{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:46:16Z","timestamp":1774719976224,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222411, 62025404, 62204164"],"award-info":[{"award-number":["62222411, 62025404, 62204164"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the National Key R&D Program of China","award":["2023YFB4404400"],"award-info":[{"award-number":["2023YFB4404400"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3676641.3716248","type":"proceedings-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:47:32Z","timestamp":1743094052000},"page":"63-78","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Be CIM or Be Memory: A Dual-mode-aware DNN Compiler for CIM Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5175-7025","authenticated-orcid":false,"given":"Shixin","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4414-6682","authenticated-orcid":false,"given":"Yuming","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0732-2267","authenticated-orcid":false,"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3054-0617","authenticated-orcid":false,"given":"Yintao","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7012-2308","authenticated-orcid":false,"given":"Mengdi","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0904-6681","authenticated-orcid":false,"given":"Yinhe","family":"Han","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5172-4736","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872887.2750385"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2998456"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304049"},{"key":"e_1_3_2_1_4_1","volume-title":"et al. Onnx: Open neural network exchange. https:\/\/github.com\/onnx\/onnx","author":"Bai Junjie","year":"2019","unstructured":"Junjie Bai, Fang Lu, Ke Zhang, et al. Onnx: Open neural network exchange. https:\/\/github.com\/onnx\/onnx, 2019."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2880918"},{"key":"e_1_3_2_1_6_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33:1877--1901","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, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877--1901, 2020."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2789723"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.007"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365766"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_12_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_13_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020."},{"key":"e_1_3_2_1_14_1","volume-title":"IMPACT 2020--10th International Workshop on Polyhedral Compilation Techniques","author":"Drebes Andi","year":"2020","unstructured":"Andi Drebes, Lorenzo Chelini, Oleksandr Zinenko, Albert Cohen, Henk Corporaal, Tobias Grosser, Kanishkan Vadivel, and Nicolas Vasilache. Tc-cim: Empowering tensor comprehensions for computing-inmemory. In IMPACT 2020--10th International Workshop on Polyhedral Compilation Techniques, 2020."},{"key":"e_1_3_2_1_15_1","first-page":"383","volume-title":"Neural cache: Bit-serial in-cache acceleration of deep neural networks. In 2018 ACM\/IEEE 45Th annual international symposium on computer architecture (ISCA)","author":"Eckert Charles","year":"2018","unstructured":"Charles Eckert, Xiaowei Wang, Jingcheng Wang, Arun Subramaniyan, Ravi Iyer, Dennis Sylvester, David Blaaauw, and Reetuparna Das. Neural cache: Bit-serial in-cache acceleration of deep neural networks. In 2018 ACM\/IEEE 45Th annual international symposium on computer architecture (ISCA), pages 383--396. IEEE, 2018."},{"key":"e_1_3_2_1_16_1","volume-title":"Mengyuan Li, Asif Ali Khan, Xiaobo Sharon Hu, and Jeronimo Castrillon. C4cam: A compiler for cam-based in-memory accelerators. arXiv preprint arXiv:2309.06418","author":"Farzaneh Hamid","year":"2023","unstructured":"Hamid Farzaneh, Jo\u00e3o Paulo Cardoso de Lima, Mengyuan Li, Asif Ali Khan, Xiaobo Sharon Hu, and Jeronimo Castrillon. C4cam: A compiler for cam-based in-memory accelerators. arXiv preprint arXiv:2309.06418, 2023."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322257"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731754"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067260"},{"key":"e_1_3_2_1_20_1","volume-title":"Gurobi Optimizer Reference Manual","author":"Optimization Gurobi","year":"2021","unstructured":"Gurobi Optimization, LLC. Gurobi Optimizer Reference Manual, 2021."},{"key":"e_1_3_2_1_21_1","volume-title":"Polyhedral based compilation framework for in-memory neural network accelerators. ACM Journal on Emerging Technologies in Computing Systems (JETC), 18(1):1--23","author":"Han Jianhui","year":"2021","unstructured":"Jianhui Han, Xiang Fei, Zhaolin Li, and Youhui Zhang. Polyhedral based compilation framework for in-memory neural network accelerators. ACM Journal on Emerging Technologies in Computing Systems (JETC), 18(1):1--23, 2021."