Advertisement

likwid-bench: An Extensible Microbenchmarking Platform for x86 Multicore Compute Nodes

  • Jan Treibig
  • Georg Hager
  • Gerhard Wellein
Conference paper

Abstract

Microbenchmarking is an essential tool for characterizing modern compute nodes. Apart from determining raw performance capabilities microbenchmarking can be used to aquire input parameters for performance models or mimic the behavior of more complex applications. Many existing microbenchmarks are not extensible and implemented in C or Fortran. One problem with microbenchmarks in a high level language is that many performance issues are only apparent on the instruction level. The code quality of the compiler is an additional source of variation. likwid-bench is a framework enabling rapid prototyping of loop-based, threaded assembly kernels. It eases the process of implementing assembly kernels by providing a portable assembly language independent from any concrete assembler program. likwid-bench already includes many standard microbenchmarking testcases and can be used out of the box as a microbenchmarking tool.

Keywords

Assembly Language Data Placement Instruction Code Shared Cache Bandwidth Bottleneck 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

We are indebted to Intel Germany for providing test systems and early access hardware for benchmarking. This work was supported by the Competence Network for Scientific and Technical High Performance Computing in Bavaria (KONWIHR) under the project “OMI4papps.”

References

  1. 1.
    Araiza, R., Pham, T., Aguilera, M.G.: Towards a cross-platform microbenchmark suite for evaluating hardware performance counter data. In: Richard Tapia Celebration of Diversity in Computing Conference, Albuquerque. New Mexico (2005)Google Scholar
  2. 2.
    Homepage of LIKWID tool suite. http://code.google.com/p/likwid/
  3. 3.
    Kredel, H., Merz, M.: The design of the IPACS distributed software architecture. In: 2nd Workshop on Distributed Objects Research, Experiences Applications (DOREA 2), Las Vegas (2004)Google Scholar
  4. 4.
    LLCbench – Low Level Architectural Characterization Benchmark Suite Homepage. http://icl.cs.utk.edu/projects/llcbench/
  5. 5.
    LMbench – Tools for Performance Analysis Homepage. http://lmbench.sourceforge.net
  6. 6.
    McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. In: IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter. New York (1995)Google Scholar
  7. 7.
    Treibig, J., Hager, G.: Introducing a performance model for bandwidth-limited loop kernels. In: Proceedings of the Workshop Memory issues on Multi- and Manycore Platforms at PPAM 2009, Wroclaw (2009)Google Scholar
  8. 8.
    Treibig, J., Hager, G., Wellein, G.: LIKWID: a lightweight performance-oriented tool suite for x86 multicore environments. In: Proceedings of PSTI2010, the First International Workshop on Parallel Software Tools and Tool Infrastructures, San Diego (2010)Google Scholar
  9. 9.
    Treibig, J., Hager, G., Wellein, G.: LIKWID performance tools. In: Bischof, C., et al. (eds.) Competence in High Performance Computing 2010, pp. 165–175. Springer, ISBN 978-3-642-24025-6 (2012)Google Scholar
  10. 10.
    Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52, 65–76 (2009). New YorkGoogle Scholar
  11. 11.
    Yotov, K., Pingali, K., Stodghill, P.: X-ray: a tool for automatic measurement of hardware parameters. In: Second International Conference on the Quantitative Evaluation of Systems, Torino. IEEE Computer Society, Los Alamitos (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Erlangen Regional Computing Center (RRZE)Friedrich-Alexander Universität Erlangen-NürnbergErlangenGermany

Personalised recommendations