Transforming Applications from the Control Flow to the Dataflow Paradigm

  • Veljko Milutinovic
  • Jakob Salom
  • Dragan Veljovic
  • Nenad Korolija
  • Dejan Markovic
  • Luka Petrovic
Part of the Computer Communications and Networks book series (CCN)


This chapter analyzes potentials of accelerating applications by transforming them from control flow to dataflow representation and mapping them directly to the hardware based on the FPGA. Firstly, potentials for improvements will be analyzed. Both reduction in execution time and power consumption will be analyzed. Transforming control flow to dataflow applications will be analyzed on a Huxley muscle model implemented using the dataflow approach.



This research was supported by School of Electrical Engineering, Ministry of Education, Science, and Technological Development of the Republic of Serbia [TR32047] and Maxeler Technologies, Belgrade, Serbia.


  1. 1.
    A. Kos, S. Tomažič, J. Salom, N. Trifunovic, M. Valero, and V. Milutinovic, “New Benchmarking Methodology and Programming Model for Big Data Processing,” International Journal of Distributed Sensor Networks, vol. 2015, Article ID 271752, pp. 1–7.Google Scholar
  2. 2.
    M. Flynn, O. Mencer, V., Milutinovic, G., Rakocevic, P., Stenstrom, M., Valero, and R., Trobec, “Moving from PetaFlops to PetaData,” Communications of the ACM, May 2013, pp. 39–43.Google Scholar
  3. 3.
    N. Trifunovic, V. Milutinovic, J. Salom, and A. Kos, “Paradigm Shift in Big Data SuperComputing: DataFlow vs. ControlFlow,” Journal of Big Data, 2015.Google Scholar
  4. 4.
    Blagojevic, et al, “A Systematic Approach to Generation of New Ideas for PhD Research in Computing,” Advances in Computers, Vol. 102, 2015.Google Scholar
  5. 5.
    A. Hurson and V. Milutinovic, “Special Issue on DataFlow SuperComputing,” Advances in Computers, Vol. 96, 2015.Google Scholar
  6. 6.
    V. Milutinovic, J. Salom, N. Trifunovic, and R. Giorgi, “Guide to DataFlow Supercomputing,” Springer International Publishing, 2015, pp. 1–129.Google Scholar
  7. 7.
    V. Milutinovic and A. Hurson, “Dataflow Processing,” Academic Press, 1st edition, 2015, pp. 1–266.Google Scholar
  8. 8.
    R. P. Feynman, “Lectures on Computation,” The ACM Digital Library, 1998.zbMATHGoogle Scholar
  9. 9.
    T. Nowatzki, V. Gangadhar, and K. Sankaralingam, “Exploring the potential of heterogeneous von neumann/dataflow execution models,” Proceedings of the 42nd Annual International Symposium on Computer Architecture, June 13, 2015, ACM, pp. 298–310.Google Scholar
  10. 10.
    S. Stojanovic, D. Bojic, and M. Bojovic, “An Overview of Selected Heterogeneous and Reconfigurable Architectures,” Advances in Computers, Vol. 96, Burlington: Academic Press, 2015, pp. 1–45.Google Scholar
  11. 11.
    N. Korolija, T. Djukic, V. Milutinovic, and N. Filipovic, “Accelerating Lattice-Boltzman Method Using the Maxeler DataFlow Approach,” Transactions on Internet Research, Vol. 9, No. 2, July 2013, pp. 5–10.Google Scholar
  12. 12.
    S. Stojanovic, D. Bojic, and V. Milutinovic, “Solving Gross Pitaevskii Equation Using Dataflow Paradigm,” Transactions on Internet Research, Vol. 9, No. 2, July 2013.Google Scholar
  13. 13.
    A. Kos, V. Rankovic, and S. Tomazic, “Sorting networks on Maxeler dataflow supercomputing systems,” Advances in computers, Vol. 96. Amsterdam, Elsevier: Academic Press, cop, 2015, pp. 139–186.Google Scholar
  14. 14.
    V. Rankovic, A. Kos, and V. Milutinovic, “Bitonic Merge Sort Implementation on the Maxeler Dataflow Supercomputing System,” Transactions on Internet Research, Vol. 9, No. 2, July 2013, pp. 34–42.Google Scholar
  15. 15.
    J. Gustafson, “Reevaluating Amdahl’s law,” Communications of the ACM 31.5 (1988): 532–533.CrossRefGoogle Scholar
  16. 16.
    O. Pell, J. Bower, R. Dimond, O. Mencer, and M. J. Flynn “Finite Difference Wave Propagation Modeling on Special Purpose Dataflow Machines,” IEEE Transactions on Parallel and Distributed Systems, 2012, doi: 10.1109/TPDS.2012.198.Google Scholar
  17. 17.
    P. Marchetti, D. Oriato, O. Pell, A.M. Cristini, and D. Theis, “Fast 3D ZO CRS Stack,” 72nd European Association of Geoscientists and Engineers (EAGE) Conference, June 2010.Google Scholar
  18. 18.
    O. Lindtjorn, R. G. Clapp, O. Pell, O. Mencer, and M. J. Flynn, “Surviving the End of Scaling of Traditional Microprocessors in HPC,” IEEE HOT CHIPS 22, Stanford, USA, August 2010.Google Scholar
  19. 19., web site visited on March 17, 2017.
  20. 20.
    N. Trifunovic, V. Milutinovic, et al, “The for BigData SuperComputing,” Journal of Big Data, Springer, 2016.Google Scholar
  21. 21.
    N. Korolija, J. Popovi, M. Cvetanovi, and M. Bojovi, “Dataflow Based Parallelization of Control-Flow Algorithms,” Creativity in Computing and Dataflow Supercomputing, Advances in Computers, Vol. 104, 2017.Google Scholar
  22. 22.
    S. Stojanovic et al., “Coupling finite element and huxley models in multiscale muscle modeling,” Bioinformatics and Bioengineering (BIBE), 2015 IEEE 15th International Conference on. IEEE, 2015.Google Scholar
  23. 23.
    M. Ivanovi et al., “Distributed multi-scale muscle simulation in a hybrid MPICUDA computational environment,” Simulation 92.1 (2016): 19–31.CrossRefGoogle Scholar
  24. 24.
    A. Kaplarevi-Malii, et al., “Employing phenomenological model in load-balancing optimization of parallel multi-scale muscle simulations,” Bioinformatics and Bioengineering (BIBE), 2015 IEEE 15th International Conference on. IEEE, 2015.Google Scholar
  25. 25.
  26. 26.
  27. 27.
  28. 28.
    Blagojevic, V., et al, “A Systematic Approach to Generation of New Ideas for PhD Research in Computing,” Advances in Computers, Elsevier, Vol. 104, 2016, pp. 1–19.Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Veljko Milutinovic
    • 1
  • Jakob Salom
    • 2
  • Dragan Veljovic
    • 3
  • Nenad Korolija
    • 1
  • Dejan Markovic
    • 1
  • Luka Petrovic
    • 1
  1. 1.University of BelgradeBelgradeSerbia
  2. 2.Serbian Academy of Sciences and ArtsBelgradeSerbia
  3. 3.Motionlogic GmbHBerlinGermany

Personalised recommendations