{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T08:54:57Z","timestamp":1775638497946,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2106635"],"award-info":[{"award-number":["2106635"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002484","name":"Micron Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002484","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3545008.3545054","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T01:04:08Z","timestamp":1673744648000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Exploiting CXL-based Memory for Distributed Deep Learning"],"prefix":"10.1145","author":[{"given":"Moiz","family":"Arif","sequence":"first","affiliation":[{"name":"Computer Science, Rochester Institute of Technology, United States of America"}]},{"given":"Kevin","family":"Assogba","sequence":"additional","affiliation":[{"name":"Computer Science, Rochester Institute of Technology, United States of America"}]},{"given":"M. Mustafa","family":"Rafique","sequence":"additional","affiliation":[{"name":"Computer Science, Rochester Institute of Technology, United States of America"}]},{"given":"Sudharshan","family":"Vazhkudai","sequence":"additional","affiliation":[{"name":"Micron Technology, Inc., United States of America"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2022. FIO - flexible i\/o tester synthetic benchmark. https:\/\/github.com\/axboe\/fio"},{"key":"e_1_3_2_1_2_1","unstructured":"2022. Gen-Z. https:\/\/genzconsortium.org\/"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. Intel PCM. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/performance-counter-monitor.html"},{"key":"e_1_3_2_1_4_1","unstructured":"2022. NVIDIA Data Loading Library (DALI). https:\/\/developer.nvidia.com\/DALI"},{"key":"e_1_3_2_1_5_1","unstructured":"2022. OakRidge Learning Computing Facility (OLCF). https:\/\/www.olcf.ornl.gov\/"},{"key":"e_1_3_2_1_6_1","unstructured":"2022. SYSSTAT. http:\/\/sebastien.godard.pagesperso-orange.fr\/"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 12th USENIX symposium on operating systems design and implementation (OSDI). USENIX Association, 265\u2013283","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 Proceedings of the 12th USENIX symposium on operating systems design and implementation (OSDI). USENIX Association, 265\u2013283."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS50786.2020.9285969"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00031"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDSW-DISCS.2018.00011"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357569"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337902"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476181"},{"key":"e_1_3_2_1_16_1","volume-title":"The network RamDisk: Using remote memory on heterogeneous NOWs. Cluster computing 2, 4","author":"Flouris D","year":"1999","unstructured":"Michail\u00a0D Flouris and Evangelos\u00a0P Markatos. 1999. The network RamDisk: Using remote memory on heterogeneous NOWs. Cluster computing 2, 4 (1999), 281\u2013293."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3012173"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI). USENIX Association","author":"Gu Juncheng","year":"2017","unstructured":"Juncheng Gu, Youngmoon Lee, Yiwen Zhang, Mosharaf Chowdhury, and Kang\u00a0G. Shin. 2017. Efficient Memory Disaggregation with Infiniswap. In Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI). USENIX Association, Boston, MA, 649\u2013667."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078468.3078483"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_21_1","unstructured":"Andrew\u00a0G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. CoRR abs\/1704.04861(2017). arXiv:1704.04861"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3035933"},{"key":"e_1_3_2_1_23_1","volume-title":"Green","author":"Jiang Wenbin","unstructured":"Wenbin Jiang, Pai Liu, Hai Jin, and Jing Peng. 2020. An Efficient Data Prefetch Strategy for Deep Learning Based on Non-volatile Memory. In Green, Pervasive, and Cloud Computing, Zhiwen Yu, Christian Becker, and Guoliang Xing (Eds.). Springer, Cham, 101\u2013114."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422575.3422804"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E52221.2021.00024"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671461"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 18th USENIX Conference on File and Storage Technologies (FAST). USENIX Association","author":"Kumar Abhishek\u00a0Vijaya","year":"2020","unstructured":"Abhishek\u00a0Vijaya Kumar and Muthian Sivathanu. 2020. Quiver: An Informed Storage Cache for Deep Learning. In Proceedings of the 18th USENIX Conference on File and Storage Technologies (FAST). USENIX Association, Santa Clara, CA, 283\u2013296."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-03101-3"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00096"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3363554"},{"key":"e_1_3_2_1_31_1","volume-title":"Memory bandwidth and machine balance in current high performance computers","author":"D McCalpin","year":"1995","unstructured":"John\u00a0D McCalpin 1995. Memory bandwidth and machine balance in current high performance computers. IEEE computer society technical committee on computer architecture (TCCA) newsletter 2, 19-25 (1995)."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the USENIX annual technical conference","author":"McVoy W","year":"1996","unstructured":"Larry\u00a0W McVoy, Carl Staelin, 1996. lmbench: Portable Tools for Performance Analysis.. In Proceedings of the USENIX annual technical conference. San Diego, CA, USA, USENIX Association, 279\u2013294."},{"key":"e_1_3_2_1_33_1","unstructured":"Derek\u00a0Gordon Murray Jiri Simsa Ana Klimovic and Ihor Indyk. 2021. tf.data: A Machine Learning Data Processing Framework. CoRR abs\/2101.12127(2021). arXiv:2101.12127"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00033"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806887"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems, Vol.\u00a032","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Proceedings of the Advances in Neural Information Processing Systems, Vol.\u00a032. Curran Associates, Inc."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW52791.2021.00127"},{"key":"e_1_3_2_1_38_1","volume-title":"Improved protein structure prediction using potentials from deep learning. Nature 577, 7792","author":"Senior W","year":"2020","unstructured":"Andrew\u00a0W Senior, Richard Evans, John Jumper, James Kirkpatrick, Laurent Sifre, Tim Green, Chongli Qin, Augustin \u017d\u00eddek, Alexander\u00a0WR Nelson, Alex Bridgland, 2020. Improved protein structure prediction using potentials from deep learning. Nature 577, 7792 (2020), 706\u2013710."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3008250"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2019.00017"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3517824"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446083"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3003665.3003669"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.12.004"},{"key":"e_1_3_2_1_46_1","unstructured":"Zhao Zhang Lei Huang Uri Manor Linjing Fang Gabriele Merlo Craig Michoski John Cazes and Niall Gaffney. 2018. FanStore: Enabling Efficient and Scalable I\/O for Distributed Deep Learning. CoRR abs\/1809.10799(2018). arXiv:1809.10799"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891023"}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","location":"Bordeaux France","acronym":"ICPP '22"},"container-title":["Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545054","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545054","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545054","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:44Z","timestamp":1750186964000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545054"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":47,"alternative-id":["10.1145\/3545008.3545054","10.1145\/3545008"],"URL":"https:\/\/doi.org\/10.1145\/3545008.3545054","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}