Newsgroups: comp.parallel From: Robert van de Geijn Subject: OOC Dense Linear Solver Paper Organization: CS Dept, University of Texas at Austin Date: 29 May 1995 15:32:41 GMT Message-ID: <3qcpep$23b@usenet.srv.cis.pitt.edu> We would like to bring the following paper to the attention of the comp.parallel community 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. to view the paper: http://www.cs.utexas.edu/users/rvdg/conference.html ======================================================================== Robert A. van de Geijn rvdg@cs.utexas.edu Associate Professor http://www.cs.utexas.edu/users/rvdg Department of Computer Sciences (Work) (512) 471-9720 The University of Texas (Home) (512) 251-8301 Austin, TX 78712 (FAX) (512) 471-8885