Embedded Systems HW/SW Partitioning Based on Lagrangian Relaxation Method

  • Adil Iguider
  • Mouhcine Chami
  • Oussama Elissati
  • Abdeslam En-Nouaary
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 37)


Embedded systems (ES) are nowadays, in the heart of every complex electronic device. An ES is a system that combines both hardware blocks and software blocks in a single chip. The necessity to decrease the cost and the development time of the design flow of the ES and to keep the overall performance of the system require the development of new design approaches for such systems. The compound design (co-design) is a very interesting approach used to fulfill the latter requirements. The partitioning of blocks between hardware and software is one of the most important steps in this process of co-design. In this paper, we present a novel method (heuristic) based on optimal path optimization technique (lagrangian relaxation method) to deal with the partitioning problem. The solution aims to optimize the hardware area (cost) of the ES while respecting a given constraint time of execution. To validate the effectiveness of our approach, we give a comparison with the results obtained with the Genetic Algorithm (GA).


Embedded systems HW/SW partitioning Lagrangian relaxation Heuristic algorithms Co-design 


  1. 1.
    Schaumont, P.: A practical introduction to hardware/software codesign (2012)Google Scholar
  2. 2.
    Clausen, J.: Branch and bound algorithms-principles and examples. Department of Computer Science, University of Copenhagen, pp. 1–30 (1999)Google Scholar
  3. 3.
    Mann, Z.A., Orban, A., Arato, P.: Finding optimal hardware/software partitions. Formal Meth. Syst. Des. 31(3), 241–263 (2007)CrossRefzbMATHGoogle Scholar
  4. 4.
    Niemann, R., Marwedel, P.: Hardware/software partitioning using integer programming. In: Proceedings of the 1996 European Conference on Design and Test, p. 473 (1996)Google Scholar
  5. 5.
    Knudsen, P.V., Madsen, J.: Pace: a dynamic programming algorithm for hardware/software partitioning. In: Proceedings of the 4th International Workshop on Hardware/Software Co-design, p. 85 (1996)Google Scholar
  6. 6.
    Eles, P., Peng, Z., Kuchcinski, K., Doboli, A.: Hardware/software partitioning with iterative improvement heuristics. In: Proceedings of the 9th International Symposium on System Synthesis, p. 71 (1996) Google Scholar
  7. 7.
    Banerjee, S., Dutt, N.: Very fast simulated annealing for hw-sw partitioning. Technical report, CECS-TR-04-17 (2004)Google Scholar
  8. 8.
    Zhao, X., Zhang, H., Jiang, Y., Song, S., Jiao, X., Gu, M.: An effective heuristic-based approach for partitioning. J. Appl. Math. 2013, 1–8 (2013)Google Scholar
  9. 9.
    Saha, D., Mitra, R., Basu, A.: Hardware software partitioning using genetic algorithm. In: Proceedings of the Tenth International Conference on VLSI Design, pp. 155–160 (1997)Google Scholar
  10. 10.
    Purnaprajna, M., Reformat, M., Pedrycz, W.: Genetic algorithms for hardware-software partitioning and optimal resource allocation. J. Syst. Architect. 53(7), 339–354 (2007)CrossRefGoogle Scholar
  11. 11.
    Arato, P., Juhasz, S., Mann, Z.A., Orban, A., Papp, D.: Hardware-software partitioning in embedded system design. In: Proceedings of the 2003 IEEE International Symposium on Intelligent Signal Processing, pp. 197–202 (2003)Google Scholar
  12. 12.
    Chehida, K.B., Auguin, M.: Hw/sw partitioning approach for reconfigurable system design. In: Proceedings of the 2002 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, pp. 247–251 (2002)Google Scholar
  13. 13.
    Knerr, B., Holzer, M., Rupp, M.: Novel genome coding of genetic algorithms for the system partitioning problem. In: Proceedings of the 2007 International Symposium on Industrial Embedded Systems, pp. 134–141 (2007)Google Scholar
  14. 14.
    Li, S.G., Feng, F.J., Hu, H.J., Wang, C., Qi, D.: Hardware/software partitioning algorithm based on genetic algorithm. J. Comput. 9(6), 1309–1315 (2014)Google Scholar
  15. 15.
    Mudry, P.A., Zuerey, G., Tempesti, G.: A hybrid genetic algorithm for constrained hardware-software partitioning. In: Proceedings of the 2006 IEEE Design and Diagnostics of Electronic Circuits and systems, pp. 1–6 (2006)Google Scholar
  16. 16.
    Li, G., Feng, J., Wang, C., Wang, J.: Hardware/software partitioning algorithm based on the combination of genetic algorithm and tabu search. Eng. Rev. 34(2), 151–160 (2014)MathSciNetGoogle Scholar
  17. 17.
    Lin, G., Zhu, W., Ali, M.M.: A tabu search-based memetic algorithm for hardware/software partitioning. Math. Prob. Eng. 2014, 1–15 (2014)Google Scholar
  18. 18.
    Bhuvaneswari, M., Jagadeeswari, M.: Hardware/software partitioning for embedded systems. In: Application of Evolutionary Algorithms for Multi-objective Optimization in VLSI and Embedded Systems, pp. 21–36 (2015)Google Scholar
  19. 19.
    Lin, G.: An iterative greedy algorithm for hardware/software partitioning. In: Proceedings of 2013 Ninth International Conference on Natural Computation (ICNC), pp. 777–781 (2013)Google Scholar
  20. 20.
    Sim, J.E., Mitra, T., Wong, W.F.: Defining neighborhood relations for fast spatial-temporal partitioning of applications on reconfigurable architectures. In: Proceedings of 2008 International Conference on ICECE Technology, pp. 121–128 (2008)Google Scholar
  21. 21.
    Rini, D.P., Shamsuddin, S.M., Yuhaniz, S.S.: Particle swarm optimization: technique, system and challenges. Int. J. Comput. Appl. 14(1), 19–26 (2011)Google Scholar
  22. 22.
    Farmahini-Farahani, A., Kamal, M., Fakhraie, S.M., Safari, S.: HW/SW partitioning using discrete particle swarm. In: Proceedings of the 17th ACM Great Lakes symposium on VLSI, pp. 359–364 (2007)Google Scholar
  23. 23.
    Wu, J., Srikanthan, T., Lei, T.: Efficient heuristic algorithms for path-based hardware/software partitioning. Math. Comput. Model. 51(7), 974–984 (2010)CrossRefzbMATHGoogle Scholar
  24. 24.
    Fisher, M.L.: The lagrangian relaxation method for solving integer programming problems. Manage. Sci. 27(1), 1–18 (1981)MathSciNetCrossRefzbMATHGoogle Scholar
  25. 25.
    Czibula, O.G., Gu, H., Zinder, Y.: Lagrangian relaxation versus genetic algorithm based matheuristic for a large partitioning problem. Theor. Comput. Sci. (2017)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Institut National des Postes et Télécomunications, Lab. STRSRabatMorocco

Personalised recommendations