Multi-core parallel robust structured multifrontal factorization method for large discretized PDEs
| Autor: | Tong-xiang Gu, Aiqing Zhang, Ze-yao Mo, Xiao-wen Xu, Xian-Yu Zuo |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Multi-core processor
Theoretical computer science Current (mathematics) Discretization Nested dissection Applied Mathematics Binary number 010103 numerical & computational mathematics Parallel computing 01 natural sciences 010101 applied mathematics Computational Mathematics Factorization Decomposition (computer science) Factorization method 0101 mathematics Mathematics |
| Zdroj: | Journal of Computational and Applied Mathematics. 296:36-46 |
| ISSN: | 0377-0427 |
| DOI: | 10.1016/j.cam.2015.09.012 |
| Popis: | In this paper, based on the current mainstream multi-core architecture of parallel computer and the robust structured multifrontal factorization (in brief, RSMF) method, we propose a multi-core parallelization of RSMF (in brief, MRSMF) method. MRSMF method parallelizes the nested dissection ordering, symbolic decomposition and numerical decomposition of RSMF method, which aims to implement these operations on the multi-core parallel machine. The multi-core parallelization of symbolic decomposition and numerical decomposition are based on the binary elimination tree. Numerical experiments show that the MRSMF method is effective. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect