{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:35:41Z","timestamp":1773246941721,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":18,"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":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-1703013, CCF-1901192, CCF-1936794, CCF-2324645, and CCF-2311544"],"award-info":[{"award-number":["CCF-1703013, CCF-1901192, CCF-1936794, CCF-2324645, and CCF-2311544"]}],"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\/3649476.3658709","type":"proceedings-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T12:29:41Z","timestamp":1718022581000},"page":"736-741","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["HSCONN: Hardware-Software Co-Optimization of Self-Attention Neural Networks for Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0565-5845","authenticated-orcid":false,"given":"Siqin","family":"Liu","sequence":"first","affiliation":[{"name":"Electrical Engineering and Computer Science, Ohio University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6827-3169","authenticated-orcid":false,"given":"Prakash Chand","family":"Kuve","sequence":"additional","affiliation":[{"name":"Microchip Technology Corporation, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9472-4637","authenticated-orcid":false,"given":"Avinash","family":"Karanth","sequence":"additional","affiliation":[{"name":"Ohio University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_2_1_2_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared\u00a0D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877\u20131901."},{"key":"e_1_3_2_1_3_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/1674-4926\/41\/2\/022406"},{"key":"e_1_3_2_1_6_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2942020"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3144614"},{"key":"e_1_3_2_1_10_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_11_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"e_1_3_2_1_12_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_13_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\u00a0N 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_14_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\u00a0R 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_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3004623"},{"key":"e_1_3_2_1_17_1","volume-title":"Large-scale cloze test dataset created by teachers. arXiv preprint arXiv:1711.03225","author":"Xie Qizhe","year":"2017","unstructured":"Qizhe Xie, Guokun Lai, Zihang Dai, and Eduard Hovy. 2017. Large-scale cloze test dataset created by teachers. arXiv preprint arXiv:1711.03225 (2017)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9111812"}],"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\/3649476.3658709","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649476.3658709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:31:09Z","timestamp":1755829869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":18,"alternative-id":["10.1145\/3649476.3658709","10.1145\/3649476"],"URL":"https:\/\/doi.org\/10.1145\/3649476.3658709","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"}}]}}