Hybrid parallel computing of minimum action method
Document Type
Article
Publication Date
9-17-2013
Abstract
In this work, we report a hybrid (MPI/OpenMP) parallelization strategy for the minimum action method recently proposed in [17]. For nonlinear dynamical systems, the minimum action method is a useful numerical tool to study the transition behavior induced by small noise and the structure of the phase space. The crucial part of the minimum action method is to minimize the Freidlin-Wentzell action functional. Due to the fact that the corresponding Euler-Lagrange equation is, in general, highly nonlinear and of high order, we solve the optimization problem directly instead of discretizing the Euler-Lagrange equation to provide a general but equivalent numerical framework. To enhance the efficiency of the minimum action method for general dynamical systems we consider parallel computing. In particular, we present a hybrid parallelization strategy based on MPI and OpenMP. Numerical results are presented to demonstrate the efficiency of the proposed parallelization strategy. © 2013 Elsevier B.V. All rights reserved.
Publication Source (Journal or Book title)
Parallel Computing
First Page
638
Last Page
651
Recommended Citation
Wan, X., & Lin, G. (2013). Hybrid parallel computing of minimum action method. Parallel Computing, 39 (10), 638-651. https://doi.org/10.1016/j.parco.2013.08.004