{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T20:39:52Z","timestamp":1769978392574,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":21,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Singapore National Research Foundation","award":["NRF-CRP23-2019-0003"],"award-info":[{"award-number":["NRF-CRP23-2019-0003"]}]},{"name":"Amd research gift"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3658488","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":9,"title":["SWAT: Scalable and Efficient Window Attention-based Transformers Acceleration on FPGAs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1143-0762","authenticated-orcid":false,"given":"Zhenyu","family":"Bai","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1339-6048","authenticated-orcid":false,"given":"Pranav","family":"Dangi","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8710-4472","authenticated-orcid":false,"given":"Huize","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4136-4188","authenticated-orcid":false,"given":"Tulika","family":"Mitra","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore, Singapore"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150.","author":"Iz Beltagy","year":"2020","unstructured":"Iz Beltagy et al. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Adrian M Caulfield et al. 2016. A cloud-scale acceleration architecture. In MICRO-49. IEEE 1--13.","DOI":"10.1109\/MICRO.2016.7783710"},{"key":"e_1_3_2_1_3_1","unstructured":"Tri Dao et al. 2019. Learning fast algorithms for linear transforms using butterfly factorizations. In ICML. 1517--1527."},{"key":"e_1_3_2_1_4_1","unstructured":"Tri Dao et al. 2021. Pixelated butterfly: Simple and efficient sparse training for neural network models. arXiv."},{"key":"e_1_3_2_1_5_1","volume-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness. NeurIPS-35.","author":"Tri Dao","year":"2022","unstructured":"Tri Dao et al. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. NeurIPS-35."},{"key":"e_1_3_2_1_6_1","volume-title":"2009 IEEE conference on computer vision and pattern recognition. Ieee, 248--255","author":"Jia","unstructured":"Jia Deng et al. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248--255."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Hongxiang Fan et al. 2022. Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design. In MICRO-55. IEEE 599--615.","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"e_1_3_2_1_8_1","unstructured":"Sehoon Kim et al. 2023. Full Stack Optimization of Transformer Inference. In Architecture and System Support for Transformer Models (ASSYST@ ISCA 2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Fnet: Mixing tokens with fourier transforms. arXiv preprint arXiv:2105.03824.","author":"Lee-Thorp James","year":"2021","unstructured":"James Lee-Thorp et al. 2021. Fnet: Mixing tokens with fourier transforms. arXiv preprint arXiv:2105.03824."},{"key":"e_1_3_2_1_10_1","volume-title":"Sanger: A co-design framework for enabling sparse attention using reconfigurable architecture. In MICRO-54.","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-54."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR, 4055--4064","author":"Niki","unstructured":"Niki Parmar et al. 2018. Image transformer. In International conference on machine learning. PMLR, 4055--4064."},{"key":"e_1_3_2_1_12_1","volume-title":"FACT: FFN-Attention Co-optimized Transformer Architecture with Eager Correlation Prediction. In ISCA-50. 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-50. 1--14."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Zheng Qu et al. 2022. Dota: detect and omit weak attentions for scalable transformer acceleration. In ASPLOS-27. 14--26.","DOI":"10.1145\/3503222.3507738"},{"key":"e_1_3_2_1_14_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-59. 571--576.","DOI":"10.1145\/3489517.3530504"},{"key":"e_1_3_2_1_15_1","unstructured":"Yi Tay et al. [n. d.]. Long range arena: A benchmark for efficient transformers. arXiv preprint arXiv:2011.04006."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00577"},{"key":"e_1_3_2_1_17_1","unstructured":"Ashish Vaswani et al. 2017. Attention is all you need. NeurIPS 30."},{"key":"e_1_3_2_1_18_1","volume-title":"Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768.","author":"Wang Sinong","year":"2020","unstructured":"Sinong Wang,, et al. 2020. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768."},{"key":"e_1_3_2_1_19_1","volume-title":"HPCA","author":"Haoran","year":"2023","unstructured":"Haoran You et al. [n. d.]. Vitcod: Vision transformer acceleration via dedicated algorithm and accelerator co-design. In HPCA 2023. 273--286."},{"key":"e_1_3_2_1_20_1","unstructured":"Manzil Zaheer et al. 2020. Big bird: Transformers for longer sequences. Advances in neural information processing systems 33 17283--17297."},{"key":"e_1_3_2_1_21_1","volume-title":"ICCV","author":"Pengchuan","year":"2021","unstructured":"Pengchuan Zhang et al. [n. d.]. Multi-scale vision longformer: A new vision transformer for high-resolution image encoding. In ICCV 2021. 2998--3008."}],"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\/3649329.3658488","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3658488","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:01Z","timestamp":1750295881000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3658488"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":21,"alternative-id":["10.1145\/3649329.3658488","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3658488","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"}}]}}