{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:05:35Z","timestamp":1780664735771,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3803590","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"759-779","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HetAuto: Cross-Cluster Auto-Parallelism for Heterogeneous Distributed Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0606-5109","authenticated-orcid":false,"given":"Guicheng","family":"Qi","sequence":"first","affiliation":[{"name":"Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0537-4004","authenticated-orcid":false,"given":"Junwei","family":"Su","sequence":"additional","affiliation":[{"name":"Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0152-8304","authenticated-orcid":false,"given":"Liqi","family":"Yang","sequence":"additional","affiliation":[{"name":"Meituan Corporation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9918-6003","authenticated-orcid":false,"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"Meituan Corporation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4739-9450","authenticated-orcid":false,"given":"Tingwen","family":"Xie","sequence":"additional","affiliation":[{"name":"Meituan Corporation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5452-001X","authenticated-orcid":false,"given":"Yerui","family":"Sun","sequence":"additional","affiliation":[{"name":"Meituan Corporation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6978-064X","authenticated-orcid":false,"given":"Yuchen","family":"Xie","sequence":"additional","affiliation":[{"name":"Meituan Corporation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3144-4398","authenticated-orcid":false,"given":"Chuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Computer Science, The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"RCCL: ROCm Communication Collectives Library. https:\/\/github.com\/ROCmSoftwarePlatform\/rccl.","author":"Devices Advanced Micro","year":"2024","unstructured":"Advanced Micro Devices. 2024. RCCL: ROCm Communication Collectives Library. https:\/\/github.com\/ROCmSoftwarePlatform\/rccl."},{"key":"e_1_3_2_1_2_1","unstructured":"Advanced Micro Devices. 2024. ROCm: Radeon Open Compute Platform. https:\/\/rocm.docs.amd.com\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Reed Albergotti. 2024. Microsoft Azure CTO: US data centers will soon hit size limits. Semafor. Technology."},{"key":"e_1_3_2_1_4_1","unstructured":"Anthropic. 2025. Claude Sonnet 4. https:\/\/www.anthropic.com\/claude Large language model."},{"key":"e_1_3_2_1_5_1","volume-title":"Random forests. Machine learning 45, 1","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5\u201332."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2025 USENIX Annual Technical Conference, USENIX ATC 2025","author":"Chen Tiancheng","year":"2025","unstructured":"Tiancheng Chen, Ales Kubicek, Langwen Huang, and Torsten Hoefler. 2025. CrossPipe: Towards Optimal Pipeline Schedules for Cross-Datacenter Training. In Proceedings of the 2025 USENIX Annual Technical Conference, USENIX ATC 2025, Boston, MA, USA, July 7\u20139, 2025, Deniz Altinb\u00fcken and Ryan Stutsman (Eds.). USENIX Association, 1089\u20131108. https:\/\/www.usenix.org\/conference\/atc25\/presentation\/chen-tiancheng"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624661"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620678.3624669"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2004.11.016"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Tri Dao Daniel Y Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. In NeurIPS.","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_2_1_14_1","unstructured":"DeepSeek-AI. 2025. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3443255"},{"key":"e_1_3_2_1_16_1","unstructured":"Energy Sciences Network (ESnet). 2014. iPerf3:A TCP UDP and SCTP network bandwidth measurement tool. https:\/\/iperf.fr\/ Network performance measurement tool."},{"key":"e_1_3_2_1_17_1","volume-title":"Gloo: A Collective Communications Library. https:\/\/github.com\/facebookincubator\/gloo.","year":"2017","unstructured":"Facebook. 2017. Gloo: A Collective Communications Library. https:\/\/github.com\/facebookincubator\/gloo."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData62323.2024.10825098"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"e_1_3_2_1_20_1","first-page":"1","article-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. Journal of Machine Learning Research 23, 120 (2022), 1\u201339. http:\/\/jmlr.org\/papers\/v23\/21-0998.