Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Multigrid methods with space–time concurrency

  • Original Article
  • Published:
Computing and Visualization in Science

Abstract

We consider the comparison of multigrid methods for parabolic partial differential equations that allow space–time concurrency. With current trends in computer architectures leading towards systems with more, but not faster, processors, space–time concurrency is crucial for speeding up time-integration simulations. In contrast, traditional time-integration techniques impose serious limitations on parallel performance due to the sequential nature of the time-stepping approach, allowing spatial concurrency only. This paper considers the three basic options of multigrid algorithms on space–time grids that allow parallelism in space and time: coarsening in space and time, semicoarsening in the spatial dimensions, and semicoarsening in the temporal dimension. We develop parallel software and performance models to study the three methods at scales of up to 16K cores and introduce an extension of one of them for handling multistep time integration. We then discuss advantages and disadvantages of the different approaches and their benefit compared to traditional space-parallel algorithms with sequential time stepping on modern architectures.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. One possibility to save on memory in the waveform relaxation approach is to subdivide the time interval into a sequence of “windows” that are treated sequentially [43]. However, there is an apparent parallel performance tradeoff with this reduction in storage requirement.

References

  1. Ashby, S.F., Falgout, R.D.: A parallel multigrid preconditioned conjugate gradient algorithm for groundwater flow simulations. Nucl. Sci. Eng. 124(1), 145–159 (1996). UCRL-JC-122359

    Article  Google Scholar 

  2. Bastian, P., Burmeister, J., Horton, G.: Implementation of a parallel multigrid method for parabolic partial differential equations. In: W. Hackbusch (ed.) Parallel Algorithms for PDEs, Proc. 6th GAMM Seminar Kiel, January 19–21, 1990, pp. 18–27. Vieweg, Braunschweig (1990)

  3. Bjørhus, M.: On domain decomposition, subdomain iteration and waveform relaxation. Ph.D. thesis, Department of Mathematical Sciences, Norwegian Institute of Technology, University of Trondheim, Trondheim, Norway (1995)

  4. Bolten, M., Moser, D., Speck, R.: A multigrid perspective on the parallel full approximation scheme in space and time. Numerical Linear Algebra with Applications pp. e2110–n/a (2017). E2110 nla.2110

  5. Brandt, A.: Multi-level adaptive solutions to boundary-value problems. Math. Comput. 31, 333–390 (1977)

    Article  MATH  MathSciNet  Google Scholar 

  6. Buzbee, B.L., Golub, G.H., Nielson, C.W.: On direct methods for solving Poisson’s equations. SIAM J. Numer. Anal. 7, 627–656 (1970)

    Article  MATH  MathSciNet  Google Scholar 

  7. Chartier, P., Philippe, B.: A parallel shooting technique for solving dissipative ODEs. Computing 51(3–4), 209–236 (1993)

    Article  MATH  MathSciNet  Google Scholar 

  8. Christlieb, A.J., Macdonald, C.B., Ong, B.W.: Parallel high-order integrators. SIAM J. Sci. Comput. 32(2), 818–835 (2010)

    Article  MATH  MathSciNet  Google Scholar 

  9. De Sterck, H., Manteuffel, T.A., McCormick, S.F., Olson, L.: Least-squares finite element methods and algebraic multigrid solvers for linear hyperbolic PDEs. SIAM J. Sci. Comput. 26(1), 31–54 (2004)

    Article  MATH  MathSciNet  Google Scholar 

  10. Emmett, M., Minion, M.L.: Toward an efficient parallel in time method for partial differential equations. Commun. Appl. Math. Comput. Sci. 7(1), 105–132 (2012)

    Article  MATH  MathSciNet  Google Scholar 

  11. Falgout, R.D., Jones, J.E.: Multigrid on massively parallel architectures. In: E. Dick, K. Riemslagh, J. Vierendeels (eds.) Multigrid Methods VI, Lecture Notes in Computational Science and Engineering, vol. 14, pp. 101–107. Springer (2000). Proceedings of the Sixth European Multigrid Conference held in Gent, Belgium, September 27–30, 1999. UCRL-JC-133948

  12. Falgout, R.D., Katz, A., Kolev, Tz.V., Schroder, J.B., Wissink, A., Yang, U.M.: Parallel time integration with multigrid reduction for a compressible fluid dynamics application. Lawrence Livermore National Laboratory (2014)

  13. Falgout, R.D., Friedhoff, S., Kolev, T.V., MacLachlan, S.P., Schroder, J.B.: Parallel time integration with multigrid. SIAM J. Sci. Comput. 36(6), C635–C661 (2014)

