ScaLAPACK Tutorial

Abstract. ScaLAPACK is a library of high performance linear algebra routines for distributed memory MIMD computers. It is a continuation of the LAPACK project, which designed and produced analogous software for workstations, vector supercomputers, and shared memory parallel computers. The goals of the project are e ciency to run as fast as possible, scalability as the problem size and number of processors grow, reliability including error bounds, portability across all important parallel machines, exibility so users can construct new routines from well-designed parts, and ease-of-use by making LAPACK and ScaLAPACK look as similar as possible. Many of these goals, particularly portability, are aided by developing and promoting standards, especially for low-level communication and computation routines. We have been successful in attaining these goals, limiting most machine dependencies to two standard libraries called the BLAS, or Basic Linear Algebra Subroutines, and BLACS, ...

• Type: Conference
• Year: 1995
• Where: PARA
• Authors: Jack Dongarra, Antoine Petitet
• Keywords: Applied Computing, Basic Linear Algebra, Linear Algebra, Linear Algebra Routines, PARA 1995