Parallel MCGLS and ICGLS methods for least squares problems on distributed memory architectures

Authors:
Laurence Tianruo Yang;Richard P. Brent
Affiliations:
Department of Computer Science, St. Francis Xavier University, Antigonish, NS, Canada and Computing Laboratory, Oxford University, Oxford, UK;Computing Laboratory, Oxford University, Oxford, UK
Venue:
ISPA'03 Proceedings of the 2003 international conference on Parallel and distributed processing and applications
Year:
2003

Citing 4
Cited 0

Preconditioned CG methods for sparse matrices on massively parallel machines

Parallel Computing
LSQR: An Algorithm for Sparse Linear Equations and Sparse Least Squares

ACM Transactions on Mathematical Software (TOMS)
Solving Linear Systems on Vector and Shared Memory Computers

Solving Linear Systems on Vector and Shared Memory Computers
A Parallel Version of the Quasi-Minimal Residual Method, Based on Coupled Two-Term Recurrences

PARA '96 Proceedings of the Third International Workshop on Applied Parallel Computing, Industrial Computation and Optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we mainly study the parallelization of the CGLS method, a basic iterative method for large and sparse least squares problems in which the conjugate gradient method is applied to solve normal equations. On modern parallel architectures its parallel performance is always limited because of the global communication required for inner products, the main bottleneck of parallel performance. In this paper, we describe a modified CGLS (MCGLS) method which improve parallel performance by assembling the results of a number of inner products collectively and by creating situations where communication can be overlapped with computation. More importantly, we also propose an improved CGLS (ICGLS) method to reduce inner product's global synchronization points to half, then significantly improve the parallel performance accordingly compared with the standard CGLS method and the MCGLS method.