期刊
COMPUTATIONAL MECHANICS
卷 55, 期 1, 页码 93-103出版社
SPRINGER
DOI: 10.1007/s00466-014-1084-3
关键词
Finite element; Linear solver; Parallel data structure
资金
- Leducq Foundation Network of Excellent Grant
- Burroughs Welcome Fund Career Award at the Scientific Interface
- NIH [RHL102596A]
- NSF CAREER award [OCI-105509]
- Office of Advanced Cyberinfrastructure (OAC)
- Direct For Computer & Info Scie & Enginr [1055091] Funding Source: National Science Foundation
A parallel data structure that gives optimized memory layout for problems involving iterative solution of sparse linear systems is developed, and its efficient implementation is presented. The proposed method assigns a processor to a problem subdomain, and sorts data based on the shared entries with the adjacent subdomains. Matrix-vector-product communication overhead is reduced and parallel scalability is improved by overlapping inter-processor communications and local computations. The proposed method simplifies the implementation of parallel iterative linear equation solver algorithms and reduces the computational cost of vector inner products and matrix-vector products. Numerical results demonstrate very good performance of the proposed technique.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据