An Identity Parareal Method for Temporal Parallel Computations

  • Toshiya Takami
  • Daiki Fukudome
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8384)


A new simplified definition of time-domain parallelism is introduced for explicit time evolution calculations, and is implemented on parallel machines with bucket-brigade type communications. By the use of an identity operator instead of introducing an approximate solver, a recurrence formula for the parareal-in-time algorithm is much simplified. In spite of such a simple definition, it is applicable to many of explicit time-evolution calculations. In addition, this approach overcomes several drawbacks known in the original parareal-in-time method. In order to implement this algorithm on parallel machines, a parallel bucket-brigade interface is introduced, which reduces programming and tuning costs for complicated space-time parallel programs.


Parareal-in-time Bucket-brigade communication Strong scaling Massively parallel machine Scientific computing 



This work is supported by JST, CREST.


  1. 1.
    Hoefler, T., Jumsdaine, A., Rehm, W.: Implementation and performance analysis of non-blocking collective operations for MPI. In: Proceedings of SC07, IEEE Computer Society (2007)Google Scholar
  2. 2.
    MPI 3.0 released at September 21, 2012:
  3. 3.
    Lions, J.-L., Maday, Y., Turinici, G.: A “parareal” in time discretization of PDE’s. C. R. Acad. Sci. Ser. I Math. 332, 661–668 (2001)zbMATHMathSciNetGoogle Scholar
  4. 4.
    Gander, M.J., Vandewalle, S.: Analysis of the parareal time-parallel time-integration method. SIAM J. Sci. Comput. 29, 556–578 (2007)CrossRefzbMATHMathSciNetGoogle Scholar
  5. 5.
    Takami, T., Nishida, A.: Parareal acceleration of matrix multiplication. Adv. Parallel Comput. 22, 437–444 (2012)Google Scholar
  6. 6.
    Speck, R., Ruprecht, D., Krause, R., Emmett, M., Minion, M., Winkel, M., Gibbon, P.: A massively space-time parallel n-body solver. In: Proceedings of SC12, IEEE Computer Society (2012)Google Scholar
  7. 7.
    Farhat, C., Chandesris, M.: Time-decomposed parallel time-integrators: theory and feasibility studies for fluid, structure, and fluid, structure applications. Int. J. Numer. Meth. Eng. 58, 1397–1434 (2003)CrossRefzbMATHMathSciNetGoogle Scholar
  8. 8.
    Fischer, P.F., Hecht, F., Maday, Y.: A parareal in time semi-implicit approximation of the navier-stokes equations. In: Barth, T.J., Griebel, M., Keyes, D.E., Nieminen, R.M., Roose, D., Schlick, T., Kornhuber, R., Hoppe, R., Périaux, J., Pironneau, O., Widlund, O., Xu, J. (eds.) Domain Decomposition Methods in Science and Engineering. LNCSE, vol. 40, pp. 433–440. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    Bal, G.: On the convergence and the stability of the parareal algorithm to solve partial differential equations. In: Barth, T.J., Griebel, M., Keyes, D.E., Nieminen, R.M., Roose, D., Schlick, T., Kornhuber, R., Hoppe, R., Périaux, J., Pironneau, O., Widlund, O., Xu, J. (eds.) Domain Decomposition Methods in Science and Engineering. LNCSE, vol. 40, pp. 425–432. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Samaddar, D., Newman, D.E., Sánchez, R.: Parallelization in time of numerical simulations of fully-developed plasma turbulence using the parareal algorithm. J. Comput. Phys. 229, 6558–6573 (2010)CrossRefzbMATHGoogle Scholar
  11. 11.
    Duarte, M., Massot, M., Descombes, S.: Parareal operator splitting techniques for multi-scale reaction waves: numerical analysis and strategies. ESAIM: Math. Model. Numer. Anal. 45, 825–852 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  12. 12.
    Ruprecht, D., Krause, R.: Explicit parallel-in-time integration of a linear acoustic-advection system. Comput. Fluids 59, 72–83 (2012)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Maday, Y., Turinici, G.: Parallel in time algorithms for quantum control: parareal time discretization scheme. Int. J. Quantum Chem. 93, 223–228 (2003)CrossRefGoogle Scholar
  14. 14.
    Baffico, L., Bernard, S., Maday, Y., Turinici, G., Zérah, G.: Parallel-in-time molecular-dynamics simulations. Phys. Rev. E 66, 057701 (2002)CrossRefGoogle Scholar
  15. 15.
    Srinivasan, A., Chandra, N.: Latency tolerance through parallelization of time in scientific applications. Parallel Comput. 31, 777–796 (2005)CrossRefGoogle Scholar
  16. 16.
    Bal, G., Wu, Q.: Symplectic parareal. In: Langer, U., Discacciati, M., Keyes, D.E., Widlund, O.B., Zulehner, W. (eds.) Domain Decomposition Methods in Science and Engnieering XVII. LNCSE, vol. 60, pp. 401–408. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  17. 17.
    Aubanel, E.: Scheduling of tasks in the parareal algorithm. Parallel Comput. 37, 172–182 (2011)CrossRefzbMATHMathSciNetGoogle Scholar
  18. 18.
    Elwasif, W.R., Foley, S.S., Bernholdt, D.E., Berry, L.A., Samaddar, D., Newman, D.E., Sanchez, R.: A dependency-driven formulation of parareal: parallel-in-time solution of PDEs as a many-task application. In: Proceedings of MTAGS’11, pp. 15–24 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Research Institute for Information TechnologyKyushu UniversityHigashi-kuJapan
  2. 2.Graduate School of Information Science and Electrical EngineeringKyushu UniversityNishi-kuJapan

Personalised recommendations