{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:50:17Z","timestamp":1759942217440,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,7]]},"DOI":"10.1145\/3605573.3605603","type":"proceedings-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T16:21:16Z","timestamp":1694622076000},"page":"412-422","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Mercury: Fast and Optimal Device Placement for Large Deep Learning Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1363-9394","authenticated-orcid":false,"given":"Hengwei","family":"Xu","sequence":"first","affiliation":[{"name":"University Of Science And Technology Of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7909-4059","authenticated-orcid":false,"given":"Pengyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2084-2697","authenticated-orcid":false,"given":"Haiyong","family":"Xie","sequence":"additional","affiliation":[{"name":"Advanced Innovation Center for Human Brain Protection, capital medical university, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-0557","authenticated-orcid":false,"given":"Yong","family":"Liao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, 2016. { TensorFlow} : A System for { Large-Scale} Machine Learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265\u2013283."},{"key":"e_1_3_2_1_2_1","volume-title":"Placeto: Learning generalizable device placement algorithms for distributed machine learning. arXiv preprint arXiv:1906.08879","author":"Addanki Ravichandra","year":"2019","unstructured":"Ravichandra Addanki, Shaileshh\u00a0Bojja Venkatakrishnan, Shreyan Gupta, Hongzi Mao, and Mohammad Alizadeh. 2019. Placeto: Learning generalizable device placement algorithms for distributed machine learning. arXiv preprint arXiv:1906.08879 (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3041829"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417050"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3464298.3476132"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(94)90024-8"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICS.2016.0108"},{"key":"e_1_3_2_1_8_1","volume-title":"Baechi: fast device placement of machine learning graphs. arXiv preprint arXiv:2301.08695","author":"Jeon Beomyeol","year":"2023","unstructured":"Beomyeol Jeon, Linda Cai, Pallavi Srivastava, Jintao Jiang, Xiaolan Ke, Yitao Meng, Cong Xie, and Indranil Gupta. 2023. Baechi: fast device placement of machine learning graphs. arXiv preprint arXiv:2301.08695 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"METIS: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices.","author":"Karypis George","year":"1997","unstructured":"George Karypis and Vipin Kumar. 1997. METIS: A software package for partitioning unstructured graphs, partitioning meshes, and computing fill-reducing orderings of sparse matrices. (1997)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/321623.321627"},{"key":"e_1_3_2_1_11_1","volume-title":"Accelerated Device Placement Optimization with Contrastive Learning. In 50th International Conference on Parallel Processing. 1\u201310","author":"Lan Hao","year":"2021","unstructured":"Hao Lan, Li Chen, and Baochun Li. 2021. Accelerated Device Placement Optimization with Contrastive Learning. In 50th International Conference on Parallel Processing. 1\u201310."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00068"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Learning Representations.","author":"Mirhoseini Azalia","year":"2018","unstructured":"Azalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc\u00a0V Le, and Jeff Dean. 2018. A hierarchical model for device placement. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 2430\u20132439","author":"Mirhoseini Azalia","year":"2017","unstructured":"Azalia Mirhoseini, Hieu Pham, Quoc\u00a0V Le, Benoit Steiner, Rasmus Larsen, Yuefeng Zhou, Naveen Kumar, Mohammad Norouzi, Samy Bengio, and Jeff Dean. 2017. Device placement optimization with reinforcement learning. In International Conference on Machine Learning. PMLR, 2430\u20132439."},{"key":"e_1_3_2_1_16_1","volume-title":"Towards real-time photorealistic 3D holography with deep neural networks. Nature 591, 7849","author":"Shi Liang","year":"2021","unstructured":"Liang Shi, Beichen Li, Changil Kim, Petr Kellnhofer, and Wojciech Matusik. 2021. Towards real-time photorealistic 3D holography with deep neural networks. Nature 591, 7849 (2021), 234\u2013239."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_19_1","first-page":"15451","article-title":"Efficient algorithms for device placement of dnn graph operators","volume":"33","author":"Tarnawski M","year":"2020","unstructured":"Jakub\u00a0M Tarnawski, Amar Phanishayee, Nikhil Devanur, Divya Mahajan, and Fanny Nina\u00a0Paravecino. 2020. Efficient algorithms for device placement of dnn graph operators. Advances in Neural Information Processing Systems 33 (2020), 15451\u201315463.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2808959"},{"key":"e_1_3_2_1_22_1","volume-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144","author":"Wu Yonghui","year":"2016","unstructured":"Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc\u00a0V Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, 2016. Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP52443.2021.00023"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3423211.3425675"},{"key":"e_1_3_2_1_25_1","first-page":"13844","article-title":"Transferable graph optimizers for ml compilers","volume":"33","author":"Zhou Yanqi","year":"2020","unstructured":"Yanqi Zhou, Sudip Roy, Amirali Abdolrashidi, Daniel Wong, Peter Ma, Qiumin Xu, Hanxiao Liu, Phitchaya Phothilimtha, Shen Wang, Anna Goldie, 2020. Transferable graph optimizers for ml compilers. Advances in Neural Information Processing Systems 33 (2020), 13844\u201313855.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3015188"}],"event":{"name":"ICPP 2023: 52nd International Conference on Parallel Processing","acronym":"ICPP 2023","location":"Salt Lake City UT USA"},"container-title":["Proceedings of the 52nd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605603","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605573.3605603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:04Z","timestamp":1750182544000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605573.3605603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":26,"alternative-id":["10.1145\/3605573.3605603","10.1145\/3605573"],"URL":"https:\/\/doi.org\/10.1145\/3605573.3605603","relation":{},"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-09-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}