Algorithms for Memory Hierarchies

内存层次结构算法

• 批准号: 1000226885-2011
• 负责人: Zeh, Norbert
• 金额: $ 1.82万
• 依托单位: Dalhousie University
• 依托单位国家: 加拿大
• 项目类别: Canada Research Chairs
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=642713
• 关键词: Algorithms; Memory; Hierarchies

The trend towards increasingly powerful computers with multi-core processors continues, but the sizes of the data sets we collect and process increase even faster. Traditional algorithms prove unable to fully utilize the power of modern computers in order to process massive data sets in a timely fashion. In particular, there is a need for algorithms that combine parallelism with efficient use of caches, main memory, and hard drives. This is the focus of the applicant's research with particular emphasis on geometric and graph problems motivated by applications in areas including business intelligence, geographic information systems, database systems, and web technology.

配备多核处理器的计算机越来越强大的趋势仍在继续，但我们收集和处理的数据集的大小增长得更快。 传统的算法无法充分利用现代计算机的能力来及时处理大量数据集。 特别地，需要将联合收割机并行性与高速缓存、主存储器和硬盘驱动器的有效使用相结合的算法。 这是申请人的研究重点，特别强调在商业智能，地理信息系统，数据库系统和网络技术等领域的应用程序所激发的几何和图形问题。