HPC-Netlib

High Performance Math Software

NIST Sparse BLAS

Abstract

The NIST Sparse BLAS (Basic Linear Algebra Subprogram) library provides computational kernels for fundamental sparse matrix operations, including sparse matrix products and solution of triangular systems. The current version supports compressed-row, compressed-column, and coordinate sparse storage formats, together with block and variable-block versions of these. Symmetric and skew-symmetric versions are also supported. The routines are written in ANSI C and are callable from Fortran and C. This project is part of the ongoing standardization effort of the BLAS Technical Forum.

DateOfInformation

Tue Apr 8 16:33:42 1997

Domain

Numerical Programs and Routines!Linear algebra

Name

NIST Sparse BLAS

TargetEnvironment

preliminary results show performance comparable to optimized Fortran codes on Sun SparcStations and IBM RS/6000s (between 10-15 Mflops for sparse matrices, 15-30 Mflops for block sparse matrices)

TitleLine

computational kernels for fundamental sparse matrix operations

Version

0.9

Webpage

http://math.nist.gov/spblas/

ContactIs

Karin Remington