Supernodal Sparse Cholesky Factorization on Distributed-Memory Multiprocessors

The concept of supernodes has been widely used in the design of algorithms for the solution of sparse linear systems of equations. This paper discusses the use of supernodes in the design of algorithms for sparse Cholesky factorization on distributed-memory multiprocessors. A new algorithm that is c...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:1993 International Conference on Parallel Processing - ICPP'93 Ročník 3; s. 18 - 22
Hlavní autoři: Eswar, Kalluri, Sadayappan, P., Huang, Chua-Huang, Visvanathan, V.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.08.1993
Témata:
Algorithm design and analysis
Equations
Information science
Linear systems
Parallel processing
Performance analysis
Sparse matrices
Supercomputers
Taxonomy
Workstations
ISBN:0849389836, 9780849389832
ISSN:0190-3918
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The concept of supernodes has been widely used in the design of algorithms for the solution of sparse linear systems of equations. This paper discusses the use of supernodes in the design of algorithms for sparse Cholesky factorization on distributed-memory multiprocessors. A new algorithm that is communication efficient, has good load balance, and benefits significantly from supernodes is presented.
ISBN:0849389836
9780849389832
ISSN:0190-3918
DOI:10.1109/ICPP.1993.170