{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:45:45Z","timestamp":1786391145543,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT)","award":["RS-2023-00256081"],"award-info":[{"award-number":["RS-2023-00256081"]}]},{"name":"Samsung Research Funding Center","award":["SRFC-TC1603-53"],"award-info":[{"award-number":["SRFC-TC1603-53"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,5]]},"DOI":"10.1145\/3816440.3818569","type":"proceedings-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:23:31Z","timestamp":1786389811000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MECA-CiM: A Shared-MicroExponent-aware Configurable Analog Compute-in-Memory Macro for Efficient Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8681-0025","authenticated-orcid":false,"given":"Wonkyung","family":"Han","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering \/ College of Engineering \/ VLSI Lab, Seoul National University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6658-9089","authenticated-orcid":false,"given":"Dohyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering \/ College of Engineering \/ VLSI Lab, Seoul National University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9934-2697","authenticated-orcid":false,"given":"Jihoon","family":"Park","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering \/ College of Engineering \/ VLSI Lab, Seoul National University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4389-6635","authenticated-orcid":false,"given":"Juheun","family":"Lee","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in Artificial Intelligence \/ VLSI Lab, Seoul National University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7524-5884","authenticated-orcid":false,"given":"Sukhyun","family":"Choi","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering \/ College of Engineering \/ VLSI Lab, Seoul National University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9859-2790","authenticated-orcid":false,"given":"Wonjun","family":"Han","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in Artificial Intelligence \/ VLSI Lab, Seoul National University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5175-8258","authenticated-orcid":false,"given":"Jae-Joon","family":"Kim","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering \/ College of Engineering \/ VLSI Lab, Seoul National University, Seoul, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"7","volume-title":"2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","author":"Yun Myeongji","year":"2025","unstructured":"Myeongji Yun, Jung Gyu Min, Sein Oh, Jiwoung Choi, Jang-Sik Lee, Minkyu Je, and Youngjoo Lee. Cost-efficient processing-in-memory architecture with training-free and universal error compensation. In 2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED), pages 1\u20137, 2025."},{"key":"e_1_3_2_1_2_1","first-page":"576","volume-title":"2024 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"67","author":"Yoshioka Kentaro","year":"2024","unstructured":"Kentaro Yoshioka. 34.5 a 818-4094tops\/w capacitor-reconfigured cim macro for unified acceleration of cnns and transformers. In 2024 IEEE International Solid-State Circuits Conference (ISSCC), volume 67, pages 574\u2013576, 2024."},{"key":"e_1_3_2_1_3_1","first-page":"582","volume-title":"2024 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"67","author":"Wen Tai-Hao","year":"2024","unstructured":"Tai-Hao Wen, Hung-Hsi Hsu, Win-San Khwa, Wei-Hsing Huang, Zhao-En Ke, Yu-Hsiang Chin, Hua-Jin Wen, Yu-Chen Chang, Wei-Ting Hsu, Chung-Chuan Lo, Ren-Shuo Liu, Chih-Cheng Hsieh, Kea-Tiong Tang, Shih-Hsin Teng, Chung-Cheng Chou, Yu-Der Chih, Tsung-Yung Jonathan Chang, and Meng-Fan Chang. 34.8 a 22nm 16mb floating-point reram compute-in-memory macro with 31.2tflops\/w for ai edge devices. In 2024 IEEE International Solid-State Circuits Conference (ISSCC), volume 67, pages 580\u2013582, 2024."},{"key":"e_1_3_2_1_4_1","first-page":"584","volume-title":"2024 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"67","author":"Wang Linfang","year":"2024","unstructured":"Linfang Wang, Weizeng Li, Zhidao Zhou, Hanghang Gao, Zhi Li, Wang Ye, Hongyang Hu, Jing Liu, Jinshan Yue, Jianguo Yang, Qing Luo, Chunmeng Dou, Qi Liu, and Ming Liu. 34.9 a flash-sram-adc-fused plastic computing-in-memory macro for learning in neural networks in a standard 14nm finfet process. In 2024 IEEE International Solid-State Circuits Conference (ISSCC), volume 67, pages 582\u2013584, 2024."},{"key":"e_1_3_2_1_5_1","first-page":"3","volume-title":"2025 Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)","author":"Um Soyeon","year":"2025","unstructured":"Soyeon Um, Sangwoo Ha, Sunjoo Whang, Minsung Kim, Byeongcheol Kim, Sangjin Kim, Junha Ryu, Chaeyun Jeong, Kyomin Sohn, and Hoi-Jun Yoo. Dial: An energy-efficient dram in-memory computing accelerator with compact partial product lut and twisted differential adc. In 2025 Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits), pages 1\u20133, 2025."},{"key":"e_1_3_2_1_6_1","first-page":"7","volume-title":"2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","author":"Ramachandran Akshat","year":"2025","unstructured":"Akshat Ramachandran, Souvik Kundu, Arnab Raha, Shamik Kundu, Deepak K. Mathaikutty, and Tushar Krishna. Accelerating llm inference with flexible n:m sparsity via a fully digital compute-in-memory accelerator. In 2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED), pages 1\u20137, 2025."},{"key":"e_1_3_2_1_7_1","first-page":"7","volume-title":"2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","author":"Liu Dingbang","year":"2025","unstructured":"Dingbang Liu, Ziyi Guan, Qilong Chen, Jingyun Gu, Jiaqi Yang, Kai Li, Wei Mao, Ngai Wong, Changwen Chen, and Hao Yu. A 20.98tops\/w energy-efficient binary bert model on group vector systolic cim accelerator. In 2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED), pages 1\u20137, 2025."},{"key":"e_1_3_2_1_8_1","first-page":"260","volume-title":"2025 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"68","author":"Yuan Yiyang","year":"2025","unstructured":"Yiyang Yuan, Bingxin Zhang, Yiming Yang, Yishan Luo, Qirui Chen, Shidong Lv, Hao Wu, Cailian Ma, Ming Li, Jinshan Yue, Xinghua Wang, Guozhong Xing, Pui-In Mak, Xiaoran Li, and Feng Zhang. 14.5 a 28nm 192.3tflops\/w accurate\/approximate dual-mode-transpose digital 6t-sram cim macro for floatingpoint edge training and inference. In 2025 IEEE International Solid-State Circuits Conference (ISSCC), volume 68, pages 258\u2013260, 2025."},{"key":"e_1_3_2_1_9_1","first-page":"3","volume-title":"2025 Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)","author":"Wu Zihan","year":"2025","unstructured":"Zihan Wu, Yiqi Wang, Zhen He, Bohan Yang, Yang Wang, Shaojun Wei, Yang Hu, Fengbin Tu, and Shouyi Yin. Cella: A 28nm compute-memory co-optimized real-time digital cim-based edge llm accelerator with 1.78ms-response in prefill and 31.32 token\/s in decoding. In 2025 Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits), pages 1\u20133, 2025."},{"key":"e_1_3_2_1_10_1","first-page":"332","volume-title":"2025 IEEE European Solid-State Electronics Research Conference (ESSERC)","author":"Ren Wenjie","year":"2025","unstructured":"Wenjie Ren, Meng Wu, Xiangjun Ye, Ruohang Xu, Peiyu Chen, Ying Liu, Fengyun Yan, Jiayoon Ru, Yufei Ma, Tianyu Jia, and Le Ye. A 56.2tops\/w hybrid-inner-outer-product sram compute-in-memory macro for gemm with scalable precision-adaptive systolic dataflow. In 2025 IEEE European Solid-State Electronics Research Conference (ESSERC), pages 329\u2013332, 2025."},{"key":"e_1_3_2_1_11_1","first-page":"256","volume-title":"2025 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"68","author":"Wang Xing","year":"2025","unstructured":"Xing Wang, Tianhui Jiao, Yi Yang, Shaochen Li, Dongqi Li, An Guo, Yuhui Shi, Yuchen Tang, Jinwu Chen, Zhican Zhang, Zhichao Liu, Bo Liu, Weiwei Shan, Xin Wang, Hao Cai, Wenwu Zhu, Jun Yang, and Xin Si. 14.3 a 28nm 17.83-to-62.84tflops\/w broadcast-alignment floating-point cim macro with non-two's-complement mac for cnns and transformers. In 2025 IEEE International Solid-State Circuits Conference (ISSCC), volume 68, pages 254\u2013256, 2025."},{"key":"e_1_3_2_1_12_1","first-page":"578","volume-title":"2024 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"67","author":"Yuan Yiyang","year":"2024","unstructured":"Yiyang Yuan, Yiming Yang, Xinghua Wang, Xiaoran Li, Cailian Ma, Qirui Chen, Meini Tang, Xi Wei, Zhixian Hou, Jialiang Zhu, Hao Wu, Qirui Ren, Guozhong Xing, Pui-In Mak, and Feng Zhang. 34.6 a 28nm 72.12tflops\/w hybrid-domain outer-product based floating-point sram computing-in-memory macro with logarithm bit-width residual adc. In 2024 IEEE International Solid-State Circuits Conference (ISSCC), volume 67, pages 576\u2013578, 2024."},{"key":"e_1_3_2_1_13_1","first-page":"262","volume-title":"2025 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"68","author":"Chen Xi","year":"2025","unstructured":"Xi Chen, Shaochen Li, Zhican Zhang, Wentao Zheng, Xiao Tan, Yuchen Tang, Yuhui Shi, Lizheng Ren, Yibo Mai, Feiran Liu, Jinwu Chen, Zhaoyang Zhang, An Guo, Tianzhu Xiong, Bo Wang, Xinning Liu, Weiwei Shan, Bo Liu, Hao Cai, Jun Yang, and Xin Si. 14.6 a 28nm 64kb bit-rotated hybrid-cim macro with an embedded sign-bit-processing array and a multi-bit-fusion dual-granularity cooperative quantizer. In 2025 IEEE International Solid-State Circuits Conference (ISSCC), volume 68, pages 260\u2013262, 2025."},{"key":"e_1_3_2_1_14_1","first-page":"7","volume-title":"2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","author":"Jung Sangwoo","year":"2025","unstructured":"Sangwoo Jung, Hojin Lee, Yejin Lee, Jiyong Park, Dahoon Park, Hyunseob Shin, Jong-Hyeok Yoon, and Jaeha Kung. Cam-cim: A hybrid compute-in-memory using content-addressable memory with subword split mapping for reduced adc resolution. In 2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED), pages 1\u20137, 2025."},{"key":"e_1_3_2_1_15_1","first-page":"572","volume-title":"2024 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"67","author":"Guo An","year":"2024","unstructured":"An Guo, Xi Chen, Fangyuan Dong, Jinwu Chen, Zhihang Yuan, Xing Hu, Yuanpeng Zhang, Jingmin Zhang, Yuchen Tang, Zhican Zhang, Gang Chen, Dawei Yang, Zhaoyang Zhang, Lizheng Ren, Tianzhu Xiong, Bo Wang, Bo Liu, Weiwei Shan, Xinning Liu, Hao Cai, Guangyu Sun, Jun Yang, and Xin Si. 34.3 a 22nm 64kb lightning-like hybrid computing-in-memory macro with a compressed adder tree and analog-storage quantizers for transformer and cnns. In 2024 IEEE International Solid-State Circuits Conference (ISSCC), volume 67, pages 570\u2013572, 2024."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 32(1)","author":"Song Zhourui","year":"2018","unstructured":"Zhourui Song, Zhenyu Liu, and Dongsheng Wang. Computation error analysis of block floating point arithmetic oriented convolution neural network accelerator design. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1), Apr. 2018."},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems","author":"Drumond Mario","year":"2018","unstructured":"Mario Drumond, Tao LIN, Martin Jaggi, and Babak Falsafi. Training dnns with hybrid block floating point. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018."},{"key":"e_1_3_2_1_18_1","first-page":"860","volume-title":"2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","author":"Zhang Sai Qian","year":"2021","unstructured":"Sai Qian Zhang, Bradley McDanel, and H. T. Kung. Fast: Dnn training under variable precision block floating point with stochastic rounding. 2022 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pages 846\u2013860, 2021."},{"key":"e_1_3_2_1_19_1","volume-title":"Harmonia: Algorithmhardware co-design for memory- and compute-efficient bfp-based llm inference","author":"Wang Xinyu","year":"2026","unstructured":"Xinyu Wang, Jieyu Li, Yanan Sun, and Weifeng He. Harmonia: Algorithmhardware co-design for memory- and compute-efficient bfp-based llm inference, 2026."},{"key":"e_1_3_2_1_20_1","volume-title":"Ning Xu, Dawei Yang, and Zhe Jiang. Bbal: A bidirectional block floating point-based quantisation accelerator for large language models","author":"Han Xiaomeng","year":"2025","unstructured":"Xiaomeng Han, Yuan Cheng, Jing Wang, Junyang Lu, Hui Wang, X. x. Zhang, Ning Xu, Dawei Yang, and Zhe Jiang. Bbal: A bidirectional block floating point-based quantisation accelerator for large language models, 2025."},{"key":"e_1_3_2_1_21_1","first-page":"408","volume-title":"ESSCIRC 2023- IEEE 49th European Solid State Circuits Conference (ESSCIRC)","author":"Saikia Jyotishman","year":"2023","unstructured":"Jyotishman Saikia, Amitesh Sridharan, Injune Yeo, Shreyas Venkataramanaiah, Deliang Fan, and Jae-Sun Seo. Fp-imc: A 28nm all-digital configurable floatingpoint in-memory computing macro. In ESSCIRC 2023- IEEE 49th European Solid State Circuits Conference (ESSCIRC), pages 405\u2013408, 2023."