A New Parallel Lanczos Eigensolution Technique in MSC

The Lanczos eigensolution takes the dominant amount of time in most normal modes and modal frequency response analyses. This paper introduces a way to reduce the elapsed time of large eigenvalue jobs by using a newly developed parallel option within the Lanczos algorithm. We will compare the performance of the frequency domain decomposition based distributed memory parallel method introduced in V70.7 and the new, geometry domain decomposition based distributed parallel method introduced in Version 2001. The new method may be utilized on clusters of workstations or even PCs, and naturally on distributed or shared memory parallel computers. It is applicable to very large NVH models of the automobile industry.