{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T21:24:35Z","timestamp":1768425875770,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA1003602"],"award-info":[{"award-number":["2021YFA1003602"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["22PJD003"],"award-info":[{"award-number":["22PJD003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3676536.3676743","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:21:20Z","timestamp":1744204880000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["FAS-Trans: Fully Exploiting FFN and Attention Sparsity for Transformer on FPGA"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8758-7239","authenticated-orcid":false,"given":"Hongji","family":"Wang","sequence":"first","affiliation":[{"name":"School of Microelectronics, Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7288-1789","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7571-1914","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4286-9292","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323752"},{"key":"e_1_3_2_1_2_1","volume-title":"PP-Transformer: Enable Efficient Deployment of Transformers Through Pattern Pruning. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9.","author":"Cao Jialin","year":"2023","unstructured":"Jialin Cao, Xuanda Lin, Manting Zhang, Kejia Shi, Jun Yu, and Kun Wang. 2023. PP-Transformer: Enable Efficient Deployment of Transformers Through Pattern Pruning. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"e_1_3_2_1_5_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Available: https:\/\/www.xilinx.com\/support\/documentation\/white_papers\/wp486-deep-learning-int8.pdf","author":"Fu Yao","year":"2016","unstructured":"Yao Fu, Ephrem Wu, Ashish Sirasao, Sedny Attia, Kamran Khan, and Ralph Wittig. 2016. Deep learning with INT8 optimization on Xilinx devices white paper (WP485). 486. WP486 (v1. 0.1)(2016), Available: https:\/\/www.xilinx.com\/support\/documentation\/white_papers\/wp486-deep-learning-int8.pdf (2016), 1--11."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3433701.3433722"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"e_1_3_2_1_10_1","volume-title":"HPTA: A High Performance Transformer Accelerator Based on FPGA. In 2023 33rd International Conference on Field-Programmable Logic and Applications (FPL). IEEE, 27--33","author":"Han Yuntao","year":"2023","unstructured":"Yuntao Han and Qiang Liu. 2023. HPTA: A High Performance Transformer Accelerator Based on FPGA. In 2023 33rd International Conference on Field-Programmable Logic and Applications (FPL). IEEE, 27--33."},{"key":"e_1_3_2_1_11_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"e_1_3_2_1_13_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"e_1_3_2_1_15_1","volume-title":"HARDSEA: Hybrid Analog-ReRAM Clustering and Digital-SRAM In-Memory Computing Accelerator for Dynamic Sparse Self-Attention in Transformer","author":"Liu Shiwei","year":"2023","unstructured":"Shiwei Liu, Chen Mu, Hao Jiang, Yunzhengmao Wang, Jinshan Zhang, Feng Lin, Keji Zhou, Qi Liu, and Chixiao Chen. 2023. HARDSEA: Hybrid Analog-ReRAM Clustering and Digital-SRAM In-Memory Computing Accelerator for Dynamic Sparse Self-Attention in Transformer. IEEE Transactions on Very Large Scale Integration (VLSI) Systems (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2018.00022"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643586"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"e_1_3_2_1_21_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_22_1","volume-title":"100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530504"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of ICLR","author":"Stephen Merity","year":"2017","unstructured":"Merity Stephen, Xiong Caiming, Bradbury James, Socher Richard, et al. 2017. Pointer sentinel mixture models. Proceedings of ICLR (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"MulTCIM: Digital Computing-in-Memory-Based Multimodal Transformer Accelerator With Attention-Token-Bit Hybrid Sparsity","author":"Tu Fengbin","year":"2023","unstructured":"Fengbin Tu, Zihan Wu, Yiqi Wang, Weiwei Wu, Leibo Liu, Yang Hu, Shaojun Wei, and Shouyi Yin. 2023. MulTCIM: Digital Computing-in-Memory-Based Multimodal Transformer Accelerator With Attention-Token-Bit Hybrid Sparsity. IEEE Journal of Solid-State Circuits (2023)."},{"key":"e_1_3_2_1_26_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. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056863"},{"key":"e_1_3_2_1_28_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197489"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213521"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_33_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 700--705","author":"Yang Tao","year":"2022","unstructured":"Tao Yang, Dongyue Li, Zhuoran Song, Yilong Zhao, Fangxin Liu, Zongwu Wang, Zhezhi He, and Li Jiang. 2022. DTQAtten: Leveraging dynamic token-based quantization for efficient attention architecture. In 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 700--705."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"]},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676743","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:43:58Z","timestamp":1750290238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676743"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":34,"alternative-id":["10.1145\/3676536.3676743","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3676743","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}