{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T16:07:54Z","timestamp":1788451674838,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King Abdullah University of Science and Technology Research Funding (KRF)","award":["ORA-CRG2022-5017"],"award-info":[{"award-number":["ORA-CRG2022-5017"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3721146.3721960","type":"proceedings-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T13:42:05Z","timestamp":1743514925000},"page":"176-182","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["OptimusNIC: Offloading Optimizer State to SmartNICs for Efficient Large-Scale AI Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4290-3514","authenticated-orcid":false,"given":"Achref","family":"Rebai","sequence":"first","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5051-4283","authenticated-orcid":false,"given":"Marco","family":"Canini","sequence":"additional","affiliation":[{"name":"KAUST, Thuwal, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD. AMD Alveo\u2122 V80 Compute Accelerator Card."},{"key":"e_1_3_2_1_2_1","volume-title":"AMSP: Reducing Communication Overhead of ZeRO for Efficient LLM Training","author":"Chen Qiaoling","year":"2024","unstructured":"Qiaoling Chen, Qinghao Hu, Guoteng Wang, Yingtong Xiong, Ting Huang, Xun Chen, Yang Gao, Hang Yan, Yonggang Wen, Tianwei Zhang, and Peng Sun. AMSP: Reducing Communication Overhead of ZeRO for Efficient LLM Training, 2024."},{"key":"e_1_3_2_1_3_1","unstructured":"NVIDIA Corporation. NVIDIA BlueField-3 DPU Specifications."},{"key":"e_1_3_2_1_4_1","unstructured":"NVIDIA Corporation. NVIDIA BlueField-2 DPU Specifications."},{"key":"e_1_3_2_1_5_1","volume-title":"NVIDIA DGX A100 User Guide","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation. NVIDIA DGX A100 User Guide, 2023."},{"key":"e_1_3_2_1_6_1","volume-title":"NVIDIA DGX H100\/H200 User Guide","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation. NVIDIA DGX H100\/H200 User Guide, 2023."},{"key":"e_1_3_2_1_7_1","volume-title":"The Llama 3 Herd of Models","author":"Abhimanyu Dubey","year":"2024","unstructured":"Abhimanyu Dubey et. al. The Llama 3 Herd of Models, 2024."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"e_1_3_2_1_10_1","volume-title":"Training Giant Neural Networks Using Weight Streaming on Cerebras Wafer-Scale Clusters","author":"Hall Stewart","year":"2022","unstructured":"Stewart Hall, Rob Schreiber, and Sean Lie. Training Giant Neural Networks Using Weight Streaming on Cerebras Wafer-Scale Clusters, 2022. Cerebras Systems White Paper."},{"key":"e_1_3_2_1_11_1","volume-title":"NeurIPS","author":"Huang Yanli","year":"2019","unstructured":"Yanli Huang, Shuyong Zhu, Xuying Meng, and Yujun Zhang. GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. In NeurIPS, 2019."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","first-page":"107297","DOI":"10.1109\/ACCESS.2024.3437203","volume":"12","author":"Kfoury Elie F.","year":"2024","unstructured":"Elie F. Kfoury, Samia Choueiri, Ali Mazloum, Ali AlSabeh, Jose Gomez, and Jorge Crichigno. A Comprehensive Survey on SmartNICs: Architectures, Development Models, Applications, and Research Directions. IEEE Access, 12:107297--107336, 2024.","journal-title":"Research Directions. IEEE Access"},{"key":"e_1_3_2_1_13_1","volume-title":"Marcin Chrapek, Rami Nudelman, Gil Bloch, and Torsten Hoefler. Network-Offloaded Bandwidth-Optimal Broadcast and Allgather for Distributed AI. In SC","author":"Khalilov Mikhail","year":"2024","unstructured":"Mikhail Khalilov, Salvatore Di Girolamo, Marcin Chrapek, Rami Nudelman, Gil Bloch, and Torsten Hoefler. Network-Offloaded Bandwidth-Optimal Broadcast and Allgather for Distributed AI. In SC, 2024."},{"key":"e_1_3_2_1_14_1","volume-title":"ImageNet classification with deep convolutional neural networks. Commun. ACM, 60(6)","author":"Krizhevsky Alex","year":"2017","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. ImageNet classification with deep convolutional neural networks. Commun. ACM, 60(6), 2017."},{"key":"e_1_3_2_1_15_1","volume-title":"NSDI","author":"Lao ChonLam","year":"2021","unstructured":"ChonLam Lao, Yanfang Le, Kshiteej Mahajan, Yixi Chen, Wenfei Wu, Aditya Akella, and Michael Swift. ATP: In-Network Aggregation for Multi-Tenant Learning. In NSDI, 2021."