DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Multigrid methods with space–time concurrency

Abstract

Here, 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.

Authors:
 [1];  [2];  [1];  [3];  [1];  [4]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
  2. KU Leuven Leuven (Belgium); Bergische Univ. Wuppertal, Wuppertal (Germany)
  3. Memorial Univ. of Newfoundland, St. John's (Canada)
  4. KU Leuven Leuven (Belgium)
Publication Date:
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1413170
Report Number(s):
LLNL-JRNL-678572
Journal ID: ISSN 1432-9360
Grant/Contract Number:  
AC52-07NA27344
Resource Type:
Accepted Manuscript
Journal Name:
Computing and Visualization in Science
Additional Journal Information:
Journal Volume: 18; Journal Issue: 4-5; Journal ID: ISSN 1432-9360
Publisher:
Springer
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; Multigrid methods; Space–time discretizations; Parallel-in-time integration

Citation Formats

Falgout, R. D., Friedhoff, S., Kolev, Tz. V., MacLachlan, S. P., Schroder, J. B., and Vandewalle, S. Multigrid methods with space–time concurrency. United States: N. p., 2017. Web. doi:10.1007/s00791-017-0283-9.
Falgout, R. D., Friedhoff, S., Kolev, Tz. V., MacLachlan, S. P., Schroder, J. B., & Vandewalle, S. Multigrid methods with space–time concurrency. United States. https://doi.org/10.1007/s00791-017-0283-9
Falgout, R. D., Friedhoff, S., Kolev, Tz. V., MacLachlan, S. P., Schroder, J. B., and Vandewalle, S. Fri . "Multigrid methods with space–time concurrency". United States. https://doi.org/10.1007/s00791-017-0283-9. https://www.osti.gov/servlets/purl/1413170.
@article{osti_1413170,
title = {Multigrid methods with space–time concurrency},
author = {Falgout, R. D. and Friedhoff, S. and Kolev, Tz. V. and MacLachlan, S. P. and Schroder, J. B. and Vandewalle, S.},
abstractNote = {Here, 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.},
doi = {10.1007/s00791-017-0283-9},
journal = {Computing and Visualization in Science},
number = 4-5,
volume = 18,
place = {United States},
year = {Fri Oct 06 00:00:00 EDT 2017},
month = {Fri Oct 06 00:00:00 EDT 2017}
}

Works referenced in this record:

A time-parallel multigrid-extrapolation method for parabolic partial differential equations
journal, January 1992


A Parallel Overlapping Time-Domain Decomposition Method for ODEs
book, January 2013


A parallel shooting technique for solving dissipative ODE's
journal, September 1993


Analysis of the Parareal Time‐Parallel Time‐Integration Method
journal, January 2007

  • Gander, Martin J.; Vandewalle, Stefan
  • SIAM Journal on Scientific Computing, Vol. 29, Issue 2
  • DOI: 10.1137/05064607X

Efficient Parallel Algorithms for Solving Initial-Boundary Value and Time-Periodic Parabolic Partial Differential Equations
journal, November 1992

  • Vandewalle, Stefan; Piessens, Robert
  • SIAM Journal on Scientific and Statistical Computing, Vol. 13, Issue 6
  • DOI: 10.1137/0913075

Parallel High-Order Integrators
journal, January 2010

  • Christlieb, Andrew J.; Macdonald, Colin B.; Ong, Benjamin W.
  • SIAM Journal on Scientific Computing, Vol. 32, Issue 2
  • DOI: 10.1137/09075740X

Analysis of a New Space-Time Parallel Multigrid Algorithm for Parabolic Problems
journal, January 2016

  • Gander, Martin J.; Neumüller, Martin
  • SIAM Journal on Scientific Computing, Vol. 38, Issue 4
  • DOI: 10.1137/15M1046605

Parallel methods for integrating ordinary differential equations
journal, December 1964


Interweaving PFASST and Parallel Multigrid
journal, January 2015

  • Minion, M. L.; Speck, R.; Bolten, M.
  • SIAM Journal on Scientific Computing, Vol. 37, Issue 5
  • DOI: 10.1137/14097536X

Parallel methods for the numerical integration of ordinary differential equations
journal, September 1967


A generalized predictive analysis tool for multigrid methods: A GENERALIZED PREDICTIVE ANALYSIS TOOL FOR MULTIGRID METHODS
journal, February 2015

  • Friedhoff, S.; MacLachlan, S.
  • Numerical Linear Algebra with Applications, Vol. 22, Issue 4
  • DOI: 10.1002/nla.1977

Fourier mode analysis of the multigrid waveform relaxation and time-parallel multigrid methods
journal, December 1995


Parareal and Spectral Deferred Corrections
conference, January 2008

  • Minion, Michael L.; Williams, Sarah A.
  • NUMERICAL ANALYSIS AND APPLIED MATHEMATICS: International Conference on Numerical Analysis and Applied Mathematics 2008, AIP Conference Proceedings
  • DOI: 10.1063/1.2990941

