{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:16:25Z","timestamp":1779920185010,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Jiangsu Provincial Natural Science Foundation","award":["BK20210123"],"award-info":[{"award-number":["BK20210123"]}]},{"DOI":"10.13039\/501100006374","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y2021121"],"award-info":[{"award-number":["Y2021121"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102383,61976200,62172380"],"award-info":[{"award-number":["62102383,61976200,62172380"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4501600,2022YFB4501603"],"award-info":[{"award-number":["2022YFB4501600,2022YFB4501603"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,12]]},"DOI":"10.1145\/3649476.3658810","type":"proceedings-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T12:29:41Z","timestamp":1718022581000},"page":"599-603","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Enhancing Long Sequence Input Processing in FPGA-Based Transformer Accelerators through Attention Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9404-581X","authenticated-orcid":false,"given":"Yunji","family":"Qin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2240-6672","authenticated-orcid":false,"given":"Wenqi","family":"Lou","sequence":"additional","affiliation":[{"name":"Software Engineering, University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-5575","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8391-5526","authenticated-orcid":false,"given":"Lei","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-3143","authenticated-orcid":false,"given":"Xuehai","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tri Dao 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. In NeurIPS. 16344\u201316359."},{"key":"e_1_3_2_1_2_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Jacob Devlin","year":"2018","unstructured":"Jacob Devlin 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Alexey Dosovitskiy","year":"2020","unstructured":"Alexey Dosovitskiy 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_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"e_1_3_2_1_5_1","first-page":"1573","article-title":"An algorithm\u2013hardware co-optimized framework for accelerating n: M sparse transformers","volume":"30","author":"Fang Chao","year":"2022","unstructured":"Chao Fang 2022. An algorithm\u2013hardware co-optimized framework for accelerating n: M sparse transformers. TVLSI 30, 11 (2022), 1573\u20131586.","journal-title":"TVLSI"},{"key":"e_1_3_2_1_6_1","volume-title":"MALOC: A Fully Pipelined FPGA Accelerator for Convolutional Neural Networks With All Layers Mapped on Chip. TCAD","author":"Lei Gong","year":"2018","unstructured":"Lei Gong 2018. MALOC: A Fully Pipelined FPGA Accelerator for Convolutional Neural Networks With All Layers Mapped on Chip. TCAD (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL60245.2023.00012"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"e_1_3_2_1_10_1","unstructured":"Woosuk Kwon 2022. A fast post-training pruning framework for transformers. In NeurIPS. 24101\u201324116."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"e_1_3_2_1_12_1","first-page":"1847","article-title":". OctCNN: A High Throughput FPGA Accelerator for CNNs Using Octave Convolution Algorithm","volume":"71","author":"Lou Wenqi","year":"2022","unstructured":"Wenqi Lou 2022. OctCNN: A High Throughput FPGA Accelerator for CNNs Using Octave Convolution Algorithm. TC 71, 8 (2022), 1847\u20131859.","journal-title":"TC"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137094"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323651"},{"key":"e_1_3_2_1_17_1","volume-title":"Fast Inference, and Favorable Transferability For ViTs. arXiv:2309.15755","author":"Ao Wang","year":"2023","unstructured":"Ao Wang 2023. CAIT: Triple-Win Compression towards High Accuracy, Fast Inference, and Favorable Transferability For ViTs. arXiv:2309.15755 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_2_1_19_1","first-page":"4088","article-title":"Via: A novel vision-transformer accelerator based on fpga","volume":"41","author":"Wang Teng","year":"2022","unstructured":"Teng Wang 2022. Via: A novel vision-transformer accelerator based on fpga. TCAD 41, 11 (2022), 4088\u20134099.","journal-title":"TCAD"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3549937"}],"event":{"name":"GLSVLSI '24: Great Lakes Symposium on VLSI 2024","location":"Clearwater FL USA","acronym":"GLSVLSI '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658810","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649476.3658810","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:30:13Z","timestamp":1755829813000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658810"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":20,"alternative-id":["10.1145\/3649476.3658810","10.1145\/3649476"],"URL":"https:\/\/doi.org\/10.1145\/3649476.3658810","relation":{},"subject":[],"published":{"date-parts":[[2024,6,12]]},"assertion":[{"value":"2024-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}