Abstract
Recent improvements in LANs make network of workstations a good alternative to traditional parallel computers in some applications. MPI (Message Passing Interface) standard library implementation for network of workstation holds great promise in providing both portability and performance. However, some authors point out if this hardware improvements are not supported with a reduction of software overhead, this overhead will dominate communication cost, and many applications may no benefit from the advancements in network hardware. In this paper we present an exhaustive study of MPICH implementation of MPI standard for this environment, analyzing added overhead of each layer. Finally, we propose modifications to network interface to reduce the fixed overhead of transmission.
This work was supported in part by the Spanish CICYT under Grant TIC94-0510-C02-02
Preview
Unable to display preview. Download preview PDF.
References
G. Chiola and G. Ciaccio. GAMMA: a Low-cost Network of Workstations Based on Active Messages. Procc. of 5th EUROMICRO WorkShop on Parallel and Distributed Processing. London, January 1997.
D.E. Culler et al. LogP: Towards a Realistic Model of Parallel Computation. Procc. of the 4th ACM SIGPLAN Symp. on Principles and Practice of Parallel Programming, May 1993.
B.V. Dao, S. Yalamanchili, and J. Duato. Architectural Support for Reducing Communication Overhead in Multiprocessor Interconnection Networks. Procc. of the Third Int. Symp. on High Performance Computer Architecture, February 1997.
T. Von Eicken et al. Active Messages: A Mechanism for Integrated Communication and Computation. Procc. of the 19th ISCA, pp. 256–266, May 1992.
Message Passing Interface Forum. MPI: A Message Passing Interface Standard. Int. J. of Supercomputer Applications and High Performance Computing, 8(3/4), 1994.
N. Nupairoj and L. Ni. Performance Evaluation of Some MPI Implementations on Workstation Clusters. Procc. of the Scalable Parallel Libraries Conf., Oct. 1994.
A. Skjellum, P. Vaughan, C. Roberts. UNIFY: Interoperable MPI and PVM Programming in a Workstation-Network Environment. MPI Developers Conference, University of Notre-Dame, June 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Piernas, J., Flores, A., García, J.M. (1997). Analyzing the performance of MPI in a cluster of workstations based on fast ethernet. In: Bubak, M., Dongarra, J., Waśniewski, J. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 1997. Lecture Notes in Computer Science, vol 1332. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63697-8_65
Download citation
DOI: https://doi.org/10.1007/3-540-63697-8_65
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63697-7
Online ISBN: 978-3-540-69629-2
eBook Packages: Springer Book Archive