Show simple item record

dc.contributor.advisorTamir, Dan
dc.contributor.authorBrock, Matthew V. ( )en_US
dc.date.accessioned2012-02-24T10:19:06Z
dc.date.available2012-02-24T10:19:06Z
dc.date.issued2010-08en_US
dc.identifier.citationBrock, M. V. (2010). Feature selection for slice-based workload characterization and power estimation (Unpublished thesis). Texas State University-San Marcos, San Marcos, Texas.
dc.identifier.urihttps://digital.library.txstate.edu/handle/10877/3903
dc.description.abstractModeling a microprocessor results in defining its architecture (instruction set, registers, memory hierarchy, etc.), its microarchitecture (pipelines, branch prediction,etc.), and its hardware (gate level logic, cycleaccurate timing, circuitry, etc.). Several software based modeling tools exist for describing and facilitating simulation of the microprocessor model. Simulation at the hardware or system level in order to estimate power consumption is time consuming due to the complexity and size of the system level model. Simulation at the architecture level is significantly faster, but less detailed. If the simulation trace data generated by the architecture simulation are highly correlated with the operations of system level simulation, only part of the benchmark test may be required for simulation at the system level. In other words, if a number of trace sections, or slices, are identified as similar, then the corresponding instruction stream slices will yield similar power estimation results when simulated at the system level. Thus,identifying similar slices of the architectural simulation trace data may reduce the amount of benchmark testing required at the system level. Cluster analysis is used to identify similar slices of the architectural simulation trace data, resulting in clusters of slices. Feature selection is used to eliminate less relevant features within the trace data, allowing for better clustering. Finally, domain-specific knowledge is applied by prioritizing feature selection towards known power-affecting features. Experimentation demonstrates the effectiveness of the cluster analysis, feature selection, and use of power affecting features in order to achieve accurate power estimation while reducing the amount of benchmark testing required at the system level of simulation.en_US
dc.formatText
dc.format.extent105 pages
dc.format.medium1 file (.pdf)
dc.language.isoen_US
dc.subjectWorkloaden_US
dc.subjectCharacterizationen_US
dc.subjectFeatureen_US
dc.subjectSelectionen_US
dc.subjectPoweren_US
dc.subjectEstimationen_US
dc.subjectMicroprocessoren_US
dc.subjectSimulationen_US
dc.subject.classificationComputer Sciencesen_US
dc.titleFeature Selection for Slice-Based Workload Characterization and Power Estimationen_US
txstate.documenttypeThesis
dc.contributor.committeeMemberNgu, Anne
dc.contributor.committeeMemberKaikhah, Khosrow
dc.contributor.committeeMemberHolt, James
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