Evaluation of Parallel Sparse Matrix Partitioning Software for Parallel Multilevel ILU Preconditioning on Shared-Memory Multiprocessors

被引:0
|
作者
Aliaga, Jose I. [1 ]
Bollhoefer, Matthias [2 ]
Martin, Alberto F. [1 ]
Quintana-Orti, Enrique S. [1 ]
机构
[1] Univ Jaume 1, Dept Comp Sci & Engn, Castellon de La Plana, Spain
[2] TU Braunschweig, Inst Computat Math, Braunschweig, Germany
关键词
large sparse linear systems; factorization-based preconditioning; nested dissection; parallel partitioning software; shared-memory multiprocessors;
D O I
10.3233/978-1-60750-530-3-125
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
this paper we analyze the performance of two parallel sparse matrix partitioning software packages, ParMETIS and PT-SCOTCH. We focus our analysis on the parallel performance of the nested dissection partitioning stage as well as its impact on the performance of the numerical stages of the solution of sparse linear systems via multilevel ILU preconditioned iterative methods. Experimental results on a shared-memory platform with 16 processors show that ParMETIS seems to be the best choice for our approach.
引用
收藏
页码:125 / 132
页数:8
相关论文
共 50 条