Abstract
Wait states in parallel applications can be identified by scanning event traces for characteristic patterns. In our earlier work, we have defined such patterns for mpi-2 one-sided communication, although still based on a trace-analysis scheme with limited scalability. Taking advantage of a new scalable trace-analysis approach based on a parallel replay, which was originally developed for mpi-1 point-to-point and collective communication, we show how wait states in one-sided communications can be detected in a more scalable fashion. We demonstrate the scalability of our method and its usefulness for the optimization cycle with applications running on up to 8,192 cores.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Message Passing Interface Forum: MPI: A Message-Passing Interface Standard, Version 2.1 (June 2008), http://www.mpi-forum.org/
Mirin, A.A., Sawyer, W.B.: A scalable implementation of a finite-volume dynamical core in the community atmosphere model. International Journal on High Performance Computing Applications 19(3), 203–212 (2005)
Kühnal, A., Hermanns, M.-A., Mohr, B., Wolf, F.: Specification of inefficiency patterns for MPI-2 one-sided communication. In: Nagel, W.E., Walter, W.V., Lehner, W. (eds.) Euro-Par 2006. LNCS, vol. 4128, pp. 47–62. Springer, Heidelberg (2006)
Geimer, M., Wolf, F., Wylie, B.J.N., Mohr, B.: Scalable parallel trace-based performance analysis. In: Mohr, B., Träff, J.L., Worringen, J., Dongarra, J. (eds.) PVM/MPI 2006. LNCS, vol. 4192, pp. 303–312. Springer, Heidelberg (2006)
Scalasca, http://www.scalasca.org/
Mohror, K., Karavanic, K.L.: Performance tool support for MPI-2 on Linux. In: Proceedings of the Supercomputing Conference (SC), Pittsburgh, PA (2004)
Shende, S.S., Malony, A.D.: The TAU parallel performance system. International Journal of High Performance Computing Applications 20(2), 287–331 (2006)
Knüpfer, A., Brunst, H., Doleschal, J., Jurenz, M., Lieber, M., Mickler, H., Müller, M.S., Nagel, W.E.: The Vampir performance analysis tool set. In: Resch, M., Keller, R., Himmler, V., Krammer, B., Schulz, A. (eds.) Tools for High Performance Computing, pp. 139–155. Springer, Heidelberg (2008)
Knüpfer, A.: Personal communication (2009)
Wolf, F., Mohr, B.: Automatic performance analysis of hybrid MPI/OpenMP applications. Journal of Systems Architecture 49(10-11), 421–439 (2003)
Leko, A., Su, H.H., Bonachea, D., Golden, B., Billingsley, M., George, A.: Parallel Performance Wizard: A performance analysis tool for partitioned global-address-space programming models. In: Proc. of the Supercomputing Conference (SC), vol. 186. ACM, New York (2006)
Becker, D., Rabenseifner, R., Wolf, F., Linford, J.: Replay-based synchronization of timestamps in event traces of massively parallel applications. Scalable Computing: Practice and Experience 10(1), 49–60 (2009); Special Issue International Workshop on Simulation and Modelling in Emergent Computational Systems (SMECS)
Geimer, M., Wolf, F., Wylie, B.J., Mohr, B.: A scalable tool architecture for diagnosing wait states in massively parallel applications. Parallel Computing (in press) (2009)
Bailey, D.H., Barzcz, E., Dagum, L., Simon, H.D.: NAS parallel benchmark results. IEEE Parallel Distrib. Technol. 1(1), 43–51 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hermanns, MA., Geimer, M., Mohr, B., Wolf, F. (2009). Scalable Detection of MPI-2 Remote Memory Access Inefficiency Patterns. In: Ropo, M., Westerholm, J., Dongarra, J. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 2009. Lecture Notes in Computer Science, vol 5759. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03770-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-03770-2_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03769-6
Online ISBN: 978-3-642-03770-2
eBook Packages: Computer ScienceComputer Science (R0)