MRI: Acquisition of a Scalable Parallel Supercomputer for the Science Vision Center

MRI：为科学视觉中心采购一台可扩展并行超级计算机

• 批准号: 9871088
• 负责人: Michael Palis
• 金额: $ 14.84万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1998
• 资助国家: 美国
• 起止时间: 1998-09-01 至 2001-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9871088&HistoricalAwards=false
• 关键词: MRI; Acquisition; Scalable; Parallel; Supercomputer

EIA-9871088 Palis, Michael A. Burke, Kieron Rutgers University Camden MRI: Acquisition of a Scalable Parallel Supercomputer for the Science Vision Center This proposal requests the acquisition of a scalable parallel supercomputer that will provide the computational power to handle the scientific computing requirement of researchers at the Science Vision Center. The specific equipment requested is a Silicon Graphics Origin 2000 Scalable Parallel server with four R10000 processors, 1 gigabyte of memory, and 18 gigabytes of disk storage. This powerful system is expected to deliver at least 10-fold improvement in performance over the conventional workstations on which most of the applications are currently being run. This proposal also requests four Silicon Graphics 02 client workstations, which will be used primarily for applications development, debugging, and data visualization. Together with equipment already on hand, the parallel server and client workstations will be set up as a network, which will also serve as the testbed for the High-performance Distributed Object Programming Environment Project. The goal of this project is to design a CORBA-based parallel/distributed programming environment that will harness the combined power of the parallel server and the workstations to solve large scale parallel applications.

Palis, Michael a . Burke， Kieron Rutgers University Camden MRI：为科学视觉中心获得一台可扩展的并行超级计算机本提案要求获得一台可扩展的并行超级计算机，该计算机将提供计算能力来处理科学视觉中心研究人员的科学计算需求。具体要求的设备是一台Silicon Graphics Origin 2000可扩展并行服务器，具有4个R10000处理器、1gb内存和18gb磁盘存储。与目前运行大多数应用程序的传统工作站相比，这个强大的系统预计将提供至少10倍的性能改进。该提案还需要四个Silicon Graphics 02客户端工作站，主要用于应用程序开发、调试和数据可视化。与现有设备一起，并行服务器和客户端工作站将建立一个网络，该网络也将作为高性能分布式对象编程环境项目的测试平台。该项目的目标是设计一个基于corba的并行/分布式编程环境，该环境将利用并行服务器和工作站的组合能力来解决大规模并行应用程序。