{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:30:33Z","timestamp":1773588633455,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62032023, T2125013, and 62172391"],"award-info":[{"award-number":["62032023, T2125013, and 62172391"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3779212.3790230","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:55:26Z","timestamp":1773150926000},"page":"1949-1965","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["T-Control: An Efficient Dynamic Tensor Rematerialization System for DNN Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3591-3051","authenticated-orcid":false,"given":"Zehua","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0457-4709","authenticated-orcid":false,"given":"Junmin","family":"Xiao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4060-707X","authenticated-orcid":false,"given":"Xiaochuan","family":"Deng","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6108-4232","authenticated-orcid":false,"given":"Huibing","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7083-9552","authenticated-orcid":false,"given":"Hui","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4266-908X","authenticated-orcid":false,"given":"Mingyi","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5386-3067","authenticated-orcid":false,"given":"Yunfei","family":"Pang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6361-5948","authenticated-orcid":false,"given":"Guangming","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Gustaf Ahdritz Nazim Bouatta Christina Floristean Sachin Kadyan Qinghui Xia William Gerecke Timothy J O'Donnell Daniel Berenberg Ian Fisk Niccol\u00f2 Zanichelli et al. 2024. OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. Nature Methods (2024) 1-11. doi:10.1038\/s41592-024-02272-z","DOI":"10.1038\/s41592-024-02272-z"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1906679"},{"key":"e_1_3_2_1_4_1","first-page":"23844","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Beaumont Olivier","year":"2021","unstructured":"Olivier Beaumont, Lionel Eyraud-Dubois, and Alena Shilova. 2021. Efficient Combination of Rematerialization and Offloading for Training DNNs. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 23844-23857. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/c8461bf13fca8a2b9912ab2eb1668e4b-Paper.pdf"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/0022250X.2001.9990249"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.socnet.2007.11.001"},{"key":"e_1_3_2_1_7_1","first-page":"1877","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877-1901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.110"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651330"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training Deep Nets with Sublinear Memory Cost. arXiv:1604.06174 [cs.LG] doi:10.48550\/arXiv.1604.06174","DOI":"10.48550\/arXiv.1604.06174"},{"key":"e_1_3_2_1_11_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, Vol. 23, 120 (2022), 1-39. http:\/\/jmlr.org\/papers\/v23\/21-0998.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.2307\/3033543"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640423"},{"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","first-page":"59","article-title":"Topological structures","volume":"52","author":"Herrlich Horst","year":"1974","unstructured":"Horst Herrlich. 1974. Topological structures. Math. Centre Tracts, Vol. 52 (1974), 59-122. https:\/\/www.mathunion.org\/fileadmin\/ICM\/Proceedings\/ICM1974.2\/ICM1974.2.ocr.pdf","journal-title":"Math. Centre Tracts"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524059.3532394"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7119"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Forrest Iandola Matt Moskewicz Sergey Karayev Ross Girshick Trevor Darrell and Kurt Keutzer. 2014. DenseNet: Implementing Efficient ConvNet Descriptor Pyramids. arXiv:1404.1869 [cs.CV] doi:10.48550\/arXiv.1404.1869","DOI":"10.48550\/arXiv.1404.1869"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of Machine Learning and Systems, I. Dhillon, D. Papailiopoulos, and V. Sze (Eds.)","volume":"2","author":"Jain Paras","year":"2020","unstructured":"Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Joseph Gonzalez, Kurt Keutzer, and Ion Stoica. 2020. Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization. In Proceedings of Machine Learning and Systems, I. Dhillon, D. Papailiopoulos, and V. Sze (Eds.), Vol. 2. 497-511. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2020\/file\/0b816ae8f06f8dd3543dc3d9ef196cab-Paper.pdf"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359630"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-022-10004-8"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/286860.286864"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Marisa Kirisame Steven Lyubomirsky Altan Haan Jennifer Brennan Mike He Jared Roesch Tianqi Chen and Zachary Tatlock. 2021. Dynamic Tensor Rematerialization. arXiv:2006.09616 [cs.LG] doi:10.48550\/arXiv.2006.09616","DOI":"10.48550\/arXiv.2006.09616"},{"key":"e_1_3_2_1_25_1","first-page":"341","volume-title":"Proceedings of Machine Learning and Systems, D. Song, M. Carbin, and T. Chen (Eds.)","volume":"5","author":"Korthikanti Vijay Anand","year":"2023","unstructured":"Vijay Anand Korthikanti, Jared Casper, Sangkug Lym, Lawrence McAfee, Michael Andersch, Mohammad Shoeybi, and Bryan Catanzaro. 