U.S.-German Cooperative Research in Computational Algebra and High-Speed Networks

美德在计算代数和高速网络方面的合作研究

• 批准号: 9722439
• 负责人: Gene Cooperman
• 金额: $ 1.65万
• 依托单位: Northeastern University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1997
• 资助国家: 美国
• 起止时间: 1997-08-15 至 1999-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9722439&HistoricalAwards=false
• 关键词: U.S.; German; Cooperative; Research; Computational

This international collaboration between the PI and Gerhard Michler at the Universitªt Gesamthochschule Essen will develop a better fit between network-based parallel architectures and applications. The U.S. personnel are experts in computer architectures, while the German group's expertise is in algebraic applications. The interaction collaboration between the two groups will result in ways to restructure underlying algorithms and better support software for parallel computations, as well as generate methods to reduce the current communications overhead between workstations. Lessons learned in solving problems associated with applications for parallel and distributed systems will benefit many other applications areas. In addition, flexible, stable, efficient, and user-friendly parallel systems will greatly benefit the computational infrastructure of science and engineering. Through this project, the U.S. group will gain access to a highly respected computer algebra group, and to the knowledge in the German national computer-algebra focus program administered by the German equivalent of NSF.

PI 和埃森综合学院的 Gerhard Michler 之间的国际合作将在基于网络的并行架构和应用程序之间开发出更好的配合。 美国团队是计算机体系结构方面的专家，而德国团队的专长是代数应用。 两个小组之间的互动合作将导致重组底层算法和更好地支持并行计算的软件，以及产生减少工作站之间当前通信开销的方法。 在解决与并行和分布式系统应用程序相关的问题中获得的经验教训将使许多其他应用领域受益。 此外，灵活、稳定、高效、用户友好的并行系统将极大有利于科学和工程的计算基础设施。 通过这个项目，美国小组将获得一个备受尊敬的计算机代数小组的机会，并获得由德国国家科学基金会 (NSF) 管理的德国国家计算机代数重点项目的知识。