Show simple item record

dc.contributor.advisorTaylor, Valerie E.en_US
dc.creatorLively, Charlesen_US
dc.date.accessioned2012-07-16T15:58:46Zen_US
dc.date.accessioned2012-07-16T20:31:30Z
dc.date.available2014-09-16T07:28:21Z
dc.date.created2012-05en_US
dc.date.issued2012-07-16en_US
dc.date.submittedMay 2012en_US
dc.identifier.urihttp://hdl.handle.net/1969.1/ETD-TAMU-2012-05-11095en_US
dc.description.abstractPower consumption is an important constraint in achieving efficient execution on High Performance Computing Multicore Systems. As the number of cores available on a chip continues to increase, the importance of power consumption will continue to grow. In order to achieve improved performance on multicore systems scientific applications must make use of efficient methods for reducing power consumption and must further be refined to achieve reduced execution time. In this dissertation, we introduce a performance modeling framework, E-AMOM, to enable improved execution of scientific applications on parallel multicore systems with regards to a limited power budget. We develop models for each application based upon performance hardware counters. Our models utilize different performance counters for each application and for each performance component (runtime, system power consumption, CPU power consumption, and memory power consumption) that are selected via our performance-tuned principal component analysis method. Models developed through E-AMOM provide insight into the performance characteristics of each application that affect performance for each component on a parallel multicore system. Our models are more than 92% accurate across both Hybrid (MPI/OpenMP) and MPI implementations for six scientific applications. E-AMOM includes an optimization component that utilizes our models to employ run-time Dynamic Voltage and Frequency Scaling (DVFS) and Dynamic Concurrency Throttling to reduce power consumption of the scientific applications. Further, we optimize our applications based upon insights provided by the performance models to reduce runtime of the applications. Our methods and techniques are able to save up to 18% in energy consumption for Hybrid (MPI/OpenMP) and MPI scientific applications and reduce the runtime of the applications up to 11% on parallel multicore systems.en_US
dc.format.mimetypeapplication/pdfen_US
dc.language.isoen_USen_US
dc.subjectPerformance Modelingen_US
dc.subjectPower consumptionen_US
dc.subjectMulticoreen_US
dc.subjectParallel Programmingen_US
dc.subjectMPIen_US
dc.subjectHybriden_US
dc.subjectPower predictionen_US
dc.titleE-AMOM: An Energy-Aware Modeling and Optimization Methodology for Scientific Applications on Multicore Systemsen_US
dc.typeThesisen
thesis.degree.departmentComputer Science and Engineeringen_US
thesis.degree.disciplineComputer Engineeringen_US
thesis.degree.grantorTexas A&M Universityen_US
thesis.degree.nameDoctor of Philosophyen_US
thesis.degree.levelDoctoralen_US
dc.contributor.committeeMemberKim, Eun Jungen_US
dc.contributor.committeeMemberButler-Purry, Karen L.en_US
dc.contributor.committeeMemberWilliams, Tiffanien_US
dc.type.genrethesisen_US
dc.type.materialtexten_US
local.embargo.terms2014-07-16en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record