{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:14:50Z","timestamp":1770740090492,"version":"3.49.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62350710797"],"award-info":[{"award-number":["62350710797"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Plan Project of Shenzhen","award":["JSGG20220831110002004"],"award-info":[{"award-number":["JSGG20220831110002004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tmc.2025.3622698","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:43:03Z","timestamp":1760722983000},"page":"4346-4362","source":"Crossref","is-referenced-by-count":0,"title":["Cola: Cross-Processor Operator Parallelism for Asynchronous Deep Learning Inference"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6805-2649","authenticated-orcid":false,"given":"Changyao","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenming","family":"Chen","sequence":"additional","affiliation":[{"name":"China Construction Steel Structure Engineering Corporation, LTD, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2539-8257","authenticated-orcid":false,"given":"Ziyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"NESLab, Politecnico di Milano, Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6209-6886","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Smart Farm Technologies and Systems, Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cuda multi-streams","year":"2015"},{"key":"ref2","article-title":"Multi-process service","year":"2020"},{"key":"ref3","article-title":"Multi-instance gpu","year":"2020"},{"key":"ref4","article-title":"A survey of multi-tenant deep learning inference on GPU","author":"Yu","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682900"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3568520"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS46320.2019.00042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3485938"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538948"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3492886"},{"key":"ref12","article-title":"Cuda C\/C streams and concurrency","year":"2012"},{"key":"ref13","first-page":"167","article-title":"IOS: Inter-operator scheduler for CNN acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Ding","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586953"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3511543"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538932"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596870"},{"key":"ref19","first-page":"578","article-title":"$\\lbrace${TVM $\\rbrace$}: An automated $\\lbrace${ End-to-End$\\rbrace$} optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Chen","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref21","article-title":"Neural architecture search with reinforcement learning","author":"Zoph","year":"2016"},{"key":"ref22","article-title":"Darts: Differentiable architecture search","author":"Liu","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643501"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Nvidia jetson xavier","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref27","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and<0.5 mb model size","author":"Iandola","year":"2016"},{"key":"ref28","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref29","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref30","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref32","article-title":"Nvidia jetson TX2","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0229-5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","article-title":"Nvidia a100","year":"2024"},{"key":"ref36","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref37","article-title":"Cuda programming guide","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref39","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref41","article-title":"Epyc 7002 series processors","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3754448"},{"key":"ref45","article-title":"A survey of resource-efficient LLM and multimodal foundation models","author":"Xu","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3625687"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/iiswc50251.2020.00023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3715014.3722076"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11372515\/11206434.pdf?arnumber=11206434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T21:10:09Z","timestamp":1770671409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11206434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":51,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3622698","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}