{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:03:23Z","timestamp":1776931403450,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":62,"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":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF 2107470, CCF 2316233, DGE 2146756"],"award-info":[{"award-number":["CCF 2107470, CCF 2316233, DGE 2146756"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","award":["ACE"],"award-info":[{"award-number":["ACE"]}],"id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IBM-Illinois Discovery Accelerator Institute","award":[""],"award-info":[{"award-number":[""]}]},{"name":"Illinois Campus Cluster","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\/3725843.3756096","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"884-898","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Micro-MAMA: Multi-Agent Reinforcement Learning for Multicore Prefetching"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7770-003X","authenticated-orcid":false,"given":"Charles","family":"Block","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7946-2683","authenticated-orcid":false,"given":"Gerasimos","family":"Gerogiannis","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2595-5228","authenticated-orcid":false,"given":"Josep","family":"Torrellas","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Alaa\u00a0R. Alameldeen Seth Pugsley Michael Ferdman and Mina Abbasi\u00a0Dinani. 2019. The 3rd Data Prefetching Championship. https:\/\/dpc3.compas.cs.stonybrook.edu\/"},{"key":"e_1_3_3_2_3_2","volume-title":"Multi-Agent Reinforcement Learning: Foundations and Modern Approaches","author":"Albrecht Stefano\u00a0V.","year":"2024","unstructured":"Stefano\u00a0V. Albrecht, Filippos Christianos, and Lukas Sch\u00e4fer. 2024. Multi-Agent Reinforcement Learning: Foundations and Modern Approaches. MIT Press. https:\/\/www.marl-book.com"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00053"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Rajeev Balasubramonian Andrew\u00a0B. Kahng Naveen Muralimanohar Ali Shafiee and Vaishnav Srinivas. 2017. CACTI 7: New Tools for Interconnect Exploration in Innovative Off-Chip Memories. ACM Trans. Archit. Code Optim. 14 2 Article 14 (June 2017) 25\u00a0pages. 10.1145\/3085572","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480114"},{"key":"e_1_3_3_2_7_2","volume-title":"Reinforcement learning and optimal control","author":"Bertsekas Dimitri","year":"2019","unstructured":"Dimitri Bertsekas. 2019. Reinforcement learning and optimal control. Vol.\u00a01. Athena Scientific."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_3_2_9_2","unstructured":"Ilai Bistritz and Nicholas Bambos. 2020. Cooperative multi-player bandit optimization. Advances in Neural Information Processing Systems 33 (2020) 2016\u20132027."},{"key":"e_1_3_3_2_10_2","unstructured":"Intel Corporation. 2021. Intel\u00ae Xeon\u00ae Platinum 8380 Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/212287\/intel-xeon-platinum-8380-processor-60m-cache-2-30-ghz\/specifications.html"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3326633"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00088"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000081"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669154"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","unstructured":"Stijn Eyerman and Lieven Eeckhout. 2008. System-Level Performance Metrics for Multiprogram Workloads. IEEE Micro 28 3 (2008) 42\u201353. 10.1109\/MM.2008.44","DOI":"10.1109\/MM.2008.44"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Alessandro Fogli Bo Zhao Peter Pietzuch Maximilian Bandle and Jana Giceva. 2024. OLAP on Modern Chiplet-Based Processors. Proc. VLDB Endow. 17 11 (July 2024) 3428\u20133441. 10.14778\/3681954.3682011","DOI":"10.14778\/3681954.3682011"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Abdoulaye Gamati\u00e9 Xin An Ying Zhang An Kang and Gilles Sassatelli. 2019. Empirical model-based performance prediction for application mapping on multicore architectures. Journal of Systems Architecture 98 (2019) 1\u201316. 10.1016\/j.sysarc.2019.06.001","DOI":"10.1016\/j.sysarc.2019.06.001"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623780"},{"key":"e_1_3_3_2_19_2","unstructured":"Nathan Gober Gino Chacon Lei Wang Paul\u00a0V. Gratz Daniel\u00a0A. Jimenez Elvira Teran Seth Pugsley and Jinchun Kim. 2022. The Championship Simulator: Architectural Simulation for Education and Competition. arxiv:https:\/\/arXiv.org\/abs\/2210.14324\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2210.14324"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-9247-8_10"},{"key":"e_1_3_3_2_21_2","series-title":"(UAI \u201923)","volume-title":"Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence","author":"Huang Zhiming","year":"2023","unstructured":"Zhiming Huang and Jianping Pan. 2023. A near-optimal high-probability swap-regret upper bound for multi-agent bandits in unknown general-sum games. In Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence (Pittsburgh, PA, USA) (UAI \u201923). JMLR.org, Article 86, 11\u00a0pages."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Zhiming Huang and Jianping Pan. 2024. Distributed Learning of Unknown Games for HetNet Selection. IEEE Transactions on Network Science and Engineering (2024) 1\u201313. 10.1109\/TNSE.2024.3354792","DOI":"10.1109\/TNSE.2024.3354792"},{"key":"e_1_3_3_2_23_2","unstructured":"Intel Corporation. 2023. Intel\u00ae Xeon\u00ae Platinum 8490H Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/231747\/intel-xeon-platinum-8490h-processor-112-5m-cache-1-90-ghz\/specifications.html"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651373"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Rahul Jain Preeti\u00a0Ranjan Panda and Sreenivas Subramoney. 2017. Cooperative Multi-Agent Reinforcement Learning-Based Co-optimization of Cores Caches and On-chip Network. ACM Trans. Archit. Code Optim. 14 4 Article 32 (nov 2017) 25\u00a0pages. 10.1145\/3132170","DOI":"10.1145\/3132170"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Majid Jalili and Mattan Erez. 2022. Managing Prefetchers With Deep Reinforcement Learning. IEEE Computer Architecture Letters 21 2 (2022) 105\u2013108. 10.1109\/LCA.2022.3210397","DOI":"10.1109\/LCA.2022.3210397"},{"key":"e_1_3_3_2_27_2","unstructured":"Haozhe Jiang Qiwen Cui Zhihan Xiong Maryam Fazel and Simon\u00a0S. Du. 2023. A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2306.07465\u00a0[cs.LG]"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2001.903263"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.35"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00017"},{"key":"e_1_3_3_2_31_2","series-title":"(NIPS\u201916)","first-page":"3682","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Kulkarni Tejas\u00a0D.","year":"2016","unstructured":"Tejas\u00a0D. Kulkarni, Karthik\u00a0R. Narasimhan, Ardavan Saeedi, and Joshua\u00a0B. Tenenbaum. 2016. Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. In Proceedings of the 30th International Conference on Neural Information Processing Systems (Barcelona, Spain) (NIPS\u201916). Curran Associates Inc., Red Hook, NY, USA, 3682\u20133690."},{"key":"e_1_3_3_2_32_2","unstructured":"Saurabh Kumar Pararth Shah Dilek Hakkani-Tur and Larry Heck. 2017. Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/1712.08266\u00a0[cs.AI]"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"e_1_3_3_2_34_2","unstructured":"Arm Limited. 2022. Arm\u00ae Neoverse\u2122 V2 Core Technical Reference Manual. https:\/\/developer.arm.com\/documentation\/102375\/latest\/"},{"key":"e_1_3_3_2_35_2","unstructured":"Arm Limited. 2025. Use of CBusy. https:\/\/developer.arm.com\/documentation\/109252\/0101\/MPAM-System-Guidance-for-Infrastructure\/Use-of-CBusy"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00090"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760240"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063103"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"John\u00a0F Nash\u00a0Jr. 1950. Equilibrium points in n-person games. Proceedings of the National Academy of Sciences 36 1 (1950) 48\u201349.","DOI":"10.1073\/pnas.36.1.48"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Santiago Onta\u00f1\u00f3n. 2017. Combinatorial multi-armed bandits for real-time strategy games. J. Artif. Int. Res. 58 1 (Jan. 2017) 665\u2013702.","DOI":"10.1613\/jair.5398"},{"key":"e_1_3_3_2_41_2","unstructured":"Martin\u00a0J Osborne. 2004. An Introduction to Game Theory. Oxford University Press 2 (2004) 672\u2013713."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297371"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Leeor Peled Shie Mannor Uri Weiser and Yoav Etsion. 2015. Semantic locality and context-based prefetching using reinforcement learning. SIGARCH Comput. Archit. News 43 3S (jun 2015) 285\u2013297. 10.1145\/2872887.2749473","DOI":"10.1145\/2872887.2749473"},{"key":"e_1_3_3_2_44_2","volume-title":"On-line Q-learning using connectionist systems","author":"Rummery Gavin\u00a0A","year":"1994","unstructured":"Gavin\u00a0A Rummery and Mahesan Niranjan. 