A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics
This addresses efficiency and energy consumption problems for researchers and practitioners in computational chemistry and materials science, representing an incremental improvement through specialized hardware design.
The paper tackled the computational expense of machine learning molecular dynamics by proposing a heterogeneous parallel system using FPGA and ASIC, achieving 1.6x faster speed and 10^2-10^3x better energy efficiency compared to GPU-based state-of-the-art methods while maintaining similar accuracy.
This paper proposes a special-purpose system to achieve high-accuracy and high-efficiency machine learning (ML) molecular dynamics (MD) calculations. The system consists of field programmable gate array (FPGA) and application specific integrated circuit (ASIC) working in heterogeneous parallelization. To be specific, a multiplication-less neural network (NN) is deployed on the non-von Neumann (NvN)-based ASIC (SilTerra 180 nm process) to evaluate atomic forces, which is the most computationally expensive part of MD. All other calculations of MD are done using FPGA (Xilinx XC7Z100). It is shown that, to achieve similar-level accuracy, the proposed NvN-based system based on low-end fabrication technologies (180 nm) is 1.6x faster and 10^2-10^3x more energy efficiency than state-of-the-art vN based MLMD using graphics processing units (GPUs) based on much more advanced technologies (12 nm), indicating superiority of the proposed NvN-based heterogeneous parallel architecture.