Towards Usable and Lean Parallel Linear Algebra Libraries

Almadena Chtchelkanova
Carter Edwards
John Gunnels
Greg Morrow
James Overfelt
Robert A. van de Geijn
University of Texas at Austin
Austin, TX 78712

Abstract

In this paper, we introduce a new parallel library effort, as part of the PLAPACK project, that attempts to address discrepencies between the needs of applications and parallel libraries. A number of contributions are made, including a new approach to matrix distribution, new insights into layering parallel linear algebra libraries, and the application of ``object based'' programming techniques which have recently become popular for (parallel) scientific libraries. We present an overview of a prototype library, the SL_Library , which incorporates these ideas. Preliminary performance data shows this more application-centric approach to libraries does not necessarily adversely impact performance, compared to more traditional approaches.

Almadena Chtchelkanova, Carter Edwards, John Gunnels, Greg Morrow, James Overfelt, Robert A. van de Geijn, "Towards Usable and Lean Parallel Linear Algebra Libraries," TR-96-09, Department of Computer Sciences, University of Texas, May 1996. Submitted to Supercomputing 96.
Warning: one page has graphs on it and takes ~45 min to print!

This project is extremely interested in collaboration with other library projects and applications of this technology. Corporate sponsorship would ofcourse be greatly appreciated!