A PARALLEL DAVIDSON-TYPE ALGORITHM FOR SEVERAL EIGENVALUES

In this paper we propose a new parallelization of the Davidson algorit hm adapted for many eigenvalues. In our parallelization we use a relat ionship between two consecutive subspaces which allows us to calculate eigenvalues in the subspace through an arrowhead matrix. Theoretical timing estimates for the parallel algorithm are developed and compared against our numerical results on the Paragon. Finally our algorithm i s compared against another recent parallel algorithm for multiple eige nvalues, but based on Arnoldi: PARPACK. (C) 1998 Academic Press.