Abstract
Parallel performance diagnosis can be improved with the use of performance knowledge about parallel computation models. The Hercule diagnosis system applies model-based methods to automate performance diagnosis processes and explain performance problems from high-level computation semantics. However, Hercule is limited by a single experiment view. Here we introduce the concept of relative performance diagnosis and show how it can be integrated in a model-based diagnosis framework. The paper demonstrates the effectiveness of Hercule’s approach to relative diagnosis of the well-known Sweep3D application based on a Wavefront model. Relative diagnoses of Sweep3D performance anomalies in strong and weak scaling cases are given.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
The ASCI sweep3d benchmark, http://www.llnl.gov/asci_benchmarks/asci/limited/sweep3d/
CLIPS: A tool for building expert systems, http://www.ghg.net/clips/CLIPS.html
TAU tuning and analysis utilities, http://www.cs.uoregon.edu/research/paracomp/tau/tautools/
Abramson, D., Foster, I., Michalakes, J., Sosic, R.: Relative debugging: a new paradigm for debugging scientific applications. The Communications of the Association for Computing Machinery 39(11), 67–77 (1996)
Karavanic, K., Miller, B.: A framework for multi-execution performance tuning. In: On-line Monitoring Systems and Computer Tool Interoperability, pp. 61–89. Nova Science Publishers, Inc. (2004)
Li, L., Malony, A.: Knowledge engineering for automatic parallel performance diagnosis. Concurrency and Computation: Practice and Experience (accepted)
Song, F., Wolf, F., Bhatia, N., Dongarra, J., Moore, S.: An algebra for cross-experiment performance analysis. In: ICPP 2004 (2004)
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
Li, L., Malony, A.D., Huck, K. (2006). Model-Based Relative Performance Diagnosis of Wavefront Parallel Computations. In: Gerndt, M., Kranzlmüller, D. (eds) High Performance Computing and Communications. HPCC 2006. Lecture Notes in Computer Science, vol 4208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11847366_21
Download citation
DOI: https://doi.org/10.1007/11847366_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-39368-9
Online ISBN: 978-3-540-39372-6
eBook Packages: Computer ScienceComputer Science (R0)