{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:56:26Z","timestamp":1780674986877,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":100,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and communications Technology Promotion","doi-asserted-by":"publisher","award":["10692981, 00228970, II212052"],"award-info":[{"award-number":["10692981, 00228970, II212052"]}],"id":[{"id":"10.13039\/501100010418","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\/3725843.3756056","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:21:19Z","timestamp":1760721679000},"page":"401-417","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SoftWalker: Supporting Software Page Table Walk for Irregular GPU Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0680-2642","authenticated-orcid":false,"given":"Sungbin","family":"Jang","sequence":"first","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3802-7524","authenticated-orcid":false,"given":"Junhyeok","family":"Park","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9181-4186","authenticated-orcid":false,"given":"Yongho","family":"Lee","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6021-9926","authenticated-orcid":false,"given":"Osang","family":"Kwon","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9940-2845","authenticated-orcid":false,"given":"Donghyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0646-8303","authenticated-orcid":false,"given":"Juyoung","family":"Seok","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7842-125X","authenticated-orcid":false,"given":"Seokin","family":"Hong","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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.2013.6522337"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480855"},{"key":"e_1_3_3_2_4_2","volume-title":"AMD GRAPHICS CORES NEXT (GCN) ARCHITECTURE","year":"2012","unstructured":"AMD 2012. AMD GRAPHICS CORES NEXT (GCN) ARCHITECTURE. AMD. https:\/\/www.amd.com\/Documents\/GCN_Architecture_whitepaper.pdf"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Akhil Arunkumar Evgeny Bolotin Benjamin Cho Ugljesa Milic Eiman Ebrahimi Oreste Villa Aamer Jaleel Carole-Jean Wu and David Nellans. 2017. MCM-GPU: Multi-chip-module GPUs for continued performance scalability. ACM SIGARCH Computer Architecture News 45 2 (2017) 320\u2013332.","DOI":"10.1145\/3140659.3080231"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00054"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Rachata Ausavarungnirun Vance Miller Joshua Landgraf Saugata Ghose Jayneel Gandhi Adwait Jog Christopher\u00a0J Rossbach and Onur Mutlu. 2018. Mask: Redesigning the gpu memory hierarchy to support multi-application concurrency. ACM SIGPLAN Notices 53 2 (2018) 503\u2013518.","DOI":"10.1145\/3296957.3173169"},{"key":"e_1_3_3_2_9_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 Transactions on Architecture and Code Optimization (TACO) 14 2 (2017) 1\u201325.","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00055"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063400"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3730990"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.16"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2009.4798270"},{"key":"e_1_3_3_2_16_2","volume-title":"CXL 3.1 Specification","year":"2023","unstructured":"Compute Express Link Consortium 2023. CXL 3.1 Specification. Compute Express Link Consortium. https:\/\/computeexpresslink.org\/cxl-specification\/"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00086"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00029"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/1281700.1281703"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661187"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Keith\u00a0I Farkas and Norman\u00a0P Jouppi. 1994. Complexity\/performance tradeoffs with non-blocking loads. ACM SIGARCH Computer Architecture News 22 2 (1994) 211\u2013222.","DOI":"10.1145\/192007.192029"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731011"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00065"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_3_2_26_2","unstructured":"Gary\u00a0N Hammond Koichi Yamada Stephen\u00a0G Burger James\u00a0O Hays Jonathan\u00a0K Ross and William\u00a0R Bryg. 1999. Software and hardware-managed translation lookaside buffer. US Patent 5 940 872."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993213"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Mark\u00a0D Hill and Alan\u00a0Jay Smith. 2002. Evaluating associativity in CPU caches. IEEE Trans. Comput. 38 12 (2002) 1612\u20131630.","DOI":"10.1109\/12.40842"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.23"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Won Hur Jiwon Lee Jaewon Kwon Minjae Kim and Won\u00a0Woo Ro. 2025. HashScape: Leveraging Virtual Address Dynamics for Efficient Hashed Page Tables. IEEE Trans. Comput. (2025).","DOI":"10.1109\/TC.2025.3543698"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/313817.313948"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.1997.569652"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676900"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830784"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Naifeng Jing Yao Shen Yao Lu Shrikanth Ganapathy Zhigang Mao Minyi Guo Ramon Canal and Xiaoyao Liang. 