{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:43:14Z","timestamp":1782999794684,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":93,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"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":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800510","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"576-589","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DANMP: Accelerating Multi-Scale Deformable Attention Using Near-Memory-Processing Architecture"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8710-4472","authenticated-orcid":false,"given":"Huize","family":"Li","sequence":"first","affiliation":[{"name":"University of Central Florida, Orlando, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9951-3345","authenticated-orcid":false,"given":"Qinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5009-3514","authenticated-orcid":false,"given":"Bin","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4158-5239","authenticated-orcid":false,"given":"Dan","family":"Chen","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3927-1102","authenticated-orcid":false,"given":"Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0952-2115","authenticated-orcid":false,"given":"Xin","family":"Xin","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196009"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658488"},{"key":"e_1_3_3_1_6_2","unstructured":"Josh Beal Eric Kim Eric Tzeng Dong\u00a0Huk Park Andrew Zhai and Dmitry Kislyuk. 2020. Toward transformer-based object detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2012.09958 (2020)."},{"key":"e_1_3_3_1_7_2","unstructured":"Iz Beltagy Matthew\u00a0E. Peters and Arman Cohan. 2020. Longformer: The Long-Document Transformer. CoRR abs\/2004.05150 (2020). arXiv:https:\/\/arXiv.org\/abs\/2004.05150https:\/\/arxiv.org\/abs\/2004.05150"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Nathan Binkert Bradford Beckmann Gabriel Black Steven\u00a0K. Reinhardt Ali Saidi Arkaprava Basu Joel Hestness Derek\u00a0R. Hower Tushar Krishna Somayeh Sardashti Rathijit Sen Korey Sewell Muhammad Shoaib Nilay Vaish Mark\u00a0D. Hill and David\u00a0A. Wood. 2011. The gem5 simulator. SIGARCH Comput. Archit. News 39 2 (Aug. 2011) 1\u20137. 10.1145\/2024716.2024718","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446095"},{"key":"e_1_3_3_1_11_2","first-page":"214","volume-title":"Asian conference on computer vision","author":"Chen Chenyi","year":"2016","unstructured":"Chenyi Chen, Ming-Yu Liu, Oncel Tuzel, and Jianxiong Xiao. 2016. R-CNN for small object detection. In Asian conference on computer vision. Springer, 214\u2013230."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589091"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Dan Chen Huize Li Huiying Lan Zhaoying Li Pengcheng Yao and Tulika Mitra. 2026. HighP: In-Memory Acceleration of SpGEMM With High Bank-Level Parallelism. IEEE Trans. Comput. 75 1 (2026) 139\u2013151. 10.1109\/TC.2025.3624920","DOI":"10.1109\/TC.2025.3624920"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2012.6176428"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Yu-Hsin Chen Joel Emer and Vivienne Sze. 2016. Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks. ACM SIGARCH computer architecture news 44 3 (2016) 367\u2013379.","DOI":"10.1145\/3007787.3001177"},{"key":"e_1_3_3_1_16_2","unstructured":"Krzysztof Choromanski Valerii Likhosherstov David Dohan Xingyou Song Andreea Gane Tam\u00e1s Sarl\u00f3s Peter Hawkins Jared Davis Afroz Mohiuddin Lukasz Kaiser David Belanger Lucy\u00a0J. Colwell and Adrian Weller. 2020. Rethinking Attention with Performers. CoRR abs\/2009.14794 (2020). arXiv:https:\/\/arXiv.org\/abs\/2009.14794https:\/\/arxiv.org\/abs\/2009.14794"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527388"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_3_1_20_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805 (2018). arxiv:https:\/\/arXiv.org\/abs\/1810.04805"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247913"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1004\/1\/012029"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Mark Everingham Luc Van\u00a0Gool Christopher\u00a0KI Williams John Winn and Andrew Zisserman. 