Cache-Related Preemption Delay Analysis for Multilevel Noninclusive Caches

Sudipta Chattopadhyay, Abhik Roychoudhury
{"title":"Cache-Related Preemption Delay Analysis for Multilevel Noninclusive Caches","authors":"Sudipta Chattopadhyay, Abhik Roychoudhury","doi":"10.1145/2632156","DOIUrl":null,"url":null,"abstract":"With the rapid growth of complex hardware features, timing analysis has become an increasingly difficult problem. The key to solving this problem lies in the precise and scalable modeling of performance-enhancing processor features (e.g., cache). Moreover, real-time systems are often multitasking and use preemptive scheduling, with fixed or dynamic priority assignment. For such systems, cache related preemption delay (CRPD) may increase the execution time of a task. Therefore, CRPD may affect the overall schedulability analysis. Existing works propose to bound the value of CRPD in a single-level cache. In this article, we propose a CRPD analysis framework that can be used for a two-level, noninclusive cache hierarchy. In addition, our proposed framework is also applicable in the presence of shared caches. We first show that CRPD analysis faces several new challenges in the presence of a multilevel, noninclusive cache hierarchy. Our proposed framework overcomes all such challenges and we can formally prove the correctness of our framework. We have performed experiments with several subject programs, including an unmanned aerial vehicle (UAV) controller and an in-situ space debris monitoring instrument. Our experimental results suggest that we can provide sound and precise CRPD estimates using our framework.","PeriodicalId":183677,"journal":{"name":"ACM Trans. Embed. Comput. Syst.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Trans. Embed. Comput. Syst.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2632156","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8

Abstract

With the rapid growth of complex hardware features, timing analysis has become an increasingly difficult problem. The key to solving this problem lies in the precise and scalable modeling of performance-enhancing processor features (e.g., cache). Moreover, real-time systems are often multitasking and use preemptive scheduling, with fixed or dynamic priority assignment. For such systems, cache related preemption delay (CRPD) may increase the execution time of a task. Therefore, CRPD may affect the overall schedulability analysis. Existing works propose to bound the value of CRPD in a single-level cache. In this article, we propose a CRPD analysis framework that can be used for a two-level, noninclusive cache hierarchy. In addition, our proposed framework is also applicable in the presence of shared caches. We first show that CRPD analysis faces several new challenges in the presence of a multilevel, noninclusive cache hierarchy. Our proposed framework overcomes all such challenges and we can formally prove the correctness of our framework. We have performed experiments with several subject programs, including an unmanned aerial vehicle (UAV) controller and an in-situ space debris monitoring instrument. Our experimental results suggest that we can provide sound and precise CRPD estimates using our framework.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
多级非包容缓存的缓存相关抢占延迟分析
随着复杂硬件特性的快速增长,时序分析已成为一个越来越困难的问题。解决这个问题的关键在于对性能增强的处理器特性(例如缓存)进行精确和可扩展的建模。此外,实时系统通常是多任务的,并使用抢占式调度,具有固定或动态的优先级分配。对于这样的系统,缓存相关抢占延迟(CRPD)可能会增加任务的执行时间。因此,CRPD可能会影响整体可调度性分析。现有的工作建议将CRPD的值绑定在单级缓存中。在本文中,我们提出了一个CRPD分析框架,该框架可用于两级非包容性缓存层次结构。此外,我们提出的框架也适用于存在共享缓存的情况。我们首先展示了CRPD分析在多级非包容性缓存层次结构中面临的几个新挑战。我们提出的框架克服了所有这些挑战,我们可以正式证明我们框架的正确性。我们已经进行了几个主题项目的实验,包括一个无人机(UAV)控制器和一个原位空间碎片监测仪器。我们的实验结果表明,我们可以使用我们的框架提供健全和精确的CRPD估计。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Hardware Acceleration for Embedded Keyword Spotting: Tutorial and Survey Adaptive Computation Reuse for Energy-Efficient Training of Deep Neural Networks Horizontal Auto-Scaling for Multi-Access Edge Computing Using Safe Reinforcement Learning IoT-Fog-Cloud Centric Earthquake Monitoring and Prediction Horizontal Side-Channel Vulnerabilities of Post-Quantum Key Exchange and Encapsulation Protocols
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1