{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:26:10Z","timestamp":1769732770680,"version":"3.49.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-19-1-2156"],"award-info":[{"award-number":["N00014-19-1-2156"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2021-128009OB-C31"],"award-info":[{"award-number":["PID2021-128009OB-C31"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["TED2021-131835B-I00"],"award-info":[{"award-number":["TED2021-131835B-I00"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011878","name":"Vlaamse regering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3264828","type":"journal-article","created":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T17:52:59Z","timestamp":1680717179000},"page":"35007-35021","source":"Crossref","is-referenced-by-count":8,"title":["A Pipelining-Based Heterogeneous Scheduling and Energy-Throughput Optimization Scheme for CNNs Leveraging Apache TVM"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3487-1712","authenticated-orcid":false,"given":"Delia","family":"Velasco-Montero","sequence":"first","affiliation":[{"name":"Instituto de Microelectr&#x00F3;nica de Sevilla, Universidad de Sevilla-CSIC, Seville, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1666-5483","authenticated-orcid":false,"given":"Bart","family":"Goossens","sequence":"additional","affiliation":[{"name":"Image Processing and Interpretation Research Group, imec-Ghent University, Ghent, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0476-4676","authenticated-orcid":false,"given":"Jorge","family":"Fern\u00e1ndez-Berni","sequence":"additional","affiliation":[{"name":"Instituto de Microelectr&#x00F3;nica de Sevilla, Universidad de Sevilla-CSIC, Seville, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1006-5241","authenticated-orcid":false,"given":"\u00c1ngel","family":"Rodr\u00edguez-V\u00e1zquez","sequence":"additional","affiliation":[{"name":"Instituto de Microelectr&#x00F3;nica de Sevilla, Universidad de Sevilla-CSIC, Seville, Spain"}]},{"given":"Wilfried","family":"Philips","sequence":"additional","affiliation":[{"name":"Image Processing and Interpretation Research Group, imec-Ghent University, Ghent, Belgium"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Jetson Modules","year":"2022"},{"key":"ref2","volume-title":"Jetson Nano Developer Kit","year":"2022"},{"key":"ref3","volume-title":"Jetson Xavier NX Developer Kit","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INMIC50486.2020.9318136"},{"issue":"4","key":"ref5","doi-asserted-by":"crossref","first-page":"61","DOI":"10.3390\/electronics5040061","article-title":"A Raspberry Pi cluster instrumented for fine-grained power measurement","volume":"5","author":"Cloutier","year":"2016","journal-title":"Electronics"},{"key":"ref6","article-title":"An evaluation of edge TPU accelerators for convolutional neural networks","author":"Seshadri","year":"2021","journal-title":"arXiv:2102.10423"},{"key":"ref7","article-title":"Characterizing the deep neural networks inference performance of mobile applications","author":"Ogden","year":"2019","journal-title":"arXiv:1909.04783"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3397315"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3194554.3194565"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1800506"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3229556.3229562"},{"key":"ref13","article-title":"SmartSplit: Latency-energy-memory optimisation for CNN splitting on smartphone environment","author":"Prakash","year":"2021","journal-title":"arXiv:2111.01077"},{"issue":"10","key":"ref14","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3390\/fi11100209","article-title":"Partitioning convolutional neural networks to maximize the inference rate on constrained IoT devices","volume":"11","author":"de Oliveira","year":"2019","journal-title":"Future Internet"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737614"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2972000"},{"key":"ref17","article-title":"In-edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning","author":"Wang","year":"2018","journal-title":"arXiv:1809.07857"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858384"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363312"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3107424"},{"key":"ref21","article-title":"Integrated ARM big.Little-Mali pipeline for high-throughput CNN inference","author":"Aghapour","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2944584"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073977"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038908"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2016.7460664"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530509"},{"key":"ref27","article-title":"Heterogeneous FPGA+GPU embedded systems: Challenges and opportunities","author":"Hosseinabady","year":"2019","journal-title":"arXiv:1901.06331"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375380"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267828"},{"key":"ref30","article-title":"Pipeline parallelism for inference on heterogeneous edge computing","author":"Hu","year":"2021","journal-title":"arXiv:2110.14895"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2856261"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2893250"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927211"},{"key":"ref34","first-page":"1","article-title":"Distributing deep neural networks with containerized partitions at the edge","volume-title":"Proc. 2nd USENIX Workshop Hot Topics Edge Comput. (HotEdge)","author":"Zhou"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970728"},{"key":"ref36","volume-title":"Apache TVM","year":"2020"},{"key":"ref37","first-page":"579","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Conf. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref38","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Conf. Operating Syst. Design Implement.","author":"Zheng"},{"key":"ref39","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1970.tb01770.x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827596313322"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2012.07.003"},{"key":"ref47","article-title":"SqueezeNet: AlexNet-level accuracy with 50\u00d7 fewer parameters and < 0.5 MB model size","author":"Iandola","year":"2016","journal-title":"arXiv:1602.07360"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref49","volume-title":"Introducing TVM Auto-Scheduler (A.K.A. Ansor)","author":"Zheng","year":"2021"},{"key":"ref50","volume-title":"TVM. User Tutorial. Compiling and Optimizing a Model With TVMC","year":"2020"},{"key":"ref51","volume-title":"TVM Python API","year":"2020"},{"key":"ref52","volume-title":"Multi-Stream Execution in Meta VM","author":"Ding","year":"2022"},{"key":"ref53","volume-title":"NVIDIA Jetson TX2 NX System-on-Module","year":"2022"},{"key":"ref54","volume-title":"Tegra Linux Driver Package Release Notes","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IGSC51522.2020.9290876"},{"key":"ref56","article-title":"NeuralPower: Predict and deploy energy-efficient convolutional neural networks","author":"Cai","year":"2017","journal-title":"arXiv:1710.05420"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2017.8167764"},{"key":"ref58","article-title":"Collage: Seamless integration of deep learning backends with automatic placement","author":"Jeon","year":"2021","journal-title":"arXiv:2111.00655"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tpds.2020.3030548"},{"key":"ref60","volume-title":"TVM Heterogeneous Co-Execution","author":"Velasco-Montero","year":"2022"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10092812.pdf?arnumber=10092812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T21:38:10Z","timestamp":1709242690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10092812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3264828","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}