{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:02:04Z","timestamp":1776931324724,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSF Graduate Research Fellowship Program","award":["2141064"],"award-info":[{"award-number":["2141064"]}]},{"name":"NSF PPoSS Award","award":["2118709"],"award-info":[{"award-number":["2118709"]}]},{"name":"ACE Center for Evolvable Computing","award":[""],"award-info":[{"award-number":[""]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756132","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1011-1025","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Characterizing and Optimizing Realistic Workloads on a Commercial Compute-in-SRAM Device"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2850-0176","authenticated-orcid":false,"given":"Niansong","family":"Zhang","sequence":"first","affiliation":[{"name":"Cornell University, Ithaca, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9583-7502","authenticated-orcid":false,"given":"Wenbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8874-7873","authenticated-orcid":false,"given":"Courtney","family":"Golden","sequence":"additional","affiliation":[{"name":"MIT, Cambridge, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8768-2985","authenticated-orcid":false,"given":"Dan","family":"Ilan","sequence":"additional","affiliation":[{"name":"GSI Inc., Tel Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6617-0075","authenticated-orcid":false,"given":"Hongzheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2835-667X","authenticated-orcid":false,"given":"Christopher","family":"Batten","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0778-0308","authenticated-orcid":false,"given":"Zhiru","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Amogh Agrawal Akhilesh Jaiswal Chankyu Lee and Kaushik Roy. 2018. X-SRAM: Enabling in-memory Boolean computations in CMOS static random access memories. IEEE Transactions on Circuits and Systems I: Regular Papers 65 12 (2018) 4219\u20134232.","DOI":"10.1109\/TCSI.2018.2848999"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Amogh Agrawal Akhilesh Jaiswal Deboleena Roy Bing Han Gopalakrishnan Srinivasan Aayush Ankit and Kaushik Roy. 2019. Xcel-RAM: Accelerating binary neural networks in high-throughput SRAM compute arrays. IEEE Transactions on Circuits and Systems I: Regular Papers 66 8 (2019) 3064\u20133076.","DOI":"10.1109\/TCSI.2019.2907488"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Junwhan Ahn Sungjoo Yoo Onur Mutlu and Kiyoung Choi. 2015. PIM-enabled instructions: A low-overhead locality-aware processing-in-memory architecture. ACM SIGARCH Computer Architecture News 43 3S (2015) 336\u2013348.","DOI":"10.1145\/2872887.2750385"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9181068"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071074"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Daniel Bankman Lita Yang Bert Moons Marian Verhelst and Boris Murmann. 2018. An Always-On 3.8\u03bc J 86% CIFAR-10 mixed-signal binary CNN processor with all memory on chip in 28-nm CMOS. IEEE Journal of Solid-State Circuits 54 1 (2018) 158\u2013172.","DOI":"10.1109\/JSSC.2018.2869150"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310397"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1054943.1054946"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00054"},{"key":"e_1_3_3_2_13_2","volume-title":"DRAMPower: Open-source DRAM Power & Energy Estimation Tool","author":"Chandrasekar Karthik","year":"2024","unstructured":"Karthik Chandrasekar, Christian Weis, Yonghui Li, Sven Goossens, Matthias Jung, Omar Naji, Benny Akesson, Norbert Wehn, and Kees Goossens. 2024. DRAMPower: Open-source DRAM Power & Energy Estimation Tool. TU Kaiserslautern, Microelectronic Systems Design (MSD) Research Group. http:\/\/www.drampower.info"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Johannes de Fine\u00a0Licht Maciej Besta Simon Meierhans and Torsten Hoefler. 2020. Transformations of high-level synthesis codes for high-performance computing. IEEE Transactions on Parallel and Distributed Systems 32 5 (2020) 1014\u20131029.","DOI":"10.1109\/TPDS.2020.3039409"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss Library. 10.48550\/arXiv.2401.08281 arxiv:https:\/\/arXiv.org\/abs\/2401.08281\u00a0[cs.LG]","DOI":"10.48550\/arXiv.2401.08281"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/540236"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun and Haofen Wang. 2023. Retrieval-Augmented Generation for Large Language Models: A Survey. 10.48550\/arXiv.2312.10997 arxiv:https:\/\/arXiv.org\/abs\/2312.10997\u00a0[cs.CL]","DOI":"10.48550\/arXiv.2312.10997"},{"key":"e_1_3_3_2_18_2","volume-title":"DAC \u201904: Proceedings of the 41st Annual Design Automation Conference \u2013 Student Design Contest","author":"Gebis Joseph","year":"2004","unstructured":"Joseph Gebis, Sam Williams, David Patterson, and Christos Kozyrakis. 2004. VIRAM1: A Media-Oriented Vector Processor with Embedded DRAM. In DAC \u201904: Proceedings of the 41st Annual Design Automation Conference \u2013 Student Design Contest (San Diego, CA, USA). Association for Computing Machinery, New York, NY, USA, 6\u00a0pages. https:\/\/csl.stanford.edu\/\u00a0christos\/publications\/2004.dac.iram.pdf Student Design Contest paper."},{"key":"e_1_3_3_2_19_2","volume-title":"Proceedings of the 5th Workshop on Accelerator Architecture in Computational Biology and Bioinformatics (AACBB)","author":"Golden Courtney","year":"2023","unstructured":"Courtney Golden, Dan Ilan, Nicholas Cebry, and Christopher Batten. 2023. Accelerating Seed Location Filtering in DNA Read Mapping Using a Commercial Compute-in-SRAM Architecture. In Proceedings of the 5th Workshop on Accelerator Architecture in Computational Biology and Bioinformatics (AACBB) (Orlando, FL, USA). Association for Computing Machinery, New York, NY, USA, 10\u00a0pages. https:\/\/www.csl.cornell.edu\/\u00a0cbatten\/pdfs\/golden-apu-filtering-aacbb2023.pdf Workshop held in conjunction with ISCA'50 (FCRC 2023); see also arXiv:https:\/\/arXiv.org\/abs\/2401.11685."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Courtney Golden Dan Ilan Caroline Huang Niansong Zhang Zhiru Zhang and Christopher Batten. 2024. Supporting a Virtual Vector Instruction Set on a Commercial Compute-in-SRAM Accelerator. IEEE Computer Architecture Letters 23 1 (Jan 2024) 29\u201332. 10.1109\/LCA.2023.3341389","DOI":"10.1109\/LCA.2023.3341389"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et\u00a0al. 2024. The Llama 3 Herd of Models. 10.48550\/arXiv.2407.21783 arxiv:https:\/\/arXiv.org\/abs\/2407.21783\u00a0[cs.LG]","DOI":"10.48550\/arXiv.2407.21783"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485939"},{"key":"e_1_3_3_2_23_2","volume-title":"In-Memory Acceleration for Big Data","author":"Gwennap Linley","year":"2020","unstructured":"Linley Gwennap. 2020. In-Memory Acceleration for Big Data. Technical Report. The Linley Group. https:\/\/gsitechnology.com\/wp-content\/uploads\/2023\/01\/GSIT-Gemini-WP-Final-Linley.pdf"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582018"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322237"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.1998.746322"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Supreet Jeloka Naveen\u00a0Bharathwaj Akesh Dennis Sylvester and David Blaauw. 2016. A 28 nm configurable memory (TCAM\/BCAM\/SRAM) using push-rule 6T bit cell enabling logic-in-memory. IEEE Journal of Solid-State Circuits 51 4 (2016) 1009\u20131021.","DOI":"10.1109\/JSSC.2016.2515510"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Zhewei Jiang Shihui Yin Jae-Sun Seo and Mingoo Seok. 2020. C3SRAM: An in-memory-computing SRAM macro based on robust capacitive coupling computing mechanism. IEEE Journal of Solid-State Circuits 55 7 (2020) 1888\u20131897.","DOI":"10.1109\/JSSC.2020.2992886"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Tom Kwiatkowski Jennimaria Palomaki Olivia Redfield Michael Collins Ankur Parikh Chris Alberti Danielle Epstein Illia Polosukhin Jacob Devlin Kenton Lee et\u00a0al. 2019. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics 7 (2019) 453\u2013466.","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474146"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","unstructured":"Ann\u00a0Franchesca Laguna Mohammed\u00a0Mehdi Sharifi Arman Kazemi Xunzhao Yin Michael Niemier and X.\u00a0Sharon Hu. 2022. Hardware-Software Co-Design of an In-Memory Transformer Network Accelerator. Frontiers in Electronics 3 Article 847069 (Apr 2022) 21\u00a0pages. 