首页> 外文会议>Real-Time Computing Systems and Applications, 2000. Proceedings. Seventh International Conference on >Schedulability-aware mapping of real-time object-oriented models to multi-threaded implementations
【24h】

Schedulability-aware mapping of real-time object-oriented models to multi-threaded implementations

机译:面向对象的实时模型的可调度性感知映射到多线程实现

获取原文

摘要

The object oriented design methods and their CASE tools are widely used in practice by many real time software developers. However, object oriented CASE tools require an additional step of identifying tasks from a given design model. Unfortunately, it is difficult to automate this step for a couple of reasons: (1) there are inherent discrepancies between objects and tasks; and (2) it is hard to derive tasks while maximizing real time schedulability, since this problem makes a non-trivial optimization problem. As a result, in practical object oriented CASE tools, task identification is usually performed in an ad hoc manner using hints provided by human designers. We present a systematic, schedulability-aware approach that can help mapping real time object oriented models to multithreaded implementations. In our approach, a task contains a group of mutually exclusive transactions that may possess different periods and deadline. For this new task model, we provide a schedulability analysis algorithm. We also show how the run-time system is implemented and how executable code is generated in our framework. We have performed a case study. It shows the difficulty of the task derivation problem and the utility of the automated synthesis of implementation.
机译:面向对象的设计方法及其CASE工具在许多实时软件开发人员的实践中得到了广泛使用。但是,面向对象的CASE工具需要额外的步骤才能从给定的设计模型中识别任务。不幸的是,由于以下几个原因很难使这一步骤自动化:(1)对象和任务之间存在固有的差异; (2)在最大化实时可调度性的同时,很难派生任务,因为这个问题带来了一个非平凡的优化问题。结果,在实用的面向对象的CASE工具中,通常使用人工设计人员提供的提示以临时的方式执行任务识别。我们提出了一种系统的,可调度的感知方法,可以帮助将面向对象的实时模型映射到多线程实现。在我们的方法中,任务包含一组互斥的事务,这些事务可能具有不同的期限和截止日期。对于此新任务模型,我们提供了可调度性分析算法。我们还将展示如何实现运行时系统以及如何在我们的框架中生成可执行代码。我们已经进行了案例研究。它显示了任务派生问题的难度以及实现的自动化综合的实用性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号