To predict application performance on an HPC system is an important technology for designing the computing system and developing applications. However, accurate prediction is a challenge, particularly, in the case of a future coming system with higher performance.

In this paper, we present a new method for predicting application performance on HPC systems. This method combines modeling of sequential performance on a single processor and macro-level simulations of applications for parallel performance on the entire system. In the simulation, the execution flow is traced but kernel computations are omitted for reducing the execution time. Validation on a real terascale system showed that the predicted and measured performance agreed within 10% to 20 %. We employed the method in designing a hypothetical petascale system of 32768 SIMD-extended processor cores. For predicting application performance on the petascale system, the macro-level simulation required several hours.

References

[1]

V. S. Adve, R. Bagrodia, E. Deelman and R. Sakellariou, "Compiler-optimized simulation of large-scale applications on high performance architectures," Journal of Parallel and Distributed Computing, 62(3), pp. 393--426, 2002.

Digital Library

Google Scholar

[2]

D. H. Bailey and A. Snavely, "Performance modeling: understanding the past and predicting the future," In Proceedings of Euro-Par 2005, Parallel Processing, 11th International Euro-Par Conference, pp. 185--195.

Digital Library

Google Scholar

[3]

J. Bourgeois and F. Spies, "Performance prediction of an nas benchmark program with ChronosMix environment," In Proceedings of Euro-Par 2000, Parallel Processing, 6th International Euro-Par Conference, pp. 208--216.

Digital Library

Google Scholar

[4]

R. Car and M. Parrinello, "Unified approach for molecular dynamics and density-functional approach," Phys. Rev. Lett. 55(22), pp. 2471--2474, 1985.

Crossref

Google Scholar

[5]

J. J. Dongarra and G. W. Stewart, "LINPACK - A package for solving linear systems," Sources and Development of Mathematical Software, (W. R. Cowell, Editor), Prentice-Hall Inc., New Jersey, pp. 20--48, 1984

Google Scholar

[6]

D. J. Kerbyson, H. J. Alme, A. Hoisie, F. Petrini, H. J. Wasserman and M. Gittings, "Predictive performance and scalability modeling of a large-scale application," In Proceedings of SC2001.

Digital Library

Google Scholar

[7]

T. L. Wilmarth, G. Zheng, E. J. Bohm, Y. Mehta, N. Choudhury, P. Jagadishprasad and L. V. Kale, "Performance prediction using simulation of large-scale interconnection networks in POSE," In Proceedings of the Workshop on Principles of Advanced and Distributed Simulation, pp. 109--118, 2005.

Digital Library

Google Scholar

[8]

S. Prakash and R. L. Bagrodia, "MPI-SM: using parallel simulation to evaluate MPI programs," In Proceedings of the 30th conference on Winter simulation, pp. 467--474, 1998.

Digital Library

Google Scholar

[9]

S. Prakash, E. Deelman, R. Bagrodia, "Asynchronous parallel simulation of parallel programs," IEEE Transactions on Software Engineering, 26(5), pp. 385--400, 2000.

Digital Library

Google Scholar

[10]

A. Snavely, L. Carrington, N. Wolter, J. Labarta, R. Badia and A. Purkayastha, "A framework for application performance modeling and prediction," In Proceedings of SC2002.

Digital Library

Google Scholar

[11]

A. Snavely, X. Gao, C. Lee, L. Carrington, N. Wolter, J. Labarta, J. Gimenez and P. Jones, "Performance modeling of HPC applications," In Proceedings of Parallel Computing 2003.

Google Scholar

[12]

G. Zheng, G. Kakulapati and L. V. Kale, "BigSim: A parallel simulator for performance prediction of extremely large parallel machines," In Proceedings of the International Parallel and Distributed Processing Symposium, 2004.

Google Scholar

[13]

G. Zheng, T. Wilmarth, P. Jagadishprasad and L. V. Kale, "Simulationbased performance prediction for large parallel machines," International Journal of Parallel Programming, 33(2--3), pp. 183--207, 2005.

Digital Library

Google Scholar

[14]

J. Brehm, P. H. Worley and M. Madhukar, "Performance modeling for SPMD message-pasing programs," Concurrency: Practice and Experience, 10(5), pp. 333--357, 1998

Crossref

Google Scholar

Cited By

View all

Wang JYoo WSim ANugent PWu K(2017)Parallel Variable Selection for Effective Performance PredictionProceedings of the 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing10.1109/CCGRID.2017.47(208-217)Online publication date: 14-May-2017
https://dl.acm.org/doi/10.1109/CCGRID.2017.47
Nadeem FAlghazzawi DMashat AFakeeh KAlmalaise AHagras H(2017)Modeling and predicting execution time of scientific workflows in the Grid using radial basis function neural networkCluster Computing10.1007/s10586-017-1018-x20:3(2805-2819)Online publication date: 1-Sep-2017
https://dl.acm.org/doi/10.1007/s10586-017-1018-x
Yan FHe YRuwase OSmirni EWest J(2016)SERFProceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis10.5555/3014904.3014939(1-12)Online publication date: 13-Nov-2016
https://dl.acm.org/doi/10.5555/3014904.3014939
Show More Cited By

Index Terms

Performance prediction of large-scale parallell system and application using macro-level simulation

