{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:54:19Z","timestamp":1757314459354,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"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":[[2024,10,8]]},"DOI":"10.1145\/3640457.3688037","type":"proceedings-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T15:39:28Z","timestamp":1728401968000},"page":"841-843","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Toward 100TB Recommendation Models with Embedding Offloading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6958-5997","authenticated-orcid":false,"given":"Intaik","family":"Park","sequence":"first","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1267-6887","authenticated-orcid":false,"given":"Ehsan","family":"Ardestani","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7653-5665","authenticated-orcid":false,"given":"Damian","family":"Reeves","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4662-3129","authenticated-orcid":false,"given":"Sarunya","family":"Pumma","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5835-1474","authenticated-orcid":false,"given":"Henry","family":"Tsang","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5384-7204","authenticated-orcid":false,"given":"Levy","family":"Zhao","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-6183","authenticated-orcid":false,"given":"Jian","family":"He","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9012-3254","authenticated-orcid":false,"given":"Joshua","family":"Deng","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8254-4977","authenticated-orcid":false,"given":"Dennis","family":"Van der Staay","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7243-2089","authenticated-orcid":false,"given":"Yu","family":"Guo","sequence":"additional","affiliation":[{"name":"Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1063-1372","authenticated-orcid":false,"given":"Paul","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI Infra, Meta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"High-Performance Training by Exploiting Hot-Embeddings in Recommendation Systems. CoRR abs\/2103.00686","author":"Adnan Muhammad","year":"2021","unstructured":"Muhammad Adnan, Yassaman\u00a0Ebrahimzadeh Maboud, Divya Mahajan, and Prashant\u00a0J. Nair. 2021. High-Performance Training by Exploiting Hot-Embeddings in Recommendation Systems. CoRR abs\/2103.00686 (2021). arXiv:2103.00686https:\/\/arxiv.org\/abs\/2103.00686"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Saurabh Agarwal Chengpo Yan Ziyi Zhang and Shivaram Venkataraman. 2023. BagPipe: Accelerating Deep Recommendation Model Training. arxiv:2202.12429\u00a0[cs.DC]","DOI":"10.1145\/3600006.3613142"},{"key":"e_1_3_2_1_3_1","volume-title":"Supporting Massive DLRM Inference Through Software Defined Memory. CoRR abs\/2110.11489","author":"Ardestani K.","year":"2021","unstructured":"Ehsan\u00a0K. Ardestani, Changkyu Kim, Seung\u00a0Jae Lee, Luoshang Pan, Valmiki Rampersad, Jens Axboe, Banit Agrawal, Fuxun Yu, Ansha Yu, Trung Le, Hector Yuen, Shishir Juluri, Akshat Nanda, Manoj Wodekar, Dheevatsa Mudigere, Krishnakumar Nair, Maxim Naumov, Chris Peterson, Mikhail Smelyanskiy, and Vijay Rao. 2021. Supporting Massive DLRM Inference Through Software Defined Memory. CoRR abs\/2110.11489 (2021). arXiv:2110.11489https:\/\/arxiv.org\/abs\/2110.11489"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460231.3474246"},{"key":"e_1_3_2_1_5_1","unstructured":"Mark Harris. 2013. Unified Memory in CUDA 6. https:\/\/developer.nvidia.com\/blog\/unified-memory-in-cuda-6\/"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3547387"},{"key":"e_1_3_2_1_8_1","unstructured":"Hiwot\u00a0Tadese Kassa Paul Johnson Jason Akers Mrinmoy Ghosh Andrew Tulloch Dheevatsa Mudigere Jongsoo Park Xing Liu Ronald Dreslinski and Ehsan\u00a0K. Ardestani. 2023. MTrainS: Improving DLRM training efficiency using heterogeneous memories. arxiv:2305.01515\u00a0[cs.IR]"},{"key":"e_1_3_2_1_9_1","volume-title":"FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference. CoRR abs\/2101.05615","author":"Khudia Daya\u00a0Shanker","year":"2021","unstructured":"Daya\u00a0Shanker Khudia, Jianyu Huang, Protonu Basu, Summer Deng, Haixin Liu, Jongsoo Park, and Mikhail Smelyanskiy. 2021. FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference. CoRR abs\/2101.05615 (2021). arXiv:2101.05615https:\/\/arxiv.org\/abs\/2101.05615"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.92.0078"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3533727"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR abs\/1906.00091","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov, Dheevatsa Mudigere, Hao-Jun\u00a0Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson\u00a0G. Azzolini, Dmytro Dzhulgakov, Andrey Mallevich, Ilia Cherniavskii, Yinghai Lu, Raghuraman Krishnamoorthi, Ansha Yu, Volodymyr Kondratenko, Stephanie Pereira, Xianjie Chen, Wenlin Chen, Vijay Rao, Bill Jia, Liang Xiong, and Misha Smelyanskiy. 2019. Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR abs\/1906.00091 (2019). arXiv:1906.00091http:\/\/arxiv.org\/abs\/1906.00091"},{"key":"e_1_3_2_1_13_1","unstructured":"PyTorch. 2024. FBGEMM GPU Python API. https:\/\/pytorch.org\/FBGEMM\/fbgemm_gpu-python-api\/table_batched_embedding_ops.html"},{"key":"e_1_3_2_1_14_1","volume-title":"Ping Tak\u00a0Peter Tang, and Andrew Tulloch","author":"Yang Jie\u00a0Amy","year":"2020","unstructured":"Jie\u00a0Amy Yang, Jianyu Huang, Jongsoo Park, Ping Tak\u00a0Peter Tang, and Andrew Tulloch. 2020. Mixed-Precision Embedding Using a Cache. CoRR abs\/2010.11305 (2020). arXiv:2010.11305https:\/\/arxiv.org\/abs\/2010.11305"}],"event":{"name":"RecSys '24: 18th ACM Conference on Recommender Systems","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Bari Italy","acronym":"RecSys '24"},"container-title":["18th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688037","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640457.3688037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:29Z","timestamp":1750294709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640457.3688037"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":14,"alternative-id":["10.1145\/3640457.3688037","10.1145\/3640457"],"URL":"https:\/\/doi.org\/10.1145\/3640457.3688037","relation":{},"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"2024-10-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}