Cyclic Data Flows in Computers and Embedded Systems

  • Claire HanenEmail author
  • Alix Munier-Kordon
Part of the Studies in Systems, Decision and Control book series (SSDC, volume 241)


Synchronous DataFlow Graphs (SDF in short) is a simple model of computation introduced for the description of Digital Signal Processing Applications. This formalism is today widely used to model embedded parallel applications. This chapter aims at presenting a panorama of theoretical results and practical applications in connection with cyclic scheduling problems. We first recall that the execution of a SDF can be seen as a set of cyclic dependant tasks. The structure of precedence constraints, important dominance properties and simplifications of the SDF are then presented. For the special case of uniform precedence graph, periodic schedule are dominant and the maximum throughput can be polynomially evaluated. Main results on the resource constrained problem are presented, followed by a more recent problem issued from sensor networks. In the general case, the existence of a polynomial-time algorithm to evaluate the maximum throughput of a SDF is a challenging question. However, the determination of a periodic schedule of minimum period is a polynomial problem, and many authors limit their study to this class of schedule to express optimization problems as the total buffer minimization or to evaluate the latency of a real-time periodic system.


  1. 1.
    Ahmad, A., Hanzálek, Z.: An energy efficient schedule for IEEE 802.15.4/zigbee cluster tree WSN with multiple collision domains and period crossing constraint. IEEE Trans. Ind. Inform. 14(1), 12–23 (2018)CrossRefGoogle Scholar
  2. 2.
    Alacaide, D., Chu, C., Kats, V., Levner, E., Sierksma, G.: Cyclic multiple robot scheduling with time-window constraints using a critical path approach. Eur. J. Oper. Res. 177, 147–162 (2007)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Ayala, M., Benabid, A., Artigues, C., Hanen, C.: The resource-constrained modulo scheduling problem: an experimental study. Comput. Optim. Appl. 54(3), 645–673 (2013)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Barroso, L.: The price of performance. ACM Queue 3(7), 48–53 (2005)CrossRefGoogle Scholar
  5. 5.
    Bekooij, M.J., Jansen, P.G., Smit, G.J., Wiggers, M.H.: Efficient computation of buffer capacities for cyclo-static real-time systems with back-pressure. In: 2007 44th ACM/IEEE Design Automation Conference, San Diego, CA, 4–8 June 2007, pp. 281–292. IEEE (2007)Google Scholar
  6. 6.
    Benabid, A., Hanen, C.: Worst case analysis of decomposed software pipelining for cyclic unitary RCPSP with precedence delays. J. Sched. 14(5), 511–522 (2011)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Benabid-Najjar, A., Hanen, C., Marchetti, O., Kordon, A.M.: Periodic schedules for bounded timed weighted event graphs. IEEE Trans. Autom. Control 57(5), 1222–1232 (2012)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Benazouz, M., Marchetti, O., Kordon, A.M., Urard, P.: A new approach for minimizing buffer capacities with throughput constraint for embedded system design. In: The 8th ACS/IEEE International Conference on Computer Systems and Applications, AICCSA 2010, Hammamet, Tunisia, 16–19 May 2010, pp. 1–8. IEEE (2010)Google Scholar
  9. 9.
    Benazouz, M., Marchetti, O., Munier-Kordon, A., Michel, T.: A new method for minimizing buffer sizes for cyclo-static dataflow graphs. In: 2010 8th IEEE Workshop on Embedded Systems for Real-Time Multimedia, Scottsdale, AZ, 2010, pp. 11–20. IEEE (2010)Google Scholar
  10. 10.
    Blachot, F., de Dinechin, B.D., Huard, G.: SCAN: a heuristic for near-optimal software pipelining. In: Nagel, W.E., Walter, W.V., Lehner, W. (eds.) Euro-Par 2006 Parallel Processing. Euro-Par 2006. Lecture Notes in Computer Science, vol 4128. Springer, Berlin (2006)CrossRefGoogle Scholar
  11. 11.
