{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T11:56:03Z","timestamp":1792756563532,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":15,"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":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF2022M3I7A2079267"],"award-info":[{"award-number":["NRF2022M3I7A2079267"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Samsung Research Funding and Incubation Center of Samsung Electronics","award":["SRFCMA1802-01"],"award-info":[{"award-number":["SRFCMA1802-01"]}]},{"name":"Institute of Information & communications Technology Planning & Evaluation","award":["2022-0-00266"],"award-info":[{"award-number":["2022-0-00266"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3655936","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":8,"title":["SpARC: Token Similarity-Aware Sparse Attention Transformer Accelerator via Row-wise Clustering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9010-7888","authenticated-orcid":false,"given":"Han","family":"Cho","sequence":"first","affiliation":[{"name":"Korea University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6590-192X","authenticated-orcid":false,"given":"Dongjun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1772-5638","authenticated-orcid":false,"given":"Seung-Eon","family":"Hwang","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3251-0024","authenticated-orcid":false,"given":"Jongsun","family":"Park","sequence":"additional","affiliation":[{"name":"Korea University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"6000","volume-title":"Proc. of NeurIPS","volume":"30","author":"Ashish","year":"2017","unstructured":"Ashish Vaswani et al. Attention is all you need. In Proc. of NeurIPS, volume 30, pages 6000--6010, 2017."},{"key":"e_1_3_2_1_2_1","first-page":"4171","volume-title":"Proc. of NAACL-HLT","author":"Jacob","year":"2019","unstructured":"Jacob Devlin et al. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proc. of NAACL-HLT, pages 4171--4186, 2019."},{"issue":"8","key":"e_1_3_2_1_3_1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Alec Radford","year":"2019","unstructured":"Alec Radford et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.","journal-title":"OpenAI blog"},{"key":"e_1_3_2_1_4_1","first-page":"1877","volume-title":"Proc. of NeurIPS","volume":"33","author":"Tom","year":"2020","unstructured":"Tom Brown et al. Language models are few-shot learners. In Proc. of NeurIPS, volume 33, pages 1877--1901, 2020."},{"key":"e_1_3_2_1_5_1","volume-title":"ICLR","author":"Alexey","year":"2020","unstructured":"Alexey Dosovitskiy et al. An image is worth 16\u00d716 words: Transformers for image recognition at scale. In ICLR, 2020."},{"key":"e_1_3_2_1_6_1","volume-title":"ICLR","author":"Nikita","year":"2019","unstructured":"Nikita Kitaev et al. Reformer: The efficient transformer. In ICLR, 2019."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"e_1_3_2_1_8_1","first-page":"2174","volume-title":"Proc. of EMNLP-IJCNLP","author":"Gon\u00e7alo M","year":"2019","unstructured":"Gon\u00e7alo M Correia et al. Adaptively sparse transformers. In Proc. of EMNLP-IJCNLP, pages 2174--2184, 2019."},{"key":"e_1_3_2_1_9_1","first-page":"3548","volume-title":"Proc. of EMNLP-IJCNLP","author":"Baiyun","year":"2019","unstructured":"Baiyun Cui et al. Fine-tune bert with sparse self-attention mechanism. In Proc. of EMNLP-IJCNLP, pages 3548--3553, 2019."},{"key":"e_1_3_2_1_10_1","first-page":"9438","volume-title":"Proc. of ICML","author":"Yi","year":"2020","unstructured":"Yi Tay et al. Sparse sinkhorn attention. In Proc. of ICML, pages 9438--9447. PMLR, 2020."},{"key":"e_1_3_2_1_11_1","first-page":"58","volume-title":"Proc. of HPCA","author":"Eric","year":"2020","unstructured":"Eric Qin et al. Sigma: A sparse and irregular gemm accelerator with flexible interconnects for dnn training. In Proc. of HPCA, pages 58--70. IEEE, 2020."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_3_2_1_13_1","first-page":"41","volume-title":"Proc. of MICRO","author":"Mike O'Connor","year":"2017","unstructured":"Mike O'Connor et al. Fine-grained dram: Energy-efficient dram for extreme bandwidth systems. In Proc. of MICRO, pages 41--54, 2017."},{"key":"e_1_3_2_1_14_1","first-page":"97","volume-title":"Proc. of HPCA","author":"Hanrui","year":"2021","unstructured":"Hanrui Wang et al. Spatten: Efficient sparse attention architecture with cascade token and head pruning. In Proc. of HPCA, pages 97--110. IEEE, 2021."},{"key":"e_1_3_2_1_15_1","first-page":"977","volume-title":"Proc. of MICRO","author":"Liqiang","year":"2021","unstructured":"Liqiang Lu et al. Sanger: A co-design framework for enabling sparse attention using reconfigurable architecture. In Proc. of MICRO, pages 977--991, 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\/3649329.3655936","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3655936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:48Z","timestamp":1750295868000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3655936"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":15,"alternative-id":["10.1145\/3649329.3655936","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3655936","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"}}]}}