Impact of the implementation of MPI point-to-point communications on the performance of two general sparse solvers

We examine the send and receive mechanisms of MPI and show how to implement message passing robustly so that performance is not significantly affected by changes to the MPI system. We discuss this within the context of two different parallel algorithms for sparse Gaussian elimination: a multifrontal...

Full description

Saved in:
Bibliographic Details
Published in:Parallel computing Vol. 29; no. 7; pp. 833 - 849
Main Authors: Amestoy, Patrick R, Duff, Iain S, L’Excellent, Jean-Yves, Li, Xiaoye S
Format: Journal Article
Language:English
Published: Elsevier B.V 01.07.2003
Elsevier
Subjects:
Computer Science
Data Structures and Algorithms
Direct solvers
Distributed, Parallel, and Cluster Computing
Immediate communication primitives
Message passing
MPI
Sparse matrices
Immediate communication primitives
Direct solvers
Message passing
Sparse matrices
MPI
ISSN:0167-8191, 1872-7336
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We examine the send and receive mechanisms of MPI and show how to implement message passing robustly so that performance is not significantly affected by changes to the MPI system. We discuss this within the context of two different parallel algorithms for sparse Gaussian elimination: a multifrontal solver ( MUMPS), and a supernodal one ( SuperLU). The performance of our initial strategies based on simple MPI point-to-point communication primitives is very sensitive to the MPI system, particularly the way MPI buffers are used. Using nonblocking communication primitives improves the performance and robustness, but at the cost of increased code complexity.
ISSN:0167-8191
1872-7336
DOI:10.1016/S0167-8191(03)00067-X