Dynamic Instrumentation and Performance Prediction of Application Execution
This paper presents a new technique that enhances the process and the methodology used in a performance prediction analysis. An automatic dynamic instrumentation methodology is added to Warwick’s Performance Analysis and Characterization Environment PACE . The automation process has eliminated the need to manually obtain application information and data. The Dynamic instrumentation has given PACE the ability to extract and utilize data that were hidden and unobtainable prior to execution. We give two examples to illustrate our methodology. While it was impossible to perform the analysis using the original method due to lack of essential information, the new technique successfully enabled PACE to conduct the prediction analysis in a dynamic environment. The results show that with the automated dynamic instrumentation, the performance prediction analysis of dynamic application execution is possible and the results obtained are reliable. We believe that the technique implemented here could eventually be used in other performance prediction tool-sets, and therefore enhance the ways in which the performance of systems and applications is analysed and predicted.
KeywordsDynamic instrumentation performance optimization performance analysis modelling PACE
Unable to display preview. Download preview PDF.
- 1.Nudd, G.R., Papaefstathiou, E., et.al., A layered Approach to the Characterization of Parallel Systems for Performance Prediction, in Proc. of Performance Evaluation of Parallel Systems, Warwick (1993) 26–34.Google Scholar
- 2.Foster, I., Kesselman, C.: The Grid, Morgan Kaufmann, (1998).Google Scholar
- 4.Miller, B.P., Callaghan, M.D., Cargille, J.M., Hollingsworth, J.K., Irvin, R.B., Karavanic, K.L., Kunchithapadam, K., Newhall, T.: The Paradyn Parallel Performance Measurement Tools, IEEE Computer 2811 (1995) 37–46.Google Scholar
- 5.DeRose, L., Zhang, Y., Reed, D.A.: SvPablo: A Multi-Language Performance Analysis System, in Proc. 10th Int. Conf. on Computer Performance, Spain (1998) 352–355.Google Scholar
- 6.Papaefstathiou, E., Kerbyson, D.J., Nudd, G.R., Atherton, T.J.: An overview of the CHIP3S performance prediction toolset for parallel systems, in: 8th ISCA Int. Conf. on Parallel and Distributed Computing Systems, Florida (1995) 527–533.Google Scholar
- 7.Karen L. Karavanic and Barton P. Miller, Improving Online Performance Diagnosis by the Use of Historical Performance Data, SC’99, Portland, Oregon (USA) November 1999.Google Scholar
- 8.Jeffrey K. Hollingsworth, Barton P. Miller, Marcelo J.R. Gonçalves, Oscar Naim, Zhichen Xu and Ling Zheng, MDL: A Language and Compiler for Dynamic Program Instrumentation, International Conference on Parallel Architectures and Compilation Techniques San Francisco, California, November 1997.Google Scholar
- 9.Smith, C.U.: Performance Engineering of Software Systems, Addison Wesley (1990).Google Scholar
- 11.Papaefstathiou, E., Kerbyson, D.J., Nudd, G.R., Atherton, T.J.: An overview of the CHIP3S performance prediction toolset for parallel systems, in: 8th ISCA Int. Conf. on Parallel and Distributed Computing Systems, Florida (1995) 527–533.Google Scholar
- 12.Wilson, R., French, R., Wilson, C., et.al.: An Overview of the SUIF Compiler System, Technical Report, Computer Systems Lab Stanford University (1993).Google Scholar
- 13.Kerbyson, D.J., Papaefstathiou, E., Harper, J.S., Perry, S.C., Nudd, G.R.: Is Predictive Tracing Too Late for HPC Users?, in High Performance Computing, Kluwer Academic, March 1999, 57–67.Google Scholar