{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T09:07:29Z","timestamp":1770541649542,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFB4400600"],"award-info":[{"award-number":["2022YFB4400600"]}]},{"name":"Postgraduate Research & Practice Innovation Program of Jiangsu Province","award":["KYCX24_0149"],"award-info":[{"award-number":["KYCX24_0149"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,1,20]]},"DOI":"10.1145\/3658617.3697668","type":"proceedings-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T14:32:21Z","timestamp":1741098741000},"page":"1181-1187","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6173-3983","authenticated-orcid":false,"given":"Shaobo","family":"Ma","sequence":"first","affiliation":[{"name":"Nanjing Univ., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3430-1189","authenticated-orcid":false,"given":"Chao","family":"Fang","sequence":"additional","affiliation":[{"name":"Nanjing Univ., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6965-3436","authenticated-orcid":false,"given":"Haikuo","family":"Shao","sequence":"additional","affiliation":[{"name":"Nanjing Univ., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7227-4786","authenticated-orcid":false,"given":"Zhongfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing Univ., Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926299"},{"key":"e_1_3_2_1_2_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_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_4_1","volume-title":"pommDNN: Performance optimal GPU memory management for deep neural network training. Future Generation Computer Systems","author":"Chen Weiduo","year":"2023","unstructured":"Weiduo Chen, Xiaoshe Dong, Xinhang Chen, Song Liu, Qin Xia, and Qiang Wang. 2023. pommDNN: Performance optimal GPU memory management for deep neural network training. Future Generation Computer Systems (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"Binaryconnect: Training deep neural networks with binary weights during propagations. Advances in neural information processing systems 28","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. Binaryconnect: Training deep neural networks with binary weights during propagations. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_6_1","first-page":"30318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers Tim","year":"2022","unstructured":"Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. 2022. Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. Advances in Neural Information Processing Systems 35 (2022), 30318--30332.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36","author":"Dettmers Tim","year":"2024","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2024. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476157"},{"key":"e_1_3_2_1_9_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_10_1","volume-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:2210.17323 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3013637"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_2_1_13_1","volume-title":"2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE, 927--932","author":"Huang Longwei","year":"2024","unstructured":"Longwei Huang, Chao Fang, Qiong Li, Jun Lin, and Zhongfeng Wang. 2024. A Precision-Scalable RISC-V DNN Processor with On-Device Learning Capability at the Extreme Edge. In 2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC). IEEE, 927--932."},{"key":"e_1_3_2_1_14_1","volume-title":"Dissecting the nvidia turing t4 gpu via microbenchmarking. arXiv preprint arXiv:1903.07486","author":"Jia Zhe","year":"2019","unstructured":"Zhe Jia, Marco Maggioni, Jeffrey Smith, and Daniele Paolo Scarpazza. 2019. Dissecting the nvidia turing t4 gpu via microbenchmarking. arXiv preprint arXiv:1903.07486 (2019)."},{"key":"e_1_3_2_1_15_1","volume-title":"Token-scaled logit distillation for ternary weight generative language models. Advances in Neural Information Processing Systems 36","author":"Kim Minsoo","year":"2024","unstructured":"Minsoo Kim, Sihwa Lee, Janghwan Lee, Sukjin Hong, Du-Seong Chang, Wonyong Sung, and Jungwook Choi. 2024. Token-scaled logit distillation for ternary weight generative language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Squeezellm: Dense-and-sparse quantization. arXiv preprint arXiv:2306.07629","author":"Kim Sehoon","year":"2023","unstructured":"Sehoon Kim, Coleman Hooper, Amir Gholami, Zhen Dong, Xiuyu Li, Sheng Shen, Michael W Mahoney, and Kurt Keutzer. 2023. Squeezellm: Dense-and-sparse quantization. arXiv preprint arXiv:2306.07629 (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356169"},{"key":"e_1_3_2_1_18_1","first-page":"1878","article-title":"Accelerating binarized neural networks via bittensor-cores in turing gpus","volume":"32","author":"Li Ang","year":"2020","unstructured":"Ang Li and Simon Su. 2020. Accelerating binarized neural networks via bittensor-cores in turing gpus. IEEE Transactions on Parallel and Distributed Systems 32, 7 (2020), 1878--1891.