    Article  MATH  MathSciNet  Google Scholar 

  14. Friedhoff, S., MacLachlan, S.: A generalized predictive analysis tool for multigrid methods. Numer. Linear Algebr. Appl. 22(4), 618–647 (2015)

    Article  MATH  MathSciNet  Google Scholar 

  15. Gahvari, H., Baker, A., Schulz, M., Yang, U.M., Jordan, K., Gropp, W.: Modeling the performance of an algebraic multigrid cycle on HPC platforms. In: 25th ACM International Conference on Supercomputing, Tucson, AZ (2011)

  16. Gander, M.J.: 50 years of time parallel time integration. In: Carraro, T., Geiger, M., Körkel, S., Rannacher, R. (eds.) Multiple Shooting and Time Domain Decomposition, pp. 69–113. Springer, Cham (2015)

  17. Gander, M.J., Neumüller, M.: Analysis of a new space–time parallel multigrid algorithm for parabolic problems. SIAM J. Sci. Comput. 38(4), A2173–A2208 (2016)

    Article  MATH  MathSciNet  Google Scholar 

  18. Gander, M.J., Stuart, A.M.: Space–time continuous analysis of waveform relaxation for the heat equation. SIAM J. Sci. Comput. 19(6), 2014–2031 (1998)

    Article  MATH  MathSciNet  Google Scholar 

  19. Gander, M.J., Vandewalle, S.: Analysis of the parareal time-parallel time-integration method. SIAM J. Sci. Comput. 29(2), 556–578 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  20. Güttel, S.: A parallel overlapping time-domain decomposition method for ODEs. Domain decomposition methods in science and engineering XX. Lect. Notes Comput. Sci. Eng, vol. 91, pp. 459–466. Springer, Heidelberg (2013)

  21. Hackbusch, W.: Parabolic Multigrid Methods. Computing Methods in Applied Sciences and Engineering. VI (Versailles, 1983), pp. 189–197. North-Holland, Amsterdam (1984)

    Google Scholar 

  22. Hockney, R.W.: A fast direct solution of Poisson’s equation using Fourier analysis. J. Assoc. Comput. Mach. 12, 95–113 (1965)

    Article  MATH  MathSciNet  Google Scholar 

  23. Hockney, R.W., Jesshope, C.R.: Parallel Computers: Architecture. Programming and Algorithms. Adam Hilger, Bristol (1981)

    MATH  Google Scholar 

  24. Horton, G.: The time-parallel multigrid method. Commun. Appl. Numer. Methods 8(9), 585–595 (1992)

    Article  MATH  MathSciNet  Google Scholar 

  25. Horton, G., Knirsch, R.: A time-parallel multigrid-extrapolation method for parabolic partial differential equations. Parallel Comput. 18(1), 21–29 (1992)

    Article  MATH  MathSciNet  Google Scholar 

  26. Horton, G., Vandewalle, S.: A space-time multigrid method for parabolic partial differential equations. SIAM J. Sci. Comput. 16(4), 848–864 (1995)

    Article  MATH  MathSciNet  Google Scholar 

  27. Horton, G., Vandewalle, S., Worley, P.: An algorithm with polylog parallel complexity for solving parabolic partial differential equations. SIAM J. Sci. Comput. 16(3), 531–541 (1995)

    Article  MATH  MathSciNet  Google Scholar 

  28. hypre: High performance preconditioners. http://www.llnl.gov/CASC/hypre/

  29. Keller, H.B.: Numerical Methods for Two-Point Boundary-Value Problems. Blaisdell Publishing Co. Ginn and Co., Waltham (1968)

  30. Kogge, P.M.: A parallel algorithm for the efficient solution of a general class of recurrence equations. IEEE Trans. Comput. C 22(8), 786–793 (1973)

  31. Lelarasmee, E., Ruehli, A.E., Sangiovanni-Vincentelli, A.L.: The waveform relaxation method for time-domain analysis of large scale integrated circuits. IEEE CAD 1(3), 131–145 (1982)

    Article  Google Scholar 

  32. Lions, J.L., Maday, Y., Turinici, G.: Résolution d’EDP par un schéma en temps “pararéel”. C. R. Acad. Sci. Paris Sér. I Math. 332(7), 661–668 (2001)

    Article  MATH  MathSciNet  Google Scholar 

  33. Lubich, C., Ostermann, A.: Multigrid dynamic iteration for parabolic equations. BIT 27(2), 216–234 (1987)

    Article  MATH  MathSciNet  Google Scholar 

  34. Maday, Y., Rønquist, E.M.: Parallelization in time through tensor-product space–time solvers. C. R. Math. Acad. Sci. Paris 346(1–2), 113–118 (2008)

