Efficient sparse matrix factorization for circuit simulation on vector supercomputers

Authors:
P. Sadayappan;V. Visvanathan
Affiliations:
Department of Computer and Information Science, The Ohio State University, Columbus, Ohio;AT&T Bell Laboratories, Murray Hill, New Jersey
Venue:
DAC '89 Proceedings of the 26th ACM/IEEE Design Automation Conference
Year:
1989

Citing 8
Cited 2

Computational models and task scheduling for parallel sparse Cholesky factorization

Parallel Computing
Parallel implementation of multifrontal schemes

Parallel Computing
Direct methods for sparse matrices

Direct methods for sparse matrices
Circuit Simulation on Shared-Memory Multiprocessors

IEEE Transactions on Computers
Pairwise Reduction for the Direct, Parallel Solution of Sparse, Unsymmetric Sets of Linear Equations

IEEE Transactions on Computers
Squeezing the most out of an algorithm in CRAY FORTRAN

ACM Transactions on Mathematical Software (TOMS)
Storing a sparse table

Communications of the ACM
Computer Methods for Circuit Analysis and Design

Computer Methods for Circuit Analysis and Design

Communication reduction for distributed sparse matrix factorization on a processor mesh

Proceedings of the 1989 ACM/IEEE conference on Supercomputing
Massive parallelization of SPICE device model evaluation on GPU-based SIMD architectures

IFMT '08 Proceedings of the 1st international forum on Next-generation multicore/manycore technologies

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper describes an efficient approach to sparse matrix factorization on vector supercomputers. The approach is suitable for application domains like circuit simulation that require the repeated direct solution of unsymmetric sparse linear systems of equations with identical zero-nonzero structure. An Overlap-Scatter data structure is used to represent the sparse matrix, enabling the use of multiple operand access modes to achieve higher performance than earlier proposed approaches. The superior performance of the new solver is demonstrated using a number of matrices derived from circuit simulation runs.