{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:42:57Z","timestamp":1773247377427,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3676536.3676761","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T12:53:56Z","timestamp":1744203236000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["ChatOPU: An FPGA-based Overlay Processor for Large Language Models with Unstructured Sparsity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5348-1715","authenticated-orcid":false,"given":"Tiandong","family":"Zhao","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, California, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8624-8666","authenticated-orcid":false,"given":"Shaoqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"},{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9939-8922","authenticated-orcid":false,"given":"Chen","family":"Wu","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5266-3805","authenticated-orcid":false,"given":"Lei","family":"He","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China"},{"name":"University of California, Los Angeles, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2021. cuSPARSELt: A High-Performance CUDA Library for Sparse Matrix-Matrix Multiplication. https:\/\/docs.nvidia.com\/cuda\/cusparselt\/index.html"},{"key":"e_1_3_2_1_2_1","unstructured":"2023. LightLLM. https:\/\/github.com\/ModelTC\/lightllm"},{"key":"e_1_3_2_1_3_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28960"},{"key":"e_1_3_2_1_5_1","volume-title":"FET-OPU: A Flexible and Efficient FPGA-Based Overlay Processor for Transformer Networks. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9.","author":"Bai Yueyin","year":"2023","unstructured":"Yueyin Bai, Hao Zhou, Keqing Zhao, Hongji Wang, Jianli Chen, Jun Yu, and Kun Wang. 2023. FET-OPU: A Flexible and Efficient FPGA-Based Overlay Processor for Transformer Networks. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9."},{"key":"e_1_3_2_1_6_1","volume-title":"PP-Transformer: Enable Efficient Deployment of Transformers Through Pattern Pruning. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9.","author":"Cao Jialin","year":"2023","unstructured":"Jialin Cao, Xuanda Lin, Manting Zhang, Kejia Shi, Jun Yu, and Kun Wang. 2023. PP-Transformer: Enable Efficient Deployment of Transformers Through Pattern Pruning. In 2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD). IEEE, 1--9."},{"key":"e_1_3_2_1_7_1","volume-title":"Understanding the potential of fpga-based spatial acceleration for large language model inference. arXiv preprint arXiv:2312.15159","author":"Chen Hongzheng","year":"2023","unstructured":"Hongzheng Chen, Jiahao Zhang, Yixiao Du, Shaojie Xiang, Zichao Yue, Niansong Zhang, Yaohui Cai, and Zhiru Zhang. 2023. Understanding the potential of fpga-based spatial acceleration for large language model inference. arXiv preprint arXiv:2312.15159 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"LLM-empowered chatbots for psychiatrist and patient simulation: application and evaluation. arXiv preprint arXiv:2305.13614","author":"Chen Siyuan","year":"2023","unstructured":"Siyuan Chen, Mengyue Wu, Kenny Q Zhu, Kunyao Lan, Zhiling Zhang, and Lyuchun Cui. 2023. LLM-empowered chatbots for psychiatrist and patient simulation: application and evaluation. arXiv preprint arXiv:2305.13614 (2023)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2022.3197282"},{"key":"e_1_3_2_1_10_1","volume-title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot.(2023). URL https:\/\/arxiv.org\/abs\/2301.00774","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar and Dan Alistarh. 2023. SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot.(2023). URL https:\/\/arxiv.org\/abs\/2301.00774 (2023)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569665"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392751"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. 2."},{"key":"e_1_3_2_1_16_1","volume-title":"Kun Wang, and Lei He.","author":"Khan Hamza","year":"2021","unstructured":"Hamza Khan, Asma Khan, Zainab Khan, Lun Bin Huang, Kun Wang, and Lei He. 2021. NPE: An FPGA-based overlay processor for natural language processing. arXiv preprint arXiv:2104.06535 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Shortened LLaMA: A Simple Depth Pruning for Large Language Models. arXiv preprint arXiv:2402.02834","author":"Kim Bo-Kyeong","year":"2024","unstructured":"Bo-Kyeong Kim, Geonmin Kim, Tae-Ho Kim, Thibault Castells, Shinkook Choi, Junho Shin, and Hyoung-Kyu Song. 2024. Shortened LLaMA: A Simple Depth Pruning for Large Language Models. arXiv preprint arXiv:2402.02834 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"e_1_3_2_1_20_1","volume-title":"On learning to summarize with large language models as references. arXiv preprint arXiv:2305.14239","author":"Liu Yixin","year":"2023","unstructured":"Yixin Liu, Alexander R Fabbri, Pengfei Liu, Dragomir Radev, and Arman Cohan. 2023. On learning to summarize with large language models as references. arXiv preprint arXiv:2305.14239 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 513--516","author":"Liu Zejian","year":"2021","unstructured":"Zejian Liu, Gang Li, and Jian Cheng. 2021. Hardware acceleration of fully quantized bert for efficient natural language processing. In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 513--516."},{"key":"e_1_3_2_1_22_1","unstructured":"Shaoqiang Lu Tiandong Zhao Rumin Zhang Ting-Jung Lin Chen Wu and Lei He. 2024. An FPGA-based Multi-Core Overlay Processor for Transformer-based Models. (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems 36","author":"Ma Xinyin","year":"2023","unstructured":"Xinyin Ma, Gongfan Fang, and Xinchao Wang. 2023. Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems 36 (2023), 21702--21720."},{"key":"e_1_3_2_1_24_1","volume-title":"Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, and Zhihao Jia.","author":"Miao Xupeng","year":"2023","unstructured":"Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Rae Ying Yee Wong, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, and Zhihao Jia. 2023. Specinfer: Accelerating generative llm serving with speculative inference and token tree verification. arXiv preprint arXiv:2305.09781 (2023)."},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. 2023. ChatGPT. https:\/\/chat.openai.com\/chat"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"e_1_3_2_1_27_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_28_1","volume-title":"A simple and effective pruning approach for large language models. arXiv preprint arXiv:2306.11695","author":"Sun Mingjie","year":"2023","unstructured":"Mingjie Sun, Zhuang Liu, Anna Bair, and J Zico Kolter. 2023. A simple and effective pruning approach for large language models. arXiv preprint arXiv:2306.11695 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550075"},{"key":"e_1_3_2_1_30_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_31_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 N 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_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00073"},{"key":"e_1_3_2_1_34_1","volume-title":"Flash-llm: Enabling cost-effective and highly-efficient large generative model inference with unstructured sparsity. arXiv preprint arXiv:2309.10285","author":"Xia Haojun","year":"2023","unstructured":"Haojun Xia, Zhen Zheng, Yuchao Li, Donglin Zhuang, Zhongzhu Zhou, Xiafei Qiu, Yong Li, Wei Lin, and Shuaiwen Leon Song. 2023. Flash-llm: Enabling cost-effective and highly-efficient large generative model inference with unstructured sparsity. arXiv preprint arXiv:2309.10285 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2939726"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375311"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"e_1_3_2_1_38_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"]},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676761","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:43:58Z","timestamp":1750290238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":38,"alternative-id":["10.1145\/3676536.3676761","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3676761","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}