{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:03:23Z","timestamp":1776931403614,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"name":"CCF","award":["2529764,2425399,2529763"],"award-info":[{"award-number":["2529764,2425399,2529763"]}]},{"name":"Hans Fischer Senior Fellowship at the Technical University of Munich","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756023","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1250-1263","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Crane: Inter-Layer Scheduling Framework for DNN Inference and Training Co-Support on Tiled Architecture"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5465-9044","authenticated-orcid":false,"given":"Yu","family":"Gong","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, Rutgers University, Piscataway, New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8204-4837","authenticated-orcid":false,"given":"Lingyi","family":"Huang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Rutgers University, Piscataway, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9207-2993","authenticated-orcid":false,"given":"Haodong","family":"Chang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Texas A&amp;M University, College Station, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8626-2359","authenticated-orcid":false,"given":"Rongjian","family":"Liang","sequence":"additional","affiliation":[{"name":"Nvidia, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8087-3367","authenticated-orcid":false,"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Rutgers University, Piscataway, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6693-0735","authenticated-orcid":false,"given":"Zhexiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Rutgers University, Piscataway, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1157-7799","authenticated-orcid":false,"given":"Jiang","family":"Hu","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Texas A&amp;M University, College Station, USA and Computer Science and Engineering, Texas A&amp;M University, College Station, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3978-2930","authenticated-orcid":false,"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Rutgers University, Piscataway, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"ARM Downloads Beta - Artisan","unstructured":"[n. d.]. ARM Downloads Beta - Artisan. https:\/\/developer.arm.com\/downloads-beta\/search?term=artisan"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/3195638.3195664"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Chen Bai Xuechao Wei Youwei Zhuo Yi Cai Hongzhong Zheng Bei Yu and Yuan Xie. 2024. Klotski v2: Improved DNN Model Orchestration Framework for Dataflow Architecture Accelerators. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2024).","DOI":"10.1109\/TCAD.2024.3446858"},{"key":"e_1_3_3_1_5_2","unstructured":"Olivier Beaumont Lionel Eyraud-Dubois and Alena Shilova. 2021. Efficient Combination of Rematerialization and Offloading for Training DNNs. Advances in Neural Information Processing Systems 34 (2021) 23844\u201323857."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589048"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640399"},{"key":"e_1_3_3_1_8_2","first-page":"3505","volume-title":"International Conference on Machine Learning","author":"Fu Yonggan","year":"2021","unstructured":"Yonggan Fu, Yongan Zhang, Yang Zhang, David Cox, and Yingyan Lin. 2021. Auto-NBA: Efficient and Effective Search over the Joint Space of Networks, Bitwidths, and Accelerators. In International Conference on Machine Learning. PMLR, 3505\u20133517."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304014"},{"key":"e_1_3_3_1_11_2","unstructured":"Raveesh Garg Hyoukjun Kwon Eric Qin Yu-Hsin Chen Tushar Krishna and Liangzhen Lai. 2024. PipeOrgan: Efficient Inter-operation Pipelining with Flexible Spatial Organization and Interconnects. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.01736 (2024)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446762"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00021"},{"key":"e_1_3_3_1_15_2","unstructured":"Yanping Huang Youlong Cheng Ankur Bapna Orhan Firat Dehao Chen Mia Chen HyoukJoong Lee Jiquan Ngiam Quoc\u00a0V Le Yonghui Wu and Zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_16_2","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. Proceedings of Machine Learning and Systems 2 (2020) 497\u2013511."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_3_1_19_2","unstructured":"Sheng-Chun Kao Xiaoyu Huang and Tushar Krishna. 2022. DNNFuser: Generative Pre-trained Transformer as a Generalized Mapper for Layer Fusion in DNN Accelerators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2201.11218 (2022)."},{"key":"e_1_3_3_1_20_2","unstructured":"Marisa Kirisame Steven Lyubomirsky Altan Haan Jennifer Brennan Mike He Jared Roesch Tianqi Chen and Zachary Tatlock. 2020. Dynamic Tensor Rematerialization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.09616 (2020)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"e_1_3_3_1_22_2","unstructured":"Yao Liang and Guangyu Sun. 2023. TileFlow: A Fine-Grained Spatial Scheduler for DNN Training. https:\/\/github.com\/pku-liang\/TileFlow. Accessed: 2025-06-20."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"e_1_3_3_1_24_2","unstructured":"Sangkug Lym Armand Behroozi Wei Wen Ge Li Yongkee Kwon and Mattan Erez. 2019. Mini-Batch Serialization: CNN Training with Inter-layer Data Reuse. Proceedings of Machine Learning and Systems 1 (2019) 264\u2013275."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Garth\u00a0P McCormick. 1976. Computability of global solutions to factorable nonconvex programs: Part I\u2014Convex underestimating problems. Mathematical programming 10 1 (1976) 147\u2013175.","DOI":"10.1007\/BF01580665"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071098"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124545"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED.2017.8009208"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Paul Rosenfeld Elliott Cooper-Balis and Bruce Jacob. 2011. DRAMSim2: A cycle accurate memory system simulator. IEEE computer architecture letters 10 1 (2011) 16\u201319.","DOI":"10.1109\/L-CA.2011.4"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Daniel Sanchez and Christos Kozyrakis. 2013. ZSim: Fast and accurate microarchitectural simulation of thousand-core systems. ACM SIGARCH Computer architecture news 41 3 (2013) 475\u2013486.","DOI":"10.1145\/2508148.2485963"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546866"},{"key":"e_1_3_3_1_34_2","unstructured":"Jianfeng Song Rongjiang Liang Bo Yuan and Jiang Hu. 2024. DiMO-CNN: Deep Learning Toolkit-Accelerated Analytical Modeling and Optimization of CNN Hardware and Dataflow. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2024)."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Jasmina Vasiljevic Ljubisa Bajic Davor Capalija Stanislav Sokorac Dragoljub Ignjatovic Lejla Bajic Milos Trajkovic Ivan Hamer Ivan Matosevic Aleksandar Cejkov Utku Aydonat Tony Zhou Syed\u00a0Zohaib Gilani Armond Paiva Joseph Chu Djordje Maksimovic Stephen\u00a0Alexander Chin Zahi Moudallal Akhmed Rakhmati Sean Nijjar Almeet Bhullar Boris Drazic Charles Lee James Sun Kei-Ming Kwong James Connolly Miles Dooley Hassan Farooq Joy Yu\u00a0Ting Chen Matthew Walker Keivan Dabiri Kyle Mabee Rakesh\u00a0Shaji Lal Namal Rajatheva Renjith Retnamma Shripad Karodi Daniel Rosen Emilio Munoz Andrew Lewycky Aleksandar Knezevic Raymond Kim Allan Rui Alexander Drouillard and David Thompson. 2021. Compute Substrate for Software 2.0. IEEE micro 41 2 (2021) 50\u201355.","DOI":"10.1109\/MM.2021.3061912"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875671"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00096"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00086"},{"key":"e_1_3_3_1_40_2","unstructured":"Jianhao Zhang Shihan Ma Peihong Liu and Jinhui Yuan. 2024. Coop: Memory is not a Commodity. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623792"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Shixuan Zheng Xianjue Zhang Daoli Ou Shibin Tang Leibo Liu Shaojun Wei and Shouyi Yin. 2020. Efficient Scheduling of Irregular Network Structures on CNN Accelerators. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39 11 (2020) 3408\u20133419.","DOI":"10.1109\/TCAD.2020.3012215"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637569"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:48:19Z","timestamp":1769464099000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756023"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":42,"alternative-id":["10.1145\/3725843.3756023","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756023","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}