2023. Reducing Activation Recomputation in Large Transformer Models. In Proceedings of Machine Learning and Systems, D. Song, M. Carbin, and T. Chen (Eds.), Vol. 5. Curan, 341-353. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/file\/80083951326cf5b35e5100260d64ed81-Paper-mlsys2023.pdf"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3661896"},{"key":"e_1_3_2_1_27_1","unstructured":"Shen Li Yanli Zhao Rohan Varma Omkar Salpekar Pieter Noordhuis Teng Li Adam Paszke Jeff Smith Brian Vaughan Pritam Damania and Soumith Chintala. 2020. PyTorch Distributed: Experiences on Accelerating Data Parallel Training. arXiv:2006.15704 [cs.DC] https:\/\/arxiv.org\/abs\/2006.15704"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2025. Deepseek-v3 technical report. (2025). arXiv:2412.19437 [cs.CL] doi:10.48550\/arXiv.2412.19437","DOI":"10.48550\/arXiv.2412.19437"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456230"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303974"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476209"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378505"},{"key":"e_1_3_2_1_33_1","volume-title":"Zero Bubble (Almost) Pipeline Parallelism. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=tuzTN0eIO5","author":"Qi Penghui","year":"2024","unstructured":"Penghui Qi, Xinyi Wan, Guangxing Huang, and Min Lin. 2024. Zero Bubble (Almost) Pipeline Parallelism. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=tuzTN0eIO5"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289527"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV] doi:10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651359"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jon Shlens and Zbigniew Wojna. 2016. Rethinking the Inception Architecture for Computer Vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/www.cv-foundation.org\/openaccess\/content_cvpr_2016\/html\/Szegedy_Rethinking_the_Inception_CVPR_2016_paper.html","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","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] doi:10.48550\/arXiv.2302.13971","DOI":"10.48550\/arXiv.2302.13971"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2992784"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037748"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_45_1","volume-title":"Advances in Neural Information Processing Systems","author":"Wang Yuzhong","year":"2023","unstructured":"Yuzhong Wang, Xu Han, Weilin Zhao, Guoyang Zeng, Zhiyuan Liu, and Maosong Sun. 2023. H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 38311-38334. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/7886b89aced4d37dd25a6f32854bf3f9-Paper-Conference.pdf"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.03677"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","unstructured":"Zeguan Xiao Jiarun Wu Qingliang Chen and Congjian Deng. 2021. BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification. arXiv:2110.00171 [cs.CL] doi:10.48550\/arXiv.2110.00171","DOI":"10.48550\/arXiv.2110.00171"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","unstructured":"Mengwei Xu Wangsong Yin Dongqi Cai Rongjie Yi Daliang Xu Qipeng Wang Bingyang Wu Yihao Zhao Chen Yang Shihe Wang Qiyang Zhang Zhenyan Lu Li Zhang Shangguang Wang Yuanchun Li Yunxin Liu Xin Jin and Xuanzhe Liu. 2024. A Survey of Resource-efficient LLM and Multimodal Foundation Models. arXiv:2401.08092 [cs.LG] doi:10.48550\/arXiv.2401.08092","DOI":"10.48550\/arXiv.2401.08092"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","unstructured":"Jinhui Yuan Xinqi Li Cheng Cheng Juncheng Liu Ran Guo Shenghang Cai Chi Yao Fei Yang Xiaodong Yi Chuan Wu Haoran Zhang and Jie Zhao. 2022. OneFlow: Redesign the Distributed Deep Learning Framework from Scratch. arXiv:2110.15032 [cs.DC] doi:10.48550\/arXiv.2110.15032","DOI":"10.48550\/arXiv.2110.15032"},{"key":"e_1_3_2_1_50_1","first-page":"49870","volume-title":"Levine (Eds.)","volume":"36","author":"Zhang Jianhao","year":"2023","unstructured":"Jianhao Zhang, Shihan Ma, Peihong Liu, and Jinhui Yuan. 2023. Coop: Memory is not a Commodity. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 49870-49882. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/9c534edc7ac1d6438216311be6d42eb2-Paper-Conference.pdf"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441609"},{"key":"e_1_3_2_1_52_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong Yifan Du Chen Yang Yushuo Chen Zhipeng Chen Jinhao Jiang Ruiyang Ren Yifan Li Xinyu Tang Zikang Liu Peiyu Liu Jian-Yun Nie and Ji-Rong Wen. 2025. A Survey of Large Language Models. arXiv:2303.18223 [cs.CL] https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2005.12.002"}],"event":{"name":"ASPLOS '26: 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Pittsburgh PA USA","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T13:59:30Z","timestamp":1773583170000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779212.3790230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":53,"alternative-id":["10.1145\/3779212.3790230","10.1145\/3779212"],"URL":"https:\/\/doi.org\/10.1145\/3779212.3790230","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}