TY - JOUR
T1 - Scalable parallel algorithm for sparse Cholesky factorization
AU - Gupta, Anshul
AU - Kumar, Vipin
PY - 1994/1/1
Y1 - 1994/1/1
N2 - In this paper, we describe a scalable parallel algorithm for sparse Cholesky factorization, analyze its performance and scalability, and present experimental results of its implementation on a 1024-processor nCUBE2 parallel computer. Through our analysis and experimental results, we demonstrate that our algorithm improves the state of the art in parallel direct solution of sparse linear systems by an order of magnitude - both in terms of speedups and the number of processors that can be utilized effectively for a given problem size. This algorithm incurs strictly less communication overhead and is more scalable than any known parallel formulation of sparse matrix factorization. We show that our algorithm is optimally scalable on hypercube and mesh architectures and that its asymptotic scalability is the same as that of dense matrix factorization for a wide class of sparse linear systems, including those arising in all two- and three- dimensional finite element problems.
AB - In this paper, we describe a scalable parallel algorithm for sparse Cholesky factorization, analyze its performance and scalability, and present experimental results of its implementation on a 1024-processor nCUBE2 parallel computer. Through our analysis and experimental results, we demonstrate that our algorithm improves the state of the art in parallel direct solution of sparse linear systems by an order of magnitude - both in terms of speedups and the number of processors that can be utilized effectively for a given problem size. This algorithm incurs strictly less communication overhead and is more scalable than any known parallel formulation of sparse matrix factorization. We show that our algorithm is optimally scalable on hypercube and mesh architectures and that its asymptotic scalability is the same as that of dense matrix factorization for a wide class of sparse linear systems, including those arising in all two- and three- dimensional finite element problems.
UR - http://www.scopus.com/inward/record.url?scp=0028742343&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0028742343&partnerID=8YFLogxK
U2 - 10.1145/602770.602898
DO - 10.1145/602770.602898
M3 - Conference article
AN - SCOPUS:0028742343
SN - 1063-9535
SP - 793
EP - 802
JO - Proceedings of the ACM/IEEE Supercomputing Conference
JF - Proceedings of the ACM/IEEE Supercomputing Conference
T2 - Proceedings of the 1994 Supercomputing Conference
Y2 - 14 November 1994 through 18 November 1994
ER -