},{"issue":"2","key":"e_1_3_2_1_16_1","volume":"21","author":"Ma Rui","year":"2022","unstructured":"Rui Ma, Evangelos Georganas, Alexander Heinecke, Sergey Gribok, Andrew Boutros, and Eriko Nurvitadhi. FPGA-Based AI Smart NICs for Scalable Distributed AI Training Systems. IEEE Computer Architecture Letters, 21(2), 2022.","journal-title":"Eriko Nurvitadhi. FPGA-Based AI Smart NICs for Scalable Distributed AI Training Systems. IEEE Computer Architecture Letters"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_18_1","volume-title":"SC","author":"Rajbhandari Samyam","year":"2021","unstructured":"Samyam Rajbhandari, Olatunji Ruwase, Jeff Rasley, Shaden Smith, and Yuxiong He. ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning. In SC, 2021."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the SIGCOMM Workshop on Networks for AI Computing","author":"Rebai Achref","year":"2024","unstructured":"Achref Rebai, Mubarak Adetunji Ojewale, Anees Ullah, Marco Canini, and Suhaib A. Fahmy. SqueezeNIC: Low-Latency In-NIC Compression for Distributed Deep Learning. In Proceedings of the SIGCOMM Workshop on Networks for AI Computing, 2024."},{"key":"e_1_3_2_1_20_1","volume-title":"DCC","author":"Ren Qingqing","year":"2022","unstructured":"Qingqing Ren, Shuyong Zhu, Xuying Meng, and Yujun Zhang. Gradient Compression for Distributed Training in Deep Learning. In DCC, 2022."},{"key":"e_1_3_2_1_21_1","volume-title":"NSDI","author":"Sapio Amedeo","year":"2021","unstructured":"Amedeo Sapio, Marco Canini, Chen-Yu Ho, Jacob Nelson, Panos Kalnis, Changhoon Kim, Arvind Krishnamurthy, Masoud Moshref, Dan Ports, and Peter Richtarik. Scaling Distributed Machine Learning with In-Network Aggregation. In NSDI, 2021."},{"key":"e_1_3_2_1_22_1","volume-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","author":"Shoeybi Mohammad","year":"2020","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism, 2020."},{"key":"e_1_3_2_1_23_1","volume-title":"LuWu: An End-to-End In-Network Out-of-Core Optimizer for 100B-Scale Model-in-Network Data-Parallel Training on Distributed GPUs","author":"Sun Mo","year":"2024","unstructured":"Mo Sun, Zihan Yang, Changyue Liao, Yingtao Li, Fei Wu, and Zeke Wang. LuWu: An End-to-End In-Network Out-of-Core Optimizer for 100B-Scale Model-in-Network Data-Parallel Training on Distributed GPUs, 2024."},{"key":"e_1_3_2_1_24_1","volume-title":"ICLR","author":"Wang Guanhua","year":"2024","unstructured":"Guanhua Wang, Heyang Qin, Sam Ade Jacobs, Xiaoxia Wu, Connor Holmes, Zhewei Yao, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, and Yuxiong He. ZeRO++: Extremely Efficient Collective Communication for Large Model Training. In ICLR, 2024."},{"key":"e_1_3_2_1_25_1","volume-title":"SC","author":"Xu Dong","year":"2024","unstructured":"Dong Xu, Yuan Feng, Kwangsik Shin, Daewoo Kim, Hyeran Jeon, and Dong Li. Efficient Tensor Offloading for Large Deep-Learning Model Training based on Compute Express Link. In SC, 2024."},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. VLDB Endow., 16(12)","author":"Zhao Yanli","year":"2023","unstructured":"Yanli Zhao, Andrew Gu, Rohan Varma, Liang Luo, Chien-Chin Huang, Min Xu, Less Wright, Hamid Shojanazeri, Myle Ott, Sam Shleifer, Alban Desmaison, Can Balioglu, Pritam Damania, Bernard Nguyen, Geeta Chauhan, Yuchen Hao, Ajit Mathews, and Shen Li. PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel. Proc. VLDB Endow., 16(12), 2023."}],"event":{"name":"EuroMLSys '25: 5th Workshop on Machine Learning and Systems","location":"World Trade Center Rotterdam Netherlands","acronym":"EuroMLSys '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 5th Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721146.3721960","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721146.3721960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:57:39Z","timestamp":1750283859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721146.3721960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":25,"alternative-id":["10.1145\/3721146.3721960","10.1145\/3721146"],"URL":"https:\/\/doi.org\/10.1145\/3721146.3721960","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-04-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}