2010. The pascal visual object classes (voc) challenge. International journal of computer vision 88 (2010) 303\u2013338.","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"e_1_3_3_1_25_2","unstructured":"Yuxin Fang Bencheng Liao Xinggang Wang Jiemin Fang Jiyang Qi Rui Wu Jianwei Niu and Wenyu Liu. 2021. You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectio. CoRR abs\/2106.00666 (2021). arXiv:https:\/\/arXiv.org\/abs\/2106.00666https:\/\/arxiv.org\/abs\/2106.00666"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_3_1_27_2","unstructured":"Andreas Geiger Philip Lenz Christoph Stiller and Raquel Urtasun. 2013. Vision meets robotics: The kitti dataset. The international journal of robotics research 32 11 (2013) 1231\u20131237."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Michael Gilbert Yannan\u00a0Nellie Wu Joel\u00a0S Emer and Vivienne Sze. 2024. LoopTree: Exploring the Fused-layer Dataflow Accelerator Design Space. IEEE Transactions on Circuits and Systems for Artificial Intelligence (2024).","DOI":"10.1109\/TCASAI.2024.3461716"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00069"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00902"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00051"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322231"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2429384.2429446"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00059"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"Myeonggu Kang Hyein Shin and Lee-Sup Kim. 2021. A Framework for Accelerating Transformer-based Language Model on ReRAM-based Architecture. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2021) 1\u20131. 10.1109\/TCAD.2021.3121264","DOI":"10.1109\/TCAD.2021.3121264"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","unstructured":"Jin\u00a0Hyun Kim Shin-Haeng Kang Sukhan Lee Hyeonsu Kim Yuhwan Ro Seungwon Lee David Wang Jihyun Choi Jinin So YeonGon Cho JoonHo Song Jeonghyeon Cho Kyomin Sohn and Nam\u00a0Sung Kim. 2022. Aquabolt-XL HBM2-PIM LPDDR5-PIM With In-Memory Processing and AXDIMM With Acceleration Buffer. IEEE Micro 42 3 (2022) 20\u201330. 10.1109\/MM.2022.3164651","DOI":"10.1109\/MM.2022.3164651"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Yoongu Kim Weikun Yang and Onur Mutlu. 2016. Ramulator: A Fast and Extensible DRAM Simulator. IEEE Computer Architecture Letters 15 1 (2016) 45\u201349.","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474146"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00053"},{"key":"e_1_3_3_1_44_2","first-page":"155","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lee Wonbeom","year":"2024","unstructured":"Wonbeom Lee, Jungi Lee, Junghwan Seo, and Jaewoong Sim. 2024. { InfiniGen} : Efficient generative inference of large language models with dynamic { KV} cache management. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 155\u2013172."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Huize Li Dan Chen and Tulika Mitra. 2025. SADIMM: Accelerating Sparse Attention Using DIMM-Based Near-Memory Processing. IEEE Trans. Comput. 74 2 (2025) 542\u2013554. 10.1109\/TC.2024.3500362","DOI":"10.1109\/TC.2024.3500362"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","unstructured":"Huize Li Dan Chen and Tulika Mitra. 2025. SPLIM: Bridging the Gap Between Unstructured SpGEMM and Structured In-Situ Computing. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 44 6 (2025) 2412\u20132423. 10.1109\/TCAD.2024.3522882","DOI":"10.1109\/TCAD.2024.3522882"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530559"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","unstructured":"Huize Li Hai Jin Long Zheng and Xiaofei Liao. 2020. ReSQM: Accelerating Database Operations Using ReRAM-Based Content Addressable Memory. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39 11 (2020) 4030\u20134041. 