Automatic Performance Analysis of Message Passing Applications Using the KappaPI 2 Tool

  • Josep Jorba
  • Tomas Margalef
  • Emilio Luque
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3666)


Message passing libraries offer the programmer a set of primitives that are not available in sequential programming. Developing applications using these primitives as well as application performance tuning are complex tasks for non-expert users. Therefore, automatic performance analysis tools that help the user with performance analysis and tuning phases are necessary. KappaPI 2 is a performance analysis tool designed openly to incorporate parallel performance knowledge about performance bottlenecks easily. The tool is able to detect and analyze performance bottlenecks and then make suggestions to the user to improve the application behavior.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Nagel, W.E., Arnold, A., Weber, M., Hoppe, H.C., Solchenbach, K.: VAMPIR: Visualization and Analysis of MPI Resources. In: Supercomputer 63, January 1996, vol. XII(1) (1996)Google Scholar
  2. 2.
    Cortes, T., Pillet, V., Labarta, J., Girona, S.: Paraver: A tool to visualize and analyze parallel code. In: WoTUG-18, Manchester, April 1995, pp. 17–31 (1995)Google Scholar
  3. 3.
    De Rose, L., Zhang, Y., Reed, D.A.: SvPablo: A multi-language performance analysis system. In: Puigjaner, R., Savino, N.N., Serra, B. (eds.) TOOLS 1998. LNCS, vol. 1469, p. 352. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  4. 4.
    Wolf, F., Mohr, B., Dongarra, J., Moore, S.: Efficient Pattern Search in Large Traces Through Successive Refinement. In: Danelutto, M., Vanneschi, M., Laforenza, D. (eds.) Euro-Par 2004. LNCS, vol. 3149, pp. 47–54. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  5. 5.
    Truong, H.L., Fahringer, T., Madsen, G., Malony, A.D., Moritsch, H., Shende, S.: On using SCALEA for Performance Analysis of Distributed and Parall el Programs. In: Supercomputing 2001 Conference (SC 2001), Denver, Colorado, USA, November 10-16 (2001)Google Scholar
  6. 6.
    Espinosa, A., Margalef, T., Luque, E.: Automatic Performance Evaluation of Parallel Programs. In: IEEE Proceedings of the 6th Euromicro Workshop on Parallel and Distributed Processing (January 1998)Google Scholar
  7. 7.
    Maillet, E.: TAPEPVM an efficient performance monitor for PVM applications - user guide. Technical report, LMCIMAG,University of Grenoble (1995)Google Scholar
  8. 8.
    Fahringer., T., Gerndt, M., Riley, G., Larsson, J.: Specification of Performance bottlenecks in MPI Programs with ASL. In: Proceedings of ICPP, pp. 51–58 (2000)Google Scholar
  9. 9.
    Espinosa, A., Margalef, T., Luque, E.: Automatic Performance Analysis of PVM applications. In: Dongarra, J., Kacsuk, P., Podhorszki, N. (eds.) PVM/MPI 2000. LNCS, vol. 1908, pp. 47–55. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  10. 10.
    Wolf, F., Mohr, B.: Automatic Performance Analysis of MPI Applications Based on Event Traces. In: Bode, A., Ludwig, T., Karl, W.C., Wismüller, R. (eds.) Euro-Par 2000. LNCS, vol. 1900, pp. 123–132. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  11. 11.
    Ivars, V.J.: Monitor de Aplicaciones MPICH Basado en Dyninst (in spanish), Master Thesis, Universidad Autónoma de Barcelona (2004)Google Scholar
  12. 12.
    Hollingsworth, J.K., Buck, B.: DyninstAPI Programmer’s Guide. Release 3.0. University of Maryland, (January 2002)Google Scholar
  13. 13.
    Gerndt, M., Mohr, B., Träff, J.L.: Evaluating OpenMP Performance Analysis Tools with the APART Test Suite. In: Danelutto, M., Vanneschi, M., Laforenza, D. (eds.) Euro-Par 2004. LNCS, vol. 3149, pp. 155–162. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  14. 14.
    Jorba, J., Margalef, T., Luque, E., Andre, J., Viegas, D.: Application of Parallel Computing to the Simulation of Forest Fire Propagation. In: Proceedings of International Conference in Forest Fire Propagation, Portugal, November 1998, vol. 1, pp. 891–900 (1998)Google Scholar
  15. 15.
    Seragiotto, C., Geisller, M., et al.: On Using Aksum for Semi-Automatically Searching of Performance Problems in Parallel and Distributed Programs. In: Procs. Of 11th Euromicro Conference on Parallel Distributed and Network based Processing, PDP (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Josep Jorba
    • 1
  • Tomas Margalef
    • 1
  • Emilio Luque
    • 1
  1. 1.Computer Architecture & Operating Systems DepartementUniversidad Autónoma de BarcelonaBellaterraSpain

Personalised recommendations