SuperLU

SuperLU is a collection of three ANSI C subroutine libraries for solving sparse linear systems of equations AX=B, where A is a square, nonsingular, n x n sparse matrix, and X and B are dense, n x nrhs matrices. nrhs is the number of right-hand sides and solution vectors.

SuperLU uses Gaussian elimination with partial pivoting (GEPP). The columns of A may be preordered before factorization; the preordering for sparsity is completely separate from the factorization.

It provides functionality for both real and complex matrices, in both single and double precision. The file names for the single-precision real version start with letter "s" (such as sgstrf.c); the file names for the double-precision real version start with letter "d" (such as dgstrf.c); the file names for the single-precision complex version start with letter "c" (such as cgstrf.c); the file names for the double-precision complex version start with letter "z" (such as zgstrf.c).

Installed library:

Sequential SuperLU,

designed for sequential processors with one or more layers of memory hierarchy.

Distributed SuperLU,

designed for distributed memory parallel processors using MPI for interprocess communication. It can effectively use hundreds of parallel processors on sufficiently large matrices to speed up the computation.

Installed on: BigBen.

BigBen usage

SuperLU is part of the Cray Scientific Library. Link to it by including -lsci on the compilation line.

Documentation

• The SuperLU User Guide (postscript format)

See also:

• Other software installed at PSC.