{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T09:38:43Z","timestamp":1775122723300,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"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":[[2022,2,28]]},"DOI":"10.1145\/3503222.3507777","type":"proceedings-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T20:49:01Z","timestamp":1645562941000},"page":"344-358","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":63,"title":["RecShard: statistical feature-based memory optimization for industry-scale neural recommendation"],"prefix":"10.1145","author":[{"given":"Geet","family":"Sethi","sequence":"first","affiliation":[{"name":"Stanford University, USA \/ Meta, USA"}]},{"given":"Bilge","family":"Acun","sequence":"additional","affiliation":[{"name":"Meta, USA"}]},{"given":"Niket","family":"Agarwal","sequence":"additional","affiliation":[{"name":"Meta, USA"}]},{"given":"Christos","family":"Kozyrakis","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5776-1121","authenticated-orcid":false,"given":"Caroline","family":"Trippel","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}]},{"given":"Carole-Jean","family":"Wu","sequence":"additional","affiliation":[{"name":"Meta, USA"}]}],"member":"320","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00072"},{"key":"e_1_3_2_1_2_1","volume-title":"Divya Mahajan, and Prashant J. Nair.","author":"Adnan Muhammad","year":"2021","unstructured":"Muhammad Adnan, Yassaman Ebrahimzadeh Maboud, Divya Mahajan, and Prashant J. Nair. 2021. High-Performance Training by Exploiting Hot-Embeddings in Recommendation Systems. CoRR, arxiv:2103.00686"},{"key":"e_1_3_2_1_3_1","volume-title":"Wide & Deep Learning for Recommender Systems. In Workshop on Deep Learning for Recommender Systems.","author":"Cheng Heng-Tze","year":"2016","unstructured":"Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, Greg Corrado, Wei Chai, Mustafa Ispir, Rohan Anil, Zakaria Haque, Lichan Hong, Vihan Jain, Xiaobing Liu, and Hemal Shah. 2016. Wide & Deep Learning for Recommender Systems. In Workshop on Deep Learning for Recommender Systems."},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Neural Networks for YouTube Recommendations. In ACM Recommender Systems Conference.","author":"Covington Paul","year":"2016","unstructured":"Paul Covington, Jay Adams, and Emre Sargin. 2016. Deep Neural Networks for YouTube Recommendations. In ACM Recommender Systems Conference."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_7_1","unstructured":"Facebook Research. 2021. An implementation of a deep learning recommendation model (DLRM). https:\/\/github.com\/facebookresearch\/dlrm"},{"key":"e_1_3_2_1_8_1","unstructured":"Antonio Ginart Maxim Naumov Dheevatsa Mudigere Jiyan Yang and James Zou. 2019. Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems. arXiv preprint arXiv:1909.11810."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2843948"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00084"},{"key":"e_1_3_2_1_11_1","volume-title":"The Architectural Implications of Facebook\u2019s DNN-Based Personalized Recommendation. In 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA).","author":"Gupta Udit","year":"2020","unstructured":"Udit Gupta, Carole-Jean Wu, Xiaodong Wang, Maxim Naumov, Brandon Reagen, David Brooks, Bradford Cottel, Kim Hazelwood, Mark Hempstead, Bill Jia, Hsien-Hsin S. Lee, Andrey Malevich, Dheevatsa Mudigere, Mikhail Smelyanskiy, Liang Xiong, and Xuan Zhang. 2020. The Architectural Implications of Facebook\u2019s DNN-Based Personalized Recommendation. In 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_12_1","unstructured":"Gurobi Optimization LLC. 2021. Gurobi Optimizer Reference Manual. https:\/\/www.gurobi.com"},{"key":"e_1_3_2_1_13_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_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_16_1","volume-title":"Cross-Stack Workload Characterization of Deep Recommendation Systems. In IEEE International Symposium on Workload Characterization (IISWC). IEEE Computer Society.","author":"Hsia S.","unstructured":"S. Hsia, U. Gupta, M. Wilkening, C. Wu, G. Wei, and D. Brooks. 2020. Cross-Stack Workload Characterization of Deep Recommendation Systems. In IEEE International Symposium on Workload Characterization (IISWC). IEEE Computer Society."