Priority 1: Enhancing Capability and Capacity of NCAR Supercomputing

NCAR provisions, operates, and maintains supercomputing facilities and cyberinfrastructure to advance our understanding of the atmospheric and related sciences. Excitement grew for the potential of a large, multidisciplinary geoscience computing center. Meeting the challenge of providing facilities sufficient for this research is fundamental to NCAR's fourth strategic goal. The continuing trend toward higher power density coupled with the ability to purchase more equipment for nearly the same costs each year strains the power and cooling limits of our existing facilities. This trend appears to continue well into the future.

FY06 Accomplishments

NCAR is meeting this challenge with a two-pronged approach. First, we have upgraded the NCAR Mesa Lab computing facility infrastructure to operate at or near capacity for the next three years. When the newly procured supercomputer goes into production in early FY 2007, the Mesa Lab computing facility will be pushed to its maximum capacity. Second, we are continuing to develop plans to construct a new facility for NCAR's future supercomputers. These plans evolved rapidly during FY 2006. Partnership discussions were held with a number of institutions, and potential sites were evaluated for their technical feasibility.

In part because of these discussions, excitement grew for the potential of a large, multidisciplinary geoscience computing center. As a result, NCAR planned and completed two Workshops on High Performance Computing for the Geosciences in FY 2006. The first workshop initiated a long-term, in-depth dialog between scientific researchers, computational scientists, application domain experts, vendors of HPC system components, and NSF staff. This workshop addressed the challenges of preparing geoscience applications to run on petascale (and beyond) computing systems. The second workshop proposed an expandable architecture for a geoscience collaboratory that will enable geo-specific HPC, data, and observation systems to work more effectively on the most challenging problems in the geosciences. Participants examined the nature of a large discipline-specific center that would meet the needs of all branches of the geosciences for decades.