Show simple item record

dc.contributor.advisorWolf, Matthew
dc.contributor.authorDayal, Jai
dc.date.accessioned2017-01-11T14:05:56Z
dc.date.available2017-01-11T14:05:56Z
dc.date.created2016-12
dc.date.issued2016-11-17
dc.date.submittedDecember 2016
dc.identifier.urihttp://hdl.handle.net/1853/56355
dc.description.abstractThe trend to exascale is causing researchers to rethink the entire computa- tional science stack, as future generation machines will contain both diverse hardware environments and run times that manage them. Additionally, the science applications themselves are stepping away from the traditional bulk-synchronous model and are moving towards a more dynamic and decoupled environment where analysis routines are run in situ alongside the large scale simulations. This thesis presents CoApps, a middleware that allows in situ science analytics applications to operate in a location-flexible manner. Additionally, CoApps explores methods to extract information from, and issue management operations to, lower level run times that are managing the diverse hardware expected to be found on next generation exascale machines. This work leverages experience with several extremely scalable applications in materials and fusion, and has been evaluated on machines ranging from local Linux clusters to the supercomputer Titan.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectIn situ
dc.subjectHigh performance computing
dc.subjectBig data
dc.subjectCode coupling
dc.subjectWorkflows
dc.titleMiddleware for large scale in situ analytics workflows
dc.typeDissertation
dc.description.degreePh.D.
dc.contributor.departmentComputer Science
thesis.degree.levelDoctoral
dc.contributor.committeeMemberGavrilovsk, Ada
dc.contributor.committeeMemberLofstead, Gerald
dc.contributor.committeeMemberPande, Santosh
dc.contributor.committeeMemberLiu, Ling
dc.date.updated2017-01-11T14:05:56Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record