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326937.3341255"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488792"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403288"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_21_1","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin \u017d\u00eddek Anna Potapenko Alex Bridgland Clemens Meyer Simon A. A. Kohl Andrew J. Ballard Andrew Cowie Bernardino Romera-Paredes Stanislav Nikolov Rishub Jain Jonas Adler Trevor Back Stig Petersen David Reiman Ellen Clancy Michal Zielinski Martin Steinegger Michalina Pacholska Tamas Berghammer Sebastian Bodenstein David Silver Oriol Vinyals Andrew W. Senior Koray Kavukcuoglu Pushmeet Kohli and Demis Hassabis. 2021. Highly accurate protein structure prediction with AlphaFold. Nature."},{"key":"e_1_3_2_1_22_1","volume-title":"Tiansheng Yao, Xinyang Yi, Ting Chen, Lichan Hong, and Ed H. Chi.","author":"Kang Wang-Cheng","year":"2021","unstructured":"Wang-Cheng Kang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyang Yi, Ting Chen, Lichan Hong, and Ed H. Chi. 2021. Learning to Embed Categorical Features without Embedding Tables for Recommendation. CoRR, arxiv:2010.10784"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"e_1_3_2_1_24_1","unstructured":"Sameer Kumar James Bradbury Cliff Young Yu Emma Wang Anselm Levskaya Blake Hechtman Dehao Chen HyoukJoong Lee Mehmet Deveci Naveen Kumar Pankaj Kanwar Shibo Wang Skye Wanderman-Milne Steve Lacy Tao Wang Tayo Oguntebi Yazhou Zu Yuanzhong Xu and Andy Swing. 2021. Exploring the limits of Concurrency in ML Training on Google TPUs. arxiv:2011.03641."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401436"},{"key":"e_1_3_2_1_26_1","volume-title":"Understanding Capacity-Driven Scale-Out Neural Recommendation Inference. In 2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).","author":"Lui Michael","year":"2021","unstructured":"Michael Lui, Yavuz Yetim, \u00d6zg\u00fcr \u00d6zkan, Zhuoran Zhao, Shin-Yeh Tsai, Carole-Jean Wu, and Mark Hempstead. 2021. Understanding Capacity-Driven Scale-Out Neural Recommendation Inference. In 2021 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389705"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of Machine Learning and Systems.","author":"Maeng Kiwan","year":"2021","unstructured":"Kiwan Maeng, Shivam Bharuka, Isabel Gao, Mark Jeffrey, Vikram Saraph, Bor-Yiing Su, Caroline Trippel, Jiyan Yang, Mike Rabbat, Brandon Lucia, and Carole-Jean Wu. 2021. Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery. In Proceedings of Machine Learning and Systems."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of Machine Learning and Systems.","author":"Mattson Peter","year":"2020","unstructured":"Peter Mattson, Christine Cheng, Gregory Diamos, Cody Coleman, Paulius Micikevicius, David Patterson, Hanlin Tang, Gu-Yeon Wei, Peter Bailis, Victor Bittorf, David Brooks, Dehao Chen, Debo Dutta, Udit Gupta, Kim Hazelwood, Andy Hock, Xinyuan Huang, Daniel Kang, David Kanter, Naveen Kumar, Jeffery Liao, Deepak Narayanan, Tayo Oguntebi, Gennady Pekhimenko, Lillian Pentecost, Vijay Janapa Reddi, Taylor Robie, Tom St John, Carole-Jean Wu, Lingjie Xu, Cliff Young, and Matei Zaharia. 2020. MLPerf Training Benchmark. In Proceedings of Machine Learning and Systems."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.14778\/3425879.3425883"},{"key":"e_1_3_2_1_31_1","unstructured":"Dheevatsa Mudigere Yuchen Hao Jianyu Huang Andrew Tulloch Srinivas Sridharan Xing Liu Mustafa Ozdal Jade Nie Jongsoo Park Liang Luo Jie Amy Yang Leon Gao Dmytro Ivchenko Aarti Basant Yuxi Hu Jiyan Yang Ehsan K. Ardestani Xiaodong Wang Rakesh Komuravelli Ching-Hsiang Chu Serhat Yilmaz Huayu Li Jiyuan Qian Zhuobo Feng Yinbin Ma Junjie Yang Ellie Wen Hong Li Lin Yang Chonglin Sun Whitney Zhao Dimitry Melts Krishna Dhulipala KR Kishore Tyler Graf Assaf Eisenman Kiran Kumar Matam Adi Gangidi Guoqiang Jerry Chen Manoj Krishnan Avinash Nayak Krishnakumar Nair Bharath Muthiah Mahmoud khorashadi Pallab Bhattacharya Petr Lapukhov Maxim Naumov Lin Qiao Mikhail Smelyanskiy Bill Jia and Vijay Rao. 2021. High-performance Distributed Training of Large-scale Deep Learning Recommendation Models. CoRR arxiv:2104.05158."},{"key":"e_1_3_2_1_32_1","unstructured":"Maxim Naumov John Kim Dheevatsa Mudigere Srinivas Sridharan Xiaodong Wang Whitney Zhao Serhat Yilmaz Changkyu Kim Hector Yuen Mustafa Ozdal Krishnakumar Nair Isabel Gao Bor-Yiing Su Jiyan Yang and Mikhail Smelyanskiy. 