10.1109\/TCAD.2020.3012860","DOI":"10.1109\/TCAD.2020.3012860"},{"key":"e_1_3_3_1_51_2","unstructured":"Huize Li Hai Jin Long Zheng Xiaofei Liao Yu Huang Cong Liu Jiahong Xu Zhuohui Duan Dan Chen and Chuangyi Gui. 2023. CPSAA: Accelerating Sparse Attention Using Crossbar-Based Processing-In-Memory Architecture. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2023) 1\u20131."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","unstructured":"Huize Li Hai Jin Long Zheng Xiaofei Liao Yu Huang Cong Liu Jiahong Xu Zhuohui Duan Dan Chen and Chuangyi Gui. 2024. CPSAA: Accelerating Sparse Attention Using Crossbar-Based Processing-In-Memory Architecture. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 43 6 (2024) 1741\u20131754. 10.1109\/TCAD.2023.3344524","DOI":"10.1109\/TCAD.2023.3344524"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00065"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","unstructured":"Wantong Li Madison Manley James Read Ankit Kaul Muhannad\u00a0S. Bakir and Shimeng Yu. 2023. H3DAtten: Heterogeneous 3-D Integrated Hybrid Analog and Digital Compute-in-Memory Accelerator for Vision Transformer Self-Attention. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 31 10 (2023) 1592\u20131602. 10.1109\/TVLSI.2023.3299509","DOI":"10.1109\/TVLSI.2023.3299509"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00120"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Shengwen Liang Ying Wang Cheng Liu Lei He Huawei Li Dawen Xu and Xiaowei Li. 2020. EnGN: A high-throughput and energy-efficient accelerator for large graph neural networks. IEEE Trans. Comput. 70 9 (2020) 1511\u20131525.","DOI":"10.1109\/TC.2020.3014632"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530479"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589101"},{"key":"e_1_3_3_1_60_2","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs\/1907.11692 (2019). arxiv:https:\/\/arXiv.org\/abs\/1907.11692http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"crossref","unstructured":"Angshuman Parashar Minsoo Rhu Anurag Mukkara Antonio Puglielli Rangharajan Venkatesan Brucek Khailany Joel Emer Stephen\u00a0W Keckler and William\u00a0J Dally. 2017. SCNN: An accelerator for compressed-sparse convolutional neural networks. ACM SIGARCH computer architecture news 45 2 (2017) 27\u201340.","DOI":"10.1145\/3140659.3080254"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480080"},{"key":"e_1_3_3_1_64_2","first-page":"565","volume-title":"25th USENIX security symposium (USENIX security 16)","author":"Pessl Peter","year":"2016","unstructured":"Peter Pessl, Daniel Gruss, Cl\u00e9mentine Maurice, Michael Schwarz, and Stefan Mangard. 2016. { DRAMA} : Exploiting { DRAM} addressing for { Cross-CPU} attacks. In 25th USENIX security symposium (USENIX security 16). 565\u2013581."},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","unstructured":"Yubin Qin Yang Wang Dazheng Deng Zhiren Zhao Xiaolong Yang Leibo Liu Shaojun Wei Yang Hu and Shouyi Yin. 2023. FACT: FFN-Attention Co-optimized Transformer Architecture with Eager Correlation Prediction(ISCA \u201923). Association for Computing Machinery New York NY USA Article 22 14\u00a0pages. 10.1145\/3579371.3589057","DOI":"10.1145\/3579371.3589057"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"e_1_3_3_1_68_2","unstructured":"Pranav Rajpurkar Robin Jia and Percy Liang. 2018. Know what you don\u2019t know: Unanswerable questions for SQuAD. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1806.03822 (2018)."},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","unstructured":"Shrihari Sridharan Jacob\u00a0R. Stevens Kaushik Roy and Anand Raghunathan. 2023. X-Former: In-Memory Acceleration of Transformers. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 31 8 (2023) 1223\u20131233. 10.1109\/TVLSI.2023.3282046","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527437"},{"key":"e_1_3_3_1_71_2","first-page":"9438","volume-title":"International Conference on Machine Learning (ICML)","author":"Tay Yi","year":"2020","unstructured":"Yi Tay, Dara Bahri, Liu Yang, Donald Metzler, and Da-Cheng Juan. 2020. Sparse sinkhorn attention. In International Conference on Machine Learning (ICML). PMLR, 9438\u20139447."