Anatomy of a Parallel Out-of-Core Dense Linear Solver

Robert A. van de Geijn
Texas Institute for Computational and Applied Mathematics
and
Department of Computer Sciences
University of Texas
Austin, TX 78712
rvdg@cs.utexas.edu
Kenneth Klimkowski
Texas Institute for Computational and Applied Mathematics
The University of Texas at Austin
Austin, Texas 78712
ken@ticam.utexas.edu

Abstract

In this paper, we describe the design and implementation of the Platform Independent Parallel Solver (PIPSolver) package for the out-of-core (OOC) solution of complex dense linear systems. Our approach is unique in that it allows essentially all of RAM to be filled with the current portion of the matrix (slab) to be updated and factored, thereby greatly improving the computation to I/O ratio over previous approaches. This work could be viewed in part as an exercise in maximal code reuse: By formulating the OOC LU factorization just right, we managed to reuse essentially all of a very robust and efficient incore solver, leading directly to a very robust and efficient OOC solver. Experiences and performance are reported for the Cray T3D system.

Ken Klimkowski and Robert van de Geijn, "Anatomy of an out-of-core dense linear solver", to appear in the Proceedings of the International Conference on Parallel Processing 1995.