dc.contributor.author | Hellås, Yngve | |
dc.date.accessioned | 2019-01-07T16:17:29Z | |
dc.date.available | 2019-01-07T16:17:29Z | |
dc.date.issued | 2018-12-19 | |
dc.date.submitted | 2018-12-18T23:00:03Z | |
dc.identifier.uri | https://hdl.handle.net/1956/18842 | |
dc.description.abstract | We look at multiple GPU programming, using the connected components algorithm as the basis when we look into libraries and runtime environment for multiple GPU programming. We also show that Rem is a fast parallel algorithm, that perform better than previously implemented algorithms. | en_US |
dc.language.iso | eng | eng |
dc.publisher | The University of Bergen | en_US |
dc.subject | parallel programming | eng |
dc.subject | Rem | eng |
dc.subject | Connected components | eng |
dc.subject | CUDA | eng |
dc.subject | GPU | eng |
dc.title | Computing Connected Components on Multiple GPUs | en_US |
dc.type | Master thesis | |
dc.date.updated | 2018-12-18T23:00:03Z | |
dc.rights.holder | Copyright the Author. All rights reserved | en_US |
dc.description.degree | Masteroppgave i informatikk | en_US |
dc.description.localcode | INF399 | |
dc.subject.nus | 754199 | eng |
fs.subjectcode | INF399 | |
fs.unitcode | 12-12-0 | |