Show simple item record

dc.contributor.authorAykanat, Cevdeten_US
dc.contributor.authorÖzgü, Özlemen_US
dc.contributor.authorGüven, N.en_US
dc.coverage.spatialAntalya, Turkeyen_US
dc.date.accessioned2016-02-08T12:01:41Z
dc.date.available2016-02-08T12:01:41Z
dc.date.issued1994en_US
dc.identifier.urihttp://hdl.handle.net/11693/27784
dc.descriptionDate of Conference: 12-14 April 1994en_US
dc.descriptionConference Name: 7th Mediterranean Electrotechnical Conference, MELECON 1994en_US
dc.description.abstractVector processors have promised an enormous increase in computing speed for computationally intensive and time-critical power system problems which require the repeated solution of sparse linear equations. Due to short vectors processed in these applications, standard sparsity-based algorithms need to be restructured for efficient vectorization. This paper presents a novel data storage scheme and an efficient vectorization algorithm that exploits the intrinsic architectural features of vector computers such as sectioning and chaining. As the benchmark, the solution phase of the Fast Decoupled Load Flow algorithm is used in simulations. The relative performances of the proposed and existing vectorization schemes are evaluated, both theoretically and experimentally, on IBM 3090/VF.en_US
dc.language.isoEnglishen_US
dc.source.titleProceedings of the 7th Mediterranean Electrotechnical Conference, MELECON 1994en_US
dc.relation.isversionofhttps://doi.org/10.1109/MELCON.1994.380916en_US
dc.subjectAlgorithmsen_US
dc.subjectComputer simulationen_US
dc.subjectData storage equipmenten_US
dc.subjectData structuresen_US
dc.subjectDigital arithmeticen_US
dc.subjectElectric power systemsen_US
dc.subjectMatrix algebraen_US
dc.subjectPipeline processing systemsen_US
dc.subjectProgram compilersen_US
dc.subjectVectorsen_US
dc.subjectFast decoupled load flowen_US
dc.subjectForward/backward substitutionsen_US
dc.subjectSparse linear equationsen_US
dc.subjectVector computeren_US
dc.subjectVectorizationen_US
dc.subjectComputer architectureen_US
dc.titleEfficient vectorization of forward/backward substitutions in solving sparse linear equationsen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage309en_US
dc.citation.epage312en_US
dc.identifier.doi10.1109/MELCON.1994.380916en_US
dc.publisherIEEEen_US
dc.contributor.bilkentauthorAykanat, Cevdet


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record