A General Framework for Hard-Real-Time Application System Design

硬实时应用系统设计的通用框架

• 批准号: 9972105
• 负责人: Sanjoy Baruah
• 金额: $ 7.5万
• 依托单位: University of North Carolina at Chapel Hill
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1999
• 资助国家: 美国
• 起止时间: 1999-09-15 至 2001-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9972105&HistoricalAwards=false
• 关键词: General; Framework; Hard; Real; Time

PROPOSAL NUMBER: CCR-9972105TITLE: A General Framework for Hard-Real-Time Application System DesignPI: Sanjoy K BaruahThe rate-monotonic analysis (RMA) methodology is a powerful and popular formalmethodology for the design, analysis, and implementation of hard-real-timecomputer application systems. This project proposes to address certainshortcomings of RMA --- its restrictive task model, and the limited optionsavailable in the methodology for overcoming resource-sharing bottlenecks.Morespecifically, the goals of this project will be:--- designing new abstract models of real-time tasks that may more accuratelyreflect important properties of application systems, and identifying rules formapping application systems onto the most appropriate models.--- analysing various task models in order to enhance our understanding ofwhatintrinsic properties render a model infeasible from a static-priorityfeasibility analysis point of view, and identifying very general classes oftractable models.--- determining methods (algorithms/ heuristics) for assigning appropriatepriorities to tasks specified in these general models.--- designing algorithms for overcoming resource-sharing bottlenecks, byobtaining a deeper understanding of the nature of typical shared resources andby exploiting their unique characteristics, and--- building software that both validates the usefulness of the theoreticalresults, and makes these results available to the system designer.

提案编号：速率单调分析（RMA）方法是一种用于设计、分析和实现硬实时计算机应用系统的强大而流行的形式化方法。 本项目针对RMA的某些缺点-受限的任务模型，以及克服资源共享瓶颈的方法学上的有限选择，提出了以下目标：-设计新的实时任务抽象模型，更准确地反映应用系统的重要属性，并确定将应用系统映射到最合适的模型上的规则。分析各种任务模型，以增强我们对从静态优先可行性分析的角度来看，什么内在属性使模型不可行的理解，并识别非常通用的易处理模型类别。确定方法（算法/算法），为这些通用模型中指定的任务分配适当的优先级。设计克服资源共享瓶颈的算法，通过获得对典型共享资源的性质的更深入的理解，并通过利用其独特的特性，以及-构建既验证理论结果的有用性，又使这些结果可用于系统设计者的软件。