{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:36:32Z","timestamp":1769502992138,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756087","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"78-93","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["3D-PATH: A Hierarchy LUT Processing-in-memory Accelerator with Thermal-aware Hybrid Bonding Integration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4084-3478","authenticated-orcid":false,"given":"Zhiheng","family":"Yue","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8293-8881","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6218-4659","authenticated-orcid":false,"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5117-7920","authenticated-orcid":false,"given":"Shaojun","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6942-4395","authenticated-orcid":false,"given":"Yang","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2309-572X","authenticated-orcid":false,"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC51906.2022.00178"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Nasir Ahmed T.\u00a0Raj Natarajan and K.\u00a0R. Rao. 1974. Discrete Cosine Transform. IEEE Trans. Computers 23 1 (1974) 90\u201393. 10.1109\/T-C.1974.223784","DOI":"10.1109\/T-C.1974.223784"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067269"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783753"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00034"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00054"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Tsung-Yung\u00a0Jonathan Chang Yen-Huei Chen Wei-Min Chan Hank Cheng Po-Sheng Wang Yangsyu Lin Hidehiro Fujiwara Robin Lee Hung-Jen Liao Ping-Wei Wang Geoffrey Yeap and Quincy Li. 2021. A 5-nm 135-Mb SRAM in EUV and High-Mobility Channel FinFET Technology With Metal Coupling and Charge-Sharing Write-Assist Circuitry Schemes for High-Density and Low-VMIN Applications. IEEE Journal of Solid-State Circuits 56 1 (2021) 179\u2013187. 10.1109\/JSSC.2020.3034241","DOI":"10.1109\/JSSC.2020.3034241"},{"key":"e_1_3_3_1_10_2","unstructured":"Michael Davies Adam Labiosa and Karthikeyan Sankaralingam. 2021. Understanding the Limits of Conventional Hardware Architectures for Deep-Learning. CoRR abs\/2112.02204 (2021). arXiv:https:\/\/arXiv.org\/abs\/2112.02204https:\/\/arxiv.org\/abs\/2112.02204"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196029"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317845"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2017.8008465"},{"key":"e_1_3_3_1_15_2","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy A.","year":"2021","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, and S. Gelly. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00040"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00067"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3609308.3625266"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358260"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Mingyu Gao Christina Delimitrou Dimin Niu Krishna\u00a0T. Malladi Hongzhong Zheng Bob Brennan and Christos Kozyrakis. 2017. DRAF: A Low-Power DRAM-Based Reconfigurable Acceleration Fabric. IEEE Micro 37 3 (2017) 70\u201378. 10.1109\/MM.2017.50","DOI":"10.1109\/MM.2017.50"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Esteban Garz\u00f3n Roman Golman Zuher Jahshan Robert Hanhan Natan Vinshtok-Melnik Marco Lanuzza Adam Teman and Leonid Yavits. 2022. Hamming Distance Tolerant Content-Addressable Memory (HD-CAM) for DNA Classification. IEEE Access 10 (2022) 28080\u201328093. 10.1109\/ACCESS.2022.3158305","DOI":"10.1109\/ACCESS.2022.3158305"},{"key":"e_1_3_3_1_24_2","unstructured":"Juan G\u00f3mez-Luna Izzat\u00a0El Hajj Ivan Fernandez Christina Giannoula Geraldo\u00a0F. Oliveira and Onur Mutlu. 2021. Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture. CoRR abs\/2105.03814 (2021). arXiv:https:\/\/arXiv.org\/abs\/2105.03814https:\/\/arxiv.org\/abs\/2105.03814"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00071"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00011"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00063"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614262"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00099"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","unstructured":"Roman Kaplan Leonid Yavits Ran Ginosar and Uri Weiser. 2017. A Resistive CAM Processing-in-Storage Architecture for DNA Sequence Alignment. IEEE Micro 37 4 (2017) 20\u201328. 10.1109\/MM.2017.3211121","DOI":"10.1109\/MM.2017.3211121"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2003.1249424"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1998.706788"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00030"},{"key":"e_1_3_3_1_37_2","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey\u00a0E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.FINDINGS-EMNLP.360"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310262"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00033"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527402"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","unstructured":"Dai Li and Kaiyuan Yang. 2020. A Dual-Port 8-T CAM-Based Network Intrusion Detection Engine for IoT. IEEE Solid-State Circuits Letters 3 (2020) 358\u2013361. 10.1109\/LSSC.2020.3022006","DOI":"10.1109\/LSSC.2020.3022006"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"crossref","unstructured":"S. Li Z. Yang D. Reddy A. Srivastava and B. Jacob. 2020. DRAMsim3: a Cycle-accurate Thermal-Capable DRAM Simulator. IEEE Computer Architecture Letters PP 99 (2020) 1\u20131.","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","unstructured":"Zhiting Lin Zhiyong Zhu Honglan Zhan Chunyu Peng Xiulong Wu Yuan Yao Jianchao Niu and Junning Chen. 2021. Two-Direction In-Memory Computing Based on 10T SRAM With Horizontal and Vertical Decoupled Read Ports. IEEE Journal of Solid-State Circuits 56 9 (2021) 2832\u20132844. 10.1109\/JSSC.2021.3061260","DOI":"10.1109\/JSSC.2021.3061260"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"H. Ling. 1990. An approach to implementing multiplication with small tables. IEEE Trans. Comput. 39 5 (1990) 717\u2013718. 10.1109\/12.53588","DOI":"10.1109\/12.53588"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00054"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DIC.2012.6263034"},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2004.1329351"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","unstructured":"A.S. Noetzel. 1989. An interpolating memory unit for function evaluation: analysis and design. IEEE Trans. Comput. 38 3 (1989) 377\u2013384. 10.1109\/12.21124","DOI":"10.1109\/12.21124"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/ITHERM.2016.7517703"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080254"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00085"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480080"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Jonah Philion and Sanja Fidler. 2020. Lift Splat Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D.","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/D16-1264"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00020"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2004.1358852"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","unstructured":"Teven\u00a0Le Scao Angela Fan Christopher Akiki Ellie Pavlick Suzana Ilic Daniel Hesslow Roman Castagn\u00e9 Alexandra\u00a0Sasha Luccioni Fran\u00e7ois Yvon Matthias Gall\u00e9 Jonathan Tow Alexander\u00a0M. Rush Stella Biderman Albert Webson Pawan\u00a0Sasanka Ammanamanchi Thomas Wang Beno\u00eet Sagot Niklas Muennighoff Albert\u00a0Villanova del Moral Olatunji Ruwase Rachel Bawden Stas Bekman Angelina McMillan-Major Iz Beltagy Huu Nguyen Lucile Saulnier Samson Tan Pedro\u00a0Ortiz Suarez Victor Sanh Hugo Lauren\u00e7on Yacine Jernite Julien Launay Margaret Mitchell Colin Raffel Aaron Gokaslan Adi Simhi Aitor Soroa Alham\u00a0Fikri Aji Amit Alfassy Anna Rogers Ariel\u00a0Kreisberg Nitzav Canwen Xu Chenghao Mou Chris Emezue Christopher Klamm Colin Leong Daniel van Strien David\u00a0Ifeoluwa Adelani and et al.2022. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model. CoRR abs\/2211.05100 (2022). 10.48550\/ARXIV.2211.05100 arXiv:https:\/\/arXiv.org\/abs\/2211.05100","DOI":"10.48550\/ARXIV.2211.05100"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"publisher","unstructured":"Vivek Seshadri Kevin Hsieh Amirali Boroumand Donghyuk Lee Michael\u00a0A. Kozuch Onur Mutlu Phillip\u00a0B. Gibbons and Todd\u00a0C. Mowry. 2015. Fast Bulk Bitwise AND and OR in DRAM. IEEE Comput. Archit. Lett. 14 2 (2015) 127\u2013131. 10.1109\/LCA.2015.2434872","DOI":"10.1109\/LCA.2015.2434872"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/SIPS.2007.4387592"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2004.1393259"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","unstructured":"Purab\u00a0Ranjan Sutradhar Mark Connolly Sathwika Bavikadi Sai Manoj\u00a0Pudukotai Dinakarrao Mark\u00a0A. Indovina and Amlan Ganguly. 2020. pPIM: A Programmable Processor-in-Memory Architecture With Precision-Scaling for Deep Learning. IEEE Comput. Archit. Lett. 19 2 (2020) 118\u2013121. 10.1109\/LCA.2020.3011643","DOI":"10.1109\/LCA.2020.3011643"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.1991.145565"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00052"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00033"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","unstructured":"Shengzhe Yan Jinshan Yue Chaojie He Zi Wang Zhaori Cong Yifan He Mufeng Zhou Wenyu Sun Xueqing Li Chunmeng Dou Feng Zhang Huazhong Yang Yongpan Liu and Ming Liu. 2024. A 28-nm Floating-Point Computing-in-Memory Processor Using Intensive-CIM Sparse-Digital Architecture. IEEE Journal of Solid-State Circuits 59 8 (2024) 2630\u20132643. 10.1109\/JSSC.2024.3363871","DOI":"10.1109\/JSSC.2024.3363871"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00055"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00072"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN58291.2024.00024"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00030"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona\u00a0T. Diab Xian Li Xi\u00a0Victoria Lin Todor Mihaylov Myle Ott Sam Shleifer Kurt Shuster Daniel Simig Punit\u00a0Singh Koura Anjali Sridhar Tianlu Wang and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. CoRR abs\/2205.01068 (2022). 10.48550\/ARXIV.2205.01068 arXiv:https:\/\/arXiv.org\/abs\/2205.01068","DOI":"10.48550\/ARXIV.2205.01068"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549469"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:46:44Z","timestamp":1769464004000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756087"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":77,"alternative-id":["10.1145\/3725843.3756087","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756087","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}