CSR: Small: A Comprehensive Framework for Real-Time Multiprocessor Synchronization

多核技术的出现推动了最近关于设计、部署和验证实时应用程序的多处理器实现方法的许多工作。这种方法必须植根于资源分配技术，以促进可预测的系统设计。在这类技术的研究中，分配处理器时间的调度算法受到了最大的关注。协调对其他资源的访问的同步算法受到的关注要少得多。当前关于实时多处理器同步的最新技术是，可以支持简单的锁定协议，但其他的就不多了。这是一个严重的障碍，限制了实时应用程序向“多核就绪”版本的发展。在此驱动下，该项目正在开发一套丰富的多处理器实时同步机制。这些机制是由实际应用需求驱动的，正如在at&t和诺斯罗普·格鲁曼公司的调查人员和行业同事的联合工作中出现的那样。这些机制的设计是为了在几个系统模型中使用，也是出于实际需要。其中包括存在各种复杂性的模型，例如具有不同关键度的任务、必须彼此“隔离”的多个子系统、异构硬件组件、动态任务行为等。在所有这些工作中，最优同步协议的设计是重点。这些协议正在unc制作的开源实时Linux扩展LITMUS^RT中进行原型和评估。更广泛的影响将包括继续与业界同事进行联合研究，以及开发可供其他机构用于研究和教学目的的公开可用的开源软件。

The advent of multicore technologies has fueled much recent work on methods for designing, deploying, and verifying multiprocessor implementations of real-time applications. Such methods must necessarily be rooted in resource allocation techniques that facilitate predictable system designs. In work on such techniques, scheduling algorithms, which allocate processor time, have received the greatest attention. Synchronization algorithms, which coordinate access to other resources, have received much less attention.The current state-of-the-art regarding real-time multiprocessor synchronization is that simple locking protocols can be supported, but not much else. This is a serious impediment that is limiting the evolution of real-time applications to "multicore-ready" versions. Driven by this, a rich set of multiprocessor real-time synchronization mechanisms is being developed in this project. These mechanisms are motivated by real application needs, as have arisen in joint work involving the investigators and industry colleagues at AT&T and Northrop Grumman. Such mechanisms are being designed for use within several system models, also motivated by real needs. These include models wherein various complexities exist, such as having tasks of differing criticalities, multiple subsystems that must be "isolated" from one another, heterogeneous hardware components, dynamic task behaviors, etc. In all of this work, the design of optimal synchronization protocols is being emphasized. These protocols are being prototyped and evaluated within a open-source UNC-produced real-time Linux extension called LITMUS^RT. Broader impacts will include continued joint research with industry colleagues, and the development of publicly-available open-source software that can be used by other institutions for research and teaching purposes.