High-performance computing (HPC) is a vital tool in modern scientific research, empowering researchers with the computational prowess required to solve complex problems and push the boundaries of knowledge across various disciplines.
HPC clusters consist of numerous interconnected servers with high processing power, large memory capacities, and fast network connections, working in parallel to handle massive calculations efficiently.
This allows researchers to gain new insight into critical societal issues. HPC is also used to augment or replace physical experiments when the latter is costly or dangerous to conduct.
What is the HPC service?
The HPC service is a specialised and powerful computing infrastructure provided by Sigma2 and designed to tackle computationally intensive tasks and process large datasets at incredibly high speeds, far beyond what standard desktop computers or servers can achieve.
The HPC service provides access to national computing facilities and software that have far greater capacity than is normally available the research institutions.
The service primarily facilitates running simulations for research and educational purposes. It operates as batch processing runs, allowing for the efficient execution of multiple tasks. Researchers request computer time (CPU hours) to support their research objectives.
Our high-performance computing service provides access to the national supercomputers Betzy, Fram and Saga, in addition to the new pan-European supercomputer LUMI, which is part of the EuroHPC infrastructure.
You also get
A limited amount of permanent storage is available with the High-performance computing service. More capacity is available through the NIRD Storage Service. The HPC and NIRD services are connected, thus allowing research projects to store larger amounts of scientific data for computations on NIRD.
Specialised software support is available for job configuration, workflow pipelines, and other software-related issues.
HPC can be complex to operate, and researchers often need the expertise to utilise it effectively.
We offer user support, training, and documentation to assist researchers in harnessing the full potential of the HPC resources:
- Basic technical support through a ticket-based support service.
- Training in programming, software optimisation and other relevant topics.
- Basic software portfolio, primarily comprising open-source code and basic commercial tools, such as compilers, debuggers and simulation applications.
- Availability to run commercial software by bringing your licenses (BYOL).
- Access to high-performance high-volume file systems for temporary storage during computations.
How to get access?
The most convenient way to access the resources is by applying through our regular calls, which are published twice a year. However, it is also possible to apply outside calls at any point in time through the year.
Established compute projects must also apply through the regular calls, but applications for extended time are processed continuously.
You can apply for resources on LUMI through our regular calls. However, if your project requires an extremely large amount of resources, it is advisable to apply directly through EuroHPC. For assistance with applying for resources from EuroHPC, EuroCC National Competence Centre Sweden has created a helpful video you can refer to. (Usikker på om info om denne videoen skal ligge her …)
Below you will find a selection of research projects that have utilised the national HPC service.
You might also need
We offer many related services that you may need in addition to HPC. Below, you can see a few selected ones, and if you visit our services overview, you will find all.
The HPC services going forward
Take a look at the roadmap for the development of the HPC service to follow the progress of the service: