Highly Parallel Iterative Methods for Massively Parallel Multiprocessor

Period of Performance: 01/01/1989 - 12/31/1989

$437K

Phase 2 SBIR

Recipient Firm

Scientific Comput Assoc
One Century Tower, 265 Church Street
New Haven, CT 99999
Principal Investigator

Abstract

FOR THE REST OF THIS CENTURY, TWO OF THE POTENTIALLY MOST IMPORTANT ADVANCES IN THE "TECHNOLOGY" OF LARGE SCALE SCIENTIFIC COMPUTING ARE SPARSE MATRIX (ITERATIVE) ALGORITHMS AND MASSIVELY PARALLEL PROCESSING. IN THIS PROPOSAL, WE OUTLINE OUR PLANS TO BUILD A SOFTWARE PACKAGE FOR THE MASSIVELY PARALLEL MACHINES THAT WILL BRING THE POWER OF BOTH ADVANCES TO THE AID OF THE SCIENTIFIC COMMUNITY WITHOUT FORCING THAT COMMUNITY TO BECOME EXPERT IN EITHER TECHNOLOGY. WE PROPOSE TO DEVELOP EFFICIENT MASSIVELY PARALLEL ALGORITHMS FOR THE ITERATIVE SOLUTION OF LARGE SPARSE LINEAR SYSTEMS OF EQUATIONS. THE SOLUTION TO SUCH SYSTEMS IS THE COMPUTE INTENSIVE KERNEL OF A MAJORITY OF COMPUTER SIMULATIONS. WE WILL IMPLEMENT THESE ALGORITHMS IN A PACKAGE PCGPAK/MP EXPLICITLY DESIGNED AND OPTIMIZED FOR MASSIVELY PARALLEL MACHINES. PCGPAK/MP WILL BE BASED ON OUR EXISTING PROPRIETARY PACKAGE PCGPAK(R), THE PRECONDITIONED CONJUGATE GRADIENT PACKAGE OF SUBROUTINES FOR THE ITERATIVE SOLUTION OF LARGE, SPARSE, NONSYMMETRIC SYSTEMS OF LINEAR EQUATIONS. PCGPAK IS A STATE-OF-THEART SOLVER FOR UNIPROCESSOR ARCHITECTURES. IT WAS DESIGNED AND DEVELOPED BY SCIENTIFIC COMPUTING ASSOCIATES AND IS CURRENTLY MARKETED IN A HIGHLY-PORTABLE SEQUENTIAL PROCESSOR FORTRAN IMPLEMENTATION AND A HIGHLY VECTORIZED IMPLEMENTATION FOR THE CRAY-X/MP. PCGPAK IS CURRENTLY BEING USED AT MANY SITES INCLUDING SEVERAL OF THE NSF NATIONAL SUPERCOMPUTING CENTERS. THE PROPOSED PACKAGE WILL HAVE AN IMMEDIATE IMPACT ON LARGE SCALE SCIENTIFIC COMPUTING ON MASSIVELY PARALLEL MACHINES. WE BELIEVE THAT COMBINATION OF MASSIVELY PARALLEL MACHINES AND PCGPAK/MP WILL BE SO MUCH FASTER THAN EXISTING SOLUTION TECHNOLOGIES SO AS TO COMPLETELY REVOLUTIONIZE THE STATE-OF-THE-ART IN COMPUTER SIMULATION.