Recommendations

Extraction of Parallel Application Signatures for Performance Prediction
HPCC '10: Proceedings of the 2010 IEEE 12th International Conference on High Performance Computing and Communications

Predicting performance of parallel applications is becoming increasingly complex and the best performance predictor is the application itself, but the time required to run it thoroughly is a onerous requirement. We seek to characterize the behavior of ...
An Investigation into the Application of Different Performance Prediction Methods to Distributed Enterprise Applications

Response time predictions for workload on new server architectures can enhance Service Level Agreement--based resource management. This paper evaluates two performance prediction methods using a distributed enterprise application benchmark. The ...
Parallel Application Signature for Performance Analysis and Prediction
Predicting the performance of parallel scientific applications is becoming increasingly complex. Our goal was to characterize the behavior of message-passing applications on different target machines. To achieve this goal, we developed a method called ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

SC '08: Proceedings of the 2008 ACM/IEEE conference on Supercomputing

November 2008

739 pages

ISBN:9781424428359

Conference Chair:
Patricia Teller

Publisher

IEEE Press

Publication History

Published: 15 November 2008

Check for updates

Author Tags

Qualifiers

Research-article

Conference

SC '08

Sponsor:

SIGARCH
IEEE-CS

SC '08: International Conference for High Performance Computing, Networking, Storage and Analysis

November 15 - 21, 2008

Texas, Austin

Acceptance Rates

SC '08 Paper Acceptance Rate 59 of 277 submissions, 21%;

Overall Acceptance Rate 1,516 of 6,373 submissions, 24%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

16
Total Citations
View Citations
479
Total Downloads

Downloads (Last 12 months)2
Downloads (Last 6 weeks)1

Reflects downloads up to 23 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Wang JYoo WSim ANugent PWu K(2017)Parallel Variable Selection for Effective Performance PredictionProceedings of the 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing10.1109/CCGRID.2017.47(208-217)Online publication date: 14-May-2017
https://dl.acm.org/doi/10.1109/CCGRID.2017.47
Nadeem FAlghazzawi DMashat AFakeeh KAlmalaise AHagras H(2017)Modeling and predicting execution time of scientific workflows in the Grid using radial basis function neural networkCluster Computing10.1007/s10586-017-1018-x20:3(2805-2819)Online publication date: 1-Sep-2017
https://dl.acm.org/doi/10.1007/s10586-017-1018-x
Yan FHe YRuwase OSmirni EWest J(2016)SERFProceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis10.5555/3014904.3014939(1-12)Online publication date: 13-Nov-2016
https://dl.acm.org/doi/10.5555/3014904.3014939
Cho YOh SEgger BZaks AMendelson BRauchwerger LHwu W(2016)Online Scalability Characterization of Data-Parallel Programs on Many CoresProceedings of the 2016 International Conference on Parallel Architectures and Compilation10.1145/2967938.2967960(191-205)Online publication date: 11-Sep-2016
https://dl.acm.org/doi/10.1145/2967938.2967960
Benedict SRejitha RAlex SSarkar SSureka ACotroneo DSinha NSinha VVenkatasubramanyam RJoshi PNaik RSingh PLalchandani J(2016)Energy and Performance Prediction of CUDA Applications using Dynamic Regression ModelsProceedings of the 9th India Software Engineering Conference10.1145/2856636.2856643(37-47)Online publication date: 18-Feb-2016
https://dl.acm.org/doi/10.1145/2856636.2856643
Zhang DWilke JHendry GDechev D(2016)Validating the Simulation of Large-Scale Parallel Applications Using Statistical CharacteristicsACM Transactions on Modeling and Performance Evaluation of Computing Systems10.1145/28097781:1(1-22)Online publication date: 12-Feb-2016
https://dl.acm.org/doi/10.1145/2809778
Sottile MDagit JZhang DHendry GDechev D(2015)Static Analysis Techniques for Semiautomatic Synthesis of Message Passing Software SkeletonsACM Transactions on Modeling and Computer Simulation10.1145/277888826:1(1-24)Online publication date: 29-Jun-2015
https://dl.acm.org/doi/10.1145/2778888
Cuomo ARak MVillano U(2015)Planting parallel program simulation on the cloudConcurrency and Computation: Practice & Experience10.1002/cpe.301227:6(1467-1482)Online publication date: 25-Apr-2015
https://dl.acm.org/doi/10.1002/cpe.3012
Zhai JHu JTang XMa XChen WDamkroger TDongarra J(2014)CypressProceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis10.1109/SC.2014.17(143-153)Online publication date: 16-Nov-2014
https://dl.acm.org/doi/10.1109/SC.2014.17
Wilke JSargsyan KKenny JDebusschere BNajm HHendry G(2013)Validation and uncertainty assessment of extreme-scale HPC simulation through bayesian inferenceProceedings of the 19th international conference on Parallel Processing10.1007/978-3-642-40047-6_7(41-52)Online publication date: 26-Aug-2013
https://dl.acm.org/doi/10.1007/978-3-642-40047-6_7
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Extraction of Parallel Application Signatures for Performance Prediction

An Investigation into the Application of Different Performance Prediction Methods to Distributed Enterprise Applications

Parallel Application Signature for Performance Analysis and Prediction