Article

Performance expectations and guidelines for MPI derived datatypes

Authors:

William Gropp,

Torsten Hoefler,

Rajeev Thakur,

Jesper Larsson TräffAuthors Info & Claims

EuroMPI'11: Proceedings of the 18th European MPI Users' Group conference on Recent advances in the message passing interface

Pages 150 - 159

Published: 18 September 2011 Publication History

Abstract

MPI's derived datatypes provide a powerful mechanism for concisely describing arbitrary, noncontiguous layouts of user data for use in MPI communication. This paper formulates self-consistent performance guidelines for derived datatypes. Such guidelines make performance expectations for derived datatypes explicit and suggest relevant optimizations to MPI implementers. We also identify self-consistent guidelines that are too strict to enforce, because they entail NP-hard optimization problems. Enforced self-consistent guidelines assure the user that certain manual datatype optimizations cannot lead to performance improvements, which in turn contributes to performance portability between MPI implementations that behave in accordance with the guidelines. We present results of tests with several MPI implementations, which indicate that many of them violate the guidelines.

References

[1]

Bajrović, E., Träff, J.L.: Using MPI derived datatypes in numerical libraries. In: Cotronis, Y., et al. (eds.) EuroMPI 2011. LNCS, vol. 6960, pp. 29-38. Springer, Heidelberg (2011)

Crossref

Google Scholar

[2]

Byna, S., Sun, X.-H., Thakur, R., Gropp, W.D.: Automatic memory optimizations for improving MPI derived datatype performance. In: Mohr, B., Träff, J.L., Worringen, J., Dongarra, J. (eds.) PVM/MPI 2006. LNCS, vol. 4192, pp. 238-246. Springer, Heidelberg (2006)

Crossref

Google Scholar

[3]

Gropp, W.D., Kimpe, D., Ross, R., Thakur, R., Träff, J.L.: Self-consistent MPIIO performance requirements and expectations. In: Lastovetsky, A., Kechadi, T., Dongarra, J. (eds.) EuroPVM/MPI 2008. LNCS, vol. 5205, pp. 167-176. Springer, Heidelberg (2008)

Crossref

Google Scholar

[4]

Gropp, W.D., Lusk, E., Swider, D.: Improving the performance of MPI derived datatypes. In: Proceedings of the Third MPI Developer's and User's Conference, pp. 25-30. MPI Software Technology Press (1999)

Google Scholar

[5]

Hoefler, T., Gottlieb, S.: Parallel zero-copy algorithms for fast fourier transform and conjugate gradient using MPI datatypes. In: Keller, R., Gabriel, E., Resch, M., Dongarra, J. (eds.) EuroMPI 2010. LNCS, vol. 6305, pp. 132-141. Springer, Heidelberg (2010)

Crossref

Google Scholar

[6]

Lu, Q., Wu, J., Panda, D.K., Sadayappan, P.: Applying MPI derived datatypes to the NAS benchmarks: A case study. In: 33rd International Conference on Parallel Processing Workshops (ICPP 2004 Workshops), pp. 538-545. IEEE Computer Society, Los Alamitos (2004)

Crossref

Google Scholar

[7]

MPI Forum: MPI: A Message-Passing Interface Standard. Version 2.2 (September 4, 2009), http://www.mpi-forum.org

Google Scholar

[8]

Reussner, R., Träff, J.L., Hunzelmann, G.: A benchmark for MPI derived datatypes. In: Dongarra, J., Kacsuk, P., Podhorszki, N. (eds.) PVM/MPI 2000. LNCS, vol. 1908, pp. 10-17. Springer, Heidelberg (2000)

Crossref

Google Scholar

[9]

Ross, R., Miller, N., Gropp, W.D.: Implementing fast and reusable datatype processing. In: Dongarra, J., Laforenza, D., Orlando, S. (eds.) EuroPVM/MPI 2003. LNCS, vol. 2840, pp. 404-413. Springer, Heidelberg (2003)

Google Scholar

[10]

Santhanaraman, G., Wu, J., Huang, W., Panda, D.K.: Designing zero-copy message passing interface derived datatype communication over Infiniband: Alternative approaches and performance evaluation. International Journal on High Performance Computing Applications 19(2), 129-142 (2005)

Crossref

Google Scholar

[11]

Träff, J.L., Gropp, W.D., Thakur, R.: Self-consistent MPI performance guidelines. IEEE Transactions on Parallel and Distributed Systems 21(5), 698-709 (2010)

Crossref

Google Scholar

[12]

Träff, J.L., Hempel, R., Ritzdorf, H., Zimmermann, F.: Flattening on the fly: Efficient handling of MPI derived datatypes. In: Margalef, T., Dongarra, J., Luque, E. (eds.) PVM/MPI 1999. LNCS, vol. 1697, pp. 109-116. Springer, Heidelberg (1999)

Crossref

Google Scholar

Cited By

View all

Xiong QBangalore PSkjellum AHerbordt M(2018)MPI Derived DatatypesProceedings of the 25th European MPI Users' Group Meeting10.1145/3236367.3236378(1-10)Online publication date: 23-Sep-2018
https://dl.acm.org/doi/10.1145/3236367.3236378
Carpen-Amarie AHunold STräff JDongarra JHolmes DCollis ALarsson Träff JSmith L(2016)On the Expected and Observed Communication Performance with MPI Derived DatatypesProceedings of the 23rd European MPI Users' Group Meeting10.1145/2966884.2966905(108-120)Online publication date: 25-Sep-2016
https://dl.acm.org/doi/10.1145/2966884.2966905
Träff JDongarra JHolmes DCollis ALarsson Träff JSmith L(2016)A Library for Advanced Datatype ProgrammingProceedings of the 23rd European MPI Users' Group Meeting10.1145/2966884.2966904(98-107)Online publication date: 25-Sep-2016
https://dl.acm.org/doi/10.1145/2966884.2966904
Show More Cited By

