arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1001.3764physics.comp-phcond-mat.mtrl-scicond-mat.soft
收藏

基于图形处理器的高分子分子动力学模拟

Molecular Dynamics Simulation of Macromolecules Using Graphics Processing Unit

Ji Xu, Ying Ren, Wei Ge, Xiang Yu, Xiaozhen Yang, Jinghai Li

摘要:

分子动力学(MD)模拟是研究大分子体系行为的有力计算工具。但是,许多模拟这一领域的限制,在空间或时间尺度上的可用计算资源。近年来,图形处理器(GPU)为科学应用提供了前所未有的计算能力。许多MD算法都适合GPU的多线程特性。本文提出了完全在GPU上运行的大分子系统的MD算法。与在单个CPU核心上使用免费软件GROMACS进行MD模拟相比,我们的代码在单个GPU上实现了约10倍的速度提升。为了验证,我们在GPU上进行了聚合物结晶的MD模拟,观察到的结果与CPU上的计算完全一致。因此,我们的单GPU代码已经为传统CPU集群上的大分子模拟提供了一种廉价的替代方案,它们也可以用作开发并行GPU程序的基础,以进一步加速计算。

英文摘要:

Molecular dynamics (MD) simulation is a powerful computational tool to study the behavior of macromolecular systems. But many simulations of this field are limited in spatial or temporal scale by the available computational resource. In recent years, graphics processing unit (GPU) provides unprecedented computational power for scientific applications. Many MD algorithms suit with the multithread nature of GPU. In this paper, MD algorithms for macromolecular systems that run entirely on GPU are presented. Compared to the MD simulation with free software GROMACS on a single CPU core, our codes achieve about 10 times speed-up on a single GPU. For validation, we have performed MD simulations of polymer crystallization on GPU, and the results observed perfectly agree with computations on CPU. Therefore, our single GPU codes have already provided an inexpensive alternative for macromolecular simulations on traditional CPU clusters and they can also be used as a basis to develop parallel GPU programs to further speedup the computations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