Priority Scheduling for Interactive Applications

Priority Scheduling for Interactive Applications
复制标题

交互式应用程序的优先级调度

DOI:
10.1145/3350755.3400236
复制
发表时间:
2020
期刊:
Proceedings of the 32nd ACM Symposium on Parallelism in Algorithms and Architectures
影响因子:
--
通讯作者:
Acar, Umut A.
Acar, Umut A.
中科院分区:
--
文献类型:
--
作者:
Singer, Kyle;Goldstein, Noah;Muller, Stefan K.;Agrawal, Kunal;Lee, I-Ting Angelina;Acar, Umut A.

文献摘要

参考文献

被引文献

相似文献

许多现代并行应用程序,如桌面软件和基于云的web服务,都是面向服务的、长时间运行的,并执行与外部世界的频繁交互(例如,响应用户输入)。我们希望这样的交互式应用程序提供快速的响应时间,因为通常在外部交互的另一端有一个用户在等待响应。为多核硬件设计的现有并行平台不适用于此类交互式应用程序,因为它们的设计目的是最大化吞吐量(而不是响应速度)。交互式应用程序可能同时发生交互式和计算密集型任务,调度器必须能够识别任务并确定任务的优先级,以便需要更快响应的任务优先于后台任务。我们提出交互式Cilk,或简称I-Cilk,一个任务并行平台,旨在调度这种并行交互式应用程序。I-Cilk支持一个基于c++的模板库,它允许程序员为任务并行代码指定优先级,底层运行时调度计算,以优化高优先级任务的响应时间。我们证明了I-Cilk使用的调度算法为所有优先级的任务提供了有效的响应时间,并且对高优先级的任务具有更好的响应时间。实践证明,该调度算法可以有效地实现,调度开销低,对高优先级任务的响应时间快。
Many modern parallel applications, such as desktop software and cloud-based web services, are service-oriented, long running, and perform frequent interactions with the external world (e.g., responding to user input). We want such interactive applications to provide fast response times because typically at the other end of the external interaction there is a user waiting for a response. Existing parallel platforms designed for multicore hardware do not work well for such interactive applications, because they are designed to maximize throughput (rather than responsiveness). Interactive applications may have a mixture of interactive and compute-intensive tasks occurring concurrently, and the scheduler must be able to discern and prioritize tasks so that tasks which require faster response are prioritized over background tasks.We present Interactive Cilk, or I-Cilk for short, a task parallel platform designed to schedule such parallel interactive applications. I-Cilk supports a C++-based templated library that allows the programmer to specify priorities for task-parallel code, and the underlying runtime schedules the computation so as to optimize for the response time of high-priority tasks. We show that the scheduling algorithm used by I-Cilk provides provably efficient response times for tasks at all levels of priorities, with better response time to high-priority tasks. We also empirically demonstrate that the scheduling algorithm can be implemented efficiently in practice with low scheduling overhead and provides fast response times for high-priority tasks.
安排并行程序的能力
DOI: --
发表时间: 2018
期刊: IEEE International Parallel and Distributed Processing Symposium
影响因子: --
作者:
Kunal Agrawal;Seth Gilbert
通讯作者: Seth Gilbert
响应式并行计算:桥接竞争线程和协作线程
DOI: 10.1145/3062341.3062370
发表时间: 2017
期刊: Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation
影响因子: --
作者:
Stefan K. Muller;Umut A. Acar;R. Harper
通讯作者: R. Harper
与 future 和 state 的响应式并行
DOI: 10.1145/3385412.3386013
发表时间: 2020
期刊: Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation
影响因子: --
作者:
Muller, Stefan K.;Singer, Kyle;Goldstein, Noah;Acar, Umut A.;Agrawal, Kunal;Lee, I-Ting Angelina
通讯作者: Lee, I-Ting Angelina
在线调度并行 DAG 作业以最小化平均流程时间
DOI: --
发表时间: 2016
期刊: ACM-SIAM Symposium on Discrete Algorithms
影响因子: --
作者:
Kunal Agrawal;Jing Li;Kefu Lu;Benjamin Moseley
通讯作者: Benjamin Moseley
通过可配置的调度策略窃取工作
DOI: --
发表时间: 2013
期刊: ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming
影响因子: --
作者:
Martin Wimmer;Daniel Cederman;J. Träff;P. Tsigas
通讯作者: P. Tsigas