Massively Multiscale Modeling using NASA Multiscale Analysis Tool through Partitioned Task-Parallel Approach

NASA Multiscale Analysis Tool (NASMAT) is a “plug and play” software package that allows users to conduct massively multiscale modeling of hierarchical and nonlinear materials. This work extends the scalability and improves the High Performance Computing friendliness of NASMAT by adopting a partitioned task-parallel approach. The interoperability of NAS- MAT with external software is enhanced through integration with preCICE, an open source library for multiphysics coupling in a partitioned manner. Enhancement through preCICE al- lows for easy integration of NASMAT to other macro solvers and dissociates the parallelization strategy adopted within NASMAT from the macro solver. A task-parallel framework based on the master-worker approach is implemented as the parallelization scheme. The scheme accounts for the hierarchy of multiple scales (task-dependence) and the heterogeneous nature (dynamic load balancing) of computations. The applicability and scalability of the frame- work are evaluated by analyzing multiscale problems with varying degrees of complexity and computational loads.