Title :
LAPACK: A portable linear algebra library for high-performance computers
Author :
Angerson, E. ; Bai, Z. ; Dongarra, J. ; Greenbaum, A. ; McKenney, A. ; Du Croz, J. ; Hammarling, S. ; Demmel, J. ; Bischof, C. ; Sorensen, D.
Author_Institution :
Tennessee Univ., Knoxville, TN, USA
Abstract :
The goal of the LAPACK project is to design and implement a portable linear algebra library for efficient use on a variety of high-performance computers. The library is based on the widely used LINPACK and EISPACK packages for solving linear equations, eigenvalue problems, and linear least-squares problems, but extends their functionality in a number of ways. The major methodology for making the algorithms run faster is to restructure them to perform block matrix operations (e.g., matrix-matrix multiplication) in their inner loops. These block operations may be optimized to exploit the memory hierarchy of a specific architecture. The LAPACK project is also working on new algorithms that yield higher relative accuracy for a variety of linear algebra problems
Keywords :
eigenvalues and eigenfunctions; matrix algebra; software portability; subroutines; LAPACK; block matrix operations; block operations; eigenvalue problems; functionality; inner loops; linear equations; linear least-squares problems; matrix-matrix multiplication; memory hierarchy; portable linear algebra library; relative accuracy; Computer architecture; Costs; Eigenvalues and eigenfunctions; Equations; Laboratories; Libraries; Linear algebra; Packaging; Portable computers; Sparse matrices;
Conference_Titel :
Supercomputing '90., Proceedings of
Conference_Location :
New York, NY
Print_ISBN :
0-8186-2056-0
DOI :
10.1109/SUPERC.1990.129995