1994. On-line Q-learning using connectionist systems. Vol.\u00a037. University of Cambridge, Department of Engineering Cambridge, UK."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.2015.7132972"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00033"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358319"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446752"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Julian Shun and Guy\u00a0E. Blelloch. 2013. Ligra: a lightweight graph processing framework for shared memory. SIGPLAN Not. 48 8 (Feb. 2013) 135\u2013146. 10.1145\/2517327.2442530","DOI":"10.1145\/2517327.2442530"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Allan Snavely and Dean\u00a0M. Tullsen. 2000. Symbiotic jobscheduling for a simultaneous mutlithreading processor. SIGPLAN Not. 35 11 (Nov. 2000) 234\u2013244. 10.1145\/356989.357011","DOI":"10.1145\/356989.357011"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254709"},{"key":"e_1_3_3_2_52_2","series-title":"Proceedings of Machine Learning Research","first-page":"5887","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA","volume":"97","author":"Son Kyunghwan","year":"2019","unstructured":"Kyunghwan Son, Daewoo Kim, Wan\u00a0Ju Kang, David Hostallero, and Yung Yi. 2019. QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 5887\u20135896. http:\/\/proceedings.mlr.press\/v97\/son19a.html"},{"key":"e_1_3_3_2_53_2","unstructured":"Standard Performance Evaluation Corporation. 2006. SPEC CPU 2006. https:\/\/www.spec.org\/cpu2006\/"},{"key":"e_1_3_3_2_54_2","unstructured":"Standard Performance Evaluation Corporation. 2017. SPEC CPU 2017. https:\/\/www.spec.org\/cpu2017\/"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"crossref","unstructured":"A. Stillmaker and B. Baas. 2017. Scaling equations for the accurate prediction of CMOS device performance from 180 nm to 7 nm. Integration the VLSI Journal 58 (2017) 74\u201381. http:\/\/vcl.ece.ucdavis.edu\/pubs\/2017.02.VLSIintegration.TechScale\/.","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"e_1_3_3_2_56_2","volume-title":"Reinforcement Learning, An Introduction","author":"Sutton Richard\u00a0S.","year":"2018","unstructured":"Richard\u00a0S. Sutton and Andrew\u00a0G. Barto. 2018. Reinforcement Learning, An Introduction. Cambridge University Press."},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","unstructured":"Wenjun Wang and Wei-Ming Lin. 2018. Real-time physical register file allocation with neural networks for simultaneous multi-threading processors. Int. J. High Perform. Syst. Archit. 8 3 (January 2018) 146\u2013158. 10.1504\/ijhpsa.2018.100714","DOI":"10.1504\/ijhpsa.2018.100714"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Christopher\u00a0JCH Watkins and Peter Dayan. 1992. Q-learning. Machine learning 8 (1992) 279\u2013292.","DOI":"10.1023\/A:1022676722315"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","unstructured":"Huijing Yang Juan Fang Xing Su Zhi Cai and Yuening Wang. 2024. RL-CoPref: a reinforcement learning-based coordinated prefetching controller for multiple prefetchers. The Journal of Supercomputing (2 2024). 10.1007\/s11227-024-05938-9","DOI":"10.1007\/s11227-024-05938-9"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00022"},{"key":"e_1_3_3_2_61_2","unstructured":"Meng Zhou Ziyu Liu Pengwei Sui Yixuan Li and Yuk\u00a0Ying Chung. 2020. Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2007.02529 (2020)."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","unstructured":"Yang Zhou Fang Wang Zhan Shi and Dan Feng. 2022. An End-to-End Automatic Cache Replacement Policy Using Deep Reinforcement Learning. Proceedings of the International Conference on Automated Planning and Scheduling 32 1 (Jun. 2022) 537\u2013545. 10.1609\/icaps.v32i1.19840","DOI":"10.1609\/icaps.v32i1.19840"},{"key":"e_1_3_3_2_63_2","unstructured":"Anastasios Zouzias Kleovoulos Kalaitzidis and Boris Grot. 2021. Branch Prediction as a Reinforcement Learning Problem: Why How and Case Studies. arxiv:https:\/\/arXiv.org\/abs\/2106.13429\u00a0[cs.LG]"}],"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\/3725843.3756096","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:44:52Z","timestamp":1769463892000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":62,"alternative-id":["10.1145\/3725843.3756096","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756096","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"}}]}}