{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:09:31Z","timestamp":1769501371346,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":117,"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":["2503010, 2402696, 2238665, 2504353, 2112562"],"award-info":[{"award-number":["2503010, 2402696, 2238665, 2504353, 2112562"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756069","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"418-431","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["LATPC: Accelerating GPU Address Translation Using Locality-Aware TLB Prefetching and MSHR Compression"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3418-5299","authenticated-orcid":false,"given":"Yeonan","family":"Ha","sequence":"first","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4131-7145","authenticated-orcid":false,"given":"Jiho","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0302-7503","authenticated-orcid":false,"given":"Hanna","family":"Cha","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6529-5333","authenticated-orcid":false,"given":"Jiwon","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Suwon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5432-7813","authenticated-orcid":false,"given":"Joonsung","family":"Kim","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5390-6445","authenticated-orcid":false,"given":"Won Woo","family":"Ro","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1015-9969","authenticated-orcid":false,"given":"Youngsok","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.5555\/3236002"},{"key":"e_1_3_3_2_3_2","unstructured":"Advanced Micro Devices Inc.2024. AMD64 Architecture Programmer\u2019s Manual. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/processor-tech-docs\/programmer-references\/40332.pdf."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2012.6237041"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3326334"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00050"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293901"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173169"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","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 TACO 14 2 (2017).","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/1815961.1815970"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2000064.2000101"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00055"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414639"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485943"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/1468075.1468121"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540741"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037705"},{"key":"e_1_3_3_2_20_2","unstructured":"Abhishek Bhattacharjee. 2019. Appendix L: Advanced Concepts on Address Translation. https:\/\/www.cs.yale.edu\/homes\/abhishek\/abhishek-appendix-l.pdf."},{"key":"e_1_3_3_2_21_2","volume-title":"Proc. ASPLOS","author":"Bhattacharjee Abhishek","year":"2010","unstructured":"Abhishek Bhattacharjee and Margaret Martonosi. 2010. Inter-Core Cooperative TLB Prefetchers for Chip Multiprocessors. In Proc. ASPLOS."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"John Burgess. 2020. RTX on\u2014The NVIDIA Turing GPU. IEEE Micro 40 2 (2020).","DOI":"10.1109\/MM.2020.2971677"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2012.6402918"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Hanna Cha Sungchul Lee Yeonan Ha Hanhwi Jang Joonsung Kim and Youngsok Kim. 2024. GCStack: A GPU Cycle Accounting Mechanism for Providing Accurate Insight into GPU Performance. IEEE CAL 23 2 (2024).","DOI":"10.1109\/LCA.2024.3476909"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731068"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707247"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704684"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Shuai Che Michael Boyer Jiayuan Meng David Tarjan Jeremy\u00a0W Sheaffer and Kevin Skadron. 2008. A performance study of general-purpose applications on graphics processors using CUDA. JPDC 68 10 (2008).","DOI":"10.1016\/j.jpdc.2008.05.014"},{"key":"e_1_3_3_2_30_2","volume-title":"Proc. ATC","author":"Choi Sangjin","year":"2022","unstructured":"Sangjin Choi, Taeksoo Kim, Jinwoo Jeong, Rachata Ausavarungnirun, Myeongjae Jeon, Youngjin Kwon, and Jeongseob Ahn. 2022. Memory Harvesting in Multi-GPU Systems with Hierarchical Unified Virtual Memory. In Proc. ATC."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Jack Choquette. 2023. NVIDIA Hopper H100 GPU: Scaling Performance. IEEE Micro 43 3 (2023).","DOI":"10.1109\/MM.2023.3256796"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Lawrence\u00a0T Clark Vinay Vashishtha Lucian Shifren Aditya Gujja Saurabh Sinha Brian Cline Chandarasekaran Ramamurthy and Greg Yeric. 2016. ASAP7: A 7-nm finFET predictive process design kit. Microelectronics 53 (2016).","DOI":"10.1016\/j.mejo.2016.04.006"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037704"},{"key":"e_1_3_3_2_34_2","unstructured":"Radoslav Danilak. 2009. Systems and Methods for Hardware-Based GPU Paging to System. US Patent No. 7 623 134 Nov. 24th 2009."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01743-8"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731011"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00065"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Philip\u00a0J. Fleming and John\u00a0J. Wallace. 1986. How Not to Lie With Statistics: The Correct Way to Summarize Benchmark Results. CACM 29 3 (1986).","DOI":"10.1145\/5666.5673"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322224"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Michael Garland Scott Le\u00a0Grand John Nickolls Joshua Anderson Jim Hardwick Scott Morton Everett Phillips Yao Zhang and Vasily Volkov. 2008. Parallel Computing Experiences with CUDA.","DOI":"10.1109\/MM.2008.57"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330390"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00078"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589039"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173194"},{"key":"e_1_3_3_2_46_2","unstructured":"Gur Hildesheim Chang\u00a0Kian Tan Robert\u00a0S Chappell and Rohit Bhatia. 2015. Concurrent Page Table Walker Control for TLB Miss Handling. US Patent No. 9 069 690 Jun. 30th. 2015."},{"key":"e_1_3_3_2_47_2","unstructured":"Intel Corporation. 2024. Intel\u00ae 64 and IA-32 Architectures Software Developer\u2019s Manual. https:\/\/cdrdv2-public.intel.com\/835781\/325462-sdm-vol-1-2abcd-3abcd-4.pdf."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Aamer Jaleel Eiman Ebrahimi and Sam Duncan. 2019. DUCATI: High-Performance Address Translation by Extending TLB Reach of GPU-Accelerated Systems. ACM TACO 16 (2019).","DOI":"10.1145\/3309710"},{"key":"e_1_3_3_2_49_2","unstructured":"JEDEC Solid State Technology Association. 2021. Graphics Double Data Rate (GDDR6) SGRAM Standard. JESD250D. https:\/\/www.jedec.org\/system\/files\/docs\/JESD250D.pdf."},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/545214.545237"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749471"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00086"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378529"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835963"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00024"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480105"},{"key":"e_1_3_3_2_58_2","volume-title":"Proc. ISCA","author":"Kroft David","year":"1981","unstructured":"David Kroft. 1981. Lockup-Free Instruction Fetch\/Prefetch Cache Organization. In Proc. ISCA."},{"key":"e_1_3_3_2_59_2","volume-title":"Proc. OSDI","author":"Kwon Youngjin","year":"2016","unstructured":"Youngjin Kwon, Hangchen Yu, Simon Peter, Christopher\u00a0J Rossbach, and Emmett Witchel. 2016. Coordinated and Efficient Huge Page Management with Ingens. In Proc. OSDI."},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527384"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00123"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.44"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071063"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00031"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071054"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480083"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304044"},{"key":"e_1_3_3_2_68_2","volume-title":"Workshop on ML for Systems at NeurIPS","author":"Margaritov Artemiy","year":"2018","unstructured":"Artemiy Margaritov, Dmitrii Ustiugov, Edouard Bugnion, and Boris Grot. 2018. Virtual Address Translation via Learned Page Table Indexes. In Workshop on ML for Systems at NeurIPS."},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358294"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623782"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2009.7478342"},{"key":"e_1_3_3_2_72_2","unstructured":"NVIDIA Corporation. 2016. Pascal MMU Format Change. https:\/\/nvidia.github.io\/open-gpu-doc\/pascal\/gp100-mmu-format.pdf."},{"key":"e_1_3_3_2_73_2","unstructured":"NVIDIA Corporation. 2018. NVIDIA Turing GPU Architecture. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/design-visualization\/technologies\/turing-architecture\/NVIDIA-Turing-Architecture-Whitepaper.pdf."},{"key":"e_1_3_3_2_74_2","unstructured":"NVIDIA Corporation. 2023. NVIDIA Ada GPU Architecture. https:\/\/images.nvidia.com\/aem-dam\/Solutions\/geforce\/ada\/nvidia-ada-gpu-architecture.pdf."},{"key":"e_1_3_3_2_75_2","unstructured":"NVIDIA Corporation. 2025. CUDA C++ Programming Guide. https:\/\/docs.nvidia.com\/cuda\/pdf\/CUDA_C_Programming_Guide.pdf."},{"key":"e_1_3_3_2_76_2","unstructured":"NVIDIA Corporation. 2025. CUDA Samples. https:\/\/github.com\/nvidia\/cuda-samples."},{"key":"e_1_3_3_2_77_2","unstructured":"NVIDIA Corporation. 2025. CUTLASS. https:\/\/github.com\/nvidia\/cutlass."},{"key":"e_1_3_3_2_78_2","unstructured":"NVIDIA Corporation. 2025. Nsight Compute Documentation. https:\/\/docs.nvidia.com\/nsight-compute."},{"key":"e_1_3_3_2_79_2","unstructured":"NVIDIA Corporation. 2025. NVIDIA Linux Open GPU Kernel Module Source. https:\/\/github.com\/NVIDIA\/open-gpu-kernel-modules."},{"key":"e_1_3_3_2_80_2","unstructured":"Lars Nyland John\u00a0R. Nickolls Gentaro Hirota and Tanmoy Mandal. 2011. Systems and Methods for Coalescing Memory Accesses of Parallel Threads. US Patent No. 8 086 806 Dec. 27th. 2011."},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00079"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.18"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080217"},{"key":"e_1_3_3_2_84_2","volume-title":"Proc. ASPLOS","author":"Park Chang\u00a0Hyun","year":"2022","unstructured":"Chang\u00a0Hyun Park, Ilias Vougioukas, Andreas Sandberg, and David Black-Schaffer. 2022. Every Walk\u2019s a Hit: Making Page Walks Single-Access Cache Hits. In Proc. ASPLOS."},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00029"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835964"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.32"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830773"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541942"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835965"},{"key":"e_1_3_3_2_91_2","volume-title":"Proc. MICRO","author":"Pratheek B","year":"2024","unstructured":"B Pratheek, Guilherme Cox, Jan Vesely, and Arkaprava Basu. 2024. SUV: Static analysis guided Unified Virtual Memory. In Proc. MICRO."},{"key":"e_1_3_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00059"},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00036"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"crossref","unstructured":"Antonis Psistakis Nikos Chrysos Fabien Chaix Marios Asiminakis Michalis Gianioudis Pantelis Xirouchakis Vassilis Papaefstathiou and Manolis Katevenis. 2022. Optimized Page Fault Handling During RDMA. TPDS 33 12 (2022).","DOI":"10.1109\/TPDS.2022.3175666"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540717"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.16"},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOST49136.2021.9702269"},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00025"},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00036"},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378493"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1201\/b20200"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSE.2007.44"},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"crossref","unstructured":"John\u00a0E. Stone David Gohara and Guochun Shi. 2010. OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems. IEEE CiSE 12 3 (2010).","DOI":"10.1109\/MCSE.2010.69"},{"key":"e_1_3_3_2_104_2","unstructured":"John\u00a0A Stratton Christopher Rodrigues I-Jui Sung Nady Obeid Li-Wen Chang Nasser Anssari Geng\u00a0Daniel Liu and Wen-mei\u00a0W Hwu. 2012. Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing. IMPACT Technical Report (2012)."},{"key":"e_1_3_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322230"},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/224056.224071"},{"key":"e_1_3_3_2_107_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480128"},{"key":"e_1_3_3_2_108_2","doi-asserted-by":"crossref","unstructured":"Steven\u00a0P Vanderwiel and David\u00a0J Lilja. 2000. Data Prefetch Mechanisms. ACM CSUR 32 2 (2000).","DOI":"10.1145\/358923.358939"},{"key":"e_1_3_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00016"},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482091"},{"key":"e_1_3_3_2_111_2","unstructured":"Ilias Vougioukas. 2022. How about a short walk?https:\/\/community.arm.com\/arm-research\/b\/articles\/posts\/how-about-a-short-walk."},{"key":"e_1_3_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00085"},{"key":"e_1_3_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00085"},{"key":"e_1_3_3_2_114_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00124"},{"key":"e_1_3_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322223"},{"key":"e_1_3_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378520"},{"key":"e_1_3_3_2_117_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173195"},{"key":"e_1_3_3_2_118_2","volume-title":"Proc. CCS","author":"Zhang Zhenkai","year":"2023","unstructured":"Zhenkai Zhang, Tyler Allen, Fan Yao, Xing Gao, and Rong Ge. 2023. TunneLs for Bootlegging: Fully Reverse-Engineering GPU TLBs for Challenging Isolation Guarantees of NVIDIA MIG. In Proc. CCS."}],"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\/3725843.3756069","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756069","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:43:31Z","timestamp":1769463811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756069"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":117,"alternative-id":["10.1145\/3725843.3756069","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756069","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"}}]}}