Towards Application Variability Handling with Component Models: 3D-FFT Use Case Study

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9523)

Abstract

To harness the computing power of supercomputers, HPC application algorithms have to be adapted to the underlying hardware. This is a costly and complex process which requires handling many algorithm variants. This paper studies the ability of the component model L\(^2\)C to express and handle the variability of HPC applications. The goal is to ease application adaptation. Analysis and experiments are done on a 3D-FFT use case. Results show that L\(^2\)C, and components in general, offer a generic and simple handling of 3D-FFT variants while obtaining performance close to well-known libraries.

Keywords

Application adaptation Component models High-performance computing 

References

  1. 1.
    Ansel, J., Chan, C., Wong, Y.L., Olszewski, M., Zhao, Q., Edelman, A., Amarasinghe, S.: PetaBricks: a language and compiler for algorithmic choice, vol. 44. ACM (2009)Google Scholar
  2. 2.
    Baude, F., Caromel, D., Dalmasso, C., Danelutto, M., Getov, V., Henrio, L., Pérez, C.: GCM: a grid extension to fractal for autonomous distributed components. Ann. Telecommun. 64(1–2), 5–24 (2009)CrossRefGoogle Scholar
  3. 3.
    Bernholdt, D.E., Allan, B.A., Armstrong, R., Bertrand, F., Chiu, K., Dahlgren, T.L., Damevski, K., Elwasif, W.R., Epperly, T.G., Govindaraju, M., et al.: A component architecture for high performance scientific computing. Int. J. High Perform. Comput. Appl. 20(2), 163–202 (2006)CrossRefGoogle Scholar
  4. 4.
    Bigot, J., Hou, Z., Pérez, C., Pichon, V.: A low level component model easing performance portability of HPC applications. Computing 96(12), 1115–1130 (2013). http://hal.inria.fr/hal-00911231 CrossRefGoogle Scholar
  5. 5.
    Bigot, J., Pérez, C.: High performance composition operators in component models. In: High Performance Computing: From Grids and Clouds to Exascale, Advances in Parallel Computing, vol. 20, pp. 182–201. IOS Press (2011). http://hal.inria.fr/hal-00692584
  6. 6.
    Boldt, J.: The Common Object Request Broker: Architecture and Specification (1995). http://www.omg.org/cgi-bin/doc?formal/97-02-25
  7. 7.
    Bonelli, A., Franchetti, F., Lorenz, J., Püschel, M., Überhuber, C.W.: Automatic performance optimization of the discrete fourier transform on distributed memory computers. In: Guo, M., Yang, L.T., Di Martino, B., Zima, H.P., Dongarra, J., Tang, F. (eds.) ISPA 2006. LNCS, vol. 4330, pp. 818–832. Springer, Heidelberg (2006) CrossRefGoogle Scholar
  8. 8.
    Bozga, M., Jaber, M., Sifakis, J.: Source-to-source architecture transformation for performance optimization in BIP. IEEE Trans. Indus. Inform. 6(4), 708–718 (2010)CrossRefGoogle Scholar
  9. 9.
    Desprez, F., Fox, G., Jeannot, E., Keahey, K., Kozuch, M., Margery, D., Neyron, P., Nussbaum, L., Pérez, C., Richard, O., Smith, W., Von Laszewski, G., Vöckler, J.: Supporting experimental computer science. In: Rapport de recherche RR-8035, INRIA (2012). http://hal.inria.fr/hal-00722605
  10. 10.
    Frigo, M., Johnson, S.: The design and implementation of FFTW3. Proc. IEEE 93(2), 216–231 (2005)CrossRefGoogle Scholar
  11. 11.
    McIlroy, M.D.: Mass-produced software components. In: Proceedings NATO Conference on Software Engineering, Garmisch, Germany (1968)Google Scholar
  12. 12.
    Pekurovsky, D.: P3DFFT: a framework for parallel computations of fourier transforms in three dimensions. SIAM J. Sci. Comput. 34(4), C411–C437 (2012). http://dblp.uni-trier.de/db/journals/siamsc/siamsc34.html CrossRefMathSciNetGoogle Scholar
  13. 13.
    Squyres, J.M., Lumsdaine, A.: The component architecture of open MPI enabling third-party collective algorithms. In: Getov, V., Kielmann, T. (eds.) Component Models and Systems for Grid Applications, pp. 167–185. Springer, Heidelberg (2005) CrossRefGoogle Scholar
  14. 14.
    Szyperski, C.: Component Software: Beyond Object-Oriented Programming, 2nd edn. Addison-Wesley Longman Publishing Co. Inc., Boston (2002) Google Scholar
  15. 15.
    Wang, N., Parameswaran, K., Kircher, M., Schmidt, D.C.: Applying reflective middleware techniques to optimize a QoS-enabled CORBA component model implementation. In: COMPSAC, pp. 492–499. IEEE Computer Society (2000). http://dblp.uni-trier.de/db/conf/compsac/compsac2000.html

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.École Normale Supérieure de LyonLyonFrance
  2. 2.Inria Avalon Research Team, LIPLyonFrance

Personalised recommendations