{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:24:37Z","timestamp":1783099477079,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759879","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:04:47Z","timestamp":1762963487000},"page":"505-518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Minimizing Power Waste in Heterogenous Computing via Adaptive Uncore Scaling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6617-649X","authenticated-orcid":false,"given":"Zhong","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Illinois Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4948-7811","authenticated-orcid":false,"given":"Seyfal","family":"Sultanov","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6418-5767","authenticated-orcid":false,"given":"Michael E.","family":"Papka","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory (ANL), Lemont, USA and University of Illinois Chicago, Chicago, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1047-8724","authenticated-orcid":false,"given":"Zhiling","family":"Lan","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago, Chicago, USA and Argonne National Laboratory (ANL), Lemont, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"2025. ECP proxy apps suite. https:\/\/proxyapps.exascaleproject.org\/ ecp- proxy- apps- suite\/."},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605600"},{"key":"e_1_3_3_3_4_2","unstructured":"AMD. 2024. 5TH GEN AMD EPYC\u2122 PROCESSOR ARCHITECTURE. \"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_3_5_2","unstructured":"AMD. 2025. AMD HSMP. \"https:\/\/github.com\/amd\/amd_hsmp\"."},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"crossref","unstructured":"\u00c9tienne Andr\u00e9 R\u00e9mi Dulong Amina Guermouche and Fran\u00e7ois Trahay. 2022. DUF: Dynamic Uncore Frequency scaling to reduce power consumption. Concurrency and Computation: Practice and Experience 34 3 (2022) e6580.","DOI":"10.1002\/cpe.6580"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"crossref","unstructured":"\u00c9tienne Andr\u00e9 R\u00e9mi Dulong Amina Guermouche and Fran\u00e7ois Trahay. 2022. duf: Dynamic uncore frequency scaling to reduce power consumption. Concurrency and Computation: Practice and Experience 34 3 (2022) e6580.","DOI":"10.1002\/cpe.6580"},{"key":"e_1_3_3_3_8_2","unstructured":"ARM. 2024. Add an uncore peripheral to Streamline. \"https:\/\/developer.arm.com\/documentation\/101814\/0904\/Customize-your-Streamline-report\/Add-an-uncore-peripheral-to-Streamline\"."},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00063"},{"key":"e_1_3_3_3_10_2","unstructured":"Large-scale Atomic and Molecular Massively\u00a0Parallel Simulator. 2013. Lammps. available at: http:\/lammps. sandia. gov (2013)."},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807637"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.114"},{"key":"e_1_3_3_3_13_2","unstructured":"Martha Broyles Chris Francois Andrew Geissler Michael Hollinger Todd Rosedahl Guillermo Silva Jeff Van\u00a0Heuklon and Brian Veale. 2010. IBM energyscale for POWER7 processor-based systems. white paper IBM (2010)."},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605586"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2747916"},{"key":"e_1_3_3_3_16_2","first-page":"851","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Choi Sangjin","year":"2023","unstructured":"Sangjin Choi, Inhoe Koo, Jeongseob Ahn, Myeongjae Jeon, and Youngjin Kwon. 2023. { EnvPipe} : Performance-preserving { DNN} training framework for saving energy. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 851\u2013864."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/1998582.1998590"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/1840845.1840883"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607091"},{"key":"e_1_3_3_3_20_2","unstructured":"L.\u00a0K. Documentation.2024. Intel p-state driver [Online]. \"https:\/\/www.kernel.org\/doc\/Documentation\/cpu-freq\/intel-pstate.txt\"."