Accurate and efficient molecular dynamics based on machine learning and non von Neumann architecture

Force field-based classical molecular dynamics (CMD) is efficient but its potential energy surface (PES) prediction error can be very large. Density functional theory (DFT)-based ab-initio molecular dynamics (AIMD) is accurate but computational cost limits its applications to small systems. Here, we propose a molecular dynamics (MD) methodology which can simultaneously achieve both AIMD-level high accuracy and CMD-level high efficiency. The high accuracy is achieved by exploiting deep neural network (DNN’s) arbitrarily-high precision to fit PES. The high efficiency is achieved by deploying multiplication-less DNN on a carefully-optimized special-purpose non von Neumann (vN) computer to mitigate the performance-limiting data shuttling (i.e., “memory wall bottleneck”). By testing on different molecules and bulk systems, we show that the proposed MD methodology is generally applicable to various MD tasks. The proposed MD methodology has been deployed on an in-house computing server based on reconfigurable field programmable gate array (FPGA), which is freely available at http://nvnmd.pipc.vip.

Pinghui Mo, Chang Li, Dan Zhao, Yujia Zhang, Mengchao Shi, Junhua Li, Jie Liu