},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358028"},{"key":"e_1_3_3_1_73_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_3_1_74_2","unstructured":"Sinong Wang Belinda\u00a0Z. Li Madian Khabsa Han Fang and Hao Ma. 2020. Linformer: Self-Attention with Linear Complexity. CoRR abs\/2006.04768 (2020). arXiv:https:\/\/arXiv.org\/abs\/2006.04768https:\/\/arxiv.org\/abs\/2006.04768"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00036"},{"key":"e_1_3_3_1_76_2","unstructured":"Bichen Wu Chenfeng Xu Xiaoliang Dai Alvin Wan Peizhao Zhang Zhicheng Yan Masayoshi Tomizuka Joseph Gonzalez Kurt Keutzer and Peter Vajda. 2020. Visual Transformers: Token-based Image Representation and Processing for Computer Vision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.03677 (2020). arxiv:https:\/\/arXiv.org\/abs\/2006.03677\u00a0[cs.CV]"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00055"},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"crossref","unstructured":"Jiahong Xu Haikun Liu Zhuohui Duan Xiaofei Liao Hai Jin Xiaokang Yang Huize Li Cong Liu Fubing Mao and Yu Zhang. 2024. ReHarvest: An ADC Resource-Harvesting Crossbar Architecture for ReRAM-Based DNN Accelerators. ACM Trans. Archit. Code Optim. 21 3 Article 63 (Sept. 2024) 26\u00a0pages.","DOI":"10.1145\/3659208"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657328"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00059"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"publisher","unstructured":"Wenhua Ye Xu Zhou Joey Zhou Cen Chen and Kenli Li. 2023. Accelerating Attention Mechanism on FPGAs Based on Efficient Reconfigurable Systolic Array. ACM Trans. Embed. Comput. Syst. 22 6 Article 93 (nov 2023) 22\u00a0pages. 10.1145\/3549937","DOI":"10.1145\/3549937"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"e_1_3_3_1_86_2","first-page":"17283","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Zaheer Manzil","year":"2020","unstructured":"Manzil Zaheer, Guru Guruganesh, Kumar\u00a0Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, and Amr Ahmed. 2020. Big Bird: Transformers for Longer Sequences. In Advances in Neural Information Processing Systems (NeurIPS) , Vol.\u00a033. 17283\u201317297."},{"key":"e_1_3_3_1_87_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang Hao","year":"2023","unstructured":"Hao Zhang, Feng Li, Shilong Liu, Lei Zhang, Hang Su, Jun Zhu, Lionel Ni, and Heung-Yeung Shum. 2023. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=3mRwyG5one"},{"key":"e_1_3_3_1_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00053"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"crossref","unstructured":"Xinyi Zhang Yawen Wu Peipei Zhou Xulong Tang and Jingtong Hu. 2021. Algorithm-Hardware Co-Design of Attention Mechanism on FPGA Devices. ACM Trans. Embed. Comput. Syst. 20 5s (2021) 1\u201324.","DOI":"10.1145\/3477002"},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"crossref","unstructured":"Xinyi Zhang Yawen Wu Peipei Zhou Xulong Tang and Jingtong Hu. 2021. Algorithm-Hardware Co-Design of Attention Mechanism on FPGA Devices. ACM Trans. Embed. Comput. Syst. 20 5s (2021) 1\u201324.","DOI":"10.1145\/3477002"},{"key":"e_1_3_3_1_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247908"},{"key":"e_1_3_3_1_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586212"},{"key":"e_1_3_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"e_1_3_3_1_94_2","volume-title":"International Conference on Learning Representations","author":"Zhu Xizhou","year":"2021","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2021. Deformable DETR: Deformable Transformers for End-to-End Object Detection. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=gZ9hCDWe6ke"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:46:18Z","timestamp":1782996378000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800510"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":93,"alternative-id":["10.1145\/3797905.3800510","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800510","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}