Look at scalable dense linear algebra libraries

J. Dongarra, R. van de Geijn, D. Walker

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

35 Scopus citations

Abstract

We discuss the essential design features of a library of scalable software for performing dense linear algebra computations on distributed memory concurrent computers. The square block scattered decomposition is proposed as a flexible and general-purpose way of decomposing most, if not all, dense matrix problems. An object-oriented interface to the library permits more portable applications to be written, and is easy to learn and use, since details of the parallel implementation are hidden from the user. Experiments on the Intel Touchstone Delta system with a prototype code that uses the square block scattered decomposition to perform LU factorization are presented and analyzed. It was found that the code was both scalable and efficient, performing at about 14 GFLOPS (double precision) for the largest problem considered.

Original languageEnglish
Title of host publicationProccedings of the Scalable High Performance Computing Conference-SHPCC-92
PublisherPubl by IEEE
Pages372-379
Number of pages8
ISBN (Print)0818627751
StatePublished - 1992
Externally publishedYes

Publication series

NameProccedings of the Scalable High Performance Computing Conference-SHPCC-92

Fingerprint

Dive into the research topics of 'Look at scalable dense linear algebra libraries'. Together they form a unique fingerprint.

Cite this