Computing Resources and Services
Links to our state-of-the art computing environments and cloud services, and to international computing resources.
For large-scale parallel computation that requires exceptionally powerful supercomputing resources, from several hundreds to up to thousands of cores. A collection of pre-installed applications and development tools supports massive parallelism.Read more »
Sisu user guide »
For general-purpose technical and scientific computing, from single-core serial jobs to parallel jobs of several hundred cores. A large collection of pre-installed applications and development tools. Special large-memory nodes for tasks requiring a large memory footprint.Read more »
Taito user guide »
Specialized compute nodes with NVidia Tesla GPGPU compute accelerators.Read more »
Taito-GPU user guide »
Grid computing enables applying the resources of many computers or computing clusters in a network to a single problem at the same time. The grid combines various computing resources, data banks, and measuring devices that comprise a pool of resources for coordinated, integrated and flexible shared use.Read more »
FGCI user guide »
Using cPouta, customers can quickly deploy self-administered servers using a simple user interface.Read more »
Pouta user guide »
In ePouta, security is taken onto a whole new level. ePouta customers have dedicated connections from their home networks directly to their ePouta servers. ePouta is ideal for organizations that require high performance, high security and a certified environment for sensitive data handling.Read more »
Pouta user guide »
Rahti is a cloud computing service that allows Users to host applications and make them accessible over the web. Users can manage their resources using a web interface accessible through a web browser and through a set of APIs which allow programmatic management of resources.Read more »
Partnership for Advanced Computing in Europe (PRACE) is a persistent, pan-European Research Infrastructure (RI) for High-Performance Computing (HPC) managed as a single European entity.Read more »
The CSC Grand Challenge calls are aimed at scientific research projects that require computational resources exceeding CSC's standard project resources.Read more »
HPC-Europa is an EC programme which funds researchers to carry out short "transnational access" visits to other countries to collaborate with another research group and provides access to supercomputers at the host country.Read more »
High performance computing
We are in the process of implementing the next generation computing and data management environment. CSC currently hosts two supercomputers: Taito and Sisu. Sisu will be decommisioned after summer, and Taito in December. A new air-cooled supercomputer Puhti and data management system Allas will be installed by the summer of 2019. In the second phase, a new liquid-cooled Atos BullSequana XH2000 supercomputer Mahti with 6.4 Petaflops of total peak performance will be installed and taken into use in early 2020.
The Sisu supercomputer (sisu.csc.fi) is the most powerful supercomputer in Finland and one of the most powerful in Northern Europe. Sisu's Cray XC40 system architecture is designed from the ground up for High Performance Computing (HPC). Sisu is targeted at massively parallel applications that can effectively run on hundreds to thousands of compute cores in parallel. Obtaining this level of scaling with even very tightly-coupled parallel computations is made possible by the extremely high-bandwidth, low-latency Aries interconnect.
The Taito supercluster (taito.csc.fi) is intended for serial (single-core) and small to medium-size parallel jobs. There are also several "fat nodes" for jobs requiring a large amount of memory.
The Taito GPU system contains servers with NVidia GPU accelerators. These specialized processors are specifically designed for high performance computing and can provide superior performance compared to traditional CPUs. However, to utilize the capabilities fully, one needs to either have an existing application that is compatible with the processors or perform the porting and optimization work.
CSC's cloud computing platforms, cPouta and ePouta, offer high performance computing with superior flexibility and user experience via Infrastructure as a Service (IaaS).
CSC's Pouta Cloud Services are an ideal and cost-efficient computing solution for research and education. The computing needs can be related to scientific modeling and number crunching in various areas of science, such as life sciences, big data, astronomy, material sciences, earth sciences or financial analytics.
Both cPouta and ePouta are secure and highly scalable. Using these services liberates our customers from managing their own hardware and data centers regardless whether they need the resources for an hour or a year. Our services are hosted in Finland, assuring that your data is safe in our data centers. The systems are connected to the high performance Funet network. Both platforms are available as a commercial service as well.
Each of these services provides the customer with full control over one or more virtual machines as well as storage. This provides a large degree of flexibility and thus a wider range of use cases compared to traditional high performance computing systems.
The cPouta service is available to any user with access to the computing services at CSC, while the ePouta service is primarily targeted to IT administrators of organizations.
Special Resources and Projects
If the computing or storage resources offered by CSC through the normal allocation process are not sufficient or adequate for your needs, there are a number of options to turn to:
- Normal CSC resource allocation process
- The Finnish Grid and Cloud Infrastructure (FGCI)
- CSC Grand Challenge project calls
- Partnership for Advance Computing in Europe (PRACE)