{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:26:44Z","timestamp":1783531604531,"version":"3.55.0"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tc.2024.3475589","type":"journal-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T13:36:08Z","timestamp":1728394568000},"page":"325-333","source":"Crossref","is-referenced-by-count":11,"title":["Opara: Exploiting Operator Parallelism for Expediting DNN Inference on GPUs"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8373-4465","authenticated-orcid":false,"given":"Aodong","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1590-5323","authenticated-orcid":false,"given":"Fei","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5797-2554","authenticated-orcid":false,"given":"Li","family":"Han","sequence":"additional","affiliation":[{"name":"School of Software Engineering, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6571-5237","authenticated-orcid":false,"given":"Yuan","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2300-6996","authenticated-orcid":false,"given":"Li","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0987-9344","authenticated-orcid":false,"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Big Data Analysis and Processing, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8570-1345","authenticated-orcid":false,"given":"Fangming","family":"Liu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629565"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682915"},{"key":"ref4","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Des. Implementation","author":"Weng","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref7","first-page":"183","article-title":"DVABatch: Diversity-aware multi-entry multi-exit batching for efficient Processing of DNN services on GPUs","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Cui","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421284"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3232715"},{"key":"ref10","first-page":"881","article-title":"Rammer: Enabling holistic deep learning compiler optimizations with rTasks","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Des. Implementation","author":"Ma","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26343"},{"key":"ref12","first-page":"8343","article-title":"Nimble: Lightweight and parallel GPU task scheduling for deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kwon","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2017.00017"},{"key":"ref14","first-page":"167","article-title":"IOS: Inter-operator scheduler for CNN acceleration","volume-title":"Proc. Mach. Learn. Syst.","author":"Ding","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3529113.3529124"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629578"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613163"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(75)80008-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"ref20","first-page":"701","article-title":"Welder: Scheduling deep learning memory access via tile-graph","volume-title":"Proc. 17th USENIX Symp. Oper. Syst. Des. Implementation","author":"Shi","year":"2023"},{"key":"ref21","first-page":"681","article-title":"Cocktailer: Analyzing and optimizing dynamic control flow in deep learning","volume-title":"Proc. 17th USENIX Symp. Oper. Syst. Des. Implementation","author":"Zhang","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2018.00028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291211"},{"key":"ref25","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Des. Implementation","author":"Zheng","year":"2020"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/10794426\/10707307.pdf?arnumber=10707307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T04:36:13Z","timestamp":1762317373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10707307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":25,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tc.2024.3475589","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}