Show simple item record

dc.contributor.advisorQasem, Apanen_US
dc.contributor.authorVara, Suman ( )
dc.date.accessioned2012-02-01T18:48:33Z
dc.date.available2012-02-01T18:48:33Z
dc.date.created2011-05
dc.date.issued2012-02-01en_US
dc.identifier.urihttps://digital.library.txstate.edu/handle/10877/2451
dc.description.abstractEmergence of multicore architectures has opened up new opportunities for thread-level parallelism and dramatically increased the theoretical peak on current systems. However, achieving a high fraction of peak performance requires careful orchestration of many architecture-sensitive parameters. In particular, the presence of shared-caches on multicore architectures makes it necessary to consider, in concert, issues related to both parallelism and data locality. This research evaluates the shared-cache performance of several scientic kernels. A synthetic microbenchmark along with hardware performance counter measurements are used to estimate cache sharing among multiple threads in parallel applications. A novel reuse-distance based algorithm is developed to identify correlations between reused distance patterns and shared-cache utilization.en_US
dc.formatText
dc.format.extent53 pages
dc.format.medium1 file (.pdf)
dc.language.isoen_US
dc.subjectParallilism
dc.subjectMulticoreen_US
dc.subject.lcshHigh performance computingen_US
dc.subject.lcshParallel processing (Electronic computers)en_US
dc.subject.lcshMemory management (Computer science)en_US
dc.subject.lcshAdaptive computing systemsen_US
dc.titleEvaluating Shared-Cache Performance with Microbenchmarks and Reuse Distance Analysisen_US
txstate.documenttypeThesis
dc.contributor.committeeMemberHazlewood, Carolen_US
dc.contributor.committeeMemberMcKenney, Marken_US
thesis.degree.departmentComputer Science
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.grantorTexas State Universityen_US
thesis.degree.levelMasters
thesis.degree.nameMaster of Science
txstate.departmentComputer Science


Download

Thumbnail

This item appears in the following Collection(s)

Show simple item record