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698535"},{"key":"e_1_3_2_1_22_1","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2018. Accurate Large Minibatch SGD: Training ImageNet in 1 Hour. arXiv:1706.02677"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230545"},{"key":"e_1_3_2_1_24_1","volume-title":"Dehao Chen, Hyouk Joong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, Hyouk Joong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: efficient training of giant neural networks using pipeline parallelism. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_25_1","volume-title":"CANN: Compute Architecture for Neural Networks. https:\/\/www.hiascend.com\/software\/cann.","year":"2023","unstructured":"Huawei. 2023. CANN: Compute Architecture for Neural Networks. https:\/\/www.hiascend.com\/software\/cann."},{"key":"e_1_3_2_1_26_1","volume-title":"HCCL: Huawei Collective Communication Library. https:\/\/www.hiascend.com\/cann\/hccl.","year":"2023","unstructured":"Huawei. 2023. HCCL: Huawei Collective Communication Library. https:\/\/www.hiascend.com\/cann\/hccl."},{"key":"e_1_3_2_1_27_1","unstructured":"Huawei. 2023. torch_npu: PyTorch extension for Huawei Ascend NPU. https:\/\/gitee.com\/ascend\/pytorch."},{"key":"e_1_3_2_1_28_1","volume-title":"Samyam Rajbhandari, and Yuxiong He.","author":"Jacobs Sam Ade","year":"2023","unstructured":"Sam Ade Jacobs, Masahiro Tanaka, Chengming Zhang, Minjia Zhang, Shuaiwen Leon Song, Samyam Rajbhandari, and Yuxiong He. 2023. DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models. arXiv:2309.14509 [cs.LG] https:\/\/arxiv.org\/abs\/2309.14509"},{"key":"e_1_3_2_1_29_1","volume-title":"2019 USENIX Annual Technical Conference (ATC). 947\u2013960","author":"Jeon Myeongjae","year":"2019","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Wencong Xiao, and Fan Yang. 2019. Analysis of large-scale multi-tenant GPU clusters for DNN training workloads. In 2019 USENIX Annual Technical Conference (ATC). 947\u2013960."},{"key":"e_1_3_2_1_30_1","volume-title":"2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Jia Xianyan","year":"2022","unstructured":"Xianyan Jia, Le Jiang, Ang Wang, Wencong Xiao, Ziji Shi, Jie Zhang, Xinyuan Li, Langshi Chen, Yong Li, Zhen Zheng, Xiaoyong Liu, and Wei Lin. 2022. Whale: Efficient Giant Model Training over Heterogeneous GPUs. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). USENIX Association, Carlsbad, CA, 673\u2013688. https:\/\/www.usenix.org\/conference\/atc22\/presentation\/jia-xianyan"},{"key":"e_1_3_2_1_31_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra Singh Chaplot Diego de las Casas Emma Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2024. Mixtral of Experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626336"},{"key":"e_1_3_2_1_33_1","volume-title":"Adam: A Method for Stochastic Optimization. In ICLR.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"e_1_3_2_1_35_1","unstructured":"Vijay Korthikanti Jared Casper Sangkug Lym Lawrence McAfee Michael Andersch Mohammad Shoeybi and Bryan Catanzaro. 2022. Reducing Activation Recomputation in Large Transformer Models. arXiv:2205.05198 [cs.LG] https:\/\/arxiv.org\/abs\/2205.05198"},{"key":"e_1_3_2_1_36_1","volume-title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In 9th International Conference on Learning Representations (ICLR). OpenReview.net.","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In 9th International Conference on Learning Representations (ICLR). OpenReview.net."},{"key":"e_1_3_2_1_37_1","unstructured":"Cheng Li. 2023. LLM-Analysis: Latency and Memory Analysis of Transformer Models for Training and Inference. https:\/\/github.com\/cli99\/llm-analysis."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0480"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476145"},{"key":"e_1_3_2_1_40_1","volume-title":"Classification and regression by randomForest. R news 2, 3","author":"Liaw Andy","year":"2002","unstructured":"Andy Liaw and Matthew Wiener. 2002. Classification and regression by randomForest. R news 2, 3 (2002), 18\u201322."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629554"},{"key":"e_1_3_2_1_42_1","unstructured":"Hao Liu Matei Zaharia and Pieter Abbeel. 