Parallel performance of algebraic multigrid domain decomposition
Algebraic multigrid (AMG) is a widely used scalable solver and preconditioner for large-scale linear systems resulting from the discretization of a wide class of elliptic PDEs. While AMG has optimal computational complexity, the cost of communication has become a significant bottleneck that limits i...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
2021
|
| In: |
Numerical linear algebra with applications
Year: 2021, Volume: 28, Issue: 3, Pages: 1-24 |
| ISSN: | 1099-1506 |
| DOI: | 10.1002/nla.2342 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1002/nla.2342 Verlag, kostenfrei, Volltext: https://onlinelibrary.wiley.com/doi/abs/10.1002/nla.2342 
|
| Author Notes: | Wayne B. Mitchell, Robert Strzodka, Robert D. Falgout |
| Summary: | Algebraic multigrid (AMG) is a widely used scalable solver and preconditioner for large-scale linear systems resulting from the discretization of a wide class of elliptic PDEs. While AMG has optimal computational complexity, the cost of communication has become a significant bottleneck that limits its scalability as processor counts continue to grow on modern machines. This article examines the design, implementation, and parallel performance of a novel algorithm, algebraic multigrid domain decomposition (AMG-DD), designed specifically to limit communication. The goal of AMG-DD is to provide a low-communication alternative to standard AMG V-cycles by trading some additional computational overhead for a significant reduction in communication cost. Numerical results show that AMG-DD achieves superior accuracy per communication cost compared with AMG, and speedup over AMG is demonstrated on a large GPU cluster. |
|---|---|
| Item Description: | First published: 12 October 2020 Gesehen am 25.10.2021 |
| Physical Description: | Online Resource |
| ISSN: | 1099-1506 |
| DOI: | 10.1002/nla.2342 |