NVNMD-v2:基于非诺曼架构的可扩展和准确的深度学习分子动力模型
Xiaoyun Yu1, Guang Yang1, Zhuoying Zhao1
1College of Electrical and Information Engineering, Hunan University, Changsha 410082, China.
Journal of chemical theory and computation
|September 3, 2025
概括
NVNMD-v2加速了复杂材料的分子动力学 (MD) 模拟. 这种新的框架使得大规模精确的原子模拟能够减少能源消耗,从而推动材料科学研究.
科学领域:
- 计算材料科学
- 化学中的人工智能
- 高性能计算
背景情况:
- 机器学习分子动力学 (MLMD) 努力平衡复杂材料的精度,可扩展性和能效.
- 现有的MLMD框架在处理多元系统和扩展到大原子数方面是有限的.
研究的目的:
- 介绍NVNMD-v2,用于增强MLMD模拟的集成算法硬件架构.
- 克服先前的MLMD方法在精度,可扩展性和复杂系统的能源效率方面的局限性.
- 为大型多元材料模拟提供量子精确的分子动力学.
主要方法:
- 开发了NVNMD-v2,一个共同设计的算法硬件架构,在内存处理 (PIM) 加速器上具有通用深度神经网络潜力 (GDNNP).
- 实现了优化的类型嵌入描述符,以支持多达32个元素的系统,消除了取决于物种的参数缩放.
- 在单个FPGA上部署NVNMD-v2系统.
主要成果:
- NVNMD-v2可实现多元系统的DFT级精度,支持多达32种物种.
- 证明每原子的计算成本为每原子大约10^-7秒.
- 启用高达2000万个原子的模拟,在NVIDIA V100 GPU上对DeePMD进行1000倍的扩展,并减少了120倍的能量.
结论:
- NVNMD-v2显著提升了MLMD对复杂多元材料的功能.
- 共同设计的架构可以在前所未有的规模和能源效率上解锁量子精确的模拟.
- 这一突破弥合了原子真实性和工业规模模拟之间的差距.
更多相关视频
09:17Structure-Based Simulation and Sampling of Transcription Factor Protein Movements along DNA from Atomic-Scale Stepping to Coarse-Grained Diffusion
Published on: March 1, 2022
3.2K
11:29Novel 3D/VR Interactive Environment for MD Simulations, Visualization and Analysis
Published on: December 18, 2014
12.0K
相关概念视频
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
100
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
100
02:00Molecular Models
40.4K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
40.4K
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
126
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
126