Basic Linear Algebra Subprograms for Fortran Usage

  title={Basic Linear Algebra Subprograms for Fortran Usage},
  author={Charles L. Lawson and Richard J. Hanson and David R. Kincaid and Fred T. Krogh},
  journal={ACM Trans. Math. Softw.},
A package of 38 low level subprograms for many of the basic operations of numerical linear algebra is presented. The package is intended to be used with FORTRAN. The operations in the package are dot products, elementary vector operations, Givens transformations, vector copy and swap, vector norms, vector scaling, and the indices of components of largest magnitude. The subprograms and a test driver are available in portable FORTRAN. Versions of the subprograms are also provided in assembly… Expand
Benchmark of the Extended Basic Linear Algebra Subprograms on the NEC SX-2 Supercomputer
The EBLAS are a set of subprograms that represent basic matrix-vector operations and were written to take advantage of the architecture of today's supercomputers. Expand
Engineering and Scientific Subroutine Library for the IBM 3090 Vector Facility
The contents of ESSL are described and some of the techniques that were used to develop high-performance vector subroutines are presented, as well as key design considerations such as accuracy, ease of use, and error handling. Expand
Linear algebra software on IBM and CRAY computers
Abstract Mathematical software libraries represent collections of subprograms for the solution of frequently occurring numerical problems. The acceptance of mathematical software libraries stronglyExpand
Issues relating to extension of the Basic Linear Algebra Subprograms
The authors' views are Lased on their implementation of theBLAS in highly-efficient assembly language for the Cray-1 and Cray X-MP, and use of the BLAS and some of the proposed extensions in a variety of application areas. Expand
Local Basic Linear Algebra Subroutines (LBLAS) for the CM-5/5E
The implementation considerations and performance of the local BLAS, or BLAS local to each node of the system, are presented, irrespective of the data layout in node mem ory. Expand
Algorithm 692: Model implementation and test package for the Sparse Basic Linear Algebra Subprograms
A model implementation and test software are desribed for the Sparse Basic Linear Algebra Subprograms, which provides a portable set of FORTRAN 77 Sparse BLAS for the use on machines where specially tuned implementations do not exist or are not required. Expand
Preface to the special issue on the basic linear algebra subprograms (BLAS)
In this issue of the ACM Transactions on Mathematical Software, a set of research contributions are collected together which provide some of the technical background behind the development of the new BLAS standard. Expand
The Performance of Linear Algebra Subprograms on the Siemens S Series
An outstanding feature of the Siemens S series vector processors is the ability to dynamically reconfigurate the vector registers, which allows an optimal adaptation of a given application program to the VP hardware. Expand
Algorithm 663: Translation of Algorithm 539: basic linear algebra subprograms for FORTRAN usage in FORTRAN 200 for the Cyber 205
This paper describes the vectorization of the BLAS, a set of basic linear algebra subprograms for FORTRAN usage, and admits negative increment values; that is, vectors can also be treated in reverse order. Expand
A proposal for a set of level 3 basic linear algebra subprograms
The Level 3 BLAS are targeted at matrix-matrix operations with the aim of providing more efficient, but portable, implementations of algorithms on high-performance computers, especially those with hierarchical memory and parallel processing capability. Expand


A proposal for standard linear algebra subprograms
A set of FORTRAN callable subprograms are proposed which will be useful in the development of efficient portable ANSI FORTRAN subprograms and applications programs in the area of linear algebra.
A Portable Fortran Program to Find the Euclidean Norm of a Vector
This paper describes a successful version of a subprogram to find the Euclidean norm of an n-vector which is accurate and efficient, and should avoid all overflows and underflows, and is also portable. Expand
Clarification of Fortran standards—second report
The nature of the maintenance and the new set of corrections to and interpretations of the standard specifications are reported. Expand
A Note on Modifications to the Givens Plane Rotation
It has recently been shown how to perform plane rotations without square roots and with a saving in multiplications. (See for example, Gentleman, 1973). The purpose of this note is to present theExpand
The economical storage of plane rotations
SummaryPlane rotations, which have long been used in matrix computations to annihilate selected elements of a matrix, have the drawback that their definition requires two numbers. In this note it isExpand
A Fortran Multiple-Precision Arithmetic Package
Abstract : A collection of ANSI Standard FORTRAN subroutines for performing multiple-precision floating-point arithmetic and evaluating elementary and special functions is described. The subroutinesExpand
Basic linear algebra subprograms for FORTRAN usage--an extended report
  • Sandia Tech. Rep. SAND
  • 1977
Fortran BLAS timing
  • LINPACK Working Note
  • 1977
Fortran BLAS timing. LINPACK Working Note 3
  • Argonne Nat. Lab
  • 1977
Received July ACM TransacUons on MathemaUcal Software
  • Received July ACM TransacUons on MathemaUcal Software
  • 1977