A hierarchical approach to workload characterization for parallel systems
Performance evaluation studies are to be an integral part of the design and tuning of parallel applications. We propose a hierarchical approach to the systematic characterization of the workload of a parallel system, to be kept as modular and flexible as possible. The methodology is based on three different, but related, layers: the application, the algorithm, and the routine layer. For each of these layers different characteristics representing functional, sequential, parallel, and quantitative descriptions have been identified. These characteristics are specified in a system independent way to clearly separate between the workload description and the architecture description. Taking also architectural and mapping features into consideration, the hierarchical workload characterization can be applied to any type of performance studies.
KeywordsParallel System Hierarchical Approach Behavior Graph Potential Parallelism Workload Characterization
Unable to display preview. Download preview PDF.
- [CHS88]M. Calzarossa, G. Haring, and G. Serazzi. Workload Modelling for Computer Networks. In U. Kastens and F. J. Rammig, editors, Architektur und Betrieb von Rechnersystemen, pages 324–339. Springer Verlag, 1988.Google Scholar
- [CMM+94]M. Calzarossa, L. Massari, A. Merlo, D. Tessera, and A. Malagoli. Performance Debugging of Parallel Programs. In Proc. AICA Annual Conference, pages 541–556, Palermo, Italy, 1994.Google Scholar
- [Fer90]A. Ferscha. The PRM-Net Model — An Integrated Performance Model for Parallel Systems. Technical report, Austrian Center for Parallel Computation, University of Vienna, 1990.Google Scholar
- [Har86]G. Haring. Fundamental Principles of Hierarchical Workload Description. In G. Serazzi, editor, Workload Characterization of Computer Systems and Computer Networks, pages 101–110. North Holland, 1986.Google Scholar
- [Her92]U. Herzog. Performance Evaluation as an Integral Part of System Design. In M. Becker et al., editors, Proceedings of the Transputers'92 Conference. IOS Press, 1992.Google Scholar
- [MT93]A. Mitschele-Thiel. Automatic Configuration and Optimization of Parallel Transputer Applications. In Proceedings of the World Transputer Congress, Aachen, Germany, 1993. IOS Press.Google Scholar
- [RS94]E. Rosti and G. Serazzi. Workload Characterization for Performance Engineering of Parallel Applications. In Proceedings of the Euromicro Workshop on Parallel and Distributed Processing, pages 457–462. IEEE Computer Society Press, 1994.Google Scholar
- [RVH95]S. V. Raghavan, D. Vasukiammaiyar, and G. Haring. Hierarchical approach to building generative network load models. Computer Networks and ISDN, 1995. (to appear).Google Scholar
- [WH94]H. Wabnig and G. Haring. PAPS — The Parallel Program Performance Prediction Toolset. In Proc. of the 7 th Int. Conf. on Modelling Techniques and Tools for Computer Performance Evaluation, pages 284–304. Springer-Verlag, 1994.Google Scholar
- [WKH93]H. Wabnig, G. Kotsis, and G. Haring. Performance Prediction of Parallel Programs. In G. Haring and G. Kotsis, editors, Proc. of the 7th GI/ITG Conference on Measurement, Modelling and Performance Evaluation of Computer Systems, pages 64–76. Springer Verlag, 1993.Google Scholar