Pinghui Mo
YOU?
Author Swipe
View article: DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials Open
In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications…
View article: Accelerated Atomistic Modeling of Phase Change Memory Using Deep Neural Network and Specialized Hardware
Accelerated Atomistic Modeling of Phase Change Memory Using Deep Neural Network and Specialized Hardware Open
Atomistic simulations offer valuable insights into phase change memory (PCM) device research and development. Current methods, such as density functional theory (DFT) and machine learning interatomic potential (ML-IAP), face limitations in…
View article: High-speed and low-power molecular dynamics processing unit (MDPU) with ab initio accuracy
High-speed and low-power molecular dynamics processing unit (MDPU) with ab initio accuracy Open
Molecular dynamics (MD) is an indispensable atomistic-scale computational tool widely-used in various disciplines. In the past decades, nearly all ab initio MD and machine-learning MD have been based on the general-purpose central/graphics…
View article: DeePMD-kit v2: A software package for deep potential models
DeePMD-kit v2: A software package for deep potential models Open
DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used in …
View article: DeePMD-kit v2: A software package for Deep Potential models
DeePMD-kit v2: A software package for Deep Potential models Open
DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials (MLP) known as Deep Potential (DP) models. This package, which was released in 2017, has been widely us…
View article: A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics
A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics Open
This paper proposes a special-purpose system to achieve high-accuracy and\nhigh-efficiency machine learning (ML) molecular dynamics (MD) calculations. The\nsystem consists of field programmable gate array (FPGA) and application\nspecific i…
View article: Accurate and efficient molecular dynamics based on machine learning and non von Neumann architecture
Accurate and efficient molecular dynamics based on machine learning and non von Neumann architecture Open
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 computat…
View article: Electrical-field-induced magnetic Skyrmion ground state in a two-dimensional chromium tri-iodide ferromagnetic monolayer
Electrical-field-induced magnetic Skyrmion ground state in a two-dimensional chromium tri-iodide ferromagnetic monolayer Open
Using fully first-principles non-collinear self-consistent field density functional theory (DFT) calculations with relativistic spin-orbital coupling effects, we show that, by applying an out-of-plane electrical field on a free-standing tw…