2023. Ring Attention with Blockwise Transformers for Near-Infinite Context. arXiv:2310.01889 [cs.CL] https:\/\/arxiv.org\/abs\/2310.01889"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) (Proceedings of Machine Learning Research","volume":"1282","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Ag\u00fcera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) (Proceedings of Machine Learning Research, Vol. 54). PMLR, 1273\u20131282."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3570690.3570697"},{"key":"e_1_3_2_1_45_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 276\u2013281","author":"Milojicic Dejan","year":"2021","unstructured":"Dejan Milojicic, Paolo Faraboschi, Nicolas Dube, and Duncan Roweth. 2021. Future of HPC: Diversifying heterogeneity. In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 276\u2013281."},{"key":"e_1_3_2_1_46_1","volume-title":"Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21)","author":"Mohan Jayashree","year":"2021","unstructured":"Jayashree Mohan, Amar Phanishayee, and Vijay Chidambaram. 2021. CheckFreq: Frequent, Fine-Grained DNN Checkpointing. In 19th USENIX Conference on File and Storage Technologies (FAST 21). USENIX Association, 203\u2013216. https:\/\/www.usenix.org\/conference\/fast21\/presentation\/mohan"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_49_1","unstructured":"NVIDIA. 2020. NVIDIA A100 Tensor Core GPU Architecture. Whitepaper. https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf"},{"key":"e_1_3_2_1_50_1","unstructured":"NVIDIA. 2022. NVIDIA H100 Tensor Core GPU Architecture. Whitepaper. https:\/\/resources.nvidia.com\/en-us-tensor-core\/gtc22-whitepaper-hopper"},{"key":"e_1_3_2_1_51_1","volume-title":"NCCL: NVIDIA Collective Communications Library. https:\/\/developer.nvidia.com\/nccl.","author":"NVIDIA.","year":"2023","unstructured":"NVIDIA. 2023. NCCL: NVIDIA Collective Communications Library. https:\/\/developer.nvidia.com\/nccl."},{"key":"e_1_3_2_1_52_1","unstructured":"NVIDIA Corporation. 2024. CUDA C++ Programming Guide. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/ Version 12.3."},{"key":"e_1_3_2_1_53_1","unstructured":"OpenAI. 2023. GPT-4. https:\/\/openai.com\/gpt-4."},{"key":"e_1_3_2_1_54_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et al. 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in neural information processing systems. 8024\u20138035."},{"key":"e_1_3_2_1_55_1","unstructured":"PyTorch Team. 2023. PyTorch Dispatcher: A Technical Deep Dive. https:\/\/pytorch.org\/blog\/pytorch-dispatcher\/."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS63083.2025.00033"},{"key":"e_1_3_2_1_57_1","unstructured":"Penghui Qi Xinyi Wan Guangxing Huang and Min Lin. 2023. Zero Bubble Pipeline Parallelism. arXiv:2401.10241 [cs.DC] https:\/\/arxiv.org\/abs\/2401.10241"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Rajbhandari Samyam","year":"2020","unstructured":"Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He. 2020. ZeRO: memory optimizations toward training trillion parameter models. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Atlanta, Georgia) (SC '20). IEEE Press, Article 20, 16 pages."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_1_60_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In 5th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=B1ckMDqlg","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc V. Le, Geoffrey E. Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In 5th International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"e_1_3_2_1_61_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. arXiv:1909.08053"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655843"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731569.3764839"},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21)","author":"Tarnawski Jakub","year":"2021","unstructured":"Jakub Tarnawski, Deepak Narayanan, and Amar Phanishayee. 2021. Piper: multidimensional planner for DNN parallelization. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21). Curran Associates Inc., Red Hook, NY, USA, Article 1902, 12 pages."},{"key":"e_1_3_2_1_65_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. arXiv:2302.13971 [cs.CL]"},{"key":"e_1_3_2_1_66_1","volume-title":"Proceedings of the 2024 USENIX Conference on Usenix Annual Technical Conference (Santa Clara, CA, USA) (USENIX ATC'24). USENIX Association, USA, Article 35","author":"Um Taegeon","year":"2024","unstructured":"Taegeon Um, Byungsoo Oh, Minyoung Kang, Woo-Yeon Lee, Goeun Kim, Dongseob Kim, Youngtaek Kim, Mohd Muzzammil, and Myeongjae Jeon. 2024. Metis: fast automatic distributed training on heterogeneous GPUs. In Proceedings of the 2024 USENIX Conference on Usenix Annual Technical Conference (Santa Clara, CA, USA) (USENIX ATC'24). USENIX Association, USA, Article 35, 16 pages."