Large-Scale Normal Coordinate Analysis on Distributed Memory Parallel Systems

A parallel computational scheme for analyzing large-scale molecular vibration on distributed memory computing platforms is presented in this paper. This method combines the implicitly restarted Lanczos algorithm with a state-of-art parallel sparse direct solver to compute a set of low frequency vibrational modes for molecular systems containing tens of thousands of atoms. Although the original motivation for developing such a scheme was to overcome memory limitations on traditional sequential and shared memory machines, our computational experiments show that with a careful parallel design and data partitioning scheme one can achieve scalable performance on lightly coupled distributed memory parallel systems. In particular, we demonstrate performance enhancement achieved by using the latency tolerant “selective inversion" scheme in the sparse triangular substitution phase of the computation.