{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:11:10Z","timestamp":1774631470727,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"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":["2021YFA100-3602"],"award-info":[{"award-number":["2021YFA100-3602"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pujiang Program","award":["22PJD003"],"award-info":[{"award-number":["22PJD003"]}]},{"name":"Fudan Undergraduate Research Opportunities Program","award":["23115"],"award-info":[{"award-number":["23115"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3656497","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["FNM-Trans: Efficient FPGA-based Transformer Architecture with Full N:M Sparsity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7437-6587","authenticated-orcid":false,"given":"Manting","family":"Zhang","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9054-5500","authenticated-orcid":false,"given":"Jialin","family":"Cao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8471-0995","authenticated-orcid":false,"given":"Kejia","family":"Shi","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4951-4059","authenticated-orcid":false,"given":"Keqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3863-981X","authenticated-orcid":false,"given":"Genhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"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":"Fudan Universiy, 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":"Fudan University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Yueyin Bai et al. 2023. LTrans-OPU: A Low-Latency FPGA-Based Overlay Processor for Transformer Networks. In FPL. 283--287.","DOI":"10.1109\/FPL60245.2023.00048"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Jialin Cao et al. 2023. PP-Transformer: Enable Efficient Deployment of Transformers Through Pattern Pruning. In ICCAD. 1--9.","DOI":"10.1109\/ICCAD57390.2023.10323836"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Zhaodong Chen et al. 2023. Dynamic N: M fine-grained structured sparse attention mechanism. In PPoPP. 369--379.","DOI":"10.1145\/3572848.3577500"},{"key":"e_1_3_2_1_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:2020.1810.04805","author":"Jacob Devlin","year":"2018","unstructured":"Jacob Devlin et al. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:2020.1810.04805 (2018)."},{"key":"e_1_3_2_1_5_1","unstructured":"Alexey Dosovitskiy et al. 2020. An image is worth 16\u00d716 words: Transformers for image recognition at scale. arXiv preprint arXiv:11929 (2020)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Chao Fang et al. 2022. An Efficient Hardware Accelerator for Sparse Transformer Neural Networks. In ISCAS. IEEE 2670--2674.","DOI":"10.1109\/ISCAS48785.2022.9937659"},{"key":"e_1_3_2_1_7_1","first-page":"11","article-title":"2022. An algorithm-hardware co-optimized framework for accelerating n: M sparse transformers","volume":"30","author":"Chao Fang","year":"2022","unstructured":"Chao Fang et al. 2022. An algorithm-hardware co-optimized framework for accelerating n: M sparse transformers. VLSI 30, 11 (2022), 1573--1586.","journal-title":"VLSI"},{"key":"e_1_3_2_1_8_1","unstructured":"Tae Jun Ham et al. 2020. A\u02c6 3: Accelerating attention mechanisms in neural networks with approximation. In HPCA. IEEE 328--341."},{"key":"e_1_3_2_1_9_1","unstructured":"Bingbing Li et al. 2020. Ftrans: energy-efficient acceleration of transformers using fpga. In ISLPED. 175--180."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Shiwei Liu et al. 2023. 16.2 A 28nm 53.8TOPS\/W 8b Sparse Transformer Accelerator with In-Memory Butterfly Zero Skipper for Unstructured-Pruned NN and CIM-Based Local-Attention-Reusable Engine. In ISSCC. 250--252.","DOI":"10.1109\/ISSCC42615.2023.10067360"},{"key":"e_1_3_2_1_11_1","volume-title":"Sanger: A co-design framework for enabling sparse attention using reconfigurable architecture. In MICRO. 977--991.","author":"Liqiang Lu","year":"2021","unstructured":"Liqiang Lu et al. 2021. Sanger: A co-design framework for enabling sparse attention using reconfigurable architecture. In MICRO. 977--991."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Siyuan Lu et al. 2020. Hardware accelerator for multi-head attention and position-wise feed-forward in the transformer. In SOCC. IEEE 84--89.","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"e_1_3_2_1_13_1","first-page":"32","article-title":"2019. Pytorch: An imperative style, high-performance deep learning library","author":"Adam Paszke","year":"2019","unstructured":"Adam Paszke et al. 2019. Pytorch: An imperative style, high-performance deep learning library. NeurIPS 32 (2019).","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Hongwu Peng et al. 2021. Accelerating transformer-based deep learning models on fpgas using column balanced block pruning. In ISQED. IEEE 142--148.","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"e_1_3_2_1_15_1","unstructured":"Panjie Qi et al. 2021. Accommodating transformer onto fpga: Coupling the balanced model compression and fpga-implementation optimization. In GLSVLSI."},{"key":"e_1_3_2_1_16_1","volume-title":"FACT: FFN-Attention Co-optimized Transformer Architecture with Eager Correlation Prediction. In ISCA. 1--14.","author":"Yubin Qin","year":"2023","unstructured":"Yubin Qin et al. 2023. FACT: FFN-Attention Co-optimized Transformer Architecture with Eager Correlation Prediction. In ISCA. 1--14."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Guan Shen et al. 2022. SALO: an efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences. In DAC. 571--576.","DOI":"10.1145\/3489517.3530504"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Yuhong Song et al. 2021. Dancing along battery: Enabling transformer with run-time reconfigurability on mobile devices. In DAC. IEEE 1003--1008.","DOI":"10.1109\/DAC18074.2021.9586295"},{"key":"e_1_3_2_1_19_1","first-page":"30","article-title":"2017. Attention is all you need","author":"Ashish Vaswani","year":"2017","unstructured":"Ashish Vaswani et al. 2017. Attention is all you need. NeurIPS 30 (2017).","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_20_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Alex Wang","year":"2018","unstructured":"Alex Wang et al. 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_21_1","volume-title":"Transformers: State-of-the-art natural language processing. In EMNLP. 38--45.","author":"Thomas Wolf","year":"2020","unstructured":"Thomas Wolf et al. 2020. Transformers: State-of-the-art natural language processing. In EMNLP. 38--45."},{"key":"e_1_3_2_1_22_1","unstructured":"Aojun Zhou et al. 2021. Learning n: m fine-grained structured sparse neural networks from scratch. arXiv preprint arXiv:2102.04010 (2021)."}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","location":"San Francisco CA USA","acronym":"DAC '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656497","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3656497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656497"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":22,"alternative-id":["10.1145\/3649329.3656497","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3656497","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}