A GPU-Based jDE Algorithm Applied to Continuous Unconstrained Optimization

  • Mateus Boiani
  • Gabriel Dominico
  • Rafael Stubs ParpinelliEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 940)


Population-based search algorithms, such as the Differential Evolution approach, evolve a pool of candidate solutions during the optimization process and are suitable for massively parallel architectures promoted by the use of GPUs. Hence, this paper proposes a GPU-based self-adaptive Differential Evolution employing the jDE mechanism to control its parameters, named cujDE. Two CUDA structures are employed to model the kernel functions in cujDE. The proposed algorithm is compared with another GPU-based self-adaptive DE (cuSaDE) in four continuous unconstrained benchmark functions. Also, the speedup between the CPU-based and the GPU-based jDE is measured. Results obtained suggest that the proposed approach is well suited to and competitive for continuous optimization.


CUDA GPU computing Optimization Evolutionary algorithms Parallel computing 


  1. 1.
    Brest, J., Greiner, S., Boskovic, B., Mernik, M., Zumer, V.: Self-adapting control parameters in differential evolution: a comparative study on numerical benchmark problems. IEEE Trans. Evol. Comput. 10(6), 646–657 (2006)CrossRefGoogle Scholar
  2. 2.
    Brest, J., Zamuda, A., Fister, I., Maučec, M.S.: Large scale global optimization using self-adaptive differential evolution algorithm. In: IEEE Congress on Evolutionary Computation, pp. 1–8, July 2010Google Scholar
  3. 3.
    Cook, S.: CUDA Programming: A Developer’s Guide to Parallel Computing with GPUs, 1st edn. Morgan Kaufmann Publishers Inc., San Francisco (2013)Google Scholar
  4. 4.
    Essaid, M., Idoumghar, L., Lepagnot, J., Brévilliers, M.: GPU parallelization strategies for metaheuristics: a survey. Int. J. Parallel Emergent Distrib. Syst., 1–26 (2018)Google Scholar
  5. 5.
    García, S., Molina, D., Lozano, M., Herrera, F.: A study on the use of non-parametric tests for analyzing the evolutionary algorithms’ behaviour: a case study on the CEC’2005 special session on real parameter optimization. J. Heuristics 15, 617–644 (2009)CrossRefGoogle Scholar
  6. 6.
    Hoberock, J., Bell, N.: Thrust: a parallel template library (2015).
  7. 7.
    Kirk, D.B., Hwu, W.-M.W.: Programming Massively Parallel Processors: A Hands-on Approach, 3rd edn. Morgan Kaufmann Publishers Inc., San Francisco (2016)Google Scholar
  8. 8.
    NVIDIA: CURAND Library. NVIDIA Corporation, Santa Clara, July 2017Google Scholar
  9. 9.
    Parpinelli, R.S., Plichoski, G.F., Da Silva, R.S., Narloch, P.H.: A review of technique for on-line control of parameters in swarm intelligence and evolutionary computation algorithms. Int. J. Bio-Inspired Comput. (IJBIC) 13(1), 1–20 (2019)CrossRefGoogle Scholar
  10. 10.
    Qin, A.K., Huang, V.L., Suganthan, P.N.: Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans. Evol. Comput. 13(2), 398–417 (2009)CrossRefGoogle Scholar
  11. 11.
    Storn, R., Price, K.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11(4), 341–359 (1997)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Tsutsui, S., Collet, P.: Massively Parallel Evolutionary Computation on GPGPUs. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  13. 13.
    Wong, T.H., Qin, A.K., Wang, S., Shi, Y.: cuSaDE: a CUDA-based parallel self-adaptive differential evolution algorithm. In: Handa, H., Ishibuchi, H., Ong, Y.S., Tan, K.C. (eds.) Proceedings of the 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems, vol. 2, pp. 375–388. Springer, Cham (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Mateus Boiani
    • 1
  • Gabriel Dominico
    • 1
  • Rafael Stubs Parpinelli
    • 1
    Email author
  1. 1.Graduate Program in Applied ComputingSanta Catarina State UniversityJoinvilleBrazil

Personalised recommendations