Recommendations

MPI Derived Datatypes: Performance and Portability Issues
EuroMPI '18: Proceedings of the 25th European MPI Users' Group Meeting

This paper addresses performance-portability and overall performance issues when derived datatypes are used with four MPI implementations: Open MPI, MPICH, MVAPICH2, and Intel MPI. These comparisons are particularly relevant today since most vendor ...
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 ...
A case for using MPI's derived datatypes to improve I/O performance
SC '98: Proceedings of the 1998 ACM/IEEE conference on Supercomputing

MPI-IO, the I/O part of the MPI-2 standard, is a promising new interface for parallel I/O. A key feature of MPI-IO is that it allows users to access several noncontiguous pieces of data from a file with a single I/O function call by defining file views ...

Comments

Information & Contributors

Information

Published In

EuroMPI'11: Proceedings of the 18th European MPI Users' Group conference on Recent advances in the message passing interface

September 2011

355 pages

ISBN:9783642244483

Editors:
Yiannis Cotronis
University of Athens, Greece
,
Anthony Danalis
University of Tennessee, Knoxville, TN
,
Dimitrios S. Nikolopoulos
University of Crete, Heraklion, Greece
,
Jack Dongarra
University of Tennessee, Knoxville, TN

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 18 September 2011

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

12
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 01 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Xiong QBangalore PSkjellum AHerbordt M(2018)MPI Derived DatatypesProceedings of the 25th European MPI Users' Group Meeting10.1145/3236367.3236378(1-10)Online publication date: 23-Sep-2018
https://dl.acm.org/doi/10.1145/3236367.3236378
Carpen-Amarie AHunold STräff JDongarra JHolmes DCollis ALarsson Träff JSmith L(2016)On the Expected and Observed Communication Performance with MPI Derived DatatypesProceedings of the 23rd European MPI Users' Group Meeting10.1145/2966884.2966905(108-120)Online publication date: 25-Sep-2016
https://dl.acm.org/doi/10.1145/2966884.2966905
Träff JDongarra JHolmes DCollis ALarsson Träff JSmith L(2016)A Library for Advanced Datatype ProgrammingProceedings of the 23rd European MPI Users' Group Meeting10.1145/2966884.2966904(98-107)Online publication date: 25-Sep-2016
https://dl.acm.org/doi/10.1145/2966884.2966904
Hunold SCarpen-Amarie ALübbe FTräff J(2016)Automatic Verification of Self-consistent MPI Performance GuidelinesProceedings of the 22nd International Conference on Euro-Par 2016: Parallel Processing - Volume 983310.1007/978-3-319-43659-3_32(433-446)Online publication date: 24-Aug-2016
https://dl.acm.org/doi/10.1007/978-3-319-43659-3_32
Kalany MTräff JDongarra JDenis AGoglin BJeannot EMercier G(2015)Efficient, Optimal MPI Datatype Reconstruction for Vector and Index TypesProceedings of the 22nd European MPI Users' Group Meeting10.1145/2802658.2802671(1-10)Online publication date: 21-Sep-2015
https://dl.acm.org/doi/10.1145/2802658.2802671
Träff JRougier ADongarra JIshikawa YHori A(2014)Zero-copy, Hierarchical Gather is not possible with MPI Datatypes and CollectivesProceedings of the 21st European MPI Users' Group Meeting10.1145/2642769.2642772(39-44)Online publication date: 9-Sep-2014
https://dl.acm.org/doi/10.1145/2642769.2642772
Träff JDongarra JIshikawa YHori A(2014)Optimal MPI Datatype Normalization for Vector and Index-block TypesProceedings of the 21st European MPI Users' Group Meeting10.1145/2642769.2642771(33-38)Online publication date: 9-Sep-2014
https://dl.acm.org/doi/10.1145/2642769.2642771
Träff JRougier ADongarra JIshikawa YHori A(2014)MPI Collectives and Datatypes for Hierarchical All-to-all CommunicationProceedings of the 21st European MPI Users' Group Meeting10.1145/2642769.2642770(27-32)Online publication date: 9-Sep-2014
https://dl.acm.org/doi/10.1145/2642769.2642770
Träff JRougier AHunold SBode AGerndt MStenström PRauchwerger LMiller BSchulz M(2014)Implementing a classicProceedings of the 28th ACM international conference on Supercomputing10.1145/2597652.2597662(135-144)Online publication date: 10-Jun-2014
https://dl.acm.org/doi/10.1145/2597652.2597662
Schneider TKjolstad FHoefler TDongarra JBlas JCarretero J(2013)MPI datatype processing using runtime compilationProceedings of the 20th European MPI Users' Group Meeting10.1145/2488551.2488552(19-24)Online publication date: 15-Sep-2013
https://dl.acm.org/doi/10.1145/2488551.2488552
Show More Cited By

View Options

View options

Get Access

Login options

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

Abstract

References

Cited By

Recommendations

MPI Derived Datatypes: Performance and Portability Issues

Self-Consistent MPI Performance Guidelines

A case for using MPI's derived datatypes to improve I/O performance

Comments

Information

Published In

Publisher

Publication History

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Get Access

Login options

Full Access

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations