{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:10:46Z","timestamp":1750219846330,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,5]],"date-time":"2023-06-05T00:00:00Z","timestamp":1685923200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"UM-SJTU Startup Fund"},{"name":"SRC AI Hardware program"},{"name":"CRISP, one of six centers in JUMP, a Semiconductor Research Corporation (SRC) program sponsored by DARPA"},{"name":"SJTU Explore-X Research Grant","award":["D6040004\/03"],"award-info":[{"award-number":["D6040004\/03"]}]},{"name":"CCF-Tencent Open Fund","award":["RAGR2022011"],"award-info":[{"award-number":["RAGR2022011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,5]]},"DOI":"10.1145\/3583781.3590292","type":"proceedings-article","created":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T22:40:19Z","timestamp":1685572819000},"page":"467-471","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Design Space Exploration of Layer-Wise Mixed-Precision Quantization with Tightly Integrated Edge Inference Units"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3088-8229","authenticated-orcid":false,"given":"Xiaotian","family":"Zhao","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9526-6954","authenticated-orcid":false,"given":"Yimin","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9403-6319","authenticated-orcid":false,"given":"Vaibhav","family":"Verma","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8632-0883","authenticated-orcid":false,"given":"Ruge","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0577-9976","authenticated-orcid":false,"given":"Mircea","family":"Stan","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2374-3953","authenticated-orcid":false,"given":"Xinfei","family":"Guo","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3444943"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/pr6080106"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Chen Chen Xiaoyan Xiang Chang Liu Yunhai Shang Ren Guo Dongqi Liu Yimin Lu Ziyi Hao Jiahui Luo Zhijian Chen et al. 2020. Xuantie-910: A commer- cial multi-core 12-stage pipeline out-of-order 64-bit high performance RISC-V processor with vector extension: Industrial product. In ISCA. IEEE 52--64.","DOI":"10.1109\/ISCA45697.2020.00016"},{"key":"e_1_3_2_1_5_1","volume-title":"Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan.","author":"Choi Jungwook","year":"2018","unstructured":"Jungwook Choi, Zhuo Wang, Swagath Venkataramani, Pierce I-Jen Chuang, Vijayalakshmi Srinivasan, and Kailash Gopalakrishnan. 2018. Pact: Parameterized clipping activation for quantized neural networks. arXiv preprint arXiv:1805.06085 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3009475"},{"key":"e_1_3_2_1_8_1","volume-title":"A survey of quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630","author":"Gholami Amir","year":"2021","unstructured":"Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W Mahoney, and Kurt Keutzer. 2021. A survey of quantization methods for efficient neural network inference. arXiv preprint arXiv:2103.13630 (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"e_1_3_2_1_10_1","volume-title":"Hmq: Hardware friendly mixed precision quantization block for cnns","author":"Habi Hai Victor","year":"2020","unstructured":"Hai Victor Habi, Roy H Jennings, and Arnon Netzer. 2020. Hmq: Hardware friendly mixed precision quantization block for cnns. In ECCV. Springer, 448--463."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2014.04.013"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISOCC53507.2021.9613969"},{"key":"e_1_3_2_1_14_1","volume-title":"LSMQ: A Layer-Wise Sensitivity-Based Mixed- Precision Quantization Method for Bit-Flexible CNN Accelerator. In 18th","author":"Huang Yimin","year":"2021","unstructured":"Yimin Huang, Kai Chen, Zhuang Shao, Yichuan Bai, Yafeng Huang, Yuan Du, Li Du, and Zhongfeng Wang. 2021. LSMQ: A Layer-Wise Sensitivity-Based Mixed- Precision Quantization Method for Bit-Flexible CNN Accelerator. In 18th ISOCC. IEEE, 256--257."},{"volume-title":"Evolutionary quantization of neural networks with mixed-precision","author":"Liu Zhenhua","key":"e_1_3_2_1_15_1","unstructured":"Zhenhua Liu, Xinfeng Zhang, Shanshe Wang, Siwei Ma, and Wen Gao. 2021. Evolutionary quantization of neural networks with mixed-precision. In ICASSP. IEEE, 2785--2789."},{"key":"e_1_3_2_1_16_1","volume-title":"8-bit Numerical Formats for Deep Neural Networks. arXiv preprint arXiv:2206.02915","author":"Noune Badreddine","year":"2022","unstructured":"Badreddine Noune, Philip Jones, Daniel Justus, Dominic Masters, and Carlo Luschi. 2022. 8-bit Numerical Formats for Deep Neural Networks. arXiv preprint arXiv:2206.02915 (2022)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_18_1","volume-title":"Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance. arXiv preprint arXiv:2203.08368","author":"Tang Chen","year":"2022","unstructured":"Chen Tang, Kai Ouyang, Zhi Wang, Yifei Zhu, Yaowei Wang, Wen Ji, and Wenwu Zhu. 2022. Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance. arXiv preprint arXiv:2203.08368 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00311"},{"key":"e_1_3_2_1_20_1","volume-title":"Ying Wang, Tijmen Blankevoort, and Max Welling.","author":"Baalen Mart Van","year":"2020","unstructured":"Mart Van Baalen, Christos Louizos, Markus Nagel, Rana Ali Amjad, Ying Wang, Tijmen Blankevoort, and Max Welling. 2020. Bayesian bits: Unifying quantization and pruning. Advances in neural information processing systems 33 (2020), 5741--5752."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2022.100742"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394885.3431538"},{"key":"e_1_3_2_1_24_1","volume-title":"BSQ: Exploring bit-level sparsity for mixed-precision neural network quantization. arXiv preprint arXiv:2102.10462","author":"Yang Huanrui","year":"2021","unstructured":"Huanrui Yang, Lin Duan, Yiran Chen, and Hai Li. 2021. BSQ: Exploring bit-level sparsity for mixed-precision neural network quantization. arXiv preprint arXiv:2102.10462 (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Yang Linjie","year":"2021","unstructured":"Linjie Yang and Qing Jin. 2021. Fracbits: Mixed precision quantization via frac- tional bit-widths. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 10612--10620."},{"key":"e_1_3_2_1_26_1","volume-title":"International Conference on Machine Learning. PMLR, 11875--11886","author":"Yao Zhewei","year":"2021","unstructured":"Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael Mahoney, et al. 2021. Hawq-v3: Dyadic neural network quantization. In International Conference on Machine Learning. PMLR, 11875--11886."},{"volume-title":"Search what you want: Barrier panelty NAS for mixed precision quantization","author":"Yu Haibao","key":"e_1_3_2_1_27_1","unstructured":"Haibao Yu, Qi Han, Jianbo Li, Jianping Shi, Guangliang Cheng, and Bin Fan. 2020. Search what you want: Barrier panelty NAS for mixed precision quantization. In ECCV. Springer, 1--16."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"}],"event":{"name":"GLSVLSI '23: Great Lakes Symposium on VLSI 2023","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"Knoxville TN USA","acronym":"GLSVLSI '23"},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583781.3590292","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583781.3590292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:58Z","timestamp":1750178818000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583781.3590292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,5]]},"references-count":28,"alternative-id":["10.1145\/3583781.3590292","10.1145\/3583781"],"URL":"https:\/\/doi.org\/10.1145\/3583781.3590292","relation":{},"subject":[],"published":{"date-parts":[[2023,6,5]]},"assertion":[{"value":"2023-06-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}