Abstract
Automatic performance analysis of parallel programs can be accomplished by scanning event traces of program execution for patterns representing inefficient behavior. The temporal and spatial relationships between individual runtime events recorded in the event trace allow the recognition of wait states as a result of suboptimal parallel interaction. In our earlier work [1], we have shown how patterns related to mpi point-to-point and collective communication can be easily specified using common abstractions that represent execution-state information and links between related events. In this article, we present new abstractions targeting remote memory access (also referred to as one-sided communication) as defined in the mpi-2 standard. We also describe how the general structure of these abstractions differs from our earlier work to accommodate the more complicated sequence of data-transfer and synchronization operations required for this type of communication. To demonstrate the benefits of our methodology, we specify typical performance properties related to one-sided communication.
Chapter PDF
Similar content being viewed by others
References
Wolf, F., Mohr, B.: Specifying Performance Properties of Parallel Applications Using Compound Events. Parallel and Distributed Computing Practices, Special Issue on Monitoring Systems and Tool Interoperability 4, 301–317 (2001)
Message Passing Interface Forum: MPI-2: Extensions to the Message-Passing Interface (1997), http://www.mpi-forum.org
Mirin, A., Sawyer, W.: A scalable implementation of a finite volume dynamical core in the Community Atmosphere Model. International Journal of High Performance Computing Applications 19, 203–212 (2005)
Wolf, F., Mohr, B.: Automatic performance analysis of hybrid MPI/OpenMP applications. Journal of Systems Architecture, Special Issue Evolutions in parallel distributed and network-based processing 49, 421–439 (2003)
Mohr, B., Kühnal, A., Hermanns, M.A., Wolf, F.: Performance Analysis of One-sided Communication Mechanisms. In: Proceedings of Parallel Computing (ParCo), Mini-Symposium Tools Support for Parallel Programming, Malaga, Spain (2005)
Hermanns, M.A., Mohr, B., Wolf, F.: Event-based Measurement and Analysis of One-sided Communication. In: Cunha, J.C., Medeiros, P.D. (eds.) Euro-Par 2005. LNCS, vol. 3648, pp. 156–165. Springer, Heidelberg (2005)
Mohror, K., Karavanic, K.L.: Performance Tool Support for MPI-2 on Linux. In: Proc. of the Supercomputing Conference (SC), Pittsburgh, PA (2004)
Malony, A.D., Shende, S.: Performance Technology for Complex Parallel and Distributed Systems. In: Kacsuk, P., Kotsis, G. (eds.) Quality of Parallel and Distributed Programs and Systems, pp. 25–41. Nova Science Publishers, Inc., New York (2003)
Pallas/Intel: Intel Trace Collector (2006), http://www.intel.com/software/products/cluster/tcollector/
Wolf, F.: Automatic Performance Analysis on Parallel Computers with SMP Nodes. PhD thesis, RWTH Aachen, Forschungszentrum Jülich (2003), ISBN 3-00-010003-2
Kühnal, A.: Performance Properties for One-Sided Communication Mechanisms. Diploma Thesis. Forschungszentrum Jülich (2005) (in German)
Forschungszentrum Jülich: SCALASCA (2006), http://www.scalasca.org
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kühnal, A., Hermanns, MA., Mohr, B., Wolf, F. (2006). Specification of Inefficiency Patterns for MPI-2 One-Sided Communication. In: Nagel, W.E., Walter, W.V., Lehner, W. (eds) Euro-Par 2006 Parallel Processing. Euro-Par 2006. Lecture Notes in Computer Science, vol 4128. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11823285_6
Download citation
DOI: https://doi.org/10.1007/11823285_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-37783-2
Online ISBN: 978-3-540-37784-9
eBook Packages: Computer ScienceComputer Science (R0)