Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

A PETSc Parallel-in-Time Solver based on MGRIT algorithm

Journal Article · · Concurrency and Computation: Practice and Experience
DOI:https://doi.org/10.1002/cpe.4928· OSTI ID:1510056

We address the development of a modular implementation of the MGRIT (MultiGrid-In-Time) algorithm to solve linear and nonlinear systems that arise from the discretization of evolutionary models with a parallel-in-time approach in the context of the PETSc (the Portable, Extensible Toolkit for Scientific computing) library. Our aim is to give the opportunity of predicting the performance gain achievable when using the MGRIT approach instead of the Time Stepping integrator (TS). To this end, we analyze the performance parameters of the algorithm that provide a-priori the best number of processing elements and grid levels to use to address the scaling of MGRIT, regarded as a parallel iterative algorithm proceeding along the time dimension.

Research Organization:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Organization:
European Commission (EC)
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1510056
Journal Information:
Concurrency and Computation: Practice and Experience, Vol. 30, Issue 24
Country of Publication:
United States
Language:
English

References (16)

Towards a parallel component for imaging in PETSc programming environment: a case study in 3-D echocardiography journal January 2006
Modeling the Performance of Geometric Multigrid Stencils on Multicore Computer Architectures journal January 2015
Multilevel Adaptive Computations in Fluid Dynamics journal October 1980
Modeling the performance of an algebraic multigrid cycle on HPC platforms conference January 2011
Insertion of PETSc in the NEMO stack software driving NEMO towards exascale computing conference July 2014
Parallel Time Integration with Multigrid journal January 2014
Analysis of the Parareal Time‐Parallel Time‐Integration Method journal January 2007
Towards a parallel component in a GPU–CUDA environment: a case study with the L-BFGS Harwell routine journal March 2014
Toward a fully parallel multigrid in time algorithm in PETSc environment: A case study in ocean models conference July 2015
An adjoint-based scalable algorithm for time-parallel integration journal March 2014
Global adaptive quadrature for the approximate computation of multidimensional integrals on a distributed-memory multiprocessor journal September 1992
The regional oceanic modeling system (ROMS): a split-explicit, free-surface, topography-following-coordinate oceanic model journal January 2005
Performance-influence models of multigrid methods: A case study on triangular grids: Performance-influence models of multigrid methods: a case study on triangular grids
  • Grebhahn, Alexander; Rodrigo, Carmen; Siegmund, Norbert
  • Concurrency and Computation: Practice and Experience, Vol. 29, Issue 17 https://doi.org/10.1002/cpe.4057
journal January 2017
Detection and Parallel Execution of Independent Instructions journal October 1970
A Scalable Approach for Variational Data Assimilation journal February 2014
Mathematical approach to the performance evaluation of three dimensional variational data assimilation
  • Arcucci, Rossella; D’Amore, Luisa; Mele, Valeria
  • APPLIED MATHEMATICS AND COMPUTER SCIENCE: Proceedings of the 1st International Conference on Applied Mathematics and Computer Science, AIP Conference Proceedings https://doi.org/10.1063/1.4981941
conference January 2017

Similar Records

Related Subjects