Latency analysis of self-suspending task chains
Latency analysis of self-suspending task chains
复制标题
DOI：
10.23919/date54114.2022.9774655
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Tomasz Kloda;Jiyang Chen;A. Bertout;L. Sha;M. Caccamo
中科院分区：
文献类型：
--
作者：
Tomasz Kloda;Jiyang Chen;A. Bertout;L. Sha;M. Caccamo
许多网络物理系统正在将计算量大的程序卸载到硬件加速器（例如 GPU 和 TPU），以减少执行时间。这些应用程序将在将数据卸载到加速器和获取返回结果之间自我挂起。先前的研究表明，自挂起的任务可能会导致调度异常，但没有人检查过任务间通信。本文旨在探索具有周期性激活和异步消息传递的自挂任务的数据链延迟。我们首先介绍暂停引起的延迟的原因和最坏情况的延迟分析。然后，我们提出了利用硬件协处理器来减少数据链延迟和可调度性分析的规则。仿真结果表明，所提出的策略可以改善整体延迟，同时保持系统的可调度性。
Many cyber-physical systems are offloading computation-heavy programs to hardware accelerators (e.g., GPU and TPU) to reduce execution time. These applications will self-suspend between offloading data to the accelerators and obtaining the returned results. Previous efforts have shown that self-suspending tasks can cause scheduling anomalies, but none has examined inter-task communication. This paper aims to explore self-suspending tasks' data chain latency with periodic activation and asynchronous message passing. We first present the cause for suspension-induced delays and worst-case latency analysis. We then propose a rule for utilizing the hardware co-processors to reduce data chain latency and schedulability analysis. Simulation results show that the proposed strategy can improve overall latency while preserving system schedulability.