{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:44:56Z","timestamp":1772725496399,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":113,"publisher":"ACM","funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation","award":["10692981, 00228970"],"award-info":[{"award-number":["10692981, 00228970"]}]},{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute","doi-asserted-by":"publisher","award":["25ZS1100"],"award-info":[{"award-number":["25ZS1100"]}],"id":[{"id":"10.13039\/501100003696","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\/3725843.3756090","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1040-1057","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Leveraging Chiplet-Locality for Efficient Memory Mapping in Multi-Chip Module GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3802-7524","authenticated-orcid":false,"given":"Junhyeok","family":"Park","sequence":"first","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0680-2642","authenticated-orcid":false,"given":"Sungbin","family":"Jang","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University, Suwon, Republic of Korea"}]},{"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"}]},{"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"}]},{"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"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378468"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00023"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480855"},{"key":"e_1_3_3_2_5_2","unstructured":"AMD. 2021. AMD CNA2 ARCHITECTURE. [Online]. Available: https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-business-docs\/white-papers\/amd-cdna2-white-paper.pdf."},{"key":"e_1_3_3_2_6_2","unstructured":"AMD. 2023. 4th Gen AMD EPYC Processor Architecture White Paper. [Online]. Available. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/epyc-business-docs\/white-papers\/221704010-B_en_4th-Gen-AMD-EPYC-Processor-Architecture\u2014White-Paper_pdf.pdf"},{"key":"e_1_3_3_2_7_2","unstructured":"AMD. 2023. AMD CNA3 ARCHITECTURE. [Online]. Available: https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-tech-docs\/white-papers\/amd-cdna-3-white-paper.pdf."},{"key":"e_1_3_3_2_8_2","unstructured":"AMD. 2023. AMD EPYC 9004 Series Processors BIOS and Workload Tuning Guide. [Online]. Available. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/epyc-technical-docs\/tuning-guides\/58011-epyc-9004-tg-bios-and-workload.pdf"},{"key":"e_1_3_3_2_9_2","unstructured":"AMD. 2024. 5th Gen AMD EPYC Processor Architecture White Paper. [Online]. Available. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/epyc-business-docs\/white-papers\/5th-gen-amd-epyc-processor-architecture-white-paper.pdf"},{"key":"e_1_3_3_2_10_2","unstructured":"AMD. 2024. AMD EPYC 9005 Series Processors BIOS and Workload Tuning Guide. [Online]. Available. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/epyc-technical-docs\/tuning-guides\/58467_amd-epyc-9005-tg-bios-and-workload.pdf"},{"key":"e_1_3_3_2_11_2","unstructured":"AMD. 2024. AMD64 Architecture Programmer\u2019s Manual Volumes 1-5. [Online]. Available: https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/processor-tech-docs\/programmer-references\/40332.pdf."},{"key":"e_1_3_3_2_12_2","unstructured":"AMD. 2024. Unified memory management. [Online]. Available: https:\/\/rocm.docs.amd.com\/projects\/HIP\/en\/docs-develop\/how-to\/hip_runtime_api\/memory_management\/unified_memory.html."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342195.3387518"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080231"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00063"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173169"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00030"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"e_1_3_3_2_20_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 Transactions on Architecture and Code Optimization (TACO) 14 2 Article 14 (June 2017) 25\u00a0pages. 10.1145\/3085572","DOI":"10.1145\/3085572"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00055"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.14165"},{"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":"publisher","DOI":"10.1109\/HPCA.2017.58"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2013.6704684"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037704"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00058"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/2451116.2451157"},{"key":"e_1_3_3_2_30_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731040"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731011"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00065"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322224"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.5555\/2643634.2643659"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00078"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589039"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_40_2","unstructured":"IEEE. 2022. INTERNATIONAL ROADMAP FOR DEVICES AND SYSTEMS. [Online]. Available: https:\/\/irds.ieee.org\/images\/files\/pdf\/2022\/2022IRDS_MM.pdf."