More Web Proxy on the site http://driver.im/

research-article

Performance Modeling and Evaluation of MPI

Authors:

Khalid Al-Tawil,

Csaba Andras MoritzAuthors Info & Claims

Journal of Parallel and Distributed Computing, Volume 61, Issue 2

Pages 202 - 223

https://doi.org/10.1006/jpdc.2000.1677

Published: 01 February 2001 Publication History

Abstract

Users of parallel machines need to have a good grasp for how different communication patterns and styles affect the performance of message-passing applications. LogGP is a simple performance model that reflects the most important parameters required to estimate the communication performance of parallel computers. The message passing interface (MPI) standard provides new opportunities for developing high performance parallel and distributed applications. In this paper, we use LogGP as a conceptual framework for evaluating the performance of MPI communications on three platforms: Cray-Research T3D, Convex Exemplar 1600SP, and a network of workstations (NOW). We develop a simple set of communication benchmarks to extract the LogGP parameters. Our objective in this is to compare the performance of MPI communication on several platforms and to identify a performance model suitable for MPI performance characterization. In particular, two problems are addressed: how LogGP quantifies MPI performance and what extra features are required for modeling MPI, and how MPI performance compare on the three computing platforms: Cray Research T3D, Convex Exemplar 1600SP, and workstations clusters.

References

[1]

G. Abandah and E. Davidson, Modeling the communication performance of the IBM SP2, in Proc. 10th IEEE Int'l Parallel Processing Symp., Honolulu, Hawaii, April 15-19, 1996, pp. 249-257.

Digital Library

[2]

R. Alasdair, A. Bruce, J. Mills, A. Smith, Technical Report (June 1994).

[3]

A. Alexandrov, M.F. Ionescu, K.E. Schauser, C. Scheiman, LogGP: Incorporating long messages into the LogP model¿one step closer towards a realistic model fpr parallel computation, 1995.

[4]

T. von Eicken, D. E. Culler, S. C. Goldstein and K. E. Schauser, Active Messages: A mechanism for integrated communication and computation, in Proc. of the 19th Int. Symp. on Computer Architecture, Gold Coast, Australia, May 1992, pp. 256-266.

Digital Library

[5]

C. Andras, Moritz, and, Matthew, I. Frank, LoGPC: Modeling network contention in message-passing applications, in, Performance Evaluation Review, Special Issue Vol, 26, No, and “Proceedings of ACM Joint International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS/PERFORMANCE 98, Wisconsin Madison,” June 1998.

[6]

C. Andras, K. Al-Tawil, and B. Basilio, Performance comparison of MPI on MPP and workstation clusters, in Proc. 10th Int'l Conf. Parallel and Distributed Computing Systems, New Orleans, LA, Oct. 1-3, 1997, pp. 167-172.

[7]

G. Burns, R. Daoud, J. Vaigl, May 1994.

[8]

R. Barriuso, A. Knies, Technical Report Revision 2.2 (August 1994).

[9]

K. Cameron, L.J. Clarke, A.G. Smith, Technical Report (1995).

[10]

D. Culler, R. Karp, D. Patterson, A. Sahay, K. Schauser, E. Santos, R. Subramonian, T. Eicken, LogP: Towards a realistic model of parallel computation, May 1993.

[11]

D. Culler, L. Liu, R. Martin, C. Yoshikawa, 1996.

[12]

F. Cheng, P. Vaughan, D. Reese, A. Skjeellum, The Unify System, Technical Report (July 1994).

Digital Library

[13]

B. Gropp, R. Lusk, T. Skjellum, N. Doss, Argonne National Laboratory, July 1994.

[14]

K. Keeton, T. Anderson, and D. Patterson, LogP Quantified: The Case for Low-Overhead Local Area Networks, in Hot Interconnects III: A Symp. on High Performance Interconnects, Aug. 10-12, 1995,Stanford University, Stanford, CA.

[15]

M. I. Frank, A. Agarwal, and, M. K. Vernon, LoPC: Modeling contention in parallel algorithms, in, Proc. of the SIXTH ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Las Vegas, NV, June 18, 1997.

[16]

, Internat. J. Supercomput. Appl., 8 (Fall/Winter 1994) 165-416.

[17]

, Technical Report (1994).

[18]

N. Nupairoj, L. Ni, Technical Report (Sept. 1994).

[19]

R. W. Numrich, P. L. Springer, and, J. C. Peterson, Measurement of communication rates on the Cray T3D interprocessor network, in, Proc. HPCN Europe 1994, Munich, April 18-20.

[20]

P. Worley, MPI performance evaluation and characterization using a compact application benchmark code, in: Proc. Second MPI Developers Conference and Users' Meeting, IEEE Computer Society Press, Los Alamitos, 1996, pp. 170-177.

