Partitioning sparse rectangular matrices for parallel computing of AAtX

Simple item page
buir.advisorAykanat, Cevdet
dc.contributor.authorUçar, Bora
dc.date.accessioned2016-01-08T20:16:17Z
dc.date.available2016-01-08T20:16:17Z
dc.date.issued1999-09
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionAnkara : Department of Computer Engineering and Information Science and The Institute of Engineering and Science of Bilkent University, 1999.en_US
dc.descriptionThesis (Master's) -- Bilkent University, 1999.en_US
dc.descriptionIncludes bibliographical references.en_US
dc.description.abstractMany scientific applications involve repeated sparse matrix-vector and matrixtranspose-vector product computations. Graph and hypergraph partitioning based approaches used in the literature aim at minimizing the total communication volume while maintaining computational load balance through one dimensional partitioning of sparse matrices. In this thesis, we consider two approaches which consider minimizing both the total message count and communication volume while maintaining balance on the communication loads of the processors. Two communication schemes are investigated for the fold and expand operations needed in the parallel algorithm. For the global communication scheme, we show that the problem of minimizing concurrent communication volume can be formulated as the problem of permuting the sparse matrix into a singly-bordered block-diagonal form, where the total and concurrent message count is determined by the interconnection topology. For the personalized communication scheme, a two stage approach is proposed. In the first stage, the total communication volume is minimized while maintaining balance on the computational loads of the processors. In the second stage, a novel communication hypergraph model is proposed which enables the minimization of the total message count while maintaining balance on the communication loads of the processors through hypergraph-partitioning-like methods. The solution methods are tested on various matrices and results, which are quite attractive in terms of solution quality and running times, are obtained.en_US
dc.description.degreeM.S.en_US
dc.description.statementofresponsibilityUçar, Boraen_US
dc.format.extentx, 74 leaves, graphicsen_US
dc.identifier.urihttp://hdl.handle.net/11693/18101
dc.language.isoEnglishen_US
dc.publisherBilkent Universityen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectSparse Rectangular Matricesen_US
dc.subjectComputational Hypergraph Modelen_US
dc.subjectCommunication Hypergraph Modelen_US
dc.subjectHypergraph Partitioningen_US
dc.subject.lccQA165 .U23 1999en_US
dc.subject.lcshPartitions (Mathematics).en_US
dc.subject.lcshHypergraph.en_US
dc.titlePartitioning sparse rectangular matrices for parallel computing of AAtXen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
B049439.pdf
Size:
3.84 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Dept. of Computer Engineering - Master's degree