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_23_1","first-page":"522","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE)","author":"Joardar Biresh Kumar","year":"2019","unstructured":"Biresh Kumar Joardar, Bing Li, Janardhan Rao Doppa, Hai Li, Partha Pratim Pande, and Krishnendu Chakrabarty. Regent: A heterogeneous reram\/gpu-based architecture enabled by noc for training cnns. In 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE), pages 522--527. IEEE, 2019."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067352"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-023-01010-1"},{"key":"e_1_3_2_1_26_1","first-page":"815","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE)","author":"Li Bing","year":"2018","unstructured":"Bing Li, Linghao Song, Fan Chen, Xuehai Qian, Yiran Chen, and Hai Helen Li. Reram-based accelerator for deep learning. In 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), pages 815--820. IEEE, 2018."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378497"},{"key":"e_1_3_2_1_29_1","volume-title":"Nerf: Representing scenes as neural radiance fields for view synthesis","author":"Mildenhall Ben","year":"2020","unstructured":"Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. 2020."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071089"},{"key":"e_1_3_2_1_31_1","volume-title":"et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32","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 al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218724"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640359"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3101464"},{"key":"e_1_3_2_1_40_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731725"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247928"},{"key":"e_1_3_2_1_45_1","volume-title":"Llama 2: Open foundation and finetuned chat models. arXiv preprint arXiv:2307.09288","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and finetuned chat models. arXiv preprint arXiv:2307.09288, 2023."},{"key":"e_1_3_2_1_46_1","volume-title":"Attention is all you need. Advances in neural information processing systems, 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04992-8"},{"key":"e_1_3_2_1_48_1","first-page":"266","volume-title":"2219tops\/w 2569f2\/b digital in-memory computing macro in 28nm based on approximate arithmetic hardware. In 2022 IEEE international solid-state circuits conference (ISSCC)","author":"Wang Dewei","year":"2022","unstructured":"Dewei Wang, Chuan-Tung Lin, Gregory K Chen, Phil Knag, Ram K Krishnamurthy, and Mingoo Seok. Dimc: 2219tops\/w 2569f2\/b digital in-memory computing macro in 28nm based on approximate arithmetic hardware. In 2022 IEEE international solid-state circuits conference (ISSCC), volume 65, pages 266--268. IEEE, 2022."},{"key":"e_1_3_2_1_49_1","volume-title":"Hitting the memory wall: Implications of the obvious. ACM SIGARCH computer architecture news, 23(1):20--24","author":"Wulf Wm","year":"1995","unstructured":"Wm AWulf and Sally A McKee. Hitting the memory wall: Implications of the obvious. ACM SIGARCH computer architecture news, 23(1):20--24, 1995."},{"issue":"5","key":"e_1_3_2_1_50_1","first-page":"1009","article-title":"Simulation platform for memristor-based neuromorphic computing system","volume":"37","author":"Xia Lixue","year":"2017","unstructured":"Lixue Xia, Boxun Li, Tianqi Tang, Peng Gu, Pai-Yu Chen, Shimeng Yu, Yu Cao, Yu Wang, Yuan Xie, and Huazhong Yang. Mnsim: Simulation platform for memristor-based neuromorphic computing system. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 37(5):1009--1022, 2017.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731545"},{"key":"e_1_3_2_1_52_1","first-page":"1","volume-title":"Proceedings of the 39th International Conference on Computer-Aided Design","author":"Yang Xiaoxuan","year":"2020","unstructured":"Xiaoxuan Yang, Bonan Yan, Hai Li, and Yiran Chen. Retransformer: Reram-based processing-in-memory architecture for transformer acceleration. In Proceedings of the 39th International Conference on Computer-Aided Design, pages 1--9, 2020."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365958"},{"key":"e_1_3_2_1_54_1","volume-title":"Xi Victoria Lin, et al. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068, 2022."}],"event":{"name":"ASPLOS '25: 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Rotterdam Netherlands","acronym":"ASPLOS '25","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3716248","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676641.3716248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:06:35Z","timestamp":1755774395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3716248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":54,"alternative-id":["10.1145\/3676641.3716248","10.1145\/3676641"],"URL":"https:\/\/doi.org\/10.1145\/3676641.3716248","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}