课题基金 / 基金详情

U.S.-France (INRIA) Cooperative Research: Parallel Scientific Computation

U.S.-France (INRIA) Cooperative Research: Parallel Scientific Computation
美法(INRIA)合作研究:并行科学计算
批准号:
8714471
负责人:
David Kuck
金额:
$2.14万
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
1988
资助国家:
美国
项目状态:
已结题
起止时间:
1988-04-15 至 1991-09-30

项目摘要

项目成果

David Kuck的其他基金

相似基金

相关文献

中文摘要
翻译
该奖项将支持伊利诺伊大学超级计算研究与开发中心(CSRD)和法国国家信息科学与自动化研究所(INRIA)两组美国和法国科学家在并行科学计算方面正在进行的合作研究。美国小组将由David Kuck博士和Ahmed Sameh博士领导;法国方面的项目将由INRIA-Irisa的J.Lenfant教授以及INRIA/Paris的A.Lichnewsky和W.Jalby教授领导。联合研究将集中在三个方面:1.并行算法-稠密矩阵计算-有限元和稀疏矩阵计算-组合优化方法2.体系结构--内存组织和层次--流水线处理器3.编译时优化-并行检测-优化内存层次结构-架构中的细粒度并行性这项研究加入了美国和法国两组杰出的科学计算研究人员的行列。INRIA因其集中了计算机研究、自动化、数学和科学计算方面的专业知识而得到广泛认可;它将基础研究与这些领域的工业合作完美地结合在一起。这一奖项将允许在及时和重要的并行计算领域继续进行富有成效的合作。
英文摘要
This award will support ongoing collaborative research in parallel scientific computation between two groups of U.S. and French scientists, based at the University of Illinois Center for Supercomputing Research and Development (CSRD) and at the French National Institute for Information Science and Automation (INRIA). The U.S. group will be led by Drs. David Kuck and Ahmed Sameh; on the French side the projects will be led by Professor J. Lenfant, (INRIA-IRISA) and Professors A. Lichnewsky and W. Jalby, both at INRIA/Paris. The joint research will focus on three topics: 1. Parallel algorithms -Dense Matrix computations -Finite element and sparse matrix computations -Combinatorial optimization methods 2. Architectures -Memory organizations and hierarchies -Pipeline processors 3. Compile-time optimization -Parallel detection -Optimization for memory hierarchies -Fine grain parallelism in architectures This research joins two groups of outstanding U.S. and French researchers in scientific computation. INRIA is widely recognized for its concentration of expertise in computer research, automation, mathematics and scientific computing; it provides an excellent combination of fundamental research with industrial collaboration in these areas. This award will allow fruitful collaboration to continue in the timely and important area of parallel computing.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Methodology for Performance Evaluation for High Performance Computer Systems
Software Studies for Multiprocessors and Memory Hierarchies
Cedar System Prototype
Computer System Organization
海外基金