Show simple item record

dc.contributor.authorAlonso-Jordá, Pedro
dc.contributor.authorCatalán, Sandra
dc.contributor.authorHerrero, José R.
dc.contributor.authorQuintana Ortí, Enrique S.
dc.contributor.authorRodríguez Sánchez, Rafael
dc.date.accessioned2019-05-16T09:51:53Z
dc.date.available2019-05-16T09:51:53Z
dc.date.issued2018
dc.identifier.citationALONSO, Pedro, et al. Two-sided orthogonal reductions to condensed forms on asymmetric multicore processors. Parallel Computing, 2018, vol. 78, p. 85-100.ca_CA
dc.identifier.issn0167-8191
dc.identifier.urihttp://hdl.handle.net/10234/182506
dc.description.abstractWe investigate how to leverage the heterogeneous resources of an Asymmetric Multicore Processor (AMP) in order to deliver high performance in the reduction to condensed forms for the solution of dense eigenvalue and singular-value problems. The routines that realize this type of two-sided orthogonal reductions (TSOR) in LAPACK are especially challenging, since a significant fraction of their floating-point operations are cast in terms of memory-bound kernels while the remaining part corresponds to efficient compute-bound kernels. To deal with this scenario: (1) we leverage implementations of memory-bound and compute-bound kernels specifically tuned for AMPs; (2) we select the algorithmic block size for the TSOR routines via a practical model; and (3) we adjust the type and number of cores to use at each step of the reduction. Our experiments validate the model and assess the performance of our asymmetry-aware TSOR routines, using an ARMv7 big.LITTLE AMP, for three key operations: the reduction to tridiagonal form for symmetric eigenvalue problems, the reduction to Hessenberg form for non-symmetric eigenvalue problems, and the reduction to bidiagonal form for singular-value problems.ca_CA
dc.format.extent16 p.ca_CA
dc.language.isoengca_CA
dc.publisherElsevierca_CA
dc.relation.isPartOfParallel Computing, Volume 78, October 2018.ca_CA
dc.rights0167-8191/© 2018 Elsevier B.V. All rights reserved.ca_CA
dc.subjectDense linear algebraca_CA
dc.subjectCondensed formsca_CA
dc.subjectEigenvalue problemsca_CA
dc.subjectSingular-value problemsca_CA
dc.subjectAsymmetric multicore processorsca_CA
dc.subjectHeterogeneous computingca_CA
dc.subjectMulti-threadingca_CA
dc.subjectWorkload balancingca_CA
dc.titleTwo-sided orthogonal reductions to condensed forms on asymmetric multicore processorsca_CA
dc.typeinfo:eu-repo/semantics/articleca_CA
dc.identifier.doihttps://doi.org/10.1016/j.parco.2018.03.005
dc.relation.projectIDTIN2014-53495-R ; PROMETEOII/2014/003 ; TIN2015-65316-P ; 2014 SGR 1051ca_CA
dc.rights.accessRightsinfo:eu-repo/semantics/restrictedAccessca_CA
dc.relation.publisherVersionhttps://www.sciencedirect.com/science/article/pii/S0167819118300784ca_CA
dc.type.versioninfo:eu-repo/semantics/publishedVersionca_CA


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record