基于任务行为-分析的功耗优化机制

基于任务行为-分析的功耗优化机制

ID:31981051

大小:24.47 MB

页数:75页

时间:2019-01-30

基于任务行为-分析的功耗优化机制_第1页
基于任务行为-分析的功耗优化机制_第2页
基于任务行为-分析的功耗优化机制_第3页
基于任务行为-分析的功耗优化机制_第4页
基于任务行为-分析的功耗优化机制_第5页
资源描述:

《基于任务行为-分析的功耗优化机制》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、AbstractABSTRACTWiththeemergenceofmulti-colearchitectureandrapidpromotionofcpufrequency,thepowerconsumptionthusoccurredgainsmoleandmoreattention.Standbytimehasbecomeamajorcriterionforsmartphone.Ateachleveloftop.downpoweroptimizationdesign,OSlevelpoweroptimizationhaswidercontrollablerange、short

2、erdesigncycleandlessinfluenceonsystemperformance,whichisthereasonwhywefocusonit。However,traditionalmethodsrarelyfocusonthefundamentalfactorwhichistherunningtask,andineffectivepredictiontosystemloadisbecomingthebottleneckoftraditionalmethods.Thispaperstartedwithinvestigatingtaskbehavior,analyze

3、dthecorrelationbetweentaskbehaviorandthepowerconsumptionofthesystem.Thenweextractedcriticalinformationwhichcanbeusedtopredictsystemloadofthenextstagefromtaskinformation.Finally’combinedcriticalinformationwithpoweroptimizationtechniquesalreadyexistedanddynamichardwarecontroltorealizepoweroptimi

4、zation.Inthethesis,Ihaveinvestigatedexistinglowpowermanagementtechniques,suchasdynamicvoltageandfrequencyscaling,partialarrayselfrefresh,dynamicpowermanagementandlowpowercompilertechniquesetc.Besides,byanalyzingthedetailedimplementationinOperatingSystem,wediscoveredthedeficienciesofcurrentpowe

5、rmanagement.Thenweproposedanovdpoweroptimizationpolicywhichisbasedontaskbehavioranalysis.Themainresearchworkinthethesisinclude:1.SurveyedcurrentresearchachievementsandstatusforpoweroptimizationJanalyzedtheimplementationindetailofpowermanagementinIinuxkernelandpointedouttheparswhichshouldbeimpr

6、oved.2.Investigatedthemainmeansoftaskbehavioranalysisandtherelationbetweenbehaviorandsystempowerconsumption.introducedthemotivationforpoweroptimizationbasedontaskbehaviorandprovedthefeasibilitybyreplicationexperiment.3.Analyzedtaskbehavioroncpuandt/Odevices.Besides,weextractedthecriticalinform

7、ationwhichcanbeusedtopredicttaskloadinthefollowingstage,andconstructthetaskbehaviorfeatureIibrary.4.AppliedfeaturelibrarytoOSlevelpoweroptimizationsuchasDVFSandIIIAbstractDPM,confirmthecorrectnessbyexperimentaldata.5.Appliedtaskbehavior

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。