Hypergraph models for parallel sparse matrix-matrix multiplication

Simple item page
buir.advisorAykanat, Cevdet
dc.contributor.authorAkbudak, Kadir
dc.date.accessioned2016-05-03T07:54:35Z
dc.date.available2016-05-03T07:54:35Z
dc.date.copyright2015-09
dc.date.issued2015-09
dc.date.submitted21-09-2015
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionCataloged from PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (leaves 102-107).en_US
dc.descriptionThesis (Ph. D.): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2015.en_US
dc.description.abstractMultiplication of two sparse matrices (i.e., sparse matrix-matrix multiplication, which is abbreviated as SpGEMM) is a widely used kernel in many applications such as molecular dynamics simulations, graph operations, and linear programming. We identify parallel formulations of SpGEMM operation in the form of C = AB for distributed-memory architectures. Using these formulations, we propose parallel SpGEMM algorithms that have the multiplication and communication phases: The multiplication phase consists of local SpGEMM computations without any communication and the communication phase consists of transferring required input/output matrices. For these algorithms, three hypergraph models are proposed. These models are used to partition input and output matrices simultaneously. The input matrices A and B are partitioned in one dimension in all of these hypergraph models. The output matrix C is partitioned in two dimensions, which is nonzero-based in the rst hypergraph model, and it is partitioned in one dimension in the second and third models. In partitioning of these hypergraph models, the constraint on vertex weights corresponds to computational load balancing among processors for the multiplication phase of the proposed SpGEMM algorithms, and the objective, which is minimizing cutsize de ned in terms of costs of the cut hyperedges, corresponds to minimizing the communication volume due to transferring required matrix entries in the communication phase of the SpGEMM algorithms. We also propose models for reducing the total number of messages while maintaining balance on communication volumes handled by processors during the communication phase of the SpGEMM algorithms. An SpGEMM library for distributed memory architectures is developed in order to verify the empirical validity of our models. The library uses MPI (Message Passing Interface) for performing communication in the parallel setting. The developed SpGEMM library is run on SpGEMM instances from various realistic applications and the experiments are carried out on a large parallel IBM BlueGene/Q system, named JUQUEEN. In the experimentation of the proposed hypergraph models, high speedup values are observed.en_US
dc.description.degreePh.D.en_US
dc.description.statementofresponsibilityby Kadir Akbudak.en_US
dc.embargo.release2017-09-21
dc.format.extentxv, 107 leaves : charts.en_US
dc.identifier.itemidB151489
dc.identifier.urihttp://hdl.handle.net/11693/29038
dc.language.isoEnglishen_US
dc.publisherBilkent Universityen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectSparse matricesen_US
dc.subjectMatrix partitioningen_US
dc.subjectParallel computingen_US
dc.subjectDistributed memory parallelismen_US
dc.subjectGeneralized matrix multiplicationen_US
dc.subjectGEMMen_US
dc.subjectSparse matrixmatrix multiplicationen_US
dc.subjectSpGEMMen_US
dc.subjectComputational hypergraph modelen_US
dc.subjectHypergraph partitioningen_US
dc.subjectBLAS (Basic Linear Algebra Subprograms) Level 3 operationsen_US
dc.subjectMolecular dynamics simulationsen_US
dc.subjectGraph operationsen_US
dc.subjectLinear programmingen_US
dc.titleHypergraph models for parallel sparse matrix-matrix multiplicationen_US
dc.title.alternativeParalel seyrek matris-matris çarpımı için hiperçizge modellerien_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
AKBUDAK-DOKTORA-TEZI.pdf
Size:
2.26 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Dept. of Computer Engineering - Ph.D. / Sc.D.