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_1_19_1","unstructured":"Shiyang Li Jianshu Chen Yelong Shen Zhiyu Chen Xinlu Zhang Zekun Li Hong Wang Jing Qian Baolin Peng Yi Mao et al. 2022. Explanations from large language models make small reasoners better. arXiv preprint arXiv:2210.06726 (2022)."},{"key":"e_1_3_2_1_20_1","first-page":"87","article-title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. Proceedings of Machine Learning and Systems 6 (2024), 87--100.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"Qserve: W4a8kv4 quantization and system co-design for efficient llm serving. arXiv preprint arXiv:2405.04532","author":"Lin Yujun","year":"2024","unstructured":"Yujun Lin, Haotian Tang, Shang Yang, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, and Song Han. 2024. Qserve: W4a8kv4 quantization and system co-design for efficient llm serving. arXiv preprint arXiv:2405.04532 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Llm-qat: Data-free quantization aware training for large language models. arXiv preprint arXiv:2305.17888","author":"Liu Zechun","year":"2023","unstructured":"Zechun Liu, Barlas Oguz, Changsheng Zhao, Ernie Chang, Pierre Stock, Yashar Mehdad, Yangyang Shi, Raghuraman Krishnamoorthi, and Vikas Chandra. 2023. Llm-qat: Data-free quantization aware training for large language models. arXiv preprint arXiv:2305.17888 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Benchmarking and dissecting the nvidia hopper gpu architecture. arXiv preprint arXiv:2402.13499","author":"Luo Weile","year":"2024","unstructured":"Weile Luo, Ruibo Fan, Zeyu Li, Dayou Du, Qiang Wang, and Xiaowen Chu. 2024. Benchmarking and dissecting the nvidia hopper gpu architecture. arXiv preprint arXiv:2402.13499 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2549523"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578178.3578238"},{"key":"e_1_3_2_1_26_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems 35 (2022) 27730--27744."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"e_1_3_2_1_28_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_29_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_30_1","volume-title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models. In The Twelfth International Conference on Learning Representations (ICLR).","author":"Shao Wenqi","year":"2024","unstructured":"Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, and Ping Luo. 2024. OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models. In The Twelfth International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5.","author":"Tian Jiayi","year":"2023","unstructured":"Jiayi Tian, Chao Fang, Haonan Wang, and Zhongfeng Wang. 2023. BEBERT: Efficient and robust binary ensemble BERT. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_1_33_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_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"e_1_3_2_1_35_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Wang Yuke","year":"2023","unstructured":"Yuke Wang, Boyuan Feng, Zheng Wang, Guyue Huang, and Yufei Ding. 2023. {TC-GNN}: Bridging Sparse {GNN} Computation and Dense Tensor Cores on {GPUs}. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 149--164."},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. PMLR, 38087--38099","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087--38099."},{"key":"e_1_3_2_1_37_1","volume-title":"OneBit: Towards Extremely Low-bit Large Language Models. arXiv preprint arXiv:2402.11295","author":"Xu Yuzhuang","year":"2024","unstructured":"Yuzhuang Xu, Xu Han, Zonghan Yang, Shuo Wang, Qingfu Zhu, Zhiyuan Liu, Weidong Liu, and Wanxiang Che. 2024. OneBit: Towards Extremely Low-bit Large Language Models. arXiv preprint arXiv:2402.11295 (2024)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btu047"},{"key":"e_1_3_2_1_40_1","volume-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160","author":"Zhou Shuchang","year":"2016","unstructured":"Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, and Yuheng Zou. 2016. Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients. arXiv preprint arXiv:1606.06160 (2016)."}],"event":{"name":"ASPDAC '25: 30th Asia and South Pacific Design Automation Conference","location":"Tokyo Japan","acronym":"ASPDAC '25","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEICE","IPSJ","IEEE CAS","IEEE CEDA"]},"container-title":["Proceedings of the 30th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697668","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658617.3697668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":40,"alternative-id":["10.1145\/3658617.3697668","10.1145\/3658617"],"URL":"https:\/\/doi.org\/10.1145\/3658617.3697668","relation":{},"subject":[],"published":{"date-parts":[[2025,1,20]]},"assertion":[{"value":"2025-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}