10.3389\/felec.2022.847069","DOI":"10.3389\/felec.2022.847069"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00492"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Eunyoung Lee Taeyoung Han Donguk Seo Gicheol Shin Jaerok Kim Seonho Kim Soyoun Jeong Johnny Rhe Jaehyun Park Jong\u00a0Hwan Ko et\u00a0al. 2021. A charge-domain scalable-weight in-memory computing macro with dual-SRAM architecture for precision-scalable DNN accelerators. IEEE Transactions on Circuits and Systems I: Regular Papers 68 8 (2021) 3305\u20133316.","DOI":"10.1109\/TCSI.2021.3080042"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605731.3605745"},{"key":"e_1_3_3_2_35_2","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et\u00a0al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems 33 (2020) 9459\u20139474."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Haocong Luo Yahya\u00a0Can Tu F.\u00a0Nisa Bostanci Ataberk Olgun A.\u00a0Giray Yaglikci and Onur Mutlu. 2024. Ramulator 2.0: A Modern Modular and Extensible DRAM Simulator. IEEE Computer Architecture Letters 23 1 (2024) 112\u2013116. 10.1109\/LCA.2023.3333759","DOI":"10.1109\/LCA.2023.3333759"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1998.694774"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"David Patterson Thomas Anderson Neal Cardwell Richard Fromm Kimberly Keeton Christoforos Kozyrakis Randi Thomas and Katherine Yelick. 1997. A case for intelligent RAM. IEEE micro 17 2 (1997) 34\u201344.","DOI":"10.1109\/40.592312"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.1997.585348"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Jerry Potter Johnnie Baker Stephen Scott Arvind Bansal Chokchai Leangsuksun and Chandra Asthagiri. 1994. ASC: an associative-computing paradigm. Computer 27 11 (1994) 19\u201325.","DOI":"10.1109\/2.330039"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707264"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346181"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657957"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-66400-7_9"},{"key":"e_1_3_3_2_45_2","unstructured":"GSI Technology. 2023. GSI Technology\u2019s Gemini-I\u00ae APU Showcased in \u201cIn-Memory Acceleration for Big Data\u201d. https:\/\/ir.gsitechnology.com\/news-releases\/news-release-details\/gsi-technologys-gemini-ir-apu-showcased-memory-acceleration-big."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Fengbin Tu Zihan Wu Yiqi Wang Ling Liang Liu Liu Yufei Ding Leibo Liu Shaojun Wei Yuan Xie and Shouyi Yin. 2023. TranCIM: Full-Digital Bitline-Transpose CIM-based Sparse Transformer Accelerator With Pipeline\/Parallel Reconfigurable Modes. IEEE Journal of Solid-State Circuits 58 6 (Jun 2023) 1798\u20131809. 10.1109\/JSSC.2022.3213542","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"Hongyu Wang Shuming Ma Li Dong Shaohan Huang Huaijie Wang Lingxiao Ma Fan Yang Ruiping Wang Yi Wu and Furu Wei. 2023. BitNet: Scaling 1-Bit Transformers for Large Language Models. 10.48550\/arXiv.2310.11453 arxiv:https:\/\/arXiv.org\/abs\/2310.11453\u00a0[cs.CL]","DOI":"10.48550\/arXiv.2310.11453"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00074"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Bo Zhang Shihui Yin Minkyu Kim Jyotishman Saikia Soonwan Kwon Sungmeen Myung Hyunsoo Kim Sang\u00a0Joon Kim Jae-Sun Seo and Mingoo Seok. 2023. PIMCA: A Programmable In-Memory Computing Accelerator for Energy-Efficient DNN Inference. IEEE Journal of Solid-State Circuits 58 5 (May 2023) 1436\u20131449. 10.1109\/JSSC.2022.3211290","DOI":"10.1109\/JSSC.2022.3211290"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Jintao Zhang Zhuo Wang and Naveen Verma. 2017. In-memory computation of a machine-learning classifier in a standard 6T SRAM array. IEEE Journal of Solid-State Circuits 52 4 (2017) 915\u2013924.","DOI":"10.1109\/JSSC.2016.2642198"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439296"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01215"}],"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\/3725843.3756132","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:45:04Z","timestamp":1769463904000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":51,"alternative-id":["10.1145\/3725843.3756132","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756132","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"}}]}}