A Parallel Algebraic Multigrid Preconditioned Iterative Method Based on an MPI Process Grouping Strategy for Asynchronous Concurrent Execution of the Setup and Solve Phases
Abstract
Algebraic multigrid (AMG) is one of the most effective algorithms for solving large sparse linear systems and consists of a setup phase followed by a solve phase. As supercomputer performance improves and the number of MPI processes increases, AMG faces serious challenges in algorithmic scalability and parallel scalability. To address these issues, we propose an asynchronous concurrent algebraic multigrid (ACAMG) model based on an MPI process grouping strategy for setup and solve. The setup and solve phases execute asynchronously and concurrently on separate MPI process groups. This organization can both preserve AMG hierarchy quality through an appropriate choice of the setup-group size and achieve time overlap between the two phases through asynchronous concurrent execution. Based on this model, we design and implement the MPI ACAMG algorithm. Theoretical analysis and numerical experiments show that the algorithm exhibits better algorithmic and parallel scalability. For example, for a three-dimensional diffusion problem with spatially localized anisotropy, ACAMG not only reduces the solve-phase iteration count compared with the conventional method, but also achieves speedups of 4.74 and 19.36 at 64 and 128 processes, respectively.
Related
- Online Autotuning of Algebraic Multigrid via Contextual Bandits and Reinforcement Learning
- Concurrent Coded Signal-Multiplexing Ranging for Half-Duplex Asynchronous Networks
- A Reduced Coupling-Space Multigrid Schur Preconditioner for Fictitious-Domain Interface Problems
- Robust Multigrid on Adaptive Meshes for the Integral Fractional Laplacian
- Data-driven accelerated multigrid method for Riesz space fractional diffusion equations
BibTeX
@misc{feng2026parallel,
title = {{A Parallel Algebraic Multigrid Preconditioned Iterative Method Based on an MPI Process Grouping Strategy for Asynchronous Concurrent Execution of the Setup and Solve Phases}},
author = {Chunsheng Feng and Shuai Liu and Linjie Zhang and Zirui Zhu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.39303},
eprint = {2610.39303},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.39303},
}
RIS
TY - UNPB
TI - A Parallel Algebraic Multigrid Preconditioned Iterative Method Based on an MPI Process Grouping Strategy for Asynchronous Concurrent Execution of the Setup and Solve Phases
AU - Chunsheng Feng
AU - Shuai Liu
AU - Linjie Zhang
AU - Zirui Zhu
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.39303
UR - https://arxiv.org/abs/2610.39303
AB - Algebraic multigrid (AMG) is one of the most effective algorithms for solving large sparse linear systems and consists of a setup phase followed by a solve phase. As supercomputer performance improves and the number of MPI processes increases, AMG faces serious challenges in algorithmic scalability and parallel scalability. To address these issues, we propose an asynchronous concurrent algebraic multigrid (ACAMG) model based on an MPI process grouping strategy for setup and solve. The setup and solve phases execute asynchronously and concurrently on separate MPI process groups. This organization can both preserve AMG hierarchy quality through an appropriate choice of the setup-group size and achieve time overlap between the two phases through asynchronous concurrent execution. Based on this model, we design and implement the MPI ACAMG algorithm. Theoretical analysis and numerical experiments show that the algorithm exhibits better algorithmic and parallel scalability. For example, for a three-dimensional diffusion problem with spatially localized anisotropy, ACAMG not only reduces the solve-phase iteration count compared with the conventional method, but also achieves speedups of 4.74 and 19.36 at 64 and 128 processes, respectively.
ER -