    Bodin, B., Kordon, A.M., de Dinechin, B.D.: K-periodic schedules for evaluating the maximum throughput of a synchronous dataflow graph. In: 2012 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS XII, Samos, Greece, 16–19 July 2012, pp. 152–159. IEEE (2012)Google Scholar
  12. 12.
    Bodin, B., Kordon, A.M., de Dinechin, B.D.: Optimal and fast throughput evaluation of CSDF. In: DAC ’16 Proceedings of the 53rd Annual Design Automation Conference, Austin, Texas, 5–9 June 2016, pp. 160:1–160:6. ACM, New York (2016)Google Scholar
  13. 13.
    Calland, P.Y., Darte, A., Robert, Y.: Circuit retiming applied to decomposed software pipelining. IEEE Trans. Parallel Distrib. Syst. 9(1), 24–35 (1998)CrossRefGoogle Scholar
  14. 14.
    Carlier, J., Chrétienne, P.: Problèmes d’ordonnancement: modèlisation, complexité, algorithmes. Masson, Paris (1988)Google Scholar
  15. 15.
    Claire, H.: Cyclic scheduling. In: Robert, Y., Vivien, F. (eds.) Introduction to Scheduling. Springer, Berlin (2009)Google Scholar
  16. 16.
    Cormen, T., Leiserson, C., Rivest, R.: Introduction to Algorithms. MIT Press, Cambridge (1990)Google Scholar
  17. 17.
    Darte, A., Huard, G.: Loop shifting for loop compaction. Int. J. Parallel Program. 28(499), 415–431 (2000)Google Scholar
  18. 18.
    Dasdan, A., Irani, S., Gupta, R.K.: Efficient algorithms for optimum cycle mean and optimum cost to time ratio problems. In: DAC ’99 Proceedings of the 36th Annual ACM/IEEE Design Automation Conference, New Orleans, Louisiana, USA, 21–25 June 1999, pp. 37–42. ACM, New York (1999)Google Scholar
  19. 19.
    Dupont De Dinechin, B., Artigues, C., Azem, S.: Resource-constrained moulo scheduling. In: Artigues, C., Demassey, S., Néron, E. (eds.) Resource Constrained Project Scheduling: Models, Algorithms, Extensions and Applications, Control Systems, Robotics and Manufacturing Series, pp. 267–277. ISTE-Wiley (2008)Google Scholar
  20. 20.
    Eichenberger, A., Davidson, E.: Efficient formulation for optimal modulo schedulers. In: ACM SIGPLAN Conference on Programming Language Design and Implementation, Las Vegas, Nevada, pp. 194–205 (1997)CrossRefGoogle Scholar
  21. 21.
    Gasperoni, F., Schwiegelshohn, U.: Generating close to optimum loop schedules on parallel processors. Parallel Process. Lett. 4, 391–403 (1994)MathSciNetCrossRefGoogle Scholar
  22. 22.
    Goubier, T., Sirdey, R., Louise, S., David, V.: \(\Sigma {\text{c}}\): a programming model and language for embedded manycores. In: Xiang, Y., Cuzzocrea, A., Hobbs, M., Zhou, W. (eds.) Algorithms and Architectures for Parallel Processing — 11th International Conference, ICA3PP, Melbourne, Australia, 24–26 October 2011, pp. 385–394. Springer, Berlin (2011)CrossRefGoogle Scholar
  23. 23.
    Hanen, C., Hanzalek, Z.: Grouping tasks to save energy in a cyclic scheduling problem: a complexity study. HAL CCSD (2012)Google Scholar
  24. 24.
    Hanen, C., Munier, A.: Cyclic scheduling on parallel processors: an overview. In: Chrétienne, P., Coffman, E.G., Lenstra, J.K., Liu, Z. (eds.) Scheduling Theory and Its Applications. Wiley, New York (1994)Google Scholar
  25. 25.
