Towards Fast Scalable Solvers for Charge Equilibration in Molecular Dynamics Applications

Abstract

Including atom polarizability in molecular dynamics (MD) simulations is important for high-fidelity simulations. Solvers for charge models that are used to dynamically determine atom polarizations constitute significant bottlenecks in terms of time-to-solution and the overall scalability of polarizable and reactive force fields. The objective of this work is to improve the performance of the charge equilibration (QEq) method on shared memory architectures. A number of parallel incomplete LU-based preconditioning techniques are explored to enhance the performance of the Krylov subspace methods used in the QEq model. Detailed analysis of how these techniques effect convergence rate and the overall solver performance is presented. ILU-based schemes which produce good quality factors with relatively low number of nonzeros have been observed to yield significant speedups over the diagonal inverse baseline preconditioner. These results are significant as they can enable efficient simulations of moderate-sized systems on a single node with several cores, and also because they can constitute the future building blocks for distributed memory parallel solvers.