Scalability of GPA-ES Algorithm

  • Tomas BrandejskyEmail author
  • Roman Divis
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 837)


This contribution is dedicated to analysis of GPA-ES scalability both from analytical and experimental viewpoint. The paper tries to identify limits of the algorithm, sources of possible limitations and practical ways of its application. The paper is focused to standard implementation of GPA-ES algorithm and tests were provided on task of symbolical regression of Lorenz attractor system. After introduction onto the problem, Amdahl’s law is discussed in Sect. 2, characterization of GPA-ES algorithm in Sect. 3, analysis if its computational complexity in Sect. 4, experiment results analysis to determine computing time dependency on number of threads both HW and SW in Sect. 5 and analysis of influence of population size in Sect. 6. Presented results underlines that except one anomaly all experiments concludes applicability of Amdahl’s law onto GPA-ES algorithm even if it is implemented on multi-core and many-core systems, which are out of original scope of this law.


Genetic programming algorithm Efficiency Scalability Parallel algorithm Amdahl’s law 



Computational resources were provided by the CESNET LM2015042 and the CERIT Scientific Cloud LM2015085, provided under the programme “Projects of Large Research, Development, and Innovations Infrastructures”.

Computational resources were supplied by the Ministry of Education, Youth and Sports of the Czech Republic under the Projects CESNET (Project No. LM2015042) and CERIT-Scientific Cloud (Project No. LM2015085) provided within the program Projects of Large Research, Development and Innovations Infrastructures.


  1. 1.
    Thierens, D.: Scalability problems of simple genetic algorithms. Evol. Comput. 7(4), 331–352 (1999)CrossRefGoogle Scholar
  2. 2.
    Liu, Y.Y., Wang, S.: A scalable parallel genetic algorithm for the generalized assignment problem. 46, 98–119 (2015). Article no. 2184Google Scholar
  3. 3.
    Folino, G., Pizzuti, C., Spezzano, G.: A scalable cellular implementation of parallel genetic programming. IEEE Trans. Evol. Comput. 7, 37–53 (2003)CrossRefGoogle Scholar
  4. 4.
    Virgolin, M., Alderliesten, T., Witteveen, C., Bosman, A.N.P.: Scalable genetic programming by gene-pool optimal mixing and input-space entropy-based building-block learning, vol. 1 (2017).
  5. 5.
    Christensen, S.: Towards scalable genetic programming. Ph.D. Study, Ottawa-Carleton Institute for Computer Science (2006)Google Scholar
  6. 6.
    Amdahl, G.M.: Validity of the single-processor approach to achieving large scale computing capabilities. In: AFIPS Conference Proceedings, pp. 483–485 (1967)Google Scholar
  7. 7.
    Hill, M.D., Marty, M.R.: Amdahl’s Law in the Multicore Era. Accessed 1 June 2016
  8. 8.
    Brandejsky, T.: Multi-layered evolutionary system suitable to symbolic model regression. In: Proceedings of the NAUN/IEEE.AM International Conferences, 2nd International Conference on Applied Informatics and Computing Theory, Praha, 26–28 September 2011, pp. 222–225. WSEAS Press, Athens (2011). ISBN 978-1-61804-038-1Google Scholar
  9. 9.
    Brandejsky, T.: Genetic programming algorithm with parameters preoptimization - problem of structure quality measuring. In: Osmera, P. (ed.) Mendel 2005. 11th International Conference on Soft Computing, Brno, 15–17 June 2005, pp. 138–144. Brno University of Technology, Brno (2005). ISBN 80-214-2961-5Google Scholar
  10. 10.
    Chandra, R., Menon, R., Dagu, L., Kohr, D., Maydan, D., McDonald, J.: Parallel Programming in OpenMP. Morgan Kaufmann (2000). ISBN: 9781558606715Google Scholar
  11. 11.
    Brandejsky, T., Zelinka, I.: Specific behaviour of GPA-ES evolutionary system observed in deterministic chaos regression. In: Zelinka, I. et al. (eds.) Nostradamus: Modern Methods of Prediction, Modeling and Analysis of Nonlinear Systems. Advances in Intelligent Systems and Computing, Nostradamus, Ostrava, 05–07 September 2012, pp. 73–81. Springer, Heidelberg (2013). ISSN 2194-5357, ISBN 978-3-642-33226-5Google Scholar
  12. 12.
    Brandejsky, T.: Small populations in GPA-ES algorithm In: MENDEL 2013. Brno University of Technology, Brno, Faculty of Mechanical Engineering, pp. 31–36 (2013). ISSN 1803-3814, ISBN 978-80-214-4755-4Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of PardubicePardubiceCzech Republic

Personalised recommendations