{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T14:40:59Z","timestamp":1765291259366,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3774899.3775014","type":"proceedings-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T14:35:38Z","timestamp":1765290938000},"page":"20-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Elastic MIG Reconfiguration with PCIe-Aware Placement for Multi-Tenant GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6003-0119","authenticated-orcid":false,"given":"Erfan","family":"Darzi","sequence":"first","affiliation":[{"name":"Harvard University, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0192-9925","authenticated-orcid":false,"given":"Sree Bhargavi","family":"Balija","sequence":"additional","affiliation":[{"name":"University of California, San Diego, San diego, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2246-2471","authenticated-orcid":false,"given":"Buse","family":"Demir","sequence":"additional","affiliation":[{"name":"Harvard University, Boston, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Giulio Zhou, Michael J. Franklin, Joseph E. Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). USENIX Association, Boston, MA, 613\u2013627."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC '19). USENIX Association, 947\u2013960","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. 2019. Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads. In Proceedings of the 2019 USENIX Annual Technical Conference (USENIX ATC '19). USENIX Association, 947\u2013960. https:\/\/www.usenix.org\/system\/files\/atc19-jeon.pdf"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563510"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2955119"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI '20)","author":"Mahajan Kshiteej","year":"2020","unstructured":"Kshiteej Mahajan, Arjun Balasubramanian, Arjun Singhvi, Shivaram Venkataraman, Aditya Akella, Amar Phanishayee, and Shuchi Chawla. 2020. Themis: Fair and Efficient GPU Cluster Scheduling. In Proceedings of the 17th USENIX Symposium on Networked Systems Design and Implementation (NSDI '20). USENIX Association, 289\u2013304."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655833"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3712031.3712324"},{"key":"e_1_3_2_1_8_1","volume-title":"Improving GPU Multi-Tenancy Through Dynamic Multi-Instance GPU Reconfiguration. arXiv preprint arXiv:2407.13126","author":"Wang Tianyu","year":"2024","unstructured":"Tianyu Wang, Sheng Li, Bingyao Li, Yue Dai, Ao Li, Geng Yuan, Yufei Ding, Youtao Zhang, and Xulong Tang. 2024. Improving GPU Multi-Tenancy Through Dynamic Multi-Instance GPU Reconfiguration. arXiv preprint arXiv:2407.13126 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Transparent GPU Sharing in Container Clouds for Deep Learning Workloads. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Wu Bingyang","year":"2023","unstructured":"Bingyang Wu, Zili Zhang, Zhihao Bai, Xuanzhe Liu, and Xin Jin. 2023. Transparent GPU Sharing in Container Clouds for Deep Learning Workloads. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). USENIX Association, 69\u201385."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI '18)","author":"Xiao Wencong","year":"2018","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, and Lidong Zhou. 2018. Gandiva: Introspective Cluster Scheduling for Deep Learning. In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI '18). USENIX Association, 595\u2013610."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2025 USENIX Annual Technical Conference (USENIX ATC '25). USENIX Association, 1003\u20131019","author":"Zhang Shulai","year":"2025","unstructured":"Shulai Zhang, Ao Xu, Quan Chen, Han Zhao, Weihao Cui, Zhen Wang, Yan Li, Limin Xiao, and Minyi Guo. 2025. Efficient Performance-Aware GPU Sharing with Compatibility and Isolation through Kernel Space Interception. In Proceedings of the 2025 USENIX Annual Technical Conference (USENIX ATC '25). USENIX Association, 1003\u20131019. https:\/\/www.usenix.org\/system\/files\/atc25-zhang-shulai.pdf"}],"event":{"name":"WoSC11 '25: 11th International Workshop on Serverless Computing","location":"Vanderbilt University Nashville TN USA","acronym":"WoSC11 '25","sponsor":["IFIP","Usenix"]},"container-title":["Proceedings of the 11th International Workshop on Serverless Computing"],"original-title":[],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T14:36:19Z","timestamp":1765290979000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774899.3775014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":11,"alternative-id":["10.1145\/3774899.3775014","10.1145\/3774899"],"URL":"https:\/\/doi.org\/10.1145\/3774899.3775014","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}