},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337833"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC54614.2021.00009"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/1065944.1065967"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2007.29"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356150"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942147"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00164"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00072"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Jo\u00e3o Guerreiro Aleksandar Ilic Nuno Roma and Pedro Tom\u00e1s. 2019. DVFS-aware application classification to improve GPGPUs energy efficiency. Parallel Comput. 83 (2019) 93\u2013117.","DOI":"10.1016\/j.parco.2018.02.001"},{"key":"e_1_3_3_3_30_2","first-page":"367","volume-title":"2012 USENIX Annual Technical Conference (USENIX ATC 12)","author":"Gupta Vishal","year":"2012","unstructured":"Vishal Gupta, Paul Brett, David Koufaty, Dheeraj Reddy, Scott Hahn, Karsten Schwan, and Ganapati Srinivasa. 2012. The Forgotten { \u2018Uncore\u2019} : On the { Energy-Efficiency} of Heterogeneous Cores. In 2012 USENIX Annual Technical Conference (USENIX ATC 12). 367\u2013372."},{"key":"e_1_3_3_3_31_2","unstructured":"David\u00a0L Hill Derek Bachand Selim Bilgin Robert Greiner Per Hammarlund Thomas Huff Steve Kulick and Robert Safranek. 2010. THE UNCORE: A MODULAR APPROACH TO FEEDING THE HIGH-PERFORMANCE CORES. Intel Technology Journal 14 3 (2010)."},{"key":"e_1_3_3_3_32_2","first-page":"1","volume-title":"SC\u201905: Proceedings of the 2005 ACM\/IEEE Conference on Supercomputing","author":"Hsu Chung-hsing","year":"2005","unstructured":"Chung-hsing Hsu and Wu-chun Feng. 2005. A power-aware run-time system for high-performance computing. In SC\u201905: Proceedings of the 2005 ACM\/IEEE Conference on Supercomputing. IEEE, 1\u20131."},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00011"},{"key":"e_1_3_3_3_34_2","unstructured":"Intel. 2025. Intel oneAPI. \"https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/overview.html\"."},{"key":"e_1_3_3_3_35_2","unstructured":"Intel. 2025. Intel Performance Counter Monitor. \"https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/tool\/performance-counter-monitor.html\"."},{"key":"e_1_3_3_3_36_2","unstructured":"Paul Jaccard. 1901. \u00c9tude comparative de la distribution florale dans une portion des Alpes et des Jura. Bull Soc Vaudoise Sci Nat 37 (1901) 547\u2013579."},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480063"},{"key":"e_1_3_3_3_38_2","volume-title":"Proceedings of the Humans in the Loop: Enabling and Facilitating Research on Cloud Computing","author":"Kate Keahey","year":"2019","unstructured":"Keahey Kate, Jason Anderson, Paul Ruth, Jcob Colleran, Cody Hammock, Joe Stubbs, and Zhou Zhen. 2019. Operational lessons from Chameleon. In Proceedings of the Humans in the Loop: Enabling and Facilitating Research on Cloud Computing."},{"key":"e_1_3_3_3_39_2","first-page":"219","volume-title":"2020 USENIX annual technical conference (USENIX ATC 20)","author":"Keahey Kate","year":"2020","unstructured":"Kate Keahey, Jason Anderson, Zhuo Zhen, Pierre Riteau, Paul Ruth, Dan Stanzione, Mert Cevik, Jacob Colleran, Haryadi\u00a0S Gunawi, Cody Hammock, et\u00a0al. 2020. Lessons learned from the chameleon testbed. In 2020 USENIX annual technical conference (USENIX ATC 20). 219\u2013233."},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Kashif\u00a0Nizam Khan Mikael Hirki Tapio Niemi Jukka\u00a0K Nurminen and Zhonghong Ou. 2018. Rapl in action: Experiences in using rapl for power measurements. ACM Transactions on Modeling and Performance Evaluation of Computing Systems (TOMPECS) 3 2 (2018) 1\u201326.","DOI":"10.1145\/3177754"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21867-5_1"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43222-5_11"},{"key":"e_1_3_3_3_43_2","unstructured":"Argonne\u00a0National Laboratory. 2025. Aurora. \"https:\/\/www.alcf.anl.gov\/aurora\"."},{"key":"e_1_3_3_3_44_2","unstructured":"Yuzhuo Li and Yunwei Li. 2025. AI Load Dynamics\u2013A Power Electronics Perspective. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01647 (2025)."},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2006.11"},{"key":"e_1_3_3_3_46_2","unstructured":"Linux. 2024. perf \u2014 Linux manual page. \"https:\/\/man7.org\/linux\/man-pages\/man1\/perf.1.html\"."},{"key":"e_1_3_3_3_47_2","unstructured":"Linux. 