NGS: Collaborative Research: An OpenMP Environment for Wide-Area Network Computing

NGS：协作研究：用于广域网计算的 OpenMP 环境

• 批准号: 0103582
• 负责人: Rudolf Eigenmann
• 金额: $ 34.95万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-09-15 至 2006-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0103582&HistoricalAwards=false
• 关键词: NGS; Collaborative; Research; OpenMP; Environment

EIA-0103582Rudolf EigenmannPurdue Research FoundationNGS: Collaborative Research: An OpenMP Environment for Wide-Area Network ComputingThe objective of this proposal is to develop a new programming system that will close the gap that exists between programming SMPs and networked computer clusters, by using the emerging standard (OpenMP) for SMPs and develop compiler and runtime support that will enable using OpenMP on distributed platforms with optimized performance. The proposed programming system will make it possible to program the Grid and networked computer systems using OpenMP, the emerging standard for shared-memory programming. The PI expects to attain high efficiency in the execution of OpenMP programs for collection of Grid-connected computers. Through static and dynamic compiler techniques, we expect to harness the complexity and load fluctuations of the target environment.

EIA-0103582 Rudolf EigenmannPurdue研究基金会NGS：合作研究：用于广域网计算的OpenMP环境本提案的目标是开发一种新的编程系统，该系统将缩小编程SMP和联网计算机集群之间存在的差距，通过使用新兴标准（OpenMP）并开发编译器和运行时支持，以使在分布式平台上使用OpenMP具有优化的性能。 建议的编程系统将使人们有可能使用OpenMP，共享内存编程的新兴标准的网格和联网的计算机系统进行编程。 PI希望在执行并网计算机集合的OpenMP程序时实现高效率。 通过静态和动态编译技术，我们希望利用目标环境的复杂性和负载波动。