{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:41:08Z","timestamp":1755999668030,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100010661","name":"European Union\u2019s Horizon 2020 Research and Innovation Program","doi-asserted-by":"publisher","award":["780788"],"award-info":[{"award-number":["780788"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3115243","type":"journal-article","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T22:01:13Z","timestamp":1632434473000},"page":"133289-133308","source":"Crossref","is-referenced-by-count":8,"title":["ALOHA: A Unified Platform-Aware Evaluation Method for CNNs Execution on Heterogeneous Systems at the Edge"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1434-9858","authenticated-orcid":false,"given":"Paola","family":"Busia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Svetlana","family":"Minakova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6006-9366","authenticated-orcid":false,"given":"Todor","family":"Stefanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9683-009X","authenticated-orcid":false,"given":"Luigi","family":"Raffo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-4641","authenticated-orcid":false,"given":"Paolo","family":"Meloni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2020.2968258"},{"journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems","year":"2015","author":"abadi","key":"ref38"},{"key":"ref33","article-title":"MONAS: Multi-objective neural architecture search using reinforcement learning","author":"hsu","year":"2018","journal-title":"arXiv 1806 10332"},{"key":"ref32","first-page":"288","article-title":"EdgeNAS: Discovering efficient neural architectures for edge systems","author":"luo","year":"2020","journal-title":"Proc IEEE 38th Int Conf Comput Design (ICCD)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3015531"},{"key":"ref30","article-title":"Applying the Roofline model for deep learning performance optimizations","author":"czaja","year":"2020","journal-title":"arXiv 2009 11224"},{"key":"ref37","first-page":"8024","author":"paszke","year":"2019","journal-title":"Pytorch An imperative style high-performance deep learning library"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056063"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01099"},{"key":"ref34","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","author":"cai","year":"2020","journal-title":"Proc 8th Int Conf Learn Represent (ICLR)"},{"journal-title":"Jetson TX2 Platform Technical Specification","year":"2021","author":"corporation","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3284357"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref29"},{"key":"ref2","article-title":"The history began from AlexNet: A comprehensive survey on deep learning approaches","author":"alom","year":"2018","journal-title":"arXiv 1803 01164"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","article-title":"On neural architecture search for resource-constrained hardware platforms","author":"lu","year":"2019","journal-title":"arXiv 1911 00105"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218676"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317829"},{"key":"ref24","article-title":"Paleo: A performance model for deep neural networks","author":"qi","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref23","first-page":"1","article-title":"NASCaps: A framework for neural architecture search to optimize the accuracy and hardware efficiency of convolutional capsule networks","author":"marchisio","year":"2020","journal-title":"Proc 39th Int Conf Comput -Aided Design"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3400286.3418245"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622396"},{"journal-title":"Nvidia Tensorrt Deep Learning Library and Inference Optimizer","year":"2021","author":"corporation","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2019.2947312"},{"key":"ref56","volume":"8","author":"zitzler","year":"2000","journal-title":"Comparison of multiobjective evolutionary algorithms Empirical results"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/mca22010025"},{"key":"ref54","article-title":"A comprehensive survey on hardware-aware neural architecture search","author":"benmeziane","year":"2021","journal-title":"arXiv 2101 09336"},{"key":"ref53","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"journal-title":"An531 Reducing Power With Hardware Accelerators","year":"2008","key":"ref52"},{"key":"ref10","first-page":"238","article-title":"14.1 A 2.9TOPS\/W deep convolutional neural network SoC in FD-SOI 28 nm for intelligent embedded systems","author":"desoli","year":"2017","journal-title":"IEEE Int Solid-State Circuits Conf (ISSCC) Dig Tech Papers"},{"journal-title":"Movidius Neural Compute Stick Accelerate Deep Learning Development at the Edge","year":"2020","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60939-9_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref13","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","article-title":"MicroNets: Neural network architectures for deploying TinyML applications on commodity microcontrollers","author":"banbury","year":"2020","journal-title":"arXiv 2010 11267"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00171"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref17","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00354"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2986127"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.101749"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GTSD.2018.8595590"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics8111289"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA.2016.29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref7","article-title":"Bringing AI to edge: From deep learning’s perspective","author":"liu","year":"2020","journal-title":"arXiv 2011 14808"},{"journal-title":"Drampower Open-source Dram Power & Energy Estimation Tool","year":"2021","author":"chandrasekar","key":"ref49"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2752706"},{"journal-title":"Open Neural Network Exchange (ONNX)","year":"2021","author":"tools community","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"journal-title":"Xilinx Power Estimator","year":"2021","key":"ref48"},{"journal-title":"CUDA C Best Practices Guide","year":"2021","author":"corporation","key":"ref47"},{"key":"ref42","article-title":"Not all ops are created equal!","volume":"abs 1801 4326","author":"lai","year":"2018","journal-title":"CoRR"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3358699"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342149"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09547285.pdf?arnumber=9547285","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:43Z","timestamp":1639770943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9547285\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3115243","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}