Implementations and Evaluations of Non-Numerical Algorithms for MIMD Multiprocessors

MIMD 多处理器非数值算法的实现和评估

• 批准号: 8717569
• 负责人: Peter Varman
• 金额: --
• 依托单位: William Marsh Rice University
• 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: 1987-11-15 至 1990-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=8717569&HistoricalAwards=false
• 关键词: Implementations; Evaluations; Non; Numerical; Algorithms

Multiprocessor supercomputers presently available on the market are oriented towards high-speed numerical computation. However, there is more tendency to use computers for computations that are symbolic in nature. Nonnumerical algorithms for multiprocessors are more difficult to design and evaluate than numerical algorithms. This research is aimed at developing a new and integrated methodology for the design and performance prediction of nonnumerical parallel and distributed algorithms for multiprocessors. Because of the unpredictable behavior of such algorithms, and the dependency of algorithm performance on data values, simulation is a fundamental ingredient of the methodology. The facility developed for simulating the execution of multiprocessor algorithms on uniprocessors will be expanded, improved and tuned to the purpose of this research. The simulator is trace-driven. Simulation results will be used to validate existing or new analytical or hybrid modeling techniques.

目前市场上可获得的多处理器超级计算机是 面向高速数值计算。 不过有 越来越倾向于使用计算机进行符号化的计算， 自然 多处理器的非数值算法更困难 比数值算法更容易设计和评估。 本研究是 目的是为设计和开发一种新的综合方法， 非数值并行分布式性能预测 多处理器的算法。 因为不可预测的行为 以及算法性能对数据的依赖性 价值观，模拟是一个基本要素的方法。 的 为模拟多处理机的执行而开发的一种设施 单处理器上的算法将得到扩展、改进和调整， 本研究的目的。模拟器是跟踪驱动的。 仿真 结果将用于验证现有或新的分析或混合 建模技术