2013. An energy-efficient and scalable eDRAM-based register file architecture for GPGPU. ACM SIGARCH Computer Architecture News 41 3 (2013) 344\u2013355.","DOI":"10.1145\/2508148.2485952"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818979"},{"key":"e_1_3_3_2_37_2","unstructured":"Corbet Jonathan. 2017. Five-Level Page Tables. (2017). https:\/\/lwn.net\/Articles\/717293\/"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00057"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250711"},{"key":"e_1_3_3_2_40_2","first-page":"957","volume-title":"23rd USENIX Security Symposium (USENIX Security 14)","author":"Kemerlis Vasileios\u00a0P","year":"2014","unstructured":"Vasileios\u00a0P Kemerlis, Michalis Polychronakis, and Angelos\u00a0D Keromytis. 2014. ret2dir: Rethinking kernel isolation. In 23rd USENIX Security Symposium (USENIX Security 14). 957\u2013972."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Bernhard Kerbl Georgios Kopanas Thomas Leimk\u00fchler and George Drettakis. 2023. 3d gaussian splatting for real-time radiance field rendering.ACM Trans. Graph. 42 4 (2023) 139\u20131.","DOI":"10.1145\/3592433"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378529"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Junsu Kim Jaebeom Jeon Jaeyong Park Sangun Choi Minseong Gil Seokin Hong Gunjae Koo Myung\u00a0Kuk Yoon and Yunho Oh. 2025. MOST: Memory Oversubscription-aware Scheduling for Tensor Migration on GPU Unified Storage. IEEE Computer Architecture Letters (2025).","DOI":"10.1109\/LCA.2025.3580264"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446062"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480105"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Osang Kwon Yongho Lee and Seokin Hong. 2022. Pinning page structure entries to last-level cache for fast address translation. IEEE Access 10 (2022) 114552\u2013114565.","DOI":"10.1109\/ACCESS.2022.3217484"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992823"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00013"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071063"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00123"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992771"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614269"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00031"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071054"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.1996.552663"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Jeffrey\u00a0C Mogul and Anita Borg. 1991. The effect of context switches on cache performance. ACM SIGPLAN Notices 26 4 (1991) 75\u201384.","DOI":"10.1145\/106973.106982"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/165123.165127"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807626"},{"key":"e_1_3_3_2_60_2","unstructured":"NVIDIA. 2017. NVIDIA TESLA V100 GPU ARCHITECTURE. (2017). https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf"},{"key":"e_1_3_3_2_61_2","volume-title":"Pascal MMU Format Changes","year":"2020","unstructured":"NVIDIA 2020. Pascal MMU Format Changes. NVIDIA. https:\/\/nvidia.github.io\/open-gpu-doc\/pascal\/gp100-mmu-format.pdf"},{"key":"e_1_3_3_2_62_2","volume-title":"NVIDIA AMPERE GA102 GPU ARCHITECTURE","year":"2021","unstructured":"NVIDIA 2021. NVIDIA AMPERE GA102 GPU ARCHITECTURE. NVIDIA. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf"},{"key":"e_1_3_3_2_63_2","unstructured":"NVIDIA. 2024. NVIDIA CUDA Samples. (2024). https:\/\/github.com\/NVIDIA\/cuda-samples"},{"key":"e_1_3_3_2_64_2","volume-title":"NVIDIA GH200 Grace Hopper Superchip Architecture","year":"2024","unstructured":"NVIDIA 2024. NVIDIA GH200 Grace Hopper Superchip Architecture. NVIDIA. https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-hopper"},{"key":"e_1_3_3_2_65_2","unstructured":"NVIDIA. 2024. NVIDIA High Performance Conjugate Gradient Benchmark (HPCG). https:\/\/github.com\/NVIDIA\/nvidia-hpcg"},{"key":"e_1_3_3_2_66_2","unstructured":"NVIDIA. 2025. CUDA Binary Utilites. (2025). https:\/\/docs.nvidia.com\/cuda\/cuda-binary-utilities\/contents.html"},{"key":"e_1_3_3_2_67_2","unstructured":"NVIDIA. 2025. CUDA C++ Programming Guide. (2025). https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/"},{"key":"e_1_3_3_2_68_2","unstructured":"NVIDIA. 2025. CUDA Toolkit Documentation. (2025). https:\/\/docs.nvidia.com\/cuda\/cuda-driver-api\/group__CUDA__GRAPH.html"},{"key":"e_1_3_3_2_69_2","unstructured":"NVIDIA. 