{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:25:06Z","timestamp":1770348306292,"version":"3.49.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032076113","type":"print"},{"value":"9783032076120","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-07612-0_14","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:33Z","timestamp":1763920653000},"page":"177-190","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Characterizing GPU Energy Usage in\u00a0Exascale-Ready Portable Science Applications"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2590-5178","authenticated-orcid":false,"given":"William F.","family":"Godoy","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5380-6951","authenticated-orcid":false,"given":"Oscar","family":"Hernandez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5539-4017","authenticated-orcid":false,"given":"Paul R. C.","family":"Kent","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3975-4638","authenticated-orcid":false,"given":"Maria","family":"Patrou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4004-4791","authenticated-orcid":false,"given":"Kazi","family":"Asifuzzaman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8259-8891","authenticated-orcid":false,"given":"Narasinga Rao","family":"Miniskar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1479-4310","authenticated-orcid":false,"given":"Pedro","family":"Valero-Lara","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-6720","authenticated-orcid":false,"given":"Jeffrey S.","family":"Vetter","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0189-7895","authenticated-orcid":false,"given":"Matthew D.","family":"Sinclair","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8880-8703","authenticated-orcid":false,"given":"Jason","family":"Lowe-Power","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6070-9722","authenticated-orcid":false,"given":"Bobby R.","family":"Bruce","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","unstructured":"Almgren, A., et\u00a0al.: Castro: a massively parallel compressible astrophysics simulation code. JOSS 5(54) (2020). https:\/\/doi.org\/10.21105\/joss.02513","DOI":"10.21105\/joss.02513"},{"key":"14_CR2","doi-asserted-by":"publisher","unstructured":"Besard, T., et\u00a0al.: Effective extensible programming: unleashing julia on GPUs. IEEE TPDS 30(4) (2019). https:\/\/doi.org\/10.1109\/TPDS.2018.2872064","DOI":"10.1109\/TPDS.2018.2872064"},{"issue":"1","key":"14_CR3","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1137\/141000671","volume":"59","author":"J Bezanson","year":"2017","unstructured":"Bezanson, J., et al.: Julia: a fresh approach to numerical computing. SIAM Rev. 59(1), 65\u201398 (2017). https:\/\/doi.org\/10.1137\/141000671","journal-title":"SIAM Rev."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Bridges, R.A., Imam, N., Mintz, T.M.: Understanding GPU power: a survey of profiling, modeling, and simulation methods. ACM Comput. Surv. 49(3) (2016)","DOI":"10.1145\/2962131"},{"key":"14_CR5","doi-asserted-by":"publisher","unstructured":"Corda, S., et\u00a0al.: Pmt: power measurement toolkit. In: IEEE\/ACM HUST Workshop (2022). https:\/\/doi.org\/10.1109\/HUST56722.2022.00011","DOI":"10.1109\/HUST56722.2022.00011"},{"key":"14_CR6","doi-asserted-by":"publisher","unstructured":"Elwasif, W., et\u00a0al.: Application experiences on a GPU-accelerated arm-based HPC testbed. In: Proceedings of the HPC Asia 2023 Workshops. p. 35\u201349. HPCAsia \u201923 Workshops, Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3581576.3581621","DOI":"10.1145\/3581576.3581621"},{"key":"14_CR7","doi-asserted-by":"publisher","unstructured":"Foster, B., et\u00a0al.: Evaluating energy efficiency of GPUs using ML benchmarks. In: IPDPSW (2023). https:\/\/doi.org\/10.1109\/IPDPSW59300.2023.00019","DOI":"10.1109\/IPDPSW59300.2023.00019"},{"key":"14_CR8","doi-asserted-by":"publisher","unstructured":"Godoy, W.F., et\u00a0al.: Modeling pre-exascale AMR Parallel I\/O workloads via proxy applications. In: IPDPSW (2022). https:\/\/doi.org\/10.1109\/IPDPSW55747.2022.00153","DOI":"10.1109\/IPDPSW55747.2022.00153"},{"key":"14_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2024.107502","volume":"163","author":"WF Godoy","year":"2025","unstructured":"Godoy, W.F., et al.: Software stewardship and advancement of a high-performance computing scientific application: QMCPACK. FGCS 163, 107502 (2025)","journal-title":"FGCS"},{"key":"14_CR10","doi-asserted-by":"publisher","unstructured":"Govind, A., et\u00a0al.: Comparing power signatures of HPC workloads: machine learning vs simulation. In: SC-W (2023). https:\/\/doi.org\/10.1145\/3624062.3624274","DOI":"10.1145\/3624062.3624274"},{"key":"14_CR11","doi-asserted-by":"publisher","unstructured":"Guti\u00e9rrez Hermosillo\u00a0Muriedas, J.P., et\u00a0al.: Perun: benchmarking energy consumption of high-performance computing applications. In: Euro-Par (2023). https:\/\/doi.org\/10.1007\/978-3-031-39698-4_2","DOI":"10.1007\/978-3-031-39698-4_2"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Kandiah, V., et\u00a0al.: AccelWattch: a power modeling framework for modern GPUs. In: MICRO (October 2021)","DOI":"10.1145\/3466752.3480063"},{"key":"14_CR13","doi-asserted-by":"publisher","unstructured":"Karimi, A.M., et\u00a0al.: Power profile monitoring and tracking evolution of system-wide HPC workloads. In: ICDCS (2024). https:\/\/doi.org\/10.1109\/ICDCS60910.2024.00018","DOI":"10.1109\/ICDCS60910.2024.00018"},{"key":"14_CR14","doi-asserted-by":"publisher","unstructured":"Kent, P.R.C., et al.: QMCPACK: advances in the development, efficiency, and application of auxiliary field and real-space variational and diffusion quantum Monte Carlo. J. Chem. Phys. 152(17) (2020). https:\/\/doi.org\/10.1063\/5.0004860","DOI":"10.1063\/5.0004860"},{"issue":"19","key":"14_CR15","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/aab9c3","volume":"30","author":"J Kim","year":"2018","unstructured":"Kim, J., et al.: QMCPACK: an open source ab initio quantum Monte Carlo package for the electronic structure of atoms, molecules and solids. J. Phys. Cond Matter 30(19), 195901 (2018)","journal-title":"J. Phys. Cond Matter"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Kothe, D., et\u00a0al.: Exascale computing in the united states. CiSE 21(1) (2019)","DOI":"10.1109\/MCSE.2018.2875366"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Lee, W., et\u00a0al.: PowerTrain: a learning-based calibration of McPAT power models. In: ISLPED, pp. 189\u2013194 (2015)","DOI":"10.1109\/ISLPED.2015.7273512"},{"key":"14_CR18","unstructured":"Lowe-Power, J., et\u00a0al.: The gem5 simulator: V20.0 (2020). https:\/\/arxiv.org\/abs\/2007.03152"},{"key":"14_CR19","doi-asserted-by":"publisher","unstructured":"Luo, Y., Doak, P., Kent, P.: A high-performance design for hierarchical parallelism in the QMCPACK Monte Carlo code. In: SC-W HiPar (2022). https:\/\/doi.org\/10.1109\/HiPar56574.2022.00008","DOI":"10.1109\/HiPar56574.2022.00008"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Mantovani, F., et\u00a0al.: Performance and energy consumption of HPC workloads on a cluster based on Arm ThunderX2 CPU. FGCS 112 (2020)","DOI":"10.1016\/j.future.2020.06.033"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Mittal, S., Vetter, J.S.: A survey of methods for analyzing and improving GPU energy efficiency. ACM Comput. Surv. 47(2) (2014)","DOI":"10.1145\/2636342"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Myers, A., et al.: AMReX and pyAMReX: looking beyond the exascale computing project. IJHPCA 38(6) (2024). https:\/\/doi.org\/10.1177\/10943420241271017","DOI":"10.1177\/10943420241271017"},{"key":"14_CR23","unstructured":"Reed, D., Gannon, D., Dongarra, J.: Reinventing high performance computing: challenges and opportunities (2022). https:\/\/arxiv.org\/abs\/2203.02544"},{"key":"14_CR24","doi-asserted-by":"publisher","unstructured":"Rrapaj, E., et\u00a0al.: Power consumption trends in supercomputers: a study of NERSC\u2019s