Machine and Algorithm Design for Highly Parallel General Purpose Computation

高度并行通用计算的机器和算法设计

• 批准号: 8713489
• 负责人: Gary Miller
• 金额: $ 16.76万
• 依托单位: University of Southern California
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1987
• 资助国家: 美国
• 起止时间: 1987-11-01 至 1991-03-01
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=8713489&HistoricalAwards=false
• 关键词: Machine; Algorithm; Design; Highly; Parallel

The goal of this research project is to better understand how to efficiently use the present generation of parallel computers and to influence the design of the next generation. The bulk of the research will be in the design of processor efficient parallel algorithms for abstract machines that possess a message passing architecture such as the Parallel Random Access Machine. The problems under investigation include the breadth first search of an undirected graph. Special attention will be given to architectures where the individual processors contain a relatively large amount of local memory. Message passing schemes which efficiently simulate the local memory model will be considered.

这个研究项目的目的是为了更好地了解如何有效地使用当前一代并行计算机，并影响下一代的设计。研究的主要内容是为具有消息传递架构的抽象机器（如并行随机存取机）设计处理器高效并行算法。研究的问题包括无向图的广度优先搜索。我们将特别关注单个处理器包含相对大量本地内存的体系结构。将考虑有效地模拟局部内存模型的消息传递方案。