New strategy for coarse grid solvers in parallel multigrid methods using OpenMP/MPI hybrid programming models

Authors:
Kengo Nakajima
Affiliations:
The University of Tokyo
Venue:
Proceedings of the 2012 International Workshop on Programming Models and Applications for Multicores and Manycores
Year:
2012

Citing 6
Cited 1

Domain decomposition: parallel multilevel methods for elliptic partial differential equations

Domain decomposition: parallel multilevel methods for elliptic partial differential equations
Multigrid

Multigrid
Patterns for parallel programming

Patterns for parallel programming
Flat MPI vs. Hybrid: Evaluation of Parallel Programming Models for Preconditioned Iterative Solvers on "T2K Open Supercomputer

ICPPW '09 Proceedings of the 2009 International Conference on Parallel Processing Workshops
On the performance of an algebraic multigrid solver on multicore clusters

VECPAR'10 Proceedings of the 9th international conference on High performance computing for computational science
Parallel multigrid solvers using OpenMP/MPI hybrid programming models on multi-core/multi-socket clusters

VECPAR'10 Proceedings of the 9th international conference on High performance computing for computational science

ppOpen-HPC: open source infrastructure for development and execution of large-scale scientific applications on post-peta-scale supercomputers with automatic tuning (AT)

Proceedings of the ATIP/A*CRC Workshop on Accelerator Technologies for High-Performance Computing: Does Asia Lead the Way?

Quantified Score

Hi-index	0.00

Visualization

Abstract

OpenMP/MPI hybrid parallel programming models were implemented to 3D finite-volume based simulation code for groundwater flow problems through heterogeneous porous media using parallel iterative solvers with multigrid preconditioning. Performance and robustness of the developed code has been evaluated on the "T2K Open Supercomputer (T2K/Tokyo)" using up to 8,192 cores through both of weak and strong scaling computations. Furthermore new strategy for solving equations at the coarsest level (coarse grid solver) was proposed and evaluated. New coarse grid solver improved the scalability of the multigrid solver dramatically. OpenMP/MPI hybrid parallel programming model, where one MPI process is applied to a single socket (HB 4x4) demonstrated the best performance and robustness for large-scale ill-conditioned problems with appropriate optimization and coarse grid solvers.