On Confident Task-Accurate Performance Estimation

  • Yang Xu
  • Bo Wang
  • Rafael Rosales
  • Ralph Hasholzner
  • Jürgen Teich
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7767)

Abstract

Task-accurate performance estimation methods are widely applied for design space exploration at the Electronic System Level (ESL). These methods estimate performance by simulating task-level models annotated with nominal execution time. In early design phases, source code, which is necessary for generating accurate annotations, is usually not available. Instead, extrapolated values or even estimated values are used for performance estimation, which makes the results unreliable and may eventually cause performance violations if used to guide critical design decisions. In this paper, we propose a confident task-accurate performance estimation methodology that uses high-level information available in early design phases and provides confident estimation to guide design space exploration with respect to performance constraints.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kempf, T., Doerper, M., Leupers, R., Ascheid, G., Meyr, H., Kogel, T., Vanthournout, B.: A Modular Simulation Framework for Spatial and Temporal Task Mapping onto Multi-Processor SoC Platforms. In: DATE, pp. 876–881 (2005)Google Scholar
  2. 2.
    Streubühr, M., Falk, J., Haubelt, C., Teich, J., Dorsch, R., Schlipf, T.: Task-Accurate Performance Modeling in SystemC for Real-Time Multi-Processor Architectures. In: DATE, pp. 480–481 (2006)Google Scholar
  3. 3.
    Streubühr, M., Gladigau, J., Haubelt, C., Teich, J.: Efficient Approximately-Timed Performance Modeling for Architectural Exploration of MPSoCs. In: Advances in Design Methods from Modeling Languages for Embedded Systems and SoC’s, vol. 63, pp. 59–72 (2010)Google Scholar
  4. 4.
    Schnerr, J., Bringmann, O., Viehl, A., Rosenstiel, W.: High-performance timing simulation of embedded software. In: DAC, pp. 290–295 (2008)Google Scholar
  5. 5.
    Teich, J.: Pareto-Front Exploration with Uncertain Objectives. In: 1st International Conference on Evolutionary Multi-Criterion Optimization, March 7-9, pp. 314–328 (2001)Google Scholar
  6. 6.
    Giusto, P., Martin, G., Harcourt, E.: Reliable Estimation of Execution Time of Embedded Software. In: DATE, pp. 580–589 (2001)Google Scholar
  7. 7.
    Bjuréus, P., Jantsch, A.: Performance Analysis with Confidence Intervals for Embedded Software Processes. In: Proceedings of the 14th International Symposium on Systems Synthesis, pp. 45–50 (2001)Google Scholar
  8. 8.
    Lattuada, M., Ferrandi, F.: Performance Estimation of Embedded Software with Confidence Levels. In: ASP-DAC, pp. 573–578 (2012)Google Scholar
  9. 9.
    Lee, E., Neuendorffer, S., Wirthlin, M.: Actor-Oriented Design of Embedded Hardware and Software Systems. Journal of Circuits Systems and Computers 12(3), 231–260 (2003)CrossRefGoogle Scholar
  10. 10.
    Lee, E.A., Neuendorffer, S.: Actor-Oriented Models for Codesign: Balancing Re-Use and Performance. In: Formal Methods and Models for System Design, pp. 33–56 (2004)Google Scholar
  11. 11.
    Falk, J., Haubelt, C., Teich, J.: Efficient Representation and Simulation of Model-Based Designs in System. In: Forum on Design Languages, pp. 129–134 (2006)Google Scholar
  12. 12.
    Li, X., Le, J., Pileggi, L.T.: Statistical performance modeling and optimization. Found. Trends Electron. Des. Autom. 1(4), 331–480 (2006)MATHCrossRefGoogle Scholar
  13. 13.
    Seber, G.: Multivariate Observations. Wiley Series (1984)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Yang Xu
    • 1
  • Bo Wang
    • 1
  • Rafael Rosales
    • 2
  • Ralph Hasholzner
    • 1
  • Jürgen Teich
    • 2
  1. 1.Intel Mobile CommunicationsMunichGermany
  2. 2.University of Erlangen-NurembergGermany

Personalised recommendations