Search Strategies for Automatic Performance Analysis Tools

  • Michael Gerndt
  • Edmond Kereku
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4641)


Periscope is a distributed automatic online performance analysis system for large scale parallel systems. It consists of a set of analysis agents distributed on the parallel machine. This article presents the architecture of the node agent and its central part, the search strategy driving the online search for performance properties. The focus is on strategies used to analyze memory access-related performance properties in OpenMP programs.


  1. 1.
    Fahringer, T., Gerndt, M., Riley, G., Trãff, J.: aff. Knowledge specification for automatic performance analysis. APART Technical Report (2001),
  2. 2.
    Fahringer, T., Gerndt, M., Riley, G., Träff, J.L.: Specification of performance problems in MPI-programs with ASL. In: International Conference on Parallel Processing (ICPP 2000), pp. 51–58 (2000)Google Scholar
  3. 3.
    Fahringer, T., Seragiotto, C.: Aksum: A performance analysis tool for parallel and distributed applications. In: Getov, V., Gerndt, M., Hoisie, A., Malony, A., Miller, B. (eds.) Performance Analysis and Grid Computing, pp. 189–210. Kluwer Academic Publisher, Dordrecht (2003)Google Scholar
  4. 4.
    Gerndt, M., Fürlinger, K., Kereku, E.: Advanced techniques for performance analysis. In: Joubert, G.R., Nagel, W.E., Peters, F.J., Plata, O., Tirado, P., Zapata, E. (eds.) Parallel Computing: Current&Future Issues of High-End Computing (Proceedings of the International Conference ParCo 2005), NIC Series, vol. 33, pp. 15–26a (2006)Google Scholar
  5. 5.
    Gerndt, M., Kereku, E.: Selective instrumentation and monitoring. In: International Workshop on Compilers for Parallel Computers (CPC 2004) (2004)Google Scholar
  6. 6.
    Kereku, E., Gerndt, M.: The EP-Cache automatic monitoring system. In: International Conference on Parallel and Distributed Systems (PDCS 2005) (2005)Google Scholar
  7. 7.
    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 tool. IEEE Computer 28(11), 37–46 (1995)Google Scholar
  8. 8.
    Roth, P.C., Arnold, D.C., Miller, B.P.: MRNet: A software-based multicast/reduction network for scalable tools. In: SC 2003, Phoenix (November 2003)Google Scholar
  9. 9.
    Seragiotto, C., Truong, H., Fahringer, T., Mohr, B., Gerndt, M., Li, T.: Standardized Intermediate Representation for Fortran, Java, C and C++ programs. APART Working Group Technical Report, Institute for Software Science, University of Vienna (Octorber 2004)Google Scholar
  10. 10.
    Wolf, F., Mohr, B.: Automatic performance analysis of hybrid MPI/OpenMP applications. In: 11th Euromicro Conference on Parallel, Distributed and Network-Based Processing, pp. 13 –22 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Michael Gerndt
    • 1
  • Edmond Kereku
    • 1
  1. 1.Technische Universität München, Fakultät für Informatik I10, Boltzmannstr.3, 85748 GarchingGermany

Personalised recommendations