Bunch-Kaufman factorization for real symmetric indefinite banded matrices

The Bunch–Kaufman algorithm for factoring symmetric indefinite matrices has been rejected for banded matrices because it destroys the banded structure of the matrix. Herein, it is shown that for a subclass of real symmetric matrices which arise in solving the generalized eigenvalue problem using the Lanczos method, the Bunch–Kaufman algorithm does not result in major destruction of the bandwidth. Space/time complexities of the algorithm are given and used to show that the Bunch–Kaufman algorithm is a significant improvement over banded LU factorization. Timing comparisons are used to show the advantage held by the authors’ implementation of Bunch–Kaufman over the implementation of the multifrontal algorithm for indefinite factorization in MA27 when factoring this subclass of matrices.