Energy study of Monte Carlo and Quasi-Monte Carlo algorithms for solving integral equations

Simple item page
dc.creatorVassil Nikolov Alexandrov
dc.date2016
dc.date.accessioned2018-10-18T15:34:03Z
dc.date.available2018-10-18T15:34:03Z
dc.descriptionIn the past few years the development of exascale computing technology necessitated to obtain an estimate for the energy consumption when large-scale problems are solved with different high-performance computing (HPC) systems. In this paper we study the energy efficiency of a class of Monte Carlo (MC) and Quasi-Monte Carlo (QMC) algorithms for a given integral equation using hybrid HPC systems. The algorithms are applied to solve quantum kinetic integral equations describing ultra-fast transport in quantum wire. We compare the energy performance of the algorithms using a GPU-based computer platform and CPU-based computer platform both with and without hyper-threading (HT) technology. We use SPRNG library and CURAND generator to produce parallel pseudo-random (PPR) sequences for the MC algorithms on CPU-based and GPU-based platforms, respectively. For our QMC algorithms Sobol and Halton sequences are used to produce parallel quasi-random (PQR) sequences. We compare the obtained results of the tested algorithms with respect to the given energy metric. The results of our study demonstrate the importance of taking into account not only scalability of the HPC intensive algorithms but also their energy efficiency They also show the need for further optimisation of the QMC algorithms when GPU-based computing platforms are used. © The Authors. Published by Elsevier B.V.
dc.identifier.doi10.1016/j.procs.2016.05.492
dc.identifier.endpage1905
dc.identifier.issn18770509
dc.identifier.startpage1897
dc.identifier.urihttp://hdl.handle.net/11285/630251
dc.identifier.volume80
dc.languageeng
dc.publisherElsevier B.V.
dc.relationhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84978505393&doi=10.1016%2fj.procs.2016.05.492&partnerID=40&md5=918b054c3b3b648c3e09336d3ebcb3d8
dc.relationInvestigadores
dc.relationEstudiantes
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0
dc.sourceProcedia Computer Science
dc.subjectAlgorithms
dc.subjectEnergy utilization
dc.subjectIntegral equations
dc.subjectMonte Carlo methods
dc.subjectOptimization
dc.subjectQuantum chemistry
dc.subjectSemiconductor quantum wires
dc.subjectComputing platform
dc.subjectEnergy performance
dc.subjectEnergy studies
dc.subjectExascale computing
dc.subjectHigh performance computing systems
dc.subjectLarge-scale problem
dc.subjectMonte carlo and quasi-monte carlo algorithms
dc.subjectQuasi-monte carlo algorithms
dc.subjectEnergy efficiency
dc.subject.classification7 INGENIERÍA Y TECNOLOGÍA
dc.titleEnergy study of Monte Carlo and Quasi-Monte Carlo algorithms for solving integral equations
dc.typeConferencia
refterms.dateFOA2018-10-18T15:34:03Z

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S1877050916309796.pdf
Size:
477.97 KB
Format:
Adobe Portable Document Format
Download

Collections

Ítem publicado en memoria de congreso
logo

El usuario tiene la obligación de utilizar los servicios y contenidos proporcionados por la Universidad, en particular, los impresos y recursos electrónicos, de conformidad con la legislación vigente y los principios de buena fe y en general usos aceptados, sin contravenir con su realización el orden público, especialmente, en el caso en que, para el adecuado desempeño de su actividad, necesita reproducir, distribuir, comunicar y/o poner a disposición, fragmentos de obras impresas o susceptibles de estar en formato analógico o digital, ya sea en soporte papel o electrónico. Ley 23/2006, de 7 de julio, por la que se modifica el texto revisado de la Ley de Propiedad Intelectual, aprobado

DSpace software copyright © 2002-2025

Licencia