Abstract
This tutorial will cover parallel programming with the MPI message passing interface, with special attention paid to the issues that arise in a computational grid environment. After a summary of MPI programming, we will address the issue of process management, first in a single administrative domain and the then across multiple administrative domains. We will describe the use of the MPD process management system with MPI implementations that support the Process Management Interface, and the MPICH-G2 MPI implementation for Globus-based distributed environments.
We will discuss grid-specific application programming issues such as latency-reduction techniques using message aggregation and the use of topology-aware collective operations. Remote I/O is one of the best aspects of a grid environment, and so the use of MPI-2 I/O operations will be covered. We will conclude with a discussion of fault-tolerance issues in MPI programs, including programming techniques and the state of current implementations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gropp, W., Lusk, E. (2002). MPI on the Grid. In: KranzlmĂĽller, D., Volkert, J., Kacsuk, P., Dongarra, J. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 2002. Lecture Notes in Computer Science, vol 2474. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45825-5_10
Download citation
DOI: https://doi.org/10.1007/3-540-45825-5_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44296-7
Online ISBN: 978-3-540-45825-8
eBook Packages: Springer Book Archive