Abstract
We introduce a refinement strategy to bring the parallel performance analysis closer to the user. The analysis starts with a simple high-level performance model. It is based on first-order approximations, in terms of the logical constituents of the parallel program and characteristics of the system. This model is then progressively refined with more detailed low-level performance aspects, to explain divergences from a ’normal’, linear regime. We use a causal model to structure the relations between all variables involved. The approach intends to serve as a link between detailed performance data and the developer. It is demonstrated with a parallel matrix multiplication algorithm.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Bull, J.M.: A Hierarchical Classification of Overheads in Parallel Programs. In: Proceedings of First IFIP TC10 International Workshop on Software Engineering for Parallel and Distributed Systems, Chapman Hall, pp. 208–219 (March 1996)
Crovella, M.E., Leblanc, T.J.: Parallel Performance Prediction using Lost Cycles Analysis. In: Proc. of Supercomputing 1994, IEEE Computer Society (1994)
Crijns, J., Crijns, A.: Automatische Experimentele Analyse van Systeem en Algoritmeparameters op Parallelle Performanties. Thesis, Vrije Universiteit Brussel (VUB), Brussels (2003)
Keeping, E.S.: Introduction to Statistical Inference. Dover Publications Inc., New York (1995)
Kumar, V., Grama, A., Gupta, A., Karypsis, G.: Introduction to Parallel Computing. Design and Analysis of Algorithms. Benjamin Cummings, California (1994)
Mohr, B., Wolf, F.: KOJAK - A Tool Set for Automatic Performance Analysis of Parallel Programs. In: Euro-Par Conf., pp. 1301–1304 (2003)
Nagel, W.E., Arnold, A., Weber, M., Hoppe, H.-C., Solchenbach, K.: VAMPIR: Visualization and analysis of MPI resources. Supercomputer 12(1), 69–80 (1996)
Pancake, C.M.: Applying Human Factors to the Design of Performance Tools. In: Proc. of the 5th Euro-Par Conf., Springer (1999)
Pearl, J.: Causality. Models, Reasoning and Inference. Cambridge University Press, Cambridge (2000)
Reed, D.A., Aydt, R.A., Noe, R.J., Roth, P.C., Shields, K.A., Shwartz, B.W., Tavera, L.F.: Scalable Performance Analysis: The Pablo Performance Analysis Environment. In: Proc. Scalable Parallel Libraries Conf., IEEE Computer Society Press, Los Alamitos (1993)
Sarukkai, S. R., Yan, J., Gotwals, J. K.: Normalized performance indices for message passing parallel programs. In: Proc. of the 8th international conference on Supercomputing, Manchester, England (1994)
Snavely, A., et al.: A framework for performance modeling and prediction. In: Proc. of the 2002 ACM/IEEE conference on Supercomputing, Baltimore, Maryland, pp. 1–17 (2002)
Truong, H.-L., Fahringer, T.: Performance Analysis for MPI Applications with SCALEA. In: Proc. of the 9th European PVM/MPI Conf., Linz, Austria (September 2002)
Yan, J.C., Sarukkai, S.R., Mehra, P.: Performance Measurement, Visualization and Modeling of Parallel and Distributed Programs using the AIMS Toolkit. Software Practice & Experience ( April 1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lemeire, J., Crijns, A., Crijns, J., Dirkx, E. (2004). A Refinement Strategy for a User-Oriented Performance Analysis. In: Kranzlmüller, D., Kacsuk, P., Dongarra, J. (eds) Recent Advances in Parallel Virtual Machine and Message Passing Interface. EuroPVM/MPI 2004. Lecture Notes in Computer Science, vol 3241. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30218-6_53
Download citation
DOI: https://doi.org/10.1007/978-3-540-30218-6_53
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23163-9
Online ISBN: 978-3-540-30218-6
eBook Packages: Springer Book Archive