{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:16:38Z","timestamp":1785420998137,"version":"3.56.0"},"reference-count":30,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2024,9,30]]},"abstract":"<jats:p>HMPSoCs combine different processors on a single chip. They enable powerful embedded devices, which increasingly perform ML inference tasks at the edge. State-of-the-art HMPSoCs can perform on-chip embedded inference using different processors, such as CPUs, GPUs, and NPUs. HMPSoCs can potentially overcome the limitation of low single-processor CNN inference performance and efficiency by cooperative use of multiple processors. However, standard inference frameworks for edge devices typically utilize only a single processor.<\/jats:p>\n          <jats:p>\n            We present the\n            <jats:italic>ARM-CO-UP<\/jats:italic>\n            framework built on the\n            <jats:italic>ARM-CL<\/jats:italic>\n            library. The\n            <jats:italic>ARM-CO-UP<\/jats:italic>\n            framework supports two modes of operation \u2013 Pipeline and Switch. It optimizes inference throughput using pipelined execution of network partitions for consecutive input frames in the Pipeline mode. It improves inference latency through layer-switched inference for a single input frame in the Switch mode. Furthermore, it supports layer-wise CPU\/GPU\n            <jats:italic>DVFS<\/jats:italic>\n            in both modes for improving power efficiency and energy consumption.\n            <jats:italic>ARM-CO-UP<\/jats:italic>\n            is a comprehensive framework for multi-processor CNN inference that automates CNN partitioning and mapping, pipeline synchronization, processor type switching, layer-wise\n            <jats:italic>DVFS<\/jats:italic>\n            , and closed-source NPU integration.\n          <\/jats:p>","DOI":"10.1145\/3656472","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T12:10:26Z","timestamp":1712578226000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["ARM-CO-UP: ARM COoperative Utilization of Processors"],"prefix":"10.1145","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0291-7555","authenticated-orcid":false,"given":"Ehsan","family":"Aghapour","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3590-0394","authenticated-orcid":false,"given":"Dolly","family":"Sapra","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2043-4469","authenticated-orcid":false,"given":"Andy","family":"Pimentel","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5813-7021","authenticated-orcid":false,"given":"Anuj","family":"Pathania","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,9,4]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSD57027.2022.00051"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTCSA58653.2023.00011"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-022-01814-y"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2007.904779"},{"key":"e_1_3_1_6_2","unstructured":"Tianqi Chen Thierry Moreau Ziheng Jiang Lianmin Zheng Eddie Yan Haichen Shen Meghan Cowan et\u00a0al. 2018. TVM: An automated End-to-End optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201918) 578\u2013594."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3237572"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3204975"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218542"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508391"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2021.3087707"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247989"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247989"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2004.1310764"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536165"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3058313"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3100249"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Svetlana Minakova Dolly Sapra Todor Stefanov and Andy D. Pimentel. 2022. Scenario based run-time switching for adaptive cnn-based applications at the edge. ACM Transactions on Embedded Computing Systems (TECS) 21 2 (2022) 1\u201333.","DOI":"10.1145\/3488718"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60939-9_2"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-55789-8_61"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460352"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-020-01760-x"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174257"},{"key":"e_1_3_1_24_2","unstructured":"Dawei Sun Shaoshan Liu and Jean-Luc Gaudiot. 2017. Enabling embedded inference engine with arm compute library: A case study. arXiv preprint arXiv:1704.03751 (2017)."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2944584"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2020.2968258"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3132551"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00048"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2019.00030"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS48895.2020.9073977"},{"key":"e_1_3_1_31_2","unstructured":"Sean I. Young Zhe Wang David Taubman and Bernd Girod. 2021. Transform quantization for CNN compression. IEEE Transactions on Pattern Analysis and Machine Intelligence 44 9 (2021) 5700\u20135714."}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656472","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3656472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:00Z","timestamp":1750286940000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,4]]},"references-count":30,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,9,30]]}},"alternative-id":["10.1145\/3656472"],"URL":"https:\/\/doi.org\/10.1145\/3656472","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,4]]},"assertion":[{"value":"2023-11-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}