{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:53:50Z","timestamp":1768517630336,"version":"3.49.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"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":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323041","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["HIOCS: Heuristic Inter-Operator Co-Scheduling Method for Efficient DNN Inference on GPUs"],"prefix":"10.1109","author":[{"given":"Ning","family":"Wang","sequence":"first","affiliation":[{"name":"University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand"}]},{"given":"Andrea","family":"Raith","sequence":"additional","affiliation":[{"name":"University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand"}]},{"given":"Oliver","family":"Sinnen","sequence":"additional","affiliation":[{"name":"University of Auckland,Faculty of Engineering and Design,Auckland,New Zealand"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3638757"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3475589"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3369628"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3345952"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS56603.2022.00123"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER52292.2023.00016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/0470121173"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD53106.2021.00054"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3570638"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629578"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643501"},{"key":"ref13","first-page":"8343","article-title":"Nimble: Lightweight and parallel gpu task scheduling for deep learning","volume":"33","author":"Kwon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586953"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3079202"},{"key":"ref16","first-page":"881","article-title":"Rammer: Enabling holistic deep learning compiler optimizations with \\{rTasks\\}","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Ma","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26343"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PmLR","author":"Radford","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.4324\/9781410605337-29"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref26","first-page":"578","article-title":"\\{TVM\\}: An automated \\{End-to-End\\} optimizing compiler for deep learning","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen","year":"2018"},{"key":"ref27","first-page":"863","article-title":"Ansor: Generating \\{High-Performance\\} tensor programs for deep learning","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Zheng","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref29","first-page":"167","article-title":"Ios: Inter-operator scheduler for cnn acceleration","volume":"3","author":"Ding","year":"2021","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3511543"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589048"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673155"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323041.pdf?arnumber=11323041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:54:16Z","timestamp":1768463656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323041","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}