EIGENVALUES CALCULATION ALGORITHMS FOR LAMBDA-MODES DETERMINATION - PARALLELIZATION APPROACH

In this paper, we review two methods to obtain the lambda-modes of a n uclear reactor, Subspace Iteration method and Arnoldi's method, which are popular methods to solve the partial eigenvalue problem for a give n matrix. In the developed application for the neutron diffusion equat ion we include improved acceleration techniques for both methods. Also , we propose two parallelization approaches for these methods, a coars e grain parallelization and a fine grain one, We have tested the devel oped algorithms with two realistic problems, focusing on the efficienc y of the methods according to the CPU times. Copyright (C) 1996 Elsevi er Science Ltd