A Recursive Hypergraph Bipartitioning Framework for Reducing Bandwidth and Latency Costs Simultaneously

buir.contributor.authorAykanat, Cevdet
dc.citation.epage358en_US
dc.citation.issueNumber2en_US
dc.citation.spage345en_US
dc.citation.volumeNumber28en_US
dc.contributor.authorSelvitopi, O.en_US
dc.contributor.authorAcer, S.en_US
dc.contributor.authorAykanat, Cevdeten_US
dc.date.accessioned2018-04-12T11:02:48Z
dc.date.available2018-04-12T11:02:48Z
dc.date.issued2017en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.description.abstractIntelligent partitioning models are commonly used for efficient parallelization of irregular applications on distributed systems. These models usually aim to minimize a single communication cost metric, which is either related to communication volume or message count. However, both volume- and message-related metrics should be taken into account during partitioning for a more efficient parallelization. There are only a few works that consider both of them and they usually address each in separate phases of a two-phase approach. In this work, we propose a recursive hypergraph bipartitioning framework that reduces the total volume and total message count in a single phase. In this framework, the standard hypergraph models, nets of which already capture the bandwidth cost, are augmented with message nets. The message nets encode the message count so that minimizing conventional cutsize captures the minimization of bandwidth and latency costs together. Our model provides a more accurate representation of the overall communication cost by incorporating both the bandwidth and the latency components into the partitioning objective. The use of the widely-adopted successful recursive bipartitioning framework provides the flexibility of using any existing hypergraph partitioner. The experiments on instances from different domains show that our model on the average achieves up to 52 percent reduction in total message count and hence results in 29 percent reduction in parallel running time compared to the model that considers only the total volume. © 2016 IEEE.en_US
dc.description.provenanceMade available in DSpace on 2018-04-12T11:02:48Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 179475 bytes, checksum: ea0bedeb05ac9ccfb983c327e155f0c2 (MD5) Previous issue date: 2017en
dc.identifier.doi10.1109/TPDS.2016.2577024en_US
dc.identifier.issn1045-9219en_US
dc.identifier.urihttp://hdl.handle.net/11693/37099en_US
dc.language.isoEnglishen_US
dc.publisherIEEE Computer Societyen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/TPDS.2016.2577024en_US
dc.source.titleIEEE Transactions on Parallel and Distributed Systemsen_US
dc.subjectCommunication costen_US
dc.subjectBandwidthen_US
dc.subjectLatencyen_US
dc.subjectPartitioningen_US
dc.subjectHypergraphen_US
dc.subjectRecursive bipartitioningen_US
dc.subjectLoad balancingen_US
dc.subjectSparse matrix vector multiplicationen_US
dc.subjectResource allocationen_US
dc.subjectCombinatorial scientific computingen_US
dc.titleA Recursive Hypergraph Bipartitioning Framework for Reducing Bandwidth and Latency Costs Simultaneouslyen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
A Recursive Hypergraph Bipartitioning.pdf
Size:
900.38 KB
Format:
Adobe Portable Document Format
Description:
Full printable version