{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:14:15Z","timestamp":1784906055313,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T00:00:00Z","timestamp":1739923200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725."],"award-info":[{"award-number":["DE-AC05-00OR22725."]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,19]]},"DOI":"10.1145\/3703001.3724383","type":"proceedings-article","created":{"date-parts":[[2025,4,19]],"date-time":"2025-04-19T10:29:56Z","timestamp":1745058596000},"page":"11-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Preliminary Study on Fine-Grained Power and Energy Measurements on Grace Hopper GH200 with Open-Source Performance Tools"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5380-6951","authenticated-orcid":false,"given":"Oscar","family":"Hernandez","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2491-5323","authenticated-orcid":false,"given":"Thomas","family":"Wang","sequence":"additional","affiliation":[{"name":"Camas High School, Camas, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0554-1036","authenticated-orcid":false,"given":"Wael","family":"Elwasif","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1448-5304","authenticated-orcid":false,"given":"Filippo","family":"Spiga","sequence":"additional","affiliation":[{"name":"NVIDIA Ltd, Cambridge, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5160-2664","authenticated-orcid":false,"given":"Francesca","family":"Tartaglione","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation, Santa Clara, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8805-8327","authenticated-orcid":false,"given":"Markus","family":"Eisenbach","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2179-495X","authenticated-orcid":false,"given":"Ross","family":"Miller","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,19]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2024. Linaro MAP: High-Performance Profiling and Analysis Tool. https:\/\/www.linaroforge.com\/linaro-map\/ Accessed: 2024-12-24."},{"key":"e_1_3_3_2_3_2","unstructured":"AMD. 2024. AMD Omnitrace Documentation. https:\/\/rocm.docs.amd.com\/projects\/omnitrace\/en\/latest\/doxygen\/html\/index.html. https:\/\/rocm.docs.amd.com\/projects\/omnitrace\/en\/latest\/doxygen\/html\/index.html Accessed: 2024-12-25."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00062"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607089"},{"key":"e_1_3_3_2_6_2","volume-title":"An Introduction to Numerical Analysis","author":"Atkinson Kendall\u00a0E.","year":"1989","unstructured":"Kendall\u00a0E. Atkinson. 1989. An Introduction to Numerical Analysis. John Wiley & Sons."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/HUST56722.2022.00011"},{"key":"e_1_3_3_2_8_2","unstructured":"NVIDIA Corporation. 2024. NVIDIA Data Center GPU Manager (DCGM). https:\/\/developer.nvidia.com\/dcgm. https:\/\/developer.nvidia.com\/dcgm Accessed: 2024-12-25."},{"key":"e_1_3_3_2_9_2","unstructured":"NVIDIA Corporation. 2024. NVML Power and Temperature Metrics - Nsight Systems User Guide. https:\/\/docs.nvidia.com\/nsight-systems\/UserGuide\/index.html#nvml-power-and-temperature-metrics-preview Accessed: 2024-12-21."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00061"},{"key":"e_1_3_3_2_11_2","unstructured":"Naresh Dulam Abhilash Katari and Kishore\u00a0Reddy Gade. 2017. Apache Arrow: Optimizing Data Interchange in Big Data Systems. Distributed Learning and Broad Applications in Scientific Research 3 (2017) 93\u2013114."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Markus Eisenbach Jeff Larkin Justin Lutjens Steven Rennich and James\u00a0H. Rogers. 2017. GPU acceleration of the Locally Selfconsistent Multiple Scattering code for first principles calculation of the ground state and statistical physics of materials. Computer Physics Communications 211 (2017) 2\u20137. 10.1016\/j.cpc.2016.07.013High Performance Computing for Advanced Modeling and Simulation of Materials.","DOI":"10.1016\/j.cpc.2016.07.013"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-61499-041-3-481"},{"key":"e_1_3_3_2_14_2","unstructured":"Argonne Leadership\u00a0Computing Facility. 2024. THAPI: Tracing Heterogeneous APIs. https:\/\/github.com\/argonne-lcf\/THAPI Accessed: 2024-12-24."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Markus Geimer Felix Wolf Brian\u00a0JN Wylie Erika \u00c1brah\u00e1m Daniel Becker and Bernd Mohr. 2010. The Scalasca performance toolset architecture. Concurrency and computation: Practice and experience 22 6 (2010) 702\u2013719.","DOI":"10.1002\/cpe.1556"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2916026.2916033"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Heike Jagode Anthony Danalis Giuseppe Congiu Daniel Barry Anthony Castaldo and Jack Dongarra. 