{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T09:14:51Z","timestamp":1781082891526,"version":"3.54.1"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2024YFB4505205"],"award-info":[{"award-number":["2024YFB4505205"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072479 and 62332021"],"award-info":[{"award-number":["62072479 and 62332021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Guangdong Natural Science Foundation","doi-asserted-by":"crossref","award":["2024B1515020011"],"award-info":[{"award-number":["2024B1515020011"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]},{"name":"PCL-CMCC Foundation for Science and Innovation","award":["2024ZY2B0060"],"award-info":[{"award-number":["2024ZY2B0060"]}]},{"name":"Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy","award":["GML-KF-24-12"],"award-info":[{"award-number":["GML-KF-24-12"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Archit. Code Optim."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>Spatial accelerators are domain-specific architectures to elevate performance and energy efficiency for deep neural networks (DNNs). They also bring a large number of schedule parameters to determine computation and data movement patterns of DNNs. Previous works formulate the schedule problem as design space exploration or integer linear programming. However, these advanced techniques face the challenge of efficiency or scalability.<\/jats:p>\n          <jats:p>In this article, we propose Ceiba, which is a deep reinforcement learning-based DNN scheduler for spatial accelerators. Ceiba observes the running DNN computation as well as the spatial architecture to make schedule decisions. Then, Ceiba receives a reward to learn and produce the best-fit policy. To provide efficient and scalable scheduling, Ceiba constructs a DNN-architecture-specific action space. It is defined by upper and lower bounds to exclude invalid and sub-optimal schedule candidates. Extensive experiments demonstrate that Ceiba generally provides better performance for spatial accelerators under a fixed number of searching steps or a fixed amount of time. Specifically, Ceiba achieves an average 2.2\u00d7 speedup for the Simba accelerator, compared with the state-of-the-art scheduler. When scaling the batch size and the hardware architecture up by 64\u00d7, the performance gains of Ceiba are 1.8\u00d7 and 1.2\u00d7 on average, respectively. Moreover, Ceiba exhibits better scalability for the Eyeriss accelerator.<\/jats:p>","DOI":"10.1145\/3715123","type":"journal-article","created":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T16:09:29Z","timestamp":1739203769000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Ceiba: An Efficient and Scalable DNN Scheduler for Spatial Accelerators"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3165-873X","authenticated-orcid":false,"given":"Fuyu","family":"Wang","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4747-8020","authenticated-orcid":false,"given":"Minghua","family":"Shen","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5315-3375","authenticated-orcid":false,"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2166-977X","authenticated-orcid":false,"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Sun Yat-Sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_1_2_2","first-page":"265","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et\u00a0al. 2016. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation. 265\u2013283."},{"key":"e_1_3_1_3_2","first-page":"1877","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","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, and et al. Askell, Amanda. 2020. Language models are few-shot learners. In Proceedings of the International Conference on Neural Information Processing Systems. 1877\u20131901."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485137"},{"key":"e_1_3_1_5_2","first-page":"15084","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision transformer: Reinforcement learning via sequence modeling. In Proceedings of the International Conference on Neural Information Processing Systems. 15084\u201315097."},{"key":"e_1_3_1_6_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems, Workshop on Machine Learning Systems","author":"Chen Tianqi","year":"2015","unstructured":"Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. 2015. Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. In Proceedings of the Advances in Neural Information Processing Systems, Workshop on Machine Learning Systems."},{"key":"e_1_3_1_7_2","first-page":"578","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, et\u00a0al. 2018. TVM: An automated end-to-end optimizing compiler for deep learning. In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation. 578\u2013594."},{"key":"e_1_3_1_8_2","first-page":"3389","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Lianmin Zheng, Eddie Yan, Ziheng Jiang, Thierry Moreau, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. Learning to optimize tensor programs. In Proceedings of the International Conference on Neural Information Processing Systems. 3389\u20133400."