ScaLAPACK: a scalable linear algebra library for distributed memory concurrent computers

Author

Choi, Jaeyoung ; Dongarra, Jack J. ; Pozo, Roldan ; Walker, David W.

Author_Institution

Oak Ridge Nat. Lab., TN, USA

fYear

1992

fDate

19-21 Oct 1992

Firstpage

120

Lastpage

127

Abstract

The authors describe ScaLAPACK, a distributed memory version of the LAPACK software package for dense and banded matrix computations. Key design features are the use of distributed versions of the Level 3 BLAS as building blocks, and an object-oriented interface to the library routines. The square block scattered decomposition is described. The implementation of a distributed memory version of the right-looking LU factorization algorithm on the Intel Delta multicomputer is discussed, and performance results are presented that demonstrate the scalability of the algorithm

Keywords

distributed memory systems; linear algebra; mathematics computing; object-oriented programming; performance evaluation; software packages; Intel Delta multicomputer; Level 3 BLAS; ScaLAPACK; distributed memory concurrent computers; distributed memory version; library routines; matrix computations; object-oriented interface; performance; right-looking LU factorization algorithm; scalable linear algebra library; software package; square block scattered decomposition; Algorithm design and analysis; Brillouin scattering; Concurrent computing; Contracts; Distributed computing; Linear algebra; Scalability; Software libraries; Software packages; Sparse matrices;

fLanguage

English

Publisher

ieee

Conference_Titel

Frontiers of Massively Parallel Computation, 1992., Fourth Symposium on the

Conference_Location

McLean, VA

Print_ISBN

0-8186-2772-7

Type

conf

DOI

10.1109/FMPC.1992.234898

Filename

234898