Show simple item record

Benchmarking Deep Neural Network Inference Performance on Serverless Environments With MLPerf

dc.contributor.authorElordi Hidalgo, Unai
dc.contributor.authorUnzueta Irurtia, Luis
dc.contributor.authorGoenetxea Imaz, Jon
dc.contributor.authorSánchez Carballido, Sergio
dc.contributor.authorArganda Carreras, Ignacio
dc.contributor.authorOtaegui Madurga, Oihana
dc.date.accessioned2024-12-03T17:35:34Z
dc.date.available2024-12-03T17:35:34Z
dc.date.issued2021
dc.identifier.citationIEEE Software 38(1) : 81-87 (2021)es_ES
dc.identifier.issn0740-7459
dc.identifier.issn1937-4194
dc.identifier.urihttp://hdl.handle.net/10810/70755
dc.description.abstractWe provide a novel decomposition methodology from the current MLPerf benchmark to the serverless function execution model. We have tested our approach in Amazon Lambda to benchmark the processing capabilities of OpenCV and OpenVINO inference engines.es_ES
dc.description.sponsorshipThis work has been partially supported by the program ELKARTEK 2019 of the Basque Government under project AUTOLIB.es_ES
dc.language.isoenges_ES
dc.publisherIEEEes_ES
dc.rightsinfo:eu-repo/semantics/openAccesses_ES
dc.subjectbenchmark testinges_ES
dc.subjectFAAes_ES
dc.subjecttask analysises_ES
dc.subjectengineses_ES
dc.subjectcomputer architecturees_ES
dc.subjectthroughputes_ES
dc.subjectcomputational modelinges_ES
dc.titleBenchmarking Deep Neural Network Inference Performance on Serverless Environments With MLPerfes_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.rights.holder© 2021 IEEEes_ES
dc.relation.publisherversionhttps://doi.org/10.1109/MS.2020.3030199es_ES
dc.identifier.doi10.1109/MS.2020.3030199
dc.departamentoesCiencia de la computación e inteligencia artificiales_ES
dc.departamentoeuKonputazio zientziak eta adimen artifizialaes_ES


Files in this item

Thumbnail
Name:
Elordi et al., Benchmarking DNN ...
Size:
1.494Mb
Format:
PDF
Description:
Postprint
View/Open

This item appears in the following Collection(s)

Show simple item record