CSR-AES: Feedback-Driven Adaptive Multithreading

本研究计画探讨如何扩充动态多执行绪的可扩充模型，使其包含三个关键功能-多重程式设计、处理器间通讯及支援I/O -而不需要费力的手动规划、调优或组态。研究特别侧重于使用可证明良好的“反馈驱动”战略来实现这一目标。研究人员正在开发一个多程序多线程系统，以体现这些战略，并提供一个研究工具，发现其他属性的互动自适应工作。正在研究的技术之一是“基于历史的反馈”，它为可证明有效的调度和资源分配策略提供了一个有希望的基础。这项研究希望使多处理器更有效率，更容易被绝大多数计算机用户使用，而不仅仅是专家级的计算机科学家。在研究过程中开发的开源软件可以在万维网上免费提供给任何人。关于多处理器调度的课程材料是通过麻省理工学院的开放式课程项目分发的。

This research project investigates how to extend the scalable model ofdynamic multithreading to encompass three key functionalities ---multiprogramming, interprocess communication, and support for I/O ---without requiring painstaking manual planning, tuning, or configuring. The research focuses particularly on using provably good``feedback-driven'' strategies to accomplish this end. Theresearchers are developing a multiprogrammed multithreaded system toembody these strategies and provide a research vehicle for discovering additional properties of interacting adaptive jobs. Among thetechniques under study is ``history-based feedback,'' which offers apromising foundation for provably effective scheduling and resourceallocation strategies. This research hopes to make multiprocessors more efficient and easierto use by the vast majority of computer users, not just by expertcomputer scientists. Open-source software developed in the course ofthe research is freely available to anyone on the World Wide Web. Course materials on multiprocessor scheduling are distributed via theMIT OpenCourseWare project.