David E. Keyes

Fu Foundation Professor of Applied Mathematics
Department of Applied Physics & Applied Mathematics at Columbia University

Presentation

HPC Software Technology

Highest end scientific software is mostly pre-commercial, because the market is relatively small and the supporting hardware volatile, but this niche is nevertheless vital and populated by many government supported projects to which international user communities contribute. The Centers for Enabling Technology in the Scientific Discovery through Advanced Computing (SciDAC) program of the U.S. Department of Energy are noteworthy examples, two of which are substantially anchored in New York State. These projects concentrate on the middle of the software hierarchy - above the hardware-specific and below the physics-specific, where there is significant potential for use across a wide range of applications. Examples include meshers, partitioners, solvers, visualizers, and workflow controllers. We review the evolution, present state, and scientific and technological justification for these projects, and compare them internationally, drawing upon recent federally funded studies. We present a few "high water marks" drawing upon the history of the Gordon Bell Prize, and we hazard a few projections based on trends in the vendor industry.

Biography

David E. Keyes is the Fu Foundation Professor of Applied Mathematics in the Department of Applied Physics and Applied Mathematics at Columbia University, and the Chair-designate of the Mathematical and Computer Sciences and Engineering Division at KAUST. With backgrounds in engineering, applied mathematics, and computer science, Keyes works at the algorithmic interface between parallel computing and the numerical analysis of partial differential equations, across a variety of applications. Newton-Krylov-Schwarz parallel implicit methods, introduced in a 1993 paper, are now widely used throughout computational physics and engineering and scale to many thousands of processors. Keyes is currently the Vice President-at-Large of SIAM, and a member of the advisory committees of the Mathematics and Physical Sciences Directorate and the Office of CyberInfrastructure of the NSF.

updated: 2008-09-16