{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:00:11Z","timestamp":1785952811865,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF","award":["2124039"],"award-info":[{"award-number":["2124039"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,2,28]]},"DOI":"10.1145\/3503222.3507738","type":"proceedings-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T20:49:01Z","timestamp":1645562941000},"page":"14-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":123,"title":["DOTA: detect and omit weak attentions for scalable transformer acceleration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6574-0649","authenticated-orcid":false,"given":"Zheng","family":"Qu","sequence":"first","affiliation":[{"name":"University of California at Santa Barbara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0792-8146","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"University of California at Santa Barbara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2228-8829","authenticated-orcid":false,"given":"Fengbin","family":"Tu","sequence":"additional","affiliation":[{"name":"University of California at Santa Barbara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9601-4586","authenticated-orcid":false,"given":"Zhaodong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California at Santa Barbara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8716-5793","authenticated-orcid":false,"given":"Yufei","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California at Santa Barbara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2093-1788","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California at Santa Barbara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/375551.375608"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00061"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2013.418"},{"key":"e_1_3_2_1_4_1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. arxiv:2005.14165."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815993"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning, Hal Daum\u00e9 III and Aarti Singh (Eds.) (Proceedings of Machine Learning Research","volume":"1703","author":"Chen Mark","year":"2020","unstructured":"Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative Pretraining From Pixels. In Proceedings of the 37th International Conference on Machine Learning, Hal Daum\u00e9 III and Aarti Singh (Eds.) (Proceedings of Machine Learning Research, Vol. 119). PMLR, 1691\u20131703. https:\/\/proceedings.mlr.press\/v119\/chen20s.html"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"e_1_3_2_1_11_1","unstructured":"Rewon Child Scott Gray Alec Radford and Ilya Sutskever. 2019. Generating Long Sequences with Sparse Transformers. arxiv:1904.10509."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2011.5981829"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. 1737\u20131746","author":"Gupta Suyog","year":"2015","unstructured":"Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan, and Pritish Narayanan. 2015. Deep learning with limited numerical precision. In International conference on machine learning. 1737\u20131746."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242044"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465893"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322214"},{"key":"e_1_3_2_1_23_1","unstructured":"Jianqiu Ji Jianmin Li Shuicheng Yan Bo Zhang and Qi Tian. 2012. Super-bit locality-sensitive hashing. In Advances in neural information processing systems. 108\u2013116."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2016.2597140"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"e_1_3_2_1_27_1","volume-title":"Reformer: The Efficient Transformer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkgNKkHtvB","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, Lukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The Efficient Transformer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkgNKkHtvB"},{"key":"e_1_3_2_1_28_1","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3205295"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694358"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00066"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.043191125"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_1_34_1","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843."},{"key":"e_1_3_2_1_35_1","unstructured":"Naveen Muralimanohar Rajeev Balasubramonian and Norman Jouppi. 2009. Cacti 6.0: A tool to model large caches. HP Laboratories 01."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"e_1_3_2_1_37_1","first-page":"363","article-title":"OPTIMUS: OPTImized matrix MUltiplication Structure for Transformer neural network accelerator","volume":"2","author":"Park Junki","year":"2020","unstructured":"Junki Park, Hyunsung Yoon, Daehyun Ahn, Jungwook Choi, and Jae-Joon Kim. 2020. OPTIMUS: OPTImized matrix MUltiplication Structure for Transformer neural network accelerator. Proceedings of Machine Learning and Systems, 2 (2020), 363\u2013378.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"International Conference on Machine Learning. 4055\u20134064","author":"Parmar Niki","year":"2018","unstructured":"Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Noam Shazeer, Alexander Ku, and Dustin Tran. 2018. Image transformer. In International Conference on Machine Learning. 4055\u20134064."},{"key":"e_1_3_2_1_39_1","volume-title":"Sinong Wang, and Jie Tang.","author":"Qiu Jiezhong","year":"2020","unstructured":"Jiezhong Qiu, Hao Ma, Omer Levy, Scott Wen tau Yih, Sinong Wang, and Jie Tang. 2020. Blockwise Self-Attention for Long Document Understanding. arxiv:1911.02972."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-012-9211-2"},{"key":"e_1_3_2_1_41_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training."},{"key":"e_1_3_2_1_42_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog, 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1, 8 (2019), 9."},{"key":"e_1_3_2_1_43_1","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2016.2586379"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Pranav Rajpurkar Jian Zhang Konstantin Lopyrev and Percy Liang. 2016. SQuAD: 100 000+ Questions for Machine Comprehension of Text. arxiv:1606.05250.","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_46_1","unstructured":"Aditya Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Chelsea Voss Alec Radford Mark Chen and Ilya Sutskever. 2021. Zero-Shot Text-to-Image Generation. arxiv:2102.12092."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.32"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"e_1_3_2_1_50_1","volume-title":"International Conference on Machine Learning. 9438\u20139447","author":"Tay Yi","year":"2020","unstructured":"Yi Tay, Dara Bahri, Liu Yang, Donald Metzler, and Da-Cheng Juan. 2020. Sparse sinkhorn attention. In International Conference on Machine Learning. 9438\u20139447. http:\/\/proceedings.mlr.press\/v119\/tay20a.html"},{"key":"e_1_3_2_1_51_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=qVyeW-grC2k","author":"Tay Yi","year":"2021","unstructured":"Yi Tay, Mostafa Dehghani, Samira Abnar, Yikang Shen, Dara Bahri, Philip Pham, Jinfeng Rao, Liu Yang, Sebastian Ruder, and Donald Metzler. 2021. Long Range Arena : A Benchmark for Efficient Transformers. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=qVyeW-grC2k"},{"key":"e_1_3_2_1_52_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 6000\u20136010."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_2_1_54_1","volume-title":"Big Bird: Transformers for Longer Sequences. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Zaheer Manzil","year":"2020","unstructured":"Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Onta\u00f1\u00f3n, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, and Amr Ahmed. 2020. Big Bird: Transformers for Longer Sequences. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/c8512d142a2d849725f31a9a7a361ab9-Abstract.html"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684746.2689060"}],"event":{"name":"ASPLOS '22: 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Lausanne Switzerland","acronym":"ASPLOS '22","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507738","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503222.3507738","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503222.3507738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:40Z","timestamp":1750191100000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503222.3507738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":55,"alternative-id":["10.1145\/3503222.3507738","10.1145\/3503222"],"URL":"https:\/\/doi.org\/10.1145\/3503222.3507738","relation":{},"subject":[],"published":{"date-parts":[[2022,2,22]]},"assertion":[{"value":"2022-02-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}