2024. Advancements of PAPI for the exascale generation. The International Journal of High Performance Computing Applications (2024) 10943420241303884.","DOI":"10.1177\/10943420241303884"},{"key":"e_1_3_3_2_18_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_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31476-6_7"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21867-5_1"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Adam Krzywaniak and Pawel Czarnul. 2023. Dynamic GPU Power Capping with Online Performance Tracing. Future Generation Computer Systems 145 (2023) 396\u2013414.","DOI":"10.1016\/j.future.2023.03.041"},{"key":"e_1_3_3_2_22_2","volume-title":"Variorum Documentation","author":"Laboratories Sandia\u00a0National","year":"2024","unstructured":"Sandia\u00a0National Laboratories. 2024. Variorum Documentation. https:\/\/variorum.readthedocs.io\/en\/latest\/ Accessed: 2024-12-24."},{"key":"e_1_3_3_2_23_2","volume-title":"Cray User Group Conference Proceedings","author":"Martin Steven\u00a0J","year":"2014","unstructured":"Steven\u00a0J Martin and Matthew Kappel. 2014. Cray XC30 power monitoring and management. In Cray User Group Conference Proceedings."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Joseph Meyer Reza Moghimi and Noah Sturcken. 2019. Package Voltage Regulators: The Answer for Power Management Challenges. IMAPSource Proceedings 2019 1 (oct 1 2019) 438\u2013443. 10.4071\/2380-4505-2019.1.000438","DOI":"10.4071\/2380-4505-2019.1.000438"},{"key":"e_1_3_3_2_25_2","unstructured":"NVIDIA Corporation. 2023. Grace Hopper Superchip Performance Tuning Guide. https:\/\/docs.nvidia.com\/grace-perf-tuning-guide\/index.html#power-telemetry Accessed: 2024-12-18."},{"key":"e_1_3_3_2_26_2","unstructured":"NVIDIA Corporation. 2024. NVIDIA Management Library (NVML) API Documentation: Device Queries. https:\/\/docs.nvidia.com\/deploy\/nvml-api\/group__nvmlDeviceQueries.html#group__nvmlDeviceQueries_1g7ef7dff0ff14238d08a19ad7fb23fc87 Accessed: 2024-12-19."},{"key":"e_1_3_3_2_27_2","volume-title":"CUDA Profiling Tools Interface (CUPTI) Documentation","author":"Corporation NVIDIA","year":"2025","unstructured":"NVIDIA Corporation. 2025. CUDA Profiling Tools Interface (CUPTI) Documentation. https:\/\/docs.nvidia.com\/cupti\/index.html."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Pavel Saviankou Michael Knobloch Anke Visser and Bernd Mohr. 2015. Cube v4: From performance report explorer to performance analysis tool. Procedia Computer Science 51 (2015) 1343\u20131352.","DOI":"10.1016\/j.procs.2015.05.320"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56702-0_4"},{"key":"e_1_3_3_2_30_2","unstructured":"Sameer Shende and Allen\u00a0D Malony. 2011. TAU: Performance Analysis and Tuning. Innovative Parallel Computing (InPar) (2011)."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Sameer\u00a0S Shende and Allen\u00a0D Malony. 2006. The TAU parallel performance system. The International Journal of High Performance Computing Applications 20 2 (2006) 287\u2013311.","DOI":"10.1177\/1094342006064482"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624272"},{"key":"e_1_3_3_2_33_2","unstructured":"Supermicro. 2025. NVIDIA GH200 Grace Hopper Superchip system supporting NVIDIA BlueField-3 or NVIDIA ConnectX-7. https:\/\/www.supermicro.com\/en\/products\/system\/gpu\/1u\/ars-111gl-nhr Accessed: 2025-01-13."},{"key":"e_1_3_3_2_34_2","unstructured":"Vince Weaver. 2012. New features in the PAPI 5.0 release. University of Tennessee Tech. Rep (2012)."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-17872-7_7"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Zeyu Yang Karel Adamek and Wesley Armour. 2024. Accurate and Convenient Energy Measurements for GPUs: A Detailed Study of NVIDIA GPU\u2019s Built-In Power Sensor(SC \u201924). IEEE Press Article 22 17\u00a0pages. 10.1109\/SC41406.2024.00028","DOI":"10.1109\/SC41406.2024.00028"}],"event":{"name":"HPCASIA '25: 2025 International Conference on High Performance Computing in Asia-Pacific Region Workshops Proceedings","location":"Hsinchu Taiwan","acronym":"HPCASIA '25"},"container-title":["Proceedings of the 2025 International Conference on High Performance Computing in Asia-Pacific Region Workshops"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703001.3724383","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703001.3724383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:18Z","timestamp":1750295418000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703001.3724383"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,19]]},"references-count":35,"alternative-id":["10.1145\/3703001.3724383","10.1145\/3703001"],"URL":"https:\/\/doi.org\/10.1145\/3703001.3724383","relation":{},"subject":[],"published":{"date-parts":[[2025,2,19]]},"assertion":[{"value":"2025-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}