CISL Computing Services

CISL is a computing laboratory.

CISL has a proud tradition of providing world-class supercomputing and data services to its user community. The quality of these services is and will remain a core value of the laboratory. However, the makeup of these services is not static: they continually change in concert with underlying technologies and scientific demands. For example, CISL foresees providing fewer standalone services: over time, services will increasingly be virtualized and federated with other resource and service providers. Another macro-trend will be to provide more flexible and customized services, e.g., through sophisticated science gateways tied to data repositories or computational resources, rather than the current paradigm of “batch” access.

CISL sees the following Imperatives for its role as a computing laboratory:

  • CISL must deploy and operate the physical and virtual computational facilities needed to support the science community. CISL must provision mid-range, Track-2-scale computing, storage, data analysis, visualization, networking, and archival systems, customized to support the atmospheric and related sciences.

  • CISL must develop and support software infrastructure and tools specific to the simulation, analysis, and forecasting needs of the atmospheric and related sciences.

  • CISL must maintain online access to research data sets and the tools needed to access that data in a variety of user-specified ways.

As a computing laboratory, CISL faces one critical Frontier:

  • CISL must exploit supercomputing center virtualization technologies to support and enhance the development of virtual organizations around its core services.

This section of the FY2010 CISL Annual Report reports on the topics shown in the navigation tool at left.