{"title":"Deadline-aware Memory Scheduler and Governor for Heterogeneous Processors","authors":"Xue-Xin He, Ya-Shu Chen","doi":"10.1109/INDIN.2018.8471962","DOIUrl":null,"url":null,"abstract":"Mobile systems are usually equipped with heterogeneous processors and memories to trade off power and performance. The energy-efficient scheduling of such system is difficulty from two folders: tasks executed on such system with the end-to-end deadline and with varied power consumption from the heterogeneous component. A deadline-aware scheduler is proposed to deal with the performance degradation from memory bandwidth contention. A DVFS governor to manage processors and memory, and the run-time memory overclocking reclaiming are presented to minimize the energy consumption while maintaining the performance. Evaluation results show considerable schedulability and energy conservation using this framework.","PeriodicalId":6467,"journal":{"name":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","volume":"20 1","pages":"239-244"},"PeriodicalIF":0.0000,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 16th International Conference on Industrial Informatics (INDIN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INDIN.2018.8471962","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Mobile systems are usually equipped with heterogeneous processors and memories to trade off power and performance. The energy-efficient scheduling of such system is difficulty from two folders: tasks executed on such system with the end-to-end deadline and with varied power consumption from the heterogeneous component. A deadline-aware scheduler is proposed to deal with the performance degradation from memory bandwidth contention. A DVFS governor to manage processors and memory, and the run-time memory overclocking reclaiming are presented to minimize the energy consumption while maintaining the performance. Evaluation results show considerable schedulability and energy conservation using this framework.