Abstract
The Abstract Data and Communication Library (ADCL) allows for auto-tuning of communication operations for parallel applications. This paper presents a new set of interfaces introduced in ADCL in order to support most MPI collective communication operations, and thus enable the optimization of one of the most widely used features of the MPI specification. The paper discusses semantic as well as implementation aspects, and evaluates the new interfaces using the NPB FT benchmark on a large selection of platforms and MPI libraries.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bailey, D., Barszcz, E., Barton, J., Browning, D., Carter, R., Dagum, L., Fatoohi, R., Fineberg, S., Frederickson, P., Lasinski, T., Schreiber, R., Simon, H., Venkatakrishnan, V., Weeratunga, S.: The NAS Parallel Benchmarks (1994)
Benkert, K., Gabriel, E., Resch, M.M.: Outlier Detection in Performance Data of Parallel Applications. In: 9th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (2008)
Bruck, J., Ho, C.T., Kipnis, S., Weathersby, D.: Efficient algorithms for all-to-all communications in multi-port message-passing systems. In: SPAA ’94: Proceedings of the sixth annual ACM symposium on Parallel algorithms and architectures, pp. 298–309. ACM, New York, NY, USA (1994). DOI http://doi.acm.org/10.1145/181014.181756
Chen, J., Zhang, Y., Zhang, L., Yuan, W.: Performance evaluation of allgather algorithms on terascale linux cluster with fast ethernet. International Conference on High Performance Computing and Grid in Asia Pacific Region, 437–442 (2005). DOI http://doi.ieeecomputersociety.org/10.1109/HPCASIA.2005.75
Gabriel, E., Feki, S., Benkert, K., Resch, M.M.: Towards Performance Portability through Runtime Adaption for High Performance Computing Applications. Concurrency and Computation—Practice and Experience, accepted for publication (2010)
Gabriel, E., Huang, S.: Runtime optimization of application level communication patterns. In: Proceedings of the 2007 International Parallel and Distributed Processing Symposium, 12th International Workshop on High-Level Parallel Programming Models and Supportive Environments, p. 185 (2007)
Gropp, W., Lusk, E., Doss, N., Skjellum, A.: A high-performance, portable implementation of the MPI message passing interface standard. Parallel Computing 22(6), 789–828 (1996)
Jones, T.: Survey of MPI Call Usage. In: IBM System Scientific User Group (ScicomP) 10 (2004)
Rabenseifner, R.: Automatic MPI Counter Profiling. In: 42nd CUG Conference. Noorwijk, The Netherlands. (2000). URL http://scholar.google.com/scholar?hl=en&btnG=Search&q=intitle:Automatic+MPI+Counter+Profiling#0
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Benkert, K., Gabriel, E. (2010). Empirical Optimization of Collective Communications with ADCL. In: Resch, M., et al. High Performance Computing on Vector Systems 2010. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-11851-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-11851-7_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-11850-0
Online ISBN: 978-3-642-11851-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)