| 摘要: |
| 测试并分析了高性能预条件库HYPRE的多重网格解法器SMG和BoomerAMG在某国产大规模并行机数千个处理器上的可扩展性能,得到若干对线性解法器算法研究和并行实现技术发展具有启示性意义的结论.这些结论对实际复杂物理系统数值模拟中线性解法器的应用和发展具有一定的指导意义. |
| 关键词: HYPRE 线性解法器 预条件子 迭代方法 多重网格 并行计算 可扩展性能分析 |
| DOI： |
| 分类号: |
| 基金项目:Supported by the National Natural Science Foundation of China under Grant Nos.90718029, 60603050, 10701015 (国家自然科学基金); the National Basic Research Program of China under Grant No.2005CB321702 (国家重点基础研究发展计划(973)) |
|
| Parallel Scalability Analysis for Multigrid Solvers in HYPRE |
|
XU Xiao-Wen,MO Ze-Yao,CAO Xiao-Lin
|
| Abstract: |
| HYPRE is a high performance preconditioners library for solving large sparse linear systems on parallel computers. This paper analyzes the scalability of SMG and BoomerAMG, both are multigrid solvers in HYPRE, on massively parallel computer with thousands of processors. Based on the presented results, some conclusions are got to design scalable algorithms and their parallel implementation in real numerical applications. |
| Key words: HYPRE linear solver preconditioner iterative method multigrid parallel computing scalability |