    Article  MATH  MathSciNet  Google Scholar 

  35. Minion, M.L., Williams, S.A.: Parareal and spectral deferred corrections. In: T.E. Simos (ed.) Numerical Analysis and Applied Mathematics, No. 1048 in AIP Conference Proceedings, pp. 388–391. AIP (2008)

  36. Minion, M.L., Speck, R., Bolten, M., Emmett, M., Ruprecht, D.: Interweaving PFASST and parallel multigrid. SIAM J. Sci. Comput. 37(5), S244–S263 (2015)

    Article  MATH  MathSciNet  Google Scholar 

  37. Miranker, W.L., Liniger, W.: Parallel methods for the numerical integration of ordinary differential equations. Math. Comput. 21, 303–320 (1967)

    Article  MATH  MathSciNet  Google Scholar 

  38. Nievergelt, J.: Parallel methods for integrating ordinary differential equations. Commun. ACM 7, 731–733 (1964)

    Article  MATH  MathSciNet  Google Scholar 

  39. Ries, M., Trottenberg, U.: MGR-ein blitzschneller elliptischer Löser. Tech. Rep. Preprint 277 SFB 72, Universität Bonn (1979)

  40. Ries, M., Trottenberg, U., Winter, G.: A note on MGR methods. J. Linear Algebr. Appl. 49, 1–26 (1983)

    Article  MATH  MathSciNet  Google Scholar 

  41. Sheen, D., Sloan, I.H., Thomée, V.: A parallel method for time discretization of parabolic equations based on Laplace transformation and quadrature. IMA J. Numer. Anal. 23(2), 269–299 (2003)

    Article  MATH  MathSciNet  Google Scholar 

  42. Speck, R., Ruprecht, D., Emmett, M., Bolten, M., Krause, R.: A space-time parallel solver for the three-dimensional heat equation. In: Bader, M., Bode, A., Bungartz, H.-J., Gerndt, M., Joubert, G.R., Peter, F. (eds.) Parallel Computing: Accelerating Computational Science and Engineering (CSE), Advances in Parallel Computing, vol. 25, pp. 263–272. IOS Press (2014)

  43. Vandewalle, S.G., Van de Velde, E.F.: Space-time concurrent multigrid waveform relaxation. Ann. Numer. Math. 1(1–4), 347–360 (1994). Scientific computation and differential equations (Auckland, 1993)

  44. Vandewalle, S., Horton, G.: Fourier mode analysis of the multigrid waveform relaxation and time-parallel multigrid methods. Computing 54(4), 317–330 (1995)

    Article  MATH  MathSciNet  Google Scholar 

  45. Vandewalle, S., Piessens, R.: Efficient parallel algorithms for solving initial-boundary value and time-periodic parabolic partial differential equations. SIAM J. Sci. Stat. Comput. 13(6), 1330–1346 (1992)

    Article  MATH  MathSciNet  Google Scholar 

  46. Weinzierl, T., Köppl, T.: A geometric space-time multigrid algorithm for the heat equation. Numer. Math. Theory Methods Appl. 5(1), 110–130 (2012)

    MATH  MathSciNet  Google Scholar 

  47. XBraid: Parallel multigrid in time. http://llnl.gov/casc/xbraid

Download references

Author information

Author notes

  1. S. Friedhoff

    Present address: Fakultät für Mathematik und Naturwissenschaften, Bergische Universität Wuppertal, 42097, Wuppertal, Germany

Authors and Affiliations

  1. Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, P. O. Box 808, L-561, Livermore, CA, 94551, USA

    R. D. Falgout, Tz. V. Kolev & J. B. Schroder

  2. Department of Computer Science, KU Leuven, Celestijnenlaan 200a - box 2402, 3001, Leuven, Belgium

    S. Friedhoff & S. Vandewalle

  3. Department of Mathematics and Statistics, Memorial University of Newfoundland, St. John’s, NL, Canada

    S. P. MacLachlan

Authors
  1. R. D. Falgout
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. Friedhoff
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tz. V. Kolev
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. S. P. MacLachlan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. J. B. Schroder
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. S. Vandewalle
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. Friedhoff.

Additional information

Communicated by Rolf Krause.

This work performed under the auspices of the US Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344 (LLNL-JRNL-678572). The work of SF and SPM was partially supported by the National Science Foundation, under Grant DMS-1015370. The work of SPM was partially supported by an NSERC discovery grant. SF and SV acknowledge support from OPTEC (OPTimization in Engineering Center of excellence KU Leuven), which is funded by the KU Leuven Research Council under Grant No. PFV/10/002.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Falgout, R.D., Friedhoff, S., Kolev, T.V. et al. Multigrid methods with space–time concurrency. Comput. Visual Sci. 18, 123–143 (2017). https://doi.org/10.1007/s00791-017-0283-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00791-017-0283-9

Keywords

Search

Navigation