Understanding Congestion in High Performance Interconnection Networks Using Sampling

Simple item page
dc.contributor.advisorMellor-Crummey, John Men_US
dc.creatorTaffet, Philip Adamen_US
dc.date.accessioned2018-11-26T18:01:00Zen_US
dc.date.available2018-11-26T18:01:00Zen_US
dc.date.created2018-05en_US
dc.date.issued2018-04-30en_US
dc.date.submittedMay 2018en_US
dc.date.updated2018-11-26T18:01:01Zen_US
dc.description.abstractThe computational needs of many applications outstrip the capabilities of a single compute node. Communication is necessary to employ multiple nodes, but slow communication often limits application performance on multiple nodes. To improve communication performance, developers need tools that enable them to understand how their application’s communication patterns interact with the network, especially when those interactions result in congestion. Since communication performance is difficult to reason about analytically and simulation is costly, measurement-based approaches are needed. This thesis describes a new sampling-based technique to collect information about the path a packet takes and congestion it encounters. Experiments with simulations show that this strategy can distinguish problems with an application's communication patterns, its mapping onto a parallel system, and outside interference. We describe a variant of this scheme that requires only 5-6 bits of information in a monitored packet, making it practical for use in next-generation networks.en_US
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationTaffet, Philip Adam. "Understanding Congestion in High Performance Interconnection Networks Using Sampling." (2018) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/103413">https://hdl.handle.net/1911/103413</a>.en_US
dc.identifier.doihttps://doi.org/10.25611/0pec-yd57en_US
dc.identifier.urihttps://hdl.handle.net/1911/103413en_US
dc.language.isoengen_US
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.subjectnetwork congestionen_US
dc.subjectreservoir samplingen_US
dc.subjectprobabilisticen_US
dc.subjecthigh performance computingen_US
dc.subjectnetwork simulationen_US
dc.subjectInfiniBanden_US
dc.subjectinterconnection networksen_US
dc.subjectcommunication performanceen_US
dc.subjectOmni-Pathen_US
dc.subjectMPIen_US
dc.titleUnderstanding Congestion in High Performance Interconnection Networks Using Samplingen_US
dc.typeThesisen_US
dc.type.materialTexten_US
thesis.degree.departmentComputer Scienceen_US
thesis.degree.disciplineEngineeringen_US
thesis.degree.grantorRice Universityen_US
thesis.degree.levelMastersen_US
thesis.degree.majorHigh Performance Computingen_US
thesis.degree.nameMaster of Scienceen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
TAFFET-DOCUMENT-2018.pdf
Size:
6.13 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.61 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Theses and Dissertations