  • The scientific significance of the research.
  • The impact of the research (scientific, technical, economic, cultural, social).
  • How important are the sought resources for the project?
  • How suitable are CSC’s existing resources for the project?
  • The applicant’s ability to implement the project.

The general principle is to favor cutting-edge research. Extra credit will be given to projects that develop research environments and would:

  • coordinate otherwise decentralized research resources; promote multidisciplinary and interdisciplinary science; and provide opportunities for cross-disciplinary activities
  • enhance cooperation between researchers, funding channels, and the end users of research results
  • increase Finland’s global visibility in joint research
  • promote openness in the publication of research results

Please contact CSC Service Desk for more information about Grand Challenge calls.