- -

Workload Characterization for Exascale Computing Networks

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

Workload Characterization for Exascale Computing Networks

Show simple item record

Files in this item

dc.contributor.author Duro-Gómez, José es_ES
dc.contributor.author Petit Martí, Salvador Vicente es_ES
dc.contributor.author Sahuquillo Borrás, Julio es_ES
dc.contributor.author Gómez Requena, María Engracia es_ES
dc.date.accessioned 2018-11-09T11:53:12Z
dc.date.available 2018-11-09T11:53:12Z
dc.date.issued 2018-11-09
dc.identifier.isbn 978-1-5386-7877-0 es_ES
dc.identifier.uri http://hdl.handle.net/10251/112204
dc.description.abstract [EN] Exascale computing is the next step in high performance computing provided by systems composed of millions of interconnected processing cores. In order to guide the design and implementation of such systems, multiple workload characterization studies and system performance evaluations are required. This paper provides a workload characterization study in the context of the European Project ExaNeSt, which focuses, among others, on developing the network technology required to implement future exascale systems. In this work, we characterize different ExaNeSt applications from the computer network perspective by analyzing the distribution of messages, the dynamic bandwidth consumption, and the spatial communication patterns among cores. The analysis highlights three main observations; i) message sizes are, in general, below 50 kB; ii) communication patterns are usually bursty; and iii) spatial communication among cores concentrate in hot spots for most applications. Taking into account these observations, one can conclude that in order to unclog congested network links, an exascale network must be designed to briefly support higher-than-average bandwidths in the vicinity of key network cores. es_ES
dc.description.sponsorship This work was supported by the ExaNest project, funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 671553, and by the Spanish Ministerio de Econom´ıa y Competitividad (MINECO) and Plan E funds under Grant TIN2015-66972-C5-1-R.
dc.format.extent 7
dc.language Inglés
dc.publisher IEEE Computer Society es_ES
dc.relation info:eu-repo/grantAgreement/MINECO//TIN2015-66972-C5-1-R/ES/TECNICAS PARA LA MEJORA DE LAS PRESTACIONES, COSTE Y CONSUMO DE ENERGIA DE LOS SERVIDORES/
dc.relation.ispartof 2018 International Conference on High Performance Computing & Simulation (HPCS)
dc.rights Reserva de todos los derechos
dc.subject Workload characterization es_ES
dc.subject Exascale computing es_ES
dc.subject MPI es_ES
dc.title Workload Characterization for Exascale Computing Networks es_ES
dc.type Comunicación en congreso es_ES
dc.identifier.doi 10.1109/HPCS.2018.00069 es_ES
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/671553/EU/European Exascale System Interconnect and Storage/
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Informática de Sistemas y Computadores - Departament d'Informàtica de Sistemes i Computadors es_ES
dc.description.bibliographicCitation Duro-Gómez, J.; Petit Martí, SV.; Sahuquillo Borrás, J.; Gómez Requena, ME. (2018). Workload Characterization for Exascale Computing Networks. IEEE Computer Society. 383-389. https://doi.org/10.1109/HPCS.2018.00069 es_ES
dc.description.accrualMethod S es_ES
dc.relation.conferencename International Conference on High Performance Computing & Simulation (HPCS) es_ES
dc.relation.conferencedate July 16-20, 2018 es_ES
dc.relation.conferenceplace Orléans, France es_ES
dc.relation.publisherversion http://doi.org/10.1109/HPCS.2018.00069
dc.description.upvformatpinicio 383 es_ES
dc.description.upvformatpfin 389 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.relation.pasarela S\366789 es_ES
dc.contributor.funder European Commission
dc.contributor.funder Ministerio de Economía y Competitividad


This item appears in the following Collection(s)

Show simple item record