},{"key":"e_1_3_2_1_22_1","first-page":"550","volume-title":"2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC)","author":"Chang Cheng-Yang","year":"2024","unstructured":"Cheng-Yang Chang, Chi-Tse Huang, Yu-Chuan Chuang, Kuang-Chao Chou, and An-Yeu Andy Wu. Bfp-cim: Data-free quantization with dynamic block-floatingpoint arithmetic for energy-efficient computing-in-memory-based accelerator. In 2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC), pages 545\u2013550, 2024."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 50th Annual International Symposium on Computer Architecture, ISCA '23","author":"Rouhani Bita Darvish","year":"2023","unstructured":"Bita Darvish Rouhani, Ritchie Zhao, Venmugil Elango, Rasoul Shafipour, Mathew Hall, Maral Mesmakhosroshahi, Ankit More, Levi Melnick, Maximilian Golub, Girish Varatkar, Lai Shao, Gaurav Kolhe, Dimitry Melts, Jasmine Klar, Renee L'Heureux, Matt Perry, Doug Burger, Eric Chung, Zhaoxia (Summer) Deng, Sam Naghshineh, Jongsoo Park, and Maxim Naumov. With shared microexponents, a little shifting goes a long way. In Proceedings of the 50th Annual International Symposium on Computer Architecture, ISCA '23, New York, NY, USA, 2023. Association for Computing Machinery."},{"key":"e_1_3_2_1_24_1","volume-title":"Int v.s. fp: A comprehensive study of fine-grained low-bit quantization formats","author":"Chen Mengzhao","year":"2025","unstructured":"Mengzhao Chen, Meng Wu, Hui Jin, Zhihang Yuan, Jing Liu, Chaoyi Zhang, Yunshui Li, Jie Huang, Jin Ma, Zeyue Xue, Zhiheng Liu, Xingyan Bin, and Ping Luo. Int v.s. fp: A comprehensive study of fine-grained low-bit quantization formats, 2025."},{"key":"e_1_3_2_1_25_1","first-page":"498","volume-title":"Efficient post-training quantization with fp8 formats","author":"Shen Haihao","year":"2024","unstructured":"Haihao Shen, Naveen Mellempudi, Xin He, Qun Gao, Chang Wang, and Mengni Wang. Efficient post-training quantization with fp8 formats. In P. Gibbons, G. Pekhimenko, and C. De Sa, editors, Proceedings of Machine Learning and Systems, volume 6, pages 483\u2013498, 2024."},{"key":"e_1_3_2_1_26_1","volume-title":"Bitq: Tailoring block floating point precision for improved dnn efficiency on resource-constrained devices","author":"Xu Yongqi","year":"2024","unstructured":"Yongqi Xu, Yujian Lee, Gao Yi, Bosheng Liu, Yucong Chen, Peng Liu, Jigang Wu, Xiaoming Chen, and Yinhe Han. Bitq: Tailoring block floating point precision for improved dnn efficiency on resource-constrained devices, 2024."},{"key":"e_1_3_2_1_27_1","volume-title":"Benchmarking post-training quantization of large language models under microscaling floating point formats","author":"Zhang Manyi","year":"2026","unstructured":"Manyi Zhang, Ji-Fu Li, Zhongao Sun, Haoli Bai, Hui-Ling Zhen, Zhenhua Dong, and Xianzhi Yu. Benchmarking post-training quantization of large language models under microscaling floating point formats, 2026."},{"key":"e_1_3_2_1_28_1","first-page":"153","volume-title":"Proceedings of the 52nd Annual International Symposium on Computer Architecture, ISCA '25","author":"Gil Minseong","year":"2025","unstructured":"Minseong Gil, Dongho Ha, Simla Burcu Harma, Myung Kuk Yoon, Babak Falsafi, Won Woo Ro, and Yunho Oh. Avant-garde: Empowering gpus with scaled numeric formats. In Proceedings of the 52nd Annual International Symposium on Computer Architecture, ISCA '25, page 153-165, New York, NY, USA, 2025. Association for Computing Machinery."}],"event":{"name":"ISLPED '26: ACM\/IEEE International Symposium on Low Power Electronics and Design","location":"Evanston IL USA","acronym":"ISLPED '26","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the ACM\/IEEE International Symposium on Low Power Electronics and Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3816440.3818569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T19:25:40Z","timestamp":1786389940000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3816440.3818569"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":28,"alternative-id":["10.1145\/3816440.3818569","10.1145\/3816440"],"URL":"https:\/\/doi.org\/10.1145\/3816440.3818569","relation":{},"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"2026-08-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}