2024. sysfs \u2014 Linux manual page. \"https:\/\/man7.org\/linux\/man-pages\/man5\/sysfs.5.html\"."},{"key":"e_1_3_3_3_48_2","unstructured":"LLNL. 2025. CRADL. \"https:\/\/github.com\/LLNL\/CRADL\"."},{"key":"e_1_3_3_3_49_2","unstructured":"LLNL. 2025. Laghos. \"https:\/\/github.com\/CEED\/Laghos\"."},{"key":"e_1_3_3_3_50_2","unstructured":"LLNL. 2025. sw4lite. \"https:\/\/github.com\/geodynamics\/sw4lite\"."},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"crossref","unstructured":"H-Y McCreary Martha\u00a0A Broyles Michael\u00a0S Floyd Andrew\u00a0J Geissler Steven\u00a0P Hartman Freeman\u00a0L Rawson Todd\u00a0J Rosedahl Juan\u00a0C Rubio and Malcolm\u00a0S Ware. 2007. EnergyScale for IBM POWER6 microprocessor-based systems. IBM Journal of Research and Development 51 6 (2007) 775\u2013786.","DOI":"10.1147\/rd.516.0775"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"crossref","unstructured":"Paul Messina. 2017. The USDOE Exascale Computing Project\u2013Goals and Challenges.","DOI":"10.1109\/MCSE.2017.57"},{"key":"e_1_3_3_3_53_2","unstructured":"NVIDIA. 2024. nvidia-smi. \"https:\/\/developer.download.nvidia.com\/compute\/DCGM\/docs\/nvidia-smi-367.38.pdf\"."},{"key":"e_1_3_3_3_54_2","unstructured":"Nvidia. 2025. NVML. \"https:\/\/developer.nvidia.com\/management-library-nvml\"."},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.5555\/2971808.2971918"},{"key":"e_1_3_3_3_56_2","unstructured":"N. Pitre.2024. Teaching the scheduler about power management [Online]. \"https:\/\/lwn.net\/Articles\/603254\/\"."},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSA-C63560.2024.00049"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00088"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"crossref","unstructured":"\u00c1lvaro\u00a0Domingo Reguero Silverio Mart\u00ednez-Fern\u00e1ndez and Roberto Verdecchia. 2025. Energy-efficient neural network training through runtime layer freezing model quantization and early stopping. Computer Standards & Interfaces 92 (2025) 103906.","DOI":"10.1016\/j.csi.2024.103906"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"crossref","unstructured":"Vaibhav Sundriyal Masha Sosonkina Bryce Westheimer and Mark Gordon. 2018. Core and uncore joint frequency scaling strategy. Journal of Computer and Communications 6 12 (2018) 184\u2013201.","DOI":"10.4236\/jcc.2018.612018"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"crossref","unstructured":"David Van Der\u00a0Spoel Erik Lindahl Berk Hess Gerrit Groenhof Alan\u00a0E Mark and Herman\u00a0JC Berendsen. 2005. GROMACS: fast flexible and free. Journal of computational chemistry 26 16 (2005) 1701\u20131718.","DOI":"10.1002\/jcc.20291"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2018.00013"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"crossref","unstructured":"Sean Wallace Zhou Zhou Venkatram Vishwanath Susan Coghlan John Tramm Zhiling Lan and Michael\u00a0E Papka. 2016. Application power profiling on IBM Blue Gene\/Q. Parallel Comput. 57 (2016) 73\u201386.","DOI":"10.1016\/j.parco.2016.05.015"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"crossref","unstructured":"Qiang Wang and Xiaowen Chu. 2020. GPGPU performance estimation with core and memory frequency scaling. IEEE Transactions on Parallel and Distributed Systems 31 12 (2020) 2865\u20132881.","DOI":"10.1109\/TPDS.2020.3004623"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2012.39"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624542"},{"key":"e_1_3_3_3_68_2","first-page":"119","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"You Jie","year":"2023","unstructured":"Jie You, Jae-Won Chung, and Mosharaf Chowdhury. 2023. Zeus: Understanding and optimizing { GPU} energy consumption of { DNN} training. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 119\u2013139."},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER59578.2024.00026"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:49:47Z","timestamp":1773254987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759879"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":68,"alternative-id":["10.1145\/3712285.3759879","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759879","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}