2025. Nsight Compute Documentation. (2025). https:\/\/docs.nvidia.com\/nsight-compute\/index.html"},{"key":"e_1_3_3_2_70_2","volume-title":"NVML API Reference Guide","year":"2025","unstructured":"NVIDIA 2025. NVML API Reference Guide. NVIDIA. https:\/\/docs.nvidia.com\/deploy\/nvml-api\/group__NvLink.html"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322222"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3725843.3756090"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00029"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10992841"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2012.32"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"crossref","unstructured":"Bharath Pichai Lisa Hsu and Abhishek Bhattacharjee. 2014. Architectural Support for Address Translation on GPUs: Designing Memory Management Units for CPU\/GPUs with Unified Address Spaces. ACM SIGARCH Computer Architecture News 42 1 (2014) 743\u2013758.","DOI":"10.1145\/2654822.2541942"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835965"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00059"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00036"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP60621.2024.00026"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"crossref","unstructured":"Divya\u00a0Praneetha Ravipati Victor\u00a0M van Santen Shivendra\u00a0Singh Parihar Yogesh\u00a0Singh Chauhan Preeti\u00a0Ranjan Panda and Hussam Amrouch. 2025. Cryo-CACTI: Cryogenic-Aware CACTI for Cache Modeling down to 10K in Advanced 7nm FinFETs. IEEE Trans. Comput. (2025).","DOI":"10.1109\/TC.2025.3566899"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540717"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540718"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"crossref","unstructured":"Mohammad Sadrosadati Amirhossein Mirhosseini Ali Hajiabadi Seyed\u00a0Borna Ehsani Hajar Falahati Hamid Sarbazi-Azad Mario Drumond Babak Falsafi Rachata Ausavarungnirun and Onur Mutlu. 2021. Highly concurrent latency-tolerant register files for GPUs. ACM Transactions on Computer Systems (TOCS) 37 1-4 (2021) 1\u201336.","DOI":"10.1145\/3419973"},{"key":"e_1_3_3_2_85_2","volume-title":"Everything You Need to Know about Unified Memory","author":"Sakharnykh Nikolay","year":"2018","unstructured":"Nikolay Sakharnykh. 2018. Everything You Need to Know about Unified Memory. https:\/\/www.nvidia.com\/en-us\/on-demand\/session\/gtcsiliconvalley2018-s8430\/"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00025"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00036"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378493"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071061"},{"key":"e_1_3_3_2_90_2","volume-title":"DC Ultra","year":"2025","unstructured":"Synopsys 2025. DC Ultra. Synopsys. https:\/\/www.synopsys.com\/content\/dam\/synopsys\/implementation&signoff\/datasheets\/dc-ultra-ds.pdf"},{"key":"e_1_3_3_2_91_2","unstructured":"John\u00a0R Tramm Andrew\u00a0R Siegel Tanzima Islam and Martin Schulz. 2014. XSBench - The Development and Verification of a Performance Abstraction for Monte Carlo Reactor Analysis. The Role of Reactor Physics toward a Sustainable Future (PHYSOR) (2014)."},{"key":"e_1_3_3_2_92_2","volume-title":"28 Nanometer","year":"2022","unstructured":"UMC 2022. 28 Nanometer. UMC. https:\/\/www.umc.com\/upload\/media\/05_Press_Center\/3_Literatures\/Process_Technology\/28nm_Brochure.pdf"},{"key":"e_1_3_3_2_93_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"crossref","unstructured":"Nandita Vijaykumar Gennady Pekhimenko Adwait Jog Abhishek Bhowmick Rachata Ausavarungnirun Chita Das Mahmut Kandemir Todd\u00a0C Mowry and Onur Mutlu. 2015. A case for core-assisted bottleneck acceleration in GPUs: enabling flexible data compression with assist warps. ACM SIGARCH Computer Architecture News 43 3S (2015) 41\u201353.","DOI":"10.1145\/2872887.2750399"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00085"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3523227.3546765"},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637571"},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00022"},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"crossref","unstructured":"Idan Yaniv and Dan Tsafrir. 2016. Hash don\u2019t cache (the page table). ACM SIGMETRICS Performance Evaluation Review 44 1 (2016) 337\u2013350.","DOI":"10.1145\/2964791.2901456"},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"crossref","unstructured":"Myung\u00a0Kuk Yoon Keunsoo Kim Sangpil Lee Won\u00a0Woo Ro and Murali Annavaram. 2016. Virtual thread: Maximizing thread-level parallelism beyond GPU scheduling limit. ACM SIGARCH Computer Architecture News 44 3 (2016) 609\u2013621.","DOI":"10.1145\/3007787.3001201"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446077"}],"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\/3725843.3756056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:49:01Z","timestamp":1769464141000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":100,"alternative-id":["10.1145\/3725843.3756056","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756056","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"}}]}}