2020. Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems. CoRR arxiv:2003.09518."},{"key":"e_1_3_2_1_33_1","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson G. 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. arxiv:1906.00091."},{"key":"e_1_3_2_1_34_1","unstructured":"Yves Raimond. 2018. Deep Learning for Recommender Systems. https:\/\/www.slideshare.net\/moustaki\/deep-learning-for- recommender-systems-86752234"},{"key":"e_1_3_2_1_35_1","volume-title":"MLPerf Inference Benchmark. In 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA).","author":"Reddi Vijay Janapa","year":"2020","unstructured":"Vijay Janapa Reddi, Christine Cheng, David Kanter, Peter Mattson, Guenther Schmuelling, Carole-Jean Wu, Brian Anderson, Maximilien Breughe, Mark Charlebois, William Chou, Ramesh Chukka, Cody Coleman, Sam Davis, Pan Deng, Greg Diamos, Jared Duke, Dave Fick, J. Scott Gardner, Itay Hubara, Sachin Idgunji, Thomas B. Jablin, Jeff Jiao, Tom St. John, Pankaj Kanwar, David Lee, Jeffery Liao, Anton Lokhmotov, Francisco Massa, Peng Meng, Paulius Micikevicius, Colin Osborne, Gennady Pekhimenko, Arun Tejusve Raghunath Rajan, Dilip Sequeira, Ashish Sirasao, Fei Sun, Hanlin Tang, Michael Thomson, Frank Wei, Ephrem Wu, Lingjie Xu, Koichi Yamada, Bing Yu, George Yuan, Aaron Zhong, Peizhao Zhang, and Yuchen Zhou. 2020. MLPerf Inference Benchmark. In 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA)."},{"key":"e_1_3_2_1_36_1","unstructured":"Danny Sullivan. 2016. Google uses RankBrain for every search impacts rankings of \u201clots\u201d of them. https:\/\/searchengineland.com\/google-loves-rankbrain-uses-for-every-search-252526"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431388"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553516"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1029\/2020ms002109"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446763"},{"key":"e_1_3_2_1_42_1","volume-title":"Julian J. McAuley, Yves Raimond, and Hao Zhang.","author":"Wu Carole-Jean","year":"2020","unstructured":"Carole-Jean Wu, Robin Burke, Ed Chi, Joseph A. Konstan, Julian J. McAuley, Yves Raimond, and Hao Zhang. 2020. Developing a Recommendation Benchmark for MLPerf Training and Inference. CoRR, abs\/2003.07336 (2020), arxiv:2003.07336"},{"key":"e_1_3_2_1_43_1","unstructured":"Carole-Jean Wu Ramya Raghavendra Udit Gupta Bilge Acun Newsha Ardalani Kiwan Maeng Gloria Chang Fiona Aga Behram James Huang Charles Bai Michael Gschwind Anurag Gupta Myle Ott Anastasia Melnikov Salvatore Candido David Brooks Geeta Chauhan Benjamin Lee Hsien-Hsin S. Lee Bugra Akyildiz Maximilian Balandat Joe Spisak Ravi Jain Mike Rabbat and Kim Hazelwood. 2021. Sustainable AI: Environmental Implications Challenges and Opportunities. CoRR abs\/2111.00364 (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models. CoRR, abs\/2101.11714","author":"Yin Chunxing","year":"2021","unstructured":"Chunxing Yin, Bilge Acun, Xing Liu, and Carole-Jean Wu. 2021. TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models. CoRR, abs\/2101.11714 (2021), arxiv:2101.11714"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412227"},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of Machine Learning and Systems.","author":"Zhao Weijie","year":"2020","unstructured":"Weijie Zhao, Deping Xie, Ronglai Jia, Yulei Qian, Ruiquan Ding, Mingming Sun, and Ping Li. 2020. Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems. In Proceedings of Machine Learning and Systems."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015941"}],"event":{"name":"ASPLOS '22: 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Lausanne Switzerland","acronym":"ASPLOS '22","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507777","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503222.3507777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:50Z","timestamp":1750188650000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507777"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":48,"alternative-id":["10.1145\/3503222.3507777","10.1145\/3503222"],"URL":"https:\/\/doi.org\/10.1145\/3503222.3507777","relation":{},"subject":[],"published":{"date-parts":[[2022,2,22]]},"assertion":[{"value":"2022-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}