Show simple item record

dc.contributor.advisorQasem, Apan
dc.contributor.authorHay, Richard G. ( )
dc.date.accessioned2014-12-04T19:37:02Z
dc.date.available2014-12-04T19:37:02Z
dc.date.issued2014-11
dc.identifier.citationHay, R. (2014). Machine learning based DVFS for energy efficient execution of multithreaded workloads (Unpublished thesis). Texas State University, San Marcos, Texas.
dc.identifier.urihttps://digital.library.txstate.edu/handle/10877/5363
dc.description.abstractConcerns over high power consumption of large computations and data centers have been growing in recent years. Many software and hardware strategies for reducing power have been proposed as remedies. Dynamic voltage and frequency scaling (DVFS) is one technique that can be effective if given expert knowledge. However, DVFS effectiveness is sensitive to workload characteristics and architectural parameters. Lack of knowledge can hurt DVFS strategies and render it ineffective. This thesis presents a supervised machine learning (ML) strategy for automatically making smart DVFS decisions to improve energy efficiency of multi threaded and multiprogram workloads. The technique uses hardware performance counters to construct feature vectors that capture program behavior and thread interaction in a meaningful way. The resulting models have high accuracy in picking optimal frequencies. Experimental results on contemporary benchmark suite show that application of a ML technique is able to reduce energy consumption by as much as 24% on memory-intensive workloads.
dc.formatText
dc.format.extent50 pages
dc.format.medium1 file (.pdf)
dc.language.isoen_US
dc.subjectDVFS
dc.subjectMachine Learning
dc.subjectPower-aware scheduling
dc.subjectEnergy efficiency
dc.subject.lcshMachine learningen_US
dc.subject.lcshComputer networks--Energy conservationen_US
dc.subject.lcshElectronic data processing--Distributed processing--Energy conservationen_US
dc.subject.lcshGreen technologyen_US
dc.titleMachine Learning Based DVFS for Energy Efficient Execution of Multithreaded Workloads
txstate.documenttypeThesis
dc.contributor.committeeMemberTamir, Dan
dc.contributor.committeeMemberSalamy, Hassan
thesis.degree.departmentComputer Scienceen_US
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.grantorTexas State Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
txstate.departmentComputer Science


Download

Thumbnail

This item appears in the following Collection(s)

Show simple item record