Volume 6, Issue 3
Fall 1998

Volume 6, Issue 2
Spring/Summer 1998

Volume 6, Issue 1
Winter 1998

Volume 5, Issue 4
Fall 1997

Volume 5, Issue 3
Summer 1997

Volume 5, Issue 2
Spring 1997

Volume 5, Issue 1
Winter 1997

Volume 4, Issue 4
Fall 1996

Volume 4, Issue 3
Summer 1996

Volume 4, Issue 2
Spring 1996

Volume 4, Issue 1
Winter 1996

Volume 3, Issue 4
Fall 1995

Volume 3, Issue 3
Summer 1995

Volume 3, Issue 2
Spring 1995

Volume 3, Issue 1
January 1995

Volume 2, Issue 4
October 1994

Volume 2, Issue 3
July 1994

Volume 2, Issue 2
April 1994

Volume 2, Issue 1
January 1994

Volume 1, Issue 4
October 1993

Volume 1, Issue 3
July 1993

Volume 1, Issue 2
April 1993

Volume 1, Issue 1
January 1993

ScaLAPACK Software Update

Dan Sorensen, Rice University

ScaLAPACK is a collection of software for performing dense and band linear algebra computations on distributed-memory parallel computers. Version 1.5 of ScaLAPACK has recently been released and includes routines for the solution of the following problems:

Dense, band, triangular, and tridiagonal linear systems of equations Condition estimation and iterative refinement for LU and Cholesky factorizations Matrix inversions Full-rank linear least squares problems Orthogonal and generalized orthogonal factorizations Orthogonal transformation routines Reductions to upper Hessenberg, bidiagonal and tridiagonal forms Reduction of a symmetric-definite/Hermitian-definite generalized eigenproblem to standard forms Symmetric/Hermitian eigenproblems Generalized symmetric/Hermitian eigenproblems Nonsymmetric eigenproblems Singular value decompositions

Most routines are available in four data types: single precision real, double precision real, single precision complex, and double precision complex. In addition, the researchers have developed prototype software to handle the following areas:

Out-of-core linear solvers for LU, Cholesky, and QR HPF wrappers for a subset of ScaLAPACK routines The matrix sign function for eigenproblems Sparse direct solver for general problems (currently a sequential implementation based on the SuperLU work).

The software has been written to be portable across a wide range of distributed-memory environments such as the Cray T3, IBM SP, Intel series, TM CM-5, clusters of workstations, and any system for which PVM or MPI is available. A comprehensive installation guide is provided, as well as test suites for the collection.

The ScaLAPACK software is or will be part of the following vendors' provided numerical software libraries: IBM, SGI/Cray, NAG, Visual Numerics(IMSL), Fujitsu, Hewlett-Packard/Convex, Hitachi, and NEC. For more information on the availability of each of these packages and their documentation, consult the scalapack index on netlib or see http://www.netlib.org/scalapack /.

In addition, the group has just completed an updated version of the ScaLAPACK Users' Guide (SLUG). See http://www.netlib.org/scalapack/slug/scalapack_slug.html . This guide gives a detailed description of the philosophy behind ScaLAPACK, as well as an explanation of its usage. The printed SLUG was available in hardcopy at the SIAM National Meeting in July 1997 at Stanford and included a CD-ROM with the HTML version of the ScaLAPACK Users' Guide, the source code for the package, testing and timing programs, prebuilt versions of the library for a number of computers, example programs, and a full set of LAPACK Working Notes. See http://www.siam.org for addition details. The ISBN number is 0- 89871-397-8, and SIAM order code is SE04. The list price for SIAM members is $39.60; the cost for nonmembers is $49.50.

Funding for this effort comes in part from DARPA, DOE, NSF, and the CRPC. For more information on ScaLAPACK, see http://www.netlib.org/scalapack / or contact scalapack@cs.utk.edu .