Cited By

Gomez-Folgar FIndalecio GSeoane NPena TGarcia-Loureiro A(2018)MPI-Performance-Aware-ReallocationComputing10.1007/s00607-017-0573-6100:2(211-226)Online publication date: 1-Feb-2018
https://dl.acm.org/doi/10.1007/s00607-017-0573-6
Xu YViswanathan VCai W(2017)Reducing Synchronization Overhead with Computation Replication in Parallel Agent-Based Road Traffic SimulationIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2017.271416528:11(3286-3297)Online publication date: 6-Oct-2017
https://dl.acm.org/doi/10.1109/TPDS.2017.2714165
Höfinger SHaunschmid E(2017)Modelling parallel overhead from simple run-time recordsThe Journal of Supercomputing10.1007/s11227-017-2023-973:10(4390-4406)Online publication date: 1-Oct-2017
https://dl.acm.org/doi/10.1007/s11227-017-2023-9
Show More Cited By

Index Terms

Recommendations

LogGP Performance Evaluation of MPI
HPDC '98: Proceedings of the 7th IEEE International Symposium on High Performance Distributed Computing

Users of parallel machines need good performance evaluations for several communication patterns in order to develop efficient message-passing applications. LogGP is a simple parallel machine model that reflects the important parameters required to ...
Self-Consistent MPI Performance Guidelines

Message passing using the Message-Passing Interface (MPI) is at present the most widely adopted framework for programming parallel applications for distributed memory and clustered parallel systems. For reasons of (universal) implementability, the MPI ...
Performance Evaluation of MPI Implementations and MPI-Based Parallel ELLPACK Solvers
MPIDC '96: Proceedings of the Second MPI Developers Conference

Abstract: We are concerned with the parallelization of finite element mesh generation and its decomposition, and the parallel solution of sparse algebraic equations which are obtained from the parallel discretization of second order elliptic partial ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Journal of Parallel and Distributed Computing

Journal of Parallel and Distributed Computing Volume 61, Issue 2

Feb. 2001

129 pages

ISSN:0743-7315

Editors:
Allan Gottlieb
New York Univ. and NEC Research Institute
,
Kai Hwang
Univ. of Southern California
,
Sartaj Sahni
Univ. of Florida

Issue’s Table of Contents

Copyright © Academic Press.

Publisher

Academic Press, Inc.

United States

Publication History

Published: 01 February 2001

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 17 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Gomez-Folgar FIndalecio GSeoane NPena TGarcia-Loureiro A(2018)MPI-Performance-Aware-ReallocationComputing10.1007/s00607-017-0573-6100:2(211-226)Online publication date: 1-Feb-2018
https://dl.acm.org/doi/10.1007/s00607-017-0573-6
Xu YViswanathan VCai W(2017)Reducing Synchronization Overhead with Computation Replication in Parallel Agent-Based Road Traffic SimulationIEEE Transactions on Parallel and Distributed Systems10.1109/TPDS.2017.271416528:11(3286-3297)Online publication date: 6-Oct-2017
https://dl.acm.org/doi/10.1109/TPDS.2017.2714165
Höfinger SHaunschmid E(2017)Modelling parallel overhead from simple run-time recordsThe Journal of Supercomputing10.1007/s11227-017-2023-973:10(4390-4406)Online publication date: 1-Oct-2017
https://dl.acm.org/doi/10.1007/s11227-017-2023-9
Rojek KWyrzykowski R(2017)Performance modeling of 3D MPDATA simulations on GPU clusterThe Journal of Supercomputing10.1007/s11227-016-1774-z73:2(664-675)Online publication date: 1-Feb-2017
https://dl.acm.org/doi/10.1007/s11227-016-1774-z
Rico-Gallego JDíaz-Martín JLastovetsky A(2016)Extending τ -Lop to model concurrent MPI communications in multicore clustersFuture Generation Computer Systems10.1016/j.future.2016.02.02161:C(66-82)Online publication date: 1-Aug-2016
https://dl.acm.org/doi/10.1016/j.future.2016.02.021
Bridges PDosanjh MGrant RSkjellum AFarmer SBrightwell R(2015)Preparing for exascaleProceedings of the 3rd Workshop on Exascale MPI10.1145/2831129.2831134(1-8)Online publication date: 15-Nov-2015
https://dl.acm.org/doi/10.1145/2831129.2831134
Hoefler TGropp WThakur RTräff J(2010)Toward performance models of MPI implementations for understanding application scaling issuesProceedings of the 17th European MPI users' group meeting conference on Recent advances in the message passing interface10.5555/1894122.1894126(21-30)Online publication date: 12-Sep-2010
https://dl.acm.org/doi/10.5555/1894122.1894126
Avetisyan AGaisaryan SIvannikov VPadaryan V(2007)Productivity prediction of MPI programs based on modelsAutomation and Remote Control10.1134/S000511790705003768:5(750-759)Online publication date: 1-May-2007
https://dl.acm.org/doi/10.1134/S0005117907050037
Martinasso MMéhaut J(2005)Prediction of communication latency over complex network behaviors on SMP clustersProceedings of the 2005 international conference on European Performance Engineering, and Web Services and Formal Methods, international conference on Formal Techniques for Computer Systems and Business Processes10.1007/11549970_13(172-186)Online publication date: 1-Sep-2005
https://dl.acm.org/doi/10.1007/11549970_13

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents