{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:49:24Z","timestamp":1769503764120,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T00:00:00Z","timestamp":1792195200000},"content-version":"vor","delay-in-days":365,"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"},{"name":"Illinois Campus Cluster"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756081","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"170-183","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["RICH Prefetcher: Storing Rich Information in Memory to Trade Capacity and Bandwidth for Latency Hiding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6747-8500","authenticated-orcid":false,"given":"Ningzhi","family":"Ai","sequence":"first","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shanghai, China and Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6546-6907","authenticated-orcid":false,"given":"Wenjian","family":"He","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3239-430X","authenticated-orcid":false,"given":"Hu","family":"He","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4188-3983","authenticated-orcid":false,"given":"Jing","family":"Xia","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5992-5000","authenticated-orcid":false,"given":"Heng","family":"Liao","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1034-2306","authenticated-orcid":false,"given":"Guowei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"Facebook and Amazon are causing a memory shortage","author":"Patrizio Andy","year":"2018","unstructured":"Andy Patrizio. 2018. Facebook and Amazon are causing a memory shortage. https:\/\/www.networkworld.com\/article\/965006\/facebook-and-amazon-are-causing-a-memory-shortage.html"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"John Ousterhout Parag Agrawal David Erickson Christos Kozyrakis Jacob Leverich David Mazi\u00e8res Subhasish Mitra Aravind Narayanan Guru Parulkar Mendel Rosenblum Stephen\u00a0M. Rumble Eric Stratmann and Ryan Stutsman. 2010. The case for RAMClouds: scalable high-performance storage entirely in DRAM. ACM SIGOPS Operating Systems Review 43 4 (2010) 92\u2013105.","DOI":"10.1145\/1713254.1713276"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2016.7838026"},{"key":"e_1_3_3_1_5_2","volume-title":"USENIX FAST","author":"Lee Youngmoon","year":"2022","unstructured":"Youngmoon Lee, Hasan Al\u00a0Maruf, Mosharaf Chowdhury, Asaf Cidon, and Kang\u00a0G Shin. 2022. Hydra: Resilient and highly available remote memory. In USENIX FAST."},{"key":"e_1_3_3_1_6_2","volume-title":"Proc. of USENIX HotStorage","author":"Akel Ameen","year":"2011","unstructured":"Ameen Akel, Adrian\u00a0M. Caulfield, Todor\u00a0I. Mollov, Rajesh\u00a0K. Gupta, and Steven Swanson. 2011. Onyx: a Protoype Phase Change Memory Storage Array. In Proc. of USENIX HotStorage."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Takayuki Kawahara. 2010. Scalable spin-transfer torque ram technology for normally-off computing. IEEE Design & Test of Computers 28 1 (2010) 52\u201363.","DOI":"10.1109\/MDT.2010.97"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Simone Raoux Geoffrey\u00a0W Burr Matthew\u00a0J Breitwisch Charles\u00a0T Rettner Y-C Chen Robert\u00a0M Shelby Martin Salinga Daniel Krebs S-H Chen H-L Lung and C.\u00a0H. Lam. 2008. Phase-change random access memory: A scalable technology. IBM Journal of Research and Development 52 4.5 (2008) 465\u2013479.","DOI":"10.1147\/rd.524.0465"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Shimeng Yu and Pai-Yu Chen. 2016. Emerging Memory Technologies: Recent Trends and Prospects. IEEE Solid-State Circuits Magazine 8 2 (2016). 10.1109\/MSSC.2016.2546199","DOI":"10.1109\/MSSC.2016.2546199"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI55740.2022.00017"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"D. Gouk M. Kwon H. Bae S. Lee and M. Jung. 2023. Memory Pooling With CXL. IEEE MICRO (2023). 10.1109\/MM.2023.3237491","DOI":"10.1109\/MM.2023.3237491"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.38"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00053"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00071"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540730"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322225"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2009.4798239"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783763"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00072"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Saugata Ghose Tianshi Li Nastaran Hajinazar Damla\u00a0Senol Cali and Onur Mutlu. 2019. Demystifying Complex Workload\u2013DRAM Interactions: An Experimental Study. ACM Meas. Anal. Comput. Syst. Article 60 (2019). 10.1145\/3366708","DOI":"10.1145\/3366708"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Chengning Wang Dan Feng Wei Tong Jingning Liu Zheng Li Jiayi Chang Yang Zhang Bing Wu Jie Xu Wei Zhao Yilin Li and Ruoxi Ren. 2019. Cross-point Resistive Memory: Nonideal Properties and Solutions. ACM Trans. Des. Autom. Electron. Syst. (2019). 10.1145\/3325067","DOI":"10.1145\/3325067"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Scott\u00a0W. Fong Christopher\u00a0M. Neumann and H.-S.\u00a0Philip Wong. 2017. Phase-Change Memory\u2014Towards a Storage-Class Memory. IEEE Trans. on Electron Devices (2017). 10.1109\/TED.2017.2746342","DOI":"10.1109\/TED.2017.2746342"},{"key":"e_1_3_3_1_23_2","unstructured":"JEDEC. 2013. JESD235A: High Bandwidth Memory (HBM) DRAM."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818955"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3149704.3149766"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Hongjing Huang Zeke Wang Jie Zhang Zhenhao He Chao Wu Jun Xiao and Gustavo Alonso. 2022. Shuhai: A Tool for Benchmarking High Bandwidth Memory on FPGAs. IEEE TC 71 5 (2022). 10.1109\/TC.2021.3075765","DOI":"10.1109\/TC.2021.3075765"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614256"},{"key":"e_1_3_3_1_28_2","unstructured":"JEDEC. 2009. JESD79-3E: DDR3 SDRAM Standard."},{"key":"e_1_3_3_1_29_2","unstructured":"JEDEC. 2017. JESD79-4C: DDR4 SDRAM Standard."},{"key":"e_1_3_3_1_30_2","unstructured":"JEDEC. 2020. JESD79-5: DDR5 SDRAM Standard."},{"key":"e_1_3_3_1_31_2","volume-title":"A Primer on Hardware Prefetching","author":"Falsafi Babak","year":"2022","unstructured":"Babak Falsafi and Thomas\u00a0F Wenisch. 2022. A Primer on Hardware Prefetching. Springer Nature."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480114"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00021"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Hao Wu Krishnendra Nathella Matthew Pabst Dam Sunwoo Akanksha Jain and Calvin Lin. 2022. Practical Temporal Prefetching With Compressed On-Chip Metadata. IEEE Trans. Comput. 71 11 (2022). 10.1109\/TC.2021.3065909","DOI":"10.1109\/TC.2021.3065909"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771774"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/2155620.2155638"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540732"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830785"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Ali Ansari Fatemeh Golshan Rahil Barati Pejman Lotfi-Kamran and Hamid Sarbazi-Azad. 2023. MANA: Microarchitecting a Temporal Instruction Prefetcher. IEEE Trans. Comput. 72 3 (2023). 10.1109\/TC.2022.3176825","DOI":"10.1109\/TC.2022.3176825"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/360128.360135"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Suleyman Sair Timothy Sherwood and Brad Calder. 2003. A Decoupled Predictor-Directed Stream Prefetching Architecture. IEEE Trans. Comput. 52 3 (2003).","DOI":"10.1109\/TC.2003.1183943"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","unstructured":"Mohammad Bakhshalipour Seyedali Tabaeiaghdaei Pejman Lotfi-Kamran and Hamid Sarbazi-Azad. 2019. Evaluation of Hardware Data Prefetchers on Server Processors. ACM Computing Surveys (CSUR) 52 3 (2019) 1\u201329.","DOI":"10.1145\/3312740"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"crossref","unstructured":"Mohammad Bakhshalipour Pejman Lotfi-Kamran Abbas Mazloumi Farid Samandi Mahmood Naderan-Tahan Mehdi Modarressi and Hamid Sarbazi-Azad. 2018. Fast Data Delivery for Many-Core Processors. IEEE Trans. on Computers 67 10 (2018) 1416\u20131429.","DOI":"10.1109\/TC.2018.2821144"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446087"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358325"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830793"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.33"},{"key":"e_1_3_3_1_48_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2210.14324 (2022)."},{"key":"e_1_3_3_1_49_2","unstructured":"[n. d.]. The Champsim Simulator. https:\/\/github.com\/ChampSim\/ChampSim"},{"key":"e_1_3_3_1_50_2","unstructured":"2015. The 2nd Data Prefetching Championship. https:\/\/comparch-conf.gatech.edu\/dpc2\/"},{"key":"e_1_3_3_1_51_2","unstructured":"2019. The 3rd Data Prefetching Championship. https:\/\/dpc3.compas.cs.stonybrook.edu\/"},{"key":"e_1_3_3_1_52_2","unstructured":"2017. The 2nd Cache Replacement Championship. https:\/\/crc2.ece.tamu.edu\/"},{"key":"e_1_3_3_1_53_2","volume-title":"Golden Cove Microarchitecture (P-Core) Examined","author":"Ian\u00a0Cutress Andrei\u00a0Frumusanu","year":"2021","unstructured":"Andrei\u00a0Frumusanu Ian\u00a0Cutress. 2021. Golden Cove Microarchitecture (P-Core) Examined. https:\/\/www.anandtech.com\/show\/16881\/a-deep-dive-into-intels-alder-lake-microarchitectures\/3"},{"key":"e_1_3_3_1_54_2","volume-title":"Popping the Hood on Golden Cove","author":"Lam Chester","year":"2021","unstructured":"Chester Lam. 2021. Popping the Hood on Golden Cove. https:\/\/chipsandcheese.com\/p\/popping-the-hood-on-golden-cove"},{"key":"e_1_3_3_1_55_2","volume-title":"Going Armchair Quarterback on Golden Cove\u2019s Caches","author":"Lam Chester","year":"2022","unstructured":"Chester Lam. 2022. Going Armchair Quarterback on Golden Cove\u2019s Caches. https:\/\/chipsandcheese.com\/p\/going-armchair-quarterback-on-golden-coves-caches"},{"key":"e_1_3_3_1_56_2","volume-title":"Intel Architecture Day 2021: Alder Lake, Golden Cove, and Gracemont Detailed","author":"Ian\u00a0Cutress Andrei\u00a0Frumusanu","year":"2021","unstructured":"Andrei\u00a0Frumusanu Ian\u00a0Cutress. 2021. Intel Architecture Day 2021: Alder Lake, Golden Cove, and Gracemont Detailed. https:\/\/www.anandtech.com\/show\/16881\/a-deep-dive-into-intels-alder-lake-microarchitectures\/3"},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00015"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322207"},{"key":"e_1_3_3_1_59_2","unstructured":"2006. SPEC CPU 2006. https:\/\/www.spec.org\/cpu2006\/"},{"key":"e_1_3_3_1_60_2","unstructured":"2017. SPEC CPU 2017. https:\/\/www.spec.org\/cpu2017\/"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442530"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"e_1_3_3_1_63_2","volume-title":"DPC-3 Traces","unstructured":"[n. d.]. DPC-3 Traces. https:\/\/dpc3.compas.cs.stonybrook.edu\/champsim-traces\/"},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14267978"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14268118"},{"key":"e_1_3_3_1_66_2","unstructured":"Mehran Shakerinava Mohammad Bakhshalipour Pejman Lotfi-Kamran and Hamid Sarbazi-Azad. 2019. Multi-lookahead offset prefetching. The Third Data Prefetching Championship (2019)."},{"key":"e_1_3_3_1_67_2","unstructured":"Philippos Papaphilippou Paul\u00a0HJ Kelly and Wayne Luk. 2019. Pangloss: a novel Markov chain prefetcher. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.00877 (2019)."},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3473510"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716260"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358300"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00090"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00070"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00025"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2007.346185"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123951"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00057"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527398"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263597"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00040"},{"key":"e_1_3_3_1_80_2","volume-title":"ISCA","author":"Mutlu Onur","year":"2005","unstructured":"Onur Mutlu, Hyesoon Kim, and Yale\u00a0N Patt. 2005. Techniques for efficient processing in runahead execution engines. In ISCA. IEEE."},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830812"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783764"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"crossref","unstructured":"Feng Xue Chenji Han Xinyu Li Junliang Wu Tingting Zhang Tianyi Liu Yifan Hao Zidong Du Qi Guo and Fuxin Zhang. 2024. Tyche: An Efficient and General Prefetcher for Indirect Memory Accesses. ACM Trans. Archit. Code Optim. 21 2 Article 30 (March 2024) 26\u00a0pages.","DOI":"10.1145\/3641853"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507745"},{"key":"e_1_3_3_1_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378498"},{"key":"e_1_3_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519583"}],"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\/3725843.3756081","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:46:53Z","timestamp":1769464013000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":86,"alternative-id":["10.1145\/3725843.3756081","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756081","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"}}]}}