Cori and perlmutter machines. In: ISC (2024). https:\/\/doi.org\/10.23919\/ISC.2024.10528943","DOI":"10.23919\/ISC.2024.10528943"},{"key":"14_CR25","doi-asserted-by":"publisher","unstructured":"Schieffer, G., et\u00a0al.: On the rise of AMD matrix cores: performance, power efficiency, and programmability. In: ISPASS (2024). https:\/\/doi.org\/10.1109\/ISPASS61541.2024.00022","DOI":"10.1109\/ISPASS61541.2024.00022"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Shim, J.S., et\u00a0al.: DeepPM: transformer-based power and performance prediction for energy-aware software. In: DATE, pp. 1491\u20131496 (2022)","DOI":"10.23919\/DATE54114.2022.9774589"},{"key":"14_CR27","doi-asserted-by":"publisher","unstructured":"Shin, W., et\u00a0al.: Towards sustainable post-exascale leadership computing. In: SC-W (2024). https:\/\/doi.org\/10.1109\/SCW63240.2024.00225","DOI":"10.1109\/SCW63240.2024.00225"},{"key":"14_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2023.114019","volume":"189","author":"C Silva","year":"2024","unstructured":"Silva, C., et al.: A review on the decarbonization of high-performance computing centers. Renew. Sustain. Energy Rev. 189, 114019 (2024)","journal-title":"Renew. Sustain. Energy Rev."},{"key":"14_CR29","doi-asserted-by":"publisher","unstructured":"Simsek, O.S., et\u00a0al.: Accurate measurement of application-level energy consumption for energy-aware large-scale simulations. In: SC-W (2023). https:\/\/doi.org\/10.1145\/3624062.3624272","DOI":"10.1145\/3624062.3624272"},{"key":"14_CR30","doi-asserted-by":"publisher","unstructured":"Simsek, O.S., et\u00a0al.: Increasing energy efficiency of astrophysics simulations through GPU frequency scaling. In: SC-W (2024). https:\/\/doi.org\/10.1109\/SCW63240.2024.00229","DOI":"10.1109\/SCW63240.2024.00229"},{"key":"14_CR31","unstructured":"Smith, A., et\u00a0al.: Designing generalizable power models for open-source architecture simulators. In: OSCAR (2024)"},{"key":"14_CR32","doi-asserted-by":"publisher","unstructured":"Vetter, J.S., et\u00a0al.: Productive computational science in the era of extreme heterogeneity. Tech. rep., USDOE Office of Science (SC), Washington, D.C. (United States) (2018). https:\/\/doi.org\/10.2172\/1473756","DOI":"10.2172\/1473756"},{"key":"14_CR33","doi-asserted-by":"publisher","unstructured":"Wu, G., et\u00a0al.: GPGPU performance and power estimation using machine learning. In: HPCA, pp. 564\u2013576 (2015). https:\/\/doi.org\/10.1109\/HPCA.2015.7056063","DOI":"10.1109\/HPCA.2015.7056063"},{"key":"14_CR34","doi-asserted-by":"publisher","unstructured":"Yang, Z., et\u00a0al.: Accurate and convenient energy measurements for GPUs: a detailed study of NVIDIA GPU\u2019s built-in power sensor. In: SC24 (2024). https:\/\/doi.org\/10.1109\/SC41406.2024.00028","DOI":"10.1109\/SC41406.2024.00028"},{"key":"14_CR35","doi-asserted-by":"publisher","unstructured":"Yang, Z., et\u00a0al.: Accurate and convenient energy measurements for GPUs: a detailed study of NVIDIA GPU\u2019s built-in power sensor. In: SC (2024). https:\/\/doi.org\/10.1109\/SC41406.2024.00028","DOI":"10.1109\/SC41406.2024.00028"},{"key":"14_CR36","doi-asserted-by":"publisher","unstructured":"Zhang, W., et\u00a0al.: AMReX: a framework for block-structured adaptive mesh refinement. JOSS 4(37) (2019). https:\/\/doi.org\/10.21105\/joss.01370","DOI":"10.21105\/joss.01370"},{"key":"14_CR37","doi-asserted-by":"publisher","unstructured":"Zhao, Z., et\u00a0al.: Understanding VASP Power Profiles on NVIDIA A100 GPUs. In: SC-W (2024). https:\/\/doi.org\/10.1109\/SCW63240.2024.00189","DOI":"10.1109\/SCW63240.2024.00189"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07612-0_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:35Z","timestamp":1763920655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07612-0_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032076113","9783032076120"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07612-0_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}