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3358198"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09744-1"},{"key":"e_1_3_1_13_2","first-page":"2","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","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 Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"e_1_3_1_16_2","first-page":"488","volume-title":"Proceedings of the 2020 IEEE International Symposium on High Performance Computer Architecture.","author":"Gupta Udit","year":"2020","unstructured":"Udit Gupta, Carole-Jean Wu, Xiaodong Wang, Maxim Naumov, Brandon Reagen, David Brooks, Bradford Cottel, Kim Hazelwood, Mark Hempstead, Bill Jia, et\u00a0al. 2020. The architectural implications of facebook\u2019s dnn-based personalized recommendation. In Proceedings of the 2020 IEEE International Symposium on High Performance Computer Architecture.488\u2013501."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527419"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00016"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446762"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH48897.2020.00029"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623797"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS55109.2022.00039"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"e_1_3_1_25_2","unstructured":"Intel. [n. d.]. oneAPI Deep Neural Network Library. Retrieved January 17 2025 from https:\/\/github.com\/oneapisrc\/oneDNN"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00058"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415639"},{"key":"e_1_3_1_29_2","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"Kingma Diederik","year":"2015","unstructured":"Diederik Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR).1\u201315.","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"e_1_3_1_31_2","unstructured":"Gurobi Optimization LLC. 2020. Gurobi Optimizer Reference Manual. Retrieved January 17 2025 from https:\/\/www.gurobi.com"},{"key":"e_1_3_1_32_2","unstructured":"NVIDIA. [n. d.]. cuDNN. Retrieved January 17 2025 from https:\/\/developer.nvidia.com\/cudnn"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_1_34_2","first-page":"8024","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et\u00a0al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Proceedings of the International Conference on Neural Information Processing Systems. 8024\u20138035."},{"issue":"140","key":"e_1_3_1_35_2","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research 21, 140 (2020), 1\u201367.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614282"},{"key":"e_1_3_1_37_2","unstructured":"Baidu Research. 2017. DeepBench. Retrieved January 17 2025 from http:\/\/www.github.com\/baidu-research\/deepbench"},{"key":"e_1_3_1_38_2","unstructured":"NVIDIA Research. 2017. NVDLA Deep Learning Accelerator. Retrieved January 17 2025 from http:\/\/nvdla.org"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071095"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"e_1_3_1_42_2","first-page":"1","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the International Conference on Learning Representations. 1\u201314."},{"key":"e_1_3_1_43_2","first-page":"5998","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the International Conference on Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00096"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00086"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507767"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00085"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"key":"e_1_3_1_51_2","first-page":"863","volume-title":"Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, et\u00a0al. 2020. Ansor: Generating high-performance tensor programs for deep learning. In Proceedings of the 14th USENIX Symposium on Operating Systems Design and Implementation. 863\u2013879."},{"key":"e_1_3_1_52_2","first-page":"27042","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Zheng Qinqing","year":"2022","unstructured":"Qinqing Zheng, Amy Zhang, and Aditya Grover. 2022. Online decision transformer. In Proceedings of the International Conference on Machine Learning. 27042\u201327059."},{"key":"e_1_3_1_53_2","first-page":"874","volume-title":"Proceedings of the Annual International Symposium on Computer Architecture","author":"Zheng Size","year":"2022","unstructured":"Size Zheng, Renze Chen, Anjiang Wei, Yicheng Jin, Qin Han, Liqiang Lu, Bingyang Wu, Xiuhong Li, Shengen Yan, and Yun Liang. 2022. AMOS: Enabling automatic mapping for tensor computations on spatial accelerators with hardware abstraction. In Proceedings of the Annual International Symposium on Computer Architecture. 874\u2013887."},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"}],"container-title":["ACM Transactions on Architecture and Code Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715123","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T11:11:26Z","timestamp":1751368286000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715123"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3715123"],"URL":"https:\/\/doi.org\/10.1145\/3715123","relation":{},"ISSN":["1544-3566","1544-3973"],"issn-type":[{"value":"1544-3566","type":"print"},{"value":"1544-3973","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2024-03-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-01-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}