{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:40:02Z","timestamp":1755974402563,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"King Abdullah University of Science and Technology (KAUST) Office of Research Administration (ORA)","award":["ORA-CRG2020-4382"],"award-info":[{"award-number":["ORA-CRG2020-4382"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,4]]},"DOI":"10.1145\/3672198.3673793","type":"proceedings-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T12:24:10Z","timestamp":1721132650000},"page":"1-3","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Proof-of-Concept of a Flexible and High-Fidelity Approach to Distributed DNN Training Emulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9932-6096","authenticated-orcid":false,"given":"Banruo","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University and interning at KAUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3861-1782","authenticated-orcid":false,"given":"Mubarak Adetunji","family":"Ojewale","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2829-0319","authenticated-orcid":false,"given":"Yuhan","family":"Ding","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5051-4283","authenticated-orcid":false,"given":"Marco","family":"Canini","sequence":"additional","affiliation":[{"name":"KAUST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3635867"},{"key":"e_1_3_2_1_2_1","unstructured":"Jehyeon Bang Yujeong Choi Myeongwoo Kim Yongdeok Kim and Minsoo Rhu. 2023. vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training. (2023). arXiv:cs.LG\/2312.12391"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Wei Deng Junwei Pan Tian Zhou Deguang Kong Aaron Flores and Guang Lin. 2021. DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving. In WSDM.","DOI":"10.1145\/3437963.3441727"},{"key":"e_1_3_2_1_4_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT."},{"key":"e_1_3_2_1_5_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In CVPR."},{"key":"e_1_3_2_1_6_1","volume-title":"Tutel: Adaptive Mixture-of-Experts at Scale. In MLSys.","author":"Hwang Changho","year":"2023","unstructured":"Changho Hwang, Wei Cui, Yifan Xiong, Ziyue Yang, Ze Liu, Han Hu, Zilong Wang, Rafael Salas, Jithin Jose, Prabhat Ram, Joe Chau, Peng Cheng, Fan Yang, Mao Yang, and Yongqiang Xiong. 2023. Tutel: Adaptive Mixture-of-Experts at Scale. In MLSys."},{"key":"e_1_3_2_1_7_1","volume-title":"Chun cheng Jason Chen, and Mosharaf Chowdhury","author":"Lai Fan","year":"2023","unstructured":"Fan Lai, Wei Zhang, Rui Liu, William Tsai, Xiaohan Wei, Yuxi Hu, Sabin Devkota, Jianyu Huang, Jongsoo Park, Xing Liu, Zeliang Chen, Ellie Wen, Paul Rivera, Jie You, Chun cheng Jason Chen, and Mosharaf Chowdhury. 2023. AdaEmbed: Adaptive Embedding for Large-Scale Recommendation Models. In OSDI."},{"key":"e_1_3_2_1_8_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. (2019). arXiv:cs.CL\/1907.11692"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Radhika Mittal Alexander Shpiner Aurojit Panda Eitan Zahavi Arvind Krishnamurthy Sylvia Ratnasamy and Scott Shenker. 2018. Revisiting Network Support for RDMA. In SIGCOMM.","DOI":"10.1145\/3230543.3230557"},{"key":"e_1_3_2_1_10_1","unstructured":"NVIDIA. 2024. Collective Communication Library (NCCL). (2024). https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Saeed Rashidi Srinivas Sridharan Sudarshan Srinivasan and Tushar Krishna. 2020. ASTRA-SIM: Enabling SW\/HW Co-Design Exploration for Distributed DL Training Platforms. In ISPASS.","DOI":"10.1109\/ISPASS48437.2020.00018"},{"key":"e_1_3_2_1_12_1","volume-title":"Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models. In ISCA.","author":"Rashidi Saeed","year":"2022","unstructured":"Saeed Rashidi, William Won, Sudarshan Srinivasan, Srinivas Sridharan, and Tushar Krishna. 2022. Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models. In ISCA."},{"key":"e_1_3_2_1_13_1","volume-title":"Zuluaga","author":"Wilfredo J.","year":"2022","unstructured":"Wilfredo J. Robinson M., Flavio Esposito, and Maria A. Zuluaga. 2022. DTS: A Simulator to Estimate the Training Time of Distributed Deep Neural Networks. In MASCOTS."},{"key":"e_1_3_2_1_14_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2020. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. (2020). arXiv:cs.CL\/1909.08053"},{"key":"e_1_3_2_1_15_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. (2023). arXiv:cs.CL\/2302.13971"},{"key":"e_1_3_2_1_16_1","volume-title":"Xiaoxia Wu, Connor Holmes, Zhewei Yao, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, and Yuxiong He.","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. 2024. ZeRO ++: Extremely Efficient Collective Communication for Large Model Training. In ICLR."},{"key":"e_1_3_2_1_17_1","unstructured":"William Won Taekyung Heo Saeed Rashidi Srinivas Sridharan Sudarshan Srinivasan and Tushar Krishna. 2023. ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale. In ISPASS."},{"key":"e_1_3_2_1_18_1","volume-title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In OSDI.","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In OSDI."}],"event":{"name":"ACM SIGCOMM '24: ACM SIGCOMM 2024 Conference","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"],"location":"Sydney NSW Australia","acronym":"ACM SIGCOMM '24"},"container-title":["Proceedings of the 2024 SIGCOMM Workshop on Networks for AI Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672198.3673793","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3672198.3673793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:15:30Z","timestamp":1755972930000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3672198.3673793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,4]]},"references-count":18,"alternative-id":["10.1145\/3672198.3673793","10.1145\/3672198"],"URL":"https:\/\/doi.org\/10.1145\/3672198.3673793","relation":{},"subject":[],"published":{"date-parts":[[2024,8,4]]},"assertion":[{"value":"2024-08-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}