},{"key":"e_1_3_3_2_41_2","unstructured":"Intel. 2025. Intel 64 and IA-32 Architectures Software Developer\u2019s Maunal Volume 3 (3A 3B 3C and 3D): System Programming Guide. [Online]. Available: https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/technical\/intel-sdm.html."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Aamer Jaleel Eiman Ebrahimi and Sam Duncan. 2019. DUCATI: High-performance Address Translation by Extending TLB Reach of GPU-accelerated Systems. ACM Transactions on Architecture and Code Optimization (TACO) 16 1 (2019) 1\u201324. 10.1145\/3309710","DOI":"10.1145\/3309710"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676900"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Albert\u00a0Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio\u00a0Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven\u00a0Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William\u00a0El Sayed. 2023. Mistral 7B. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.06825 (2023). 10.48550\/arXiv.2310.06825","DOI":"10.48550\/arXiv.2310.06825"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00070"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623789"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614276"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00086"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00047"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Hyojong Kim Ramyad Hadidi Lifeng Nai Hyesoon Kim Nuwan Jayasena Yasuko Eckert Onur Kayiran and Gabriel Loh. 2018. CODA: Enabling Co-location of Computation and Data for Multiple GPU Systems. ACM Transactions on Architecture and Code Optimization (TACO) 15 3 (2018) 1\u201323. 10.1145\/3232521","DOI":"10.1145\/3232521"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","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 (CAL) 24 2 (2025) 213\u2013216. 10.1109\/LCA.2025.3580264","DOI":"10.1109\/LCA.2025.3580264"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080239"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480105"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00013"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00123"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071063"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614269"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247943"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00031"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071054"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480083"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731047"},{"key":"e_1_3_3_2_64_2","unstructured":"LLVM. 2025. Compiling CUDA with clang. [Online]. Available: https:\/\/llvm.org\/docs\/CompileCudaWithLLVM.html."},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124534"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480088"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070949"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807626"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","unstructured":"Juan Navarro Sitararn Iyer Peter Druschel and Alan Cox. 2003. Practical transparent operating system support for superpages. SIGOPS Oper. Syst. Rev. 36 SI (2003) 89\u2013104. 10.1145\/844128.844138","DOI":"10.1145\/844128.844138"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3433210.3453077"},{"key":"e_1_3_3_2_71_2","unstructured":"NVIDIA. 2017. NVIDIA TESLA V100 GPU ARCHITECTURE. [Online]. Available: https:\/\/images.nvidia.com\/content\/volta-architecture\/pdf\/volta-architecture-whitepaper.pdf."},{"key":"e_1_3_3_2_72_2","unstructured":"NVIDIA. 2020. NVIDIA A100. [Online]. Available: https:\/\/images.nvidia.com\/aem-dam\/en-zz\/Solutions\/data-center\/nvidia-ampere-architecture-whitepaper.pdf."},{"key":"e_1_3_3_2_73_2","volume-title":"Pascal MMU Format Changes","year":"2020","unstructured":"NVIDIA. 2020. Pascal MMU Format Changes. https:\/\/nvidia.github.io\/open-gpu-doc\/pascal\/gp100-mmu-format.pdf"},{"key":"e_1_3_3_2_74_2","unstructured":"NVIDIA. 2023. NVIDIA H100 Tensor Core GPU Architecture. [Online]. Available: https:\/\/resources.nvidia.com\/en-us-tensor-core."},{"key":"e_1_3_3_2_75_2","unstructured":"NVIDIA. 2023. NVIDIA Linux Open GPU Kernel Moudle Source. [Online]. Available: https:\/\/github.com\/NVIDIA\/open-gpu-kernel-modules."