Show simple item record

dc.contributor.authorSudharsan, Bharath
dc.contributor.authorPatel, Pankesh
dc.contributor.authorBreslin, John G.
dc.contributor.authorAli, Muhammad Intizar
dc.date.accessioned2021-05-21T09:52:30Z
dc.date.available2021-05-21T09:52:30Z
dc.date.issued2021-05-19
dc.identifier.citationSudharsan, Bharath, Patel, Pankesh, Breslin, John G., & Ali, Muhammad Intizar. (2021). SRAM optimized porting and execution of machine learning classifiers on MCU-based IoT devices: Demo abstract. Paper presented at the Proceedings of the ACM/IEEE 12th International Conference on Cyber-Physical Systems, Nashville, Tennessee, 19-21 May, https://doi.org/10.1145/3450267.3451999en_IE
dc.identifier.urihttp://hdl.handle.net/10379/16775
dc.description.abstractWith the introduction of edge analytics, IoT devices are becoming smarter and ready for AI applications. However, any increase in the training data results in a linear increase in the space complexity of the trained Machine Learning (ML) models, which means they cannot be deployed on IoT devices that have limited memory. To alleviate such memory issues, we recently proposed an SRAM-optimized classifier porting, stitching, and efficient deployment method in [3]. This is currently the most resource-friendly approach that enables large classifiers to be comfortably executed on microcontroller unit (MCU) based IoT devices, and perform ultra-fast classifications (1--4x times faster than state-of-the-art libraries) while consuming 0 bytes of SRAM. In this demo, realizing our recent SRAM-optimized approach, we port and execute 7 dataset-trained classifiers on 7 popular MCUs, and report their inference performance. It is apparent from the demo results that realizing our approach makes even the slowest Atmega328P MCU perform faster unit inference than a NVIDIA Jetson Nano GPU and Raspberry Pi 4 CPU.en_IE
dc.description.sponsorshipThis publication has emanated from research supported in part by a research grant from Science Foundation Ireland (SFI) under Grant Number SFI/16/RC/3918 (Confirm) and also by a research grant from Science Foundation Ireland (SFI) under Grant Number SFI/12/RC/2289_P2 (Insight), with both grants co-funded by the European Regional Development Fund.en_IE
dc.formatapplication/pdfen_IE
dc.language.isoenen_IE
dc.publisherAssociation for Computing Machinery (ACM)en_IE
dc.relation.ispartofICCPS '21: Proceedings of the ACM/IEEE 12th International Conference on Cyber-Physical Systemsen
dc.rightsAttribution 4.0 International (CC BY 4.0)
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectOffline Inferenceen_IE
dc.subjectIntelligent MCUsen_IE
dc.subjectEdge AIen_IE
dc.subjectSRAM Optimizationen_IE
dc.titleSRAM optimized porting and execution of machine learning classifiers on MCU-based IoT devices: Demo abstracten_IE
dc.typeConference Paperen_IE
dc.date.updated2021-05-21T09:33:02Z
dc.identifier.doi10.1145/3450267.3451999
dc.local.publishedsourcehttps://doi.org/10.1145/3450267.3451999en_IE
dc.description.peer-reviewedpeer-reviewed
dc.contributor.funderScience Foundation Irelanden_IE
dc.contributor.funderEuropean Regional Development Funden_IE
dc.internal.rssid25999426
dc.local.contactBharath Sudharsan, Insight Centre For Data Analytics, Nui Galway. Email: b.sudharsan1@nuigalway.ie
dc.local.copyrightcheckedYes
dcterms.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/en_IE
nui.item.downloads152


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's license is described as Attribution 4.0 International (CC BY 4.0)