High-end Computing

CISL's High-end Services Section (HSS) is a world leader in supercomputing for the geosciences, providing services to NCAR and over 60 UCAR member universities in the U.S. and affiliates worldwide.

Our supercomputing resources are divided into two computational facilities for the purpose of resource allocation. These two facilities share some of the same supercomputing resources and are housed in NCAR's Computing Center.

The Climate Simulation Laboratory (CSL) at NCAR is a dedicated climate model computing facility supporting the multiagency Climate Change Science Program. The purpose of the CSL is to provide high performance computing and data storage systems to support large-scale, long-running simulations of the earth's climate system, including appropriate model components, that need to be completed in a short calendar period. The CSL's long-running simulations typically require thousands of processor hours for completion and usually produce many gigabytes of model output that must be archived for analysis and intercomparison with other simulations and with observations.

Community Computing supercomputing resources are used by university scientists and NCAR researchers to investigate questions in geophysics and solar physics. The purpose is twofold — to provide computing support for NCAR research and to extend the computing resources for university scientists so they can pursue investigations beyond the scope of university computing centers. Community Computing resources are also made available to a small number of projects funded by other government agencies and by the private sector.

Production supercomputing systems run tasks such as large simulations or models that require massive computing and data-handling resources.

Data analysis and visualization systems support data preprocessing prior to a job run and data postprocessing after a run.

Dedicated systems are not available to CSL or CCF users and are reserved for specific research projects. In many cases, these machines have a different funding source and are related to large research initiatives.

Pre-deployment systems are new arrivals that are currently in acceptance testing or friendly user testing before being made available as production supercomputing systems to the CSL or CCF user communities.