The time-parallel multigrid method
journal, September 1992


Least-Squares Finite Element Methods and Algebraic Multigrid Solvers for Linear Hyperbolic PDEs
journal, January 2004

  • De Sterck, H.; Manteuffel, Thomas A.; McCormick, Stephen F.
  • SIAM Journal on Scientific Computing, Vol. 26, Issue 1
  • DOI: 10.1137/S106482750240858X

A Parallel Algorithm for the Efficient Solution of a General Class of Recurrence Equations
journal, August 1973

  • Kogge, Peter M.; Stone, Harold S.
  • IEEE Transactions on Computers, Vol. C-22, Issue 8
  • DOI: 10.1109/TC.1973.5009159

Résolution d'EDP par un schéma en temps «pararéel »
journal, April 2001

  • Lions, Jacques-Louis; Maday, Yvon; Turinici, Gabriel
  • Comptes Rendus de l'Académie des Sciences - Series I - Mathematics, Vol. 332, Issue 7
  • DOI: 10.1016/S0764-4442(00)01793-6

On Direct Methods for Solving Poisson’s Equations
journal, December 1970

  • Buzbee, B. L.; Golub, G. H.; Nielson, C. W.
  • SIAM Journal on Numerical Analysis, Vol. 7, Issue 4
  • DOI: 10.1137/0707049

Modeling the performance of an algebraic multigrid cycle on HPC platforms
conference, January 2011

  • Gahvari, Hormozd; Baker, Allison H.; Schulz, Martin
  • Proceedings of the international conference on Supercomputing - ICS '11
  • DOI: 10.1145/1995896.1995924

A note on MGR methods
journal, February 1983


Parallel Time Integration with Multigrid
journal, January 2014

  • Falgout, R. D.; Friedhoff, S.; Kolev, Tz. V.
  • SIAM Journal on Scientific Computing, Vol. 36, Issue 6
  • DOI: 10.1137/130944230

Space-Time Continuous Analysis of Waveform Relaxation for the Heat Equation
journal, November 1998


50 Years of Time Parallel Time Integration
book, January 2015


Toward an efficient parallel in time method for partial differential equations
journal, January 2012

  • Emmett, Matthew; Minion, Michael
  • Communications in Applied Mathematics and Computational Science, Vol. 7, Issue 1
  • DOI: 10.2140/camcos.2012.7.105

Multi-level adaptive solutions to boundary-value problems
journal, May 1977


Parallel time integration with multigrid: Parallel time integration with multigrid
journal, December 2014


A Parallel Multigrid Preconditioned Conjugate Gradient Algorithm for Groundwater Flow Simulations
journal, September 1996

  • Ashby, Steven F.; Falgout, Robert D.
  • Nuclear Science and Engineering, Vol. 124, Issue 1
  • DOI: 10.13182/NSE96-A24230

An Algorithm with Polylog Parallel Complexity for Solving Parabolic Partial Differential Equations
journal, May 1995

  • Horton, G.; Vandewalle, S.; Worley, P.
  • SIAM Journal on Scientific Computing, Vol. 16, Issue 3
  • DOI: 10.1137/0916034

A Fast Direct Solution of Poisson's Equation Using Fourier Analysis
journal, January 1965


A Space-Time Multigrid Method for Parabolic Partial Differential Equations
journal, July 1995

  • Horton, G.; Vandewalle, S.
  • SIAM Journal on Scientific Computing, Vol. 16, Issue 4
  • DOI: 10.1137/0916050

Parallelization in time through tensor-product space–time solvers
journal, January 2008


A parallel method for time discretization of parabolic equations based on Laplace transformation and quadrature
journal, April 2003


A Geometric Space-Time Multigrid Algorithm for the Heat Equation
journal, June 2012

  • Köppl, Tobias Weinzierl & Tobias
  • Numerical Mathematics: Theory, Methods and Applications, Vol. 5, Issue 1
  • DOI: 10.4208/nmtma.m12si07

Works referencing / citing this record:

Space-Time Block Preconditioning for Incompressible Flow
journal, February 2022

  • Danieli, Federico; Southworth, Ben S.; Wathen, Andrew J.
  • SIAM Journal on Scientific Computing, Vol. 44, Issue 1
  • DOI: 10.1137/21m1390773

Optimizing multigrid reduction-in-time (MGRIT) and Parareal coarse-grid operators for linear advection
text, January 2019


Performance Evaluation for a PETSc Parallel-in-Time Solver Based on the MGRIT Algorithm
book, December 2018


An experimental comparison of a space-time multigrid method with PFASST for a reaction-diffusion problem
preprint, January 2020


On selecting coarse-grid operators for Parareal and MGRIT applied to linear advection
preprint, January 2019