{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:40:14Z","timestamp":1768405214230,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T00:00:00Z","timestamp":1657411200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100014553","name":"Samsung Advanced Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014553","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,7,10]]},"DOI":"10.1145\/3489517.3530510","type":"proceedings-article","created":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T23:19:29Z","timestamp":1661296769000},"page":"607-612","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["PARIS and ELSA"],"prefix":"10.1145","author":[{"given":"Yunseong","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST"}]},{"given":"Yujeong","family":"Choi","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Minsoo","family":"Rhu","sequence":"additional","affiliation":[{"name":"KAIST"}]}],"member":"320","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805","author":"Devlin J.","year":"2018","unstructured":"J. Devlin et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_2_1","volume":"201","author":"Erfan Eshratifar A.","unstructured":"A. Erfan Eshratifar et al. JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services. IEEE Transactions on Mobile Computing, 2019.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_2_1_3_1","volume-title":"Conformer: Convolution-augmented Transformer for Speech Recognition. arXiv preprint arXiv:2005.08100","author":"Gulati A.","year":"2020","unstructured":"A. Gulati et al. Conformer: Convolution-augmented Transformer for Speech Recognition. arXiv preprint arXiv:2005.08100, 2020."},{"key":"e_1_3_2_1_4_1","volume-title":"DeepRecSys: A System for Optimizing End-to-end At-scale Neural Recommendation Inference. In Proceedings of the International Symposium on Computer Architecture (ISCA)","author":"Gupta U.","year":"2020","unstructured":"U. Gupta et al. DeepRecSys: A System for Optimizing End-to-end At-scale Neural Recommendation Inference. In Proceedings of the International Symposium on Computer Architecture (ISCA), 2020."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2019.00021"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749472"},{"key":"e_1_3_2_1_7_1","volume-title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861","author":"Howard A. G.","year":"2017","unstructured":"A. G. Howard et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861, 2017."},{"key":"e_1_3_2_1_8_1","volume-title":"GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. Proceedings of the International Conference on Neural Information Processing Systems (NIPS)","author":"Huang Y.","year":"2019","unstructured":"Y. Huang et al. GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. Proceedings of the International Conference on Neural Information Processing Systems (NIPS), 2019."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_11_1","volume-title":"Training and Investigating Residual Nets","author":"Gross S.","year":"2016","unstructured":"S. Gross and others. Training and Investigating Residual Nets, 2016."},{"key":"e_1_3_2_1_12_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi M.","year":"2019","unstructured":"M. Shoeybi et al. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv preprint arXiv:1909.08053, 2019."}],"event":{"name":"DAC '22: 59th ACM\/IEEE Design Automation Conference","location":"San Francisco California","acronym":"DAC '22","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the 59th ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530510","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489517.3530510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:17Z","timestamp":1750186937000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489517.3530510"}},"subtitle":["an elastic scheduling algorithm for reconfigurable multi-GPU inference servers"],"short-title":[],"issued":{"date-parts":[[2022,7,10]]},"references-count":12,"alternative-id":["10.1145\/3489517.3530510","10.1145\/3489517"],"URL":"https:\/\/doi.org\/10.1145\/3489517.3530510","relation":{},"subject":[],"published":{"date-parts":[[2022,7,10]]},"assertion":[{"value":"2022-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}