    Hanen, C., Munier, A.: A study of the cyclic scheduling problem on parallel processors. Discret. Appl. Math. 57(2–3), 167–192 (1995)MathSciNetCrossRefGoogle Scholar
  26. 26.
    Hanzálek, Z., Hanen, C.: The impact of core precedences in a cyclic RCPSP with precedence delays. J. Sched. 18(3), 275–284 (2015)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Kats, V., Levner, E.: Cyclic routing algorithms in graphs: performance analysis and applications to robot scheduling. Comput. Ind. Eng. 61(2), 279–288 (2011)CrossRefGoogle Scholar
  28. 28.
    Khatib, J., Kordon, A.M., Klikpo, E.C., Trabelsi-Colibet, K.: Computing latency of a real-time system modeled by synchronous dataflow graph. In: Proceedings of the 24th International Conference on Real-Time Networks and Systems, RTNS 2016, Brest, France, 19–21 October 2016, pp. 87–96. ACM, New York (2016)Google Scholar
  29. 29.
    Lee, E.A., Messerschmitt, D.G.: Synchronous data flow. Proc. IEEE 75(9), 1235–1245 (1987)CrossRefGoogle Scholar
  30. 30.
    Liu, C.L., Layland, J.W.: Scheduling algorithms for multiprogramming in a hard-real-time environment. J. ACM 20(1), 46–61 (1973)MathSciNetCrossRefGoogle Scholar
  31. 31.
    Marchetti, O., Kordon, A.M.: Complexity results for weighted timed event graphs. Discret. Optim. 7(3), 166–180 (2010)MathSciNetCrossRefGoogle Scholar
  32. 32.
    Marchetti, O., Munier-Kordon, A.: Cyclic scheduling for the synthesis of embedded systems. In: Robert, Y., Vivien, F. (eds.) Introduction to Scheduling. Springer, Berlin (2009)Google Scholar
  33. 33.
    Marchetti, O., Munier-Kordon, A.: A sufficient condition for the liveness of weighted event graphs. Eur. J. Oper. Res. 197(2), 532–540 (2009)MathSciNetCrossRefGoogle Scholar
  34. 34.
    Munier, A.: Régime asymptotique optimal d’un graphe d’événements temporisé généralisé: application à un problème d’assemblage. RAIRO-Automatique Productique Informatique Industrielle 27(5), 487–513 (1993)zbMATHGoogle Scholar
  35. 35.
    Munier-Kordon, A.: A graph-based analysis of the cyclic scheduling problem with time constraints: schedulability and periodicity of the earliest schedule. J. Sched. 14(1), 103–117 (2011)MathSciNetCrossRefGoogle Scholar
  36. 36.
    Oh, H., Ha, S.: Efficient code synthesis from extended dataflow graphs for multimedia applications. In: Proceedings of the 39th Design Automation Conference, DAC 2002, New Orleans, LA, USA, 10–14 June 2002, pp. 275–280. ACM, New York (2002)Google Scholar
  37. 37.
    Pempera, J., Smutnicki, C.: Open shop cyclic scheduling. Eur. J. Oper. Res. 269(2), 773–781 (2018)MathSciNetCrossRefGoogle Scholar
  38. 38.
    Rau, B.R.: Iterative modulo scheduling: an algorithm for software pipelining loops. In: MICRO 27: Proceedings of the 27th Annual International Symposium on Microarchitecture, 30 November–2 December 1994, pp. 63–74. ACM, New York (1994)Google Scholar
  39. 39.
    Robert, Y., Vivien, F.: Introduction to Scheduling. Chapman and Hall/CRC Press, Boca Raton (2009)Google Scholar
  40. 40.
    Thies, W., Karczmarek, M., Gordon, M., Maze, D.Z., Wong, J., Hoffman, H., Brown, M., Amarasinghe, S.: StreamIt: a compiler for streaming applications. Technical report, Massachussetts Institute of Technology (2001)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.UPL, Université Paris-NanterreNanterreFrance
  2. 2.Sorbonne Université, CNRS, LIP6ParisFrance

Personalised recommendations