This chapter describes the parallelization of an algorithm for the well-known Gaussian elimination method of factoring a matrix. This matrix operation, also known as LU decomposition, demonstrates both the ease of use and the power of Digital Fortran 90 used with its High Performance Fortran (HPF) extensions. This small but typical problem introduces basic HPF constructs, including DISTRIBUTE, FORALL, and INDEPENDENT.
In LU decomposition, a square matrix is factored into two matrices L and U, where L is lower triangular with ones on its diagonal, and U is upper triangular.