},{"key":"e_1_3_2_1_67_1","volume-title":"Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Unger Colin","year":"2022","unstructured":"Colin Unger, Zhihao Jia, Wei Wu, Sina Lin, Mandeep Baines, Carlos Efrain Quintero Narvaez, Vinay Ramakrishnaiah, Nirmal Prajapati, Pat McCormick, Jamaludin Mohd-Yusof, Xi Luo, Dheevatsa Mudigere, Jongsoo Park, Misha Smelyanskiy, and Alex Aiken. 2022. Unity: Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 267\u2013284. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/unger"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_69_1","volume-title":"ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25)","author":"Wan Borui","year":"2025","unstructured":"Borui Wan, Mingji Han, Yiyao Sheng, Yanghua Peng, Haibin Lin, Mofan Zhang, Zhichao Lai, Menghan Yu, Junda Zhang, Zuquan Song, Xin Liu, and Chuan Wu. 2025. ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development. In 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 25). USENIX Association, Philadelphia, PA, 559\u2013578. https:\/\/www.usenix.org\/conference\/nsdi25\/presentation\/wan-borui"},{"key":"e_1_3_2_1_70_1","volume-title":"Astra: Efficient and Money-saving Automatic Parallel Strategies Search on Heterogeneous GPUs. arXiv:2502.13480 [cs.DC] https:\/\/arxiv.org\/abs\/2502.13480","author":"Wang Peiran","year":"2025","unstructured":"Peiran Wang, Haibing Li, Fu Haohan, Shiyong Li, Yanpeng Wang, and Dou Shen. 2025. Astra: Efficient and Money-saving Automatic Parallel Strategies Search on Heterogeneous GPUs. arXiv:2502.13480 [cs.DC] https:\/\/arxiv.org\/abs\/2502.13480"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"e_1_3_2_1_72_1","volume-title":"Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21)","author":"Yu Geoffrey X.","year":"2021","unstructured":"Geoffrey X. Yu, Yubo Gao, Pavel Golikov, and Gennady Pekhimenko. 2021. Habitat: A Runtime-Based Computational Performance Predictor for Deep Neural Network Training. In 2021 USENIX Annual Technical Conference (USENIX ATC 21). USENIX Association, 503\u2013521. https:\/\/www.usenix.org\/conference\/atc21\/presentation\/yu"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629580"},{"key":"e_1_3_2_1_74_1","volume-title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","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 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 559\u2013578. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin"},{"key":"e_1_3_2_1_75_1","volume-title":"Daydream: Accurately Estimating the Efficacy of Optimizations for DNN Training. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zhu Hongyu","year":"2020","unstructured":"Hongyu Zhu, Mohamed Akrout, Boyuan Zheng, Andrew Pelegris, Anand Jayarajan, Amar Phanishayee, Bianca Schroeder, and Gennady Pekhimenko. 2020. Daydream: Accurately Estimating the Efficacy of Optimizations for DNN Training. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). 337\u2013352."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717461"},{"key":"e_1_3_2_1_77_1","volume-title":"Proceedings of Machine Learning and Systems, D. Song, M. Carbin, and T. Chen (Eds.)","volume":"5","author":"Zhuang Yonghao","year":"2023","unstructured":"Yonghao Zhuang, Lianmin Zheng, Zhuohan Li, Eric Xing, Qirong Ho, Joseph Gonzalez, Ion Stoica, Hao Zhang, and Hexu Zhao. 2023. On Optimizing the Communication of Model Parallelism. In Proceedings of Machine Learning and Systems, D. Song, M. Carbin, and T. Chen (Eds.), Vol. 5. Curan, 526\u2013540. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/file\/a42cbafcabb6dc7ce77bfe2e80f5c772-Paper-mlsys2023.pdf"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10228-y"}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3803590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:18:36Z","timestamp":1780661916000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3803590"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":78,"alternative-id":["10.1145\/3767295.3803590","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3803590","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}