},{"key":"e_1_3_3_2_76_2","unstructured":"NVIDIA. 2024. CUDA C\/C++ SDK Code Samples. [Online]. Available: https:\/\/developer.nvidia.com\/cuda-code-samples."},{"key":"e_1_3_3_2_77_2","unstructured":"NVIDIA. 2024. NVIDIA Blackwell Architecture. [Online]. Available: https:\/\/resources.nvidia.com\/en-us-blackwell-architecture."},{"key":"e_1_3_3_2_78_2","unstructured":"NVIDIA. 2024. NVIDIA Blackwell Platform Arrives to Power a New Era of Computing. [Online]. Available: https:\/\/nvidianews.nvidia.com\/news\/nvidia-blackwell-platform-arrives-to-power-a-new-era-of-computing."},{"key":"e_1_3_3_2_79_2","unstructured":"NVIDIA. 2024. NVIDIA Grace Hopper Superchip Architecture Whitepaper. [Online]. Available: https:\/\/resources.nvidia.com\/en-us-grace-cpu\/nvidia-grace-hopper."},{"key":"e_1_3_3_2_80_2","unstructured":"NVIDIA. 2025. NVIDIA NVLink-C2C. [Online]. Available: https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink-c2c\/."},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.26"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446709"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304064"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173203"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056034"},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00029"},{"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":"10.1109\/MICRO56248.2022.00036"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640369"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480062"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00054"},{"key":"e_1_3_3_2_92_2","unstructured":"Nikolay Sakharnykh. 2017. UNIFIED MEMORY ON PASCAL AND VOLTA. NVIDIA GTC (2017)."},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","unstructured":"A. Seznec. 2004. Concurrent Support of Multiple page Sizes on a Skewed Associative TLB. IEEE Transactions on Computers (TC) 53 7 (2004) 924\u2013927. 10.1109\/TC.2004.21","DOI":"10.1109\/TC.2004.21"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00025"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00036"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00068"},{"key":"e_1_3_3_2_97_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. Center for Reliable and High-Performance Computing 127 (2012) 27."},{"key":"e_1_3_3_2_98_2","unstructured":"Synopsys. 2024. Synopsys XSR PHY IP. [Online]. Available: https:\/\/www.synopsys.com\/dw\/ipdir.php?ds=dwc_usr-xsr_phy."},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. LLaMa: Open and Efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023). 10.48550\/arXiv.2302.13971","DOI":"10.48550\/arXiv.2302.13971"},{"key":"e_1_3_3_2_100_2","unstructured":"UMC. 2022. 28 Nanometer. [Online]. Available: https:\/\/www.umc.com\/upload\/media\/05_Press_Center\/3_Literatures\/Process_Technology\/28nm_Brochure.pdf."},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482091"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.42"},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00074"},{"key":"e_1_3_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080205"},{"key":"e_1_3_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00085"},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00124"},{"key":"e_1_3_3_2_107_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00035"},{"key":"e_1_3_3_2_108_2","unstructured":"Z. Bodek. 2014. Transparent Superpages for FreeBSD on ARM. [Online]. Available: https:\/\/www.bsdcan.org\/2014\/schedule\/attachments\/281_2014_arm_superpages-paper.pdf."},{"key":"e_1_3_3_2_109_2","doi-asserted-by":"publisher","unstructured":"Shiqing Zhang Mahmood Naderan-Tahan Magnus Jahre and Lieven Eeckhout. 2023. Characterizing Multi-Chip GPU Data Sharing. ACM Transactions on Architecture and Code Optimization (TACO) 20 4 (2023) 1\u201324. 10.1145\/3629521","DOI":"10.1145\/3629521"},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589078"},{"key":"e_1_3_3_2_111_2","doi-asserted-by":"publisher","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona Diab Xian Li Xi\u00a0Victoria Lin et\u00a0al. 2022. OPT: Open Pre-Trained Transformer Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.01068 (2022). 10.48550\/arXiv.2205.01068","DOI":"10.48550\/arXiv.2205.01068"},{"key":"e_1_3_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575745"},{"key":"e_1_3_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00125"},{"key":"e_1_3_3_2_114_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\/3725843.3756090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:45:36Z","timestamp":1769463936000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":113,"alternative-id":["10.1145\/3725843.3756090","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756090","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"}}]}}