CHAPTER 2
: LINPACK Subroutines

This chapter describes the subroutines in LINPACK as they are implemented in the Sun Performance Library. LINPACK is a collection of linear algebra subroutines to perform matrix factorization, solving linear systems of various forms, solutions to leastsquares problems, and other common linear algebra operations.
The routines in this chapter are 100% interfacecompatible with the LINPACK in Netlib. The input and output arrays are stored in the same format as Netlib, but arrays whose storage format is not explicitly documented in the description of the arguments may differ between Sun Performance Library and Netlib. For example, the factored array that is returned from DGEFA is not in the same format as the array returned from Netlib.
For more information about LINPACK, refer to the information in this chapter of see the LINPACK User's Guide written by Dongarra et al and available from the Society for Industrial and Applied Mathematics (SIAM) in Philadelphia.
The first four sections of this chapter describe:

conventions followed in naming arguments and subroutines

conventions used for passing arguments into and out of subroutines

error handling done by the subroutines

extensions to the standard version of LINPACK.
The remaining sections of this chapter describe the operation of each of the LINPACK subroutines. For each subroutine, the interface is shown, the operation of the subroutine is described, and a short FORTRAN 77 program is given with sample output.