DocumentCode :
2533315
Title :
An efficient block-oriented approach to parallel sparse Cholesky factorization
Author :
Rothberg, Edward ; Gupta, Anoop
Author_Institution :
Intel Supercomput. Syst. Div., Beaverton, OR, USA
fYear :
1993
fDate :
15-19 Nov. 1993
Firstpage :
503
Lastpage :
512
Abstract :
The authors explore the use of a sub-block decomposition strategy for parallel sparse Cholesky factorization, in which the sparse matrix is decomposed into rectangular blocks. Such a strategy has enormous theoretical scalability advantages over more traditional column-oriented and panel-oriented decompositions. However, little progress has been made in producing a practical sub-block method. The authors propose and evaluate an approach that is simple to implement, provides slightly higher performance than column (and panel) methods on small parallel machines, and has the potential to provide much higher performance on large parallel machines.
Keywords :
parallel algorithms; sparse matrices; block-oriented approach; parallel sparse Cholesky factorization; rectangular blocks; scalability advantages; small parallel machines; sparse matrix; sub-block decomposition strategy; Concurrent computing; High performance computing; Laboratories; Matrix decomposition; Parallel machines; Runtime; Scalability; Sparse matrices; Supercomputers; Symmetric matrices;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Supercomputing '93. Proceedings
ISSN :
1063-9535
Print_ISBN :
0-8186-4340-4
Type :
conf
DOI :
10.1109/SUPERC.1993.1263498
Filename :
1263498
Link To Document :
بازگشت