Mostra el registre d'ítem simple

dc.contributor.authorRivas-Gomez, Sergio
dc.contributor.authorPeña, Antonio J.
dc.contributor.authorMoloney, David
dc.contributor.authorLaure, Erwin
dc.contributor.authorMarkidis, Stefano
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2018-09-21T10:51:21Z
dc.date.available2018-09-21T10:51:21Z
dc.date.issued2018-08-06
dc.identifier.citationRivas-Gomez, S. [et al.]. Exploring the Vision Processing Unit as Co-Processor for Inference. A: "2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)". IEEE, 2018, p. 589-598.
dc.identifier.isbn978-1-5386-5555-9
dc.identifier.urihttp://hdl.handle.net/2117/121386
dc.description.abstractThe success of the exascale supercomputer is largely debated to remain dependent on novel breakthroughs in technology that effectively reduce the power consumption and thermal dissipation requirements. In this work, we consider the integration of co-processors in high-performance computing (HPC) to enable low-power, seamless computation offloading of certain operations. In particular, we explore the so-called Vision Processing Unit (VPU), a highly-parallel vector processor with a power envelope of less than 1W. We evaluate this chip during inference using a pre-trained GoogLeNet convolutional network model and a large image dataset from the ImageNet ILSVRC challenge. Preliminary results indicate that a multi-VPU configuration provides similar performance compared to reference CPU and GPU implementations, while reducing the thermal-design power (TDP) up to 8x in comparison.
dc.description.sponsorshipThe experimental results were performed on resources provided by the Swedish National Infrastructure for Computing (SNIC) at PDC Centre for High-Performance Com- puting (PDC-HPC). The work was funded by the European Commission through the SAGE project (Grant agreement no. 671500 / http://www.sagestorage.eu).
dc.format.extent10 p.
dc.language.isoeng
dc.publisherIEEE
dc.subjectÀrees temàtiques de la UPC::Informàtica
dc.subject.lcshHigh performance computing
dc.subject.lcshMachine learning
dc.subject.otherVision Processing Unit
dc.subject.otherHigh-Performance Computing
dc.subject.otherMachine Learning
dc.titleExploring the Vision Processing Unit as Co-Processor for Inference
dc.typeConference lecture
dc.subject.lemacSupercomputadors
dc.identifier.doi10.1109/IPDPSW.2018.00098
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/8425465/
dc.rights.accessOpen Access
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/H2020/671500/EU/SAGE/SAGE
local.citation.publicationName2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
local.citation.startingPage589
local.citation.endingPage598


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple