MRI: Acquisition of a High-Performance Computing Cluster Environment in Support of Scientific and Engineering Applications

MRI：获取高性能计算集群环境以支持科学和工程应用

• 批准号: 0619285
• 负责人: Andrew Sargent
• 金额: $ 40万
• 依托单位: East Carolina University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2006
• 资助国家: 美国
• 起止时间: 2006-09-01 至 2009-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0619285&HistoricalAwards=false
• 关键词: MRI; Acquisition; Performance; Computing; Cluster

This project, acquiring a high-performance distributed-memory cluster, will enable computationally aggressive techniques to be applied in a variety of disciplines. This cluster is designed to support the following projects:-Investigating the role of solvent in catalytic organometallic transformations,-Study of arthropod evolutionary diversification,-Computational fluid dynamics development of advanced engines,-Molecular dynamics simulations of the voltage-gated potassium channel, Kv1.3,-Study of p53-binding S100 proteins,-All-electron studies on the explosive nature of organic molecular crystals, and-Strategies to reduce the risk associated with the atmospheric emission of Hg compounds.Each of these applications is discussed and computational methods to be employed and their hardware and software requirements are presented. A system including fast interconnect and up to 256 processors with 2 GBytes of local memory, accompanied by several TBytes of online storage, is proposed.

这个项目，获得一个高性能的分布式内存集群，将使计算积极的技术被应用于各种学科。该集群旨在支持以下项目：-调查溶剂在催化有机金属转化中的作用，-研究节肢动物进化多样化，-先进发动机的计算流体动力学开发，-电压门控钾通道Kv1.3的分子动力学模拟，-研究p53结合S100蛋白，-有机分子晶体爆炸性质的全电子研究，以及-减少汞化合物大气排放风险的战略，讨论了这些应用中的每一个，并提出了将采用的计算方法及其硬件和软件要求。本文提出了一个包括快速互连和多达256个处理器的系统，该系统具有2Gbit的本地存储器，并伴有几Tbit的在线存储器。