{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:47:03Z","timestamp":1781884023685,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100011923","name":"KDDI Foundation","doi-asserted-by":"publisher","award":["None"],"award-info":[{"award-number":["None"]}],"id":[{"id":"10.13039\/501100011923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3545008.3545084","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T01:04:08Z","timestamp":1673744648000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Analyzing Performance and Power-Efficiency Variations among NVIDIA GPUs"],"prefix":"10.1145","author":[{"given":"Kohei","family":"Yoshida","sequence":"first","affiliation":[{"name":"The University of Electro-Communications, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rio","family":"Sageyama","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinobu","family":"Miwa","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayato","family":"Yamaki","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroki","family":"Honda","sequence":"additional","affiliation":[{"name":"The University of Electro-Communications, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium (IPDPS). 113\u2013122","author":"Abe Y.","unstructured":"Y. Abe, H. Sasaki, S. Kato, K. Inoue, M. Edahiro, and M. Peres. 2014. Power and Performance Characterization and Modeling of GPU-Accelerated Systems. In Proceedings of the 2014 IEEE 28th International Parallel and Distributed Processing Symposium (IPDPS). 113\u2013122."},{"key":"e_1_3_2_1_2_1","volume-title":"Power Aware Heterogeneous Node Assembly. In 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). 715\u2013727","author":"Acun Bilge","year":"2019","unstructured":"Bilge Acun, Alper Buyuktosunoglu, Eun\u00a0Kyung Lee, and Yoonho Park. 2019. Power Aware Heterogeneous Node Assembly. In 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). 715\u2013727."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926289"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/PMBS54543.2021.00011"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/40.782564"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330372"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2010.2080550"},{"key":"e_1_3_2_1_9_1","volume-title":"2017 Annual Report. Internet:www.r-ccs.riken.jp\/wp-content\/uploads\/2019\/08\/Flagship_2020_Project_2017.pdf([Nov 16","author":"Project Flagship","year":"2019","unstructured":"Flagship 2020 Project. [Nov 16, 2019]. 2017 Annual Report. Internet:www.r-ccs.riken.jp\/wp-content\/uploads\/2019\/08\/Flagship_2020_Project_2017.pdf([Nov 16, 2019])."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2766151"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2627369.2627659"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3104-7"},{"key":"e_1_3_2_1_13_1","volume-title":"Node Power Consumption Variability. In Energy-Efficient HPC WG Workshop.","author":"Hackenberg Daniel","year":"2014","unstructured":"Daniel Hackenberg. 2014. Node Power Consumption Variability. In Energy-Efficient HPC WG Workshop."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807638"},{"key":"e_1_3_2_1_15_1","volume-title":"Power-aware and Temperature Restrain Modeling for Maximizing Performance and Reliability. In DoE Workshop on Modeling and Simulation of Exascale Systems and Applications (MODSIM).","author":"Kale Laxmikant","year":"2014","unstructured":"Laxmikant Kale, Akhil Langer, and Osman Sarood. 2014. Power-aware and Temperature Restrain Modeling for Maximizing Performance and Reliability. In DoE Workshop on Modeling and Simulation of Exascale Systems and Applications (MODSIM)."},{"key":"e_1_3_2_1_16_1","volume-title":"Evaluation of Power Management Control on the Supercomputer Fugaku. In 2020 IEEE International Conference on Cluster Computing (CLUSTER). 484\u2013493","author":"Kodama Yuetsu","year":"2020","unstructured":"Yuetsu Kodama, Tetsuya Odajima, Eishi Arima, and Mitsuhisa Sato. 2020. Evaluation of Power Management Control on the Supercomputer Fugaku. In 2020 IEEE International Conference on Cluster Computing (CLUSTER). 484\u2013493."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3149412.3149421"},{"key":"e_1_3_2_1_18_1","volume-title":"An empirical survey of performance and energy efficiency variation on several generations of Intel processors","author":"Marathe A","unstructured":"A Marathe, Y Zhang, G Blanks, N Kumbhare, G Abdulla, and B Rountree. 2017. An empirical survey of performance and energy efficiency variation on several generations of Intel processors. Technical Report. Lawrence Livermore National Lab.(LLNL), Livermore, CA (United States)."},{"key":"e_1_3_2_1_19_1","volume-title":"Exascale Computing Project. In The 2016 International Conference for High Performance Computing, Networking, Storage and Analysis (Birds of a Feather).","author":"Messina Paul","year":"2016","unstructured":"Paul Messina and Stephen Lee. 2016. The U.S. Exascale Computing Project. In The 2016 International Conference for High Performance Computing, Networking, Storage and Analysis (Birds of a Feather)."},{"key":"e_1_3_2_1_21_1","unstructured":"Nagoya University. [Apr 5 2022]. Supercomputer. Internet:\/\/icts.nagoya-u.ac.jp\/en\/sc\/([Apr 5 2022])."},{"key":"e_1_3_2_1_22_1","volume-title":"NVIDIA A100 Tensor Core GPU. Internet:\/\/www.nvidia.com\/en-us\/data-center\/a100\/([Apr 6","author":"NVIDIA.","year":"2022","unstructured":"NVIDIA. [Apr 6, 2022]. NVIDIA A100 Tensor Core GPU. Internet:\/\/www.nvidia.com\/en-us\/data-center\/a100\/([Apr 6, 2022])."},{"key":"e_1_3_2_1_23_1","volume-title":"NVIDIA System Management Interface. Internet:developer.nvidia.com\/nvidia-system-management-interface([Apr 6","author":"NVIDIA.","year":"2022","unstructured":"NVIDIA. [Apr 6, 2022]. NVIDIA System Management Interface. Internet:developer.nvidia.com\/nvidia-system-management-interface([Apr 6, 2022])."},{"key":"e_1_3_2_1_24_1","volume-title":"NVIDIA Tesla P100. Internet:\/\/www.nvidia.com\/en-us\/data-center\/tesla-p100\/([Apr 6","author":"NVIDIA.","year":"2022","unstructured":"NVIDIA. [Apr 6, 2022]. NVIDIA Tesla P100. Internet:\/\/www.nvidia.com\/en-us\/data-center\/tesla-p100\/([Apr 6, 2022])."},{"key":"e_1_3_2_1_25_1","volume-title":"NVIDIA V100 Tensor Core GPU. Internet:\/\/www.nvidia.com\/en-us\/data-center\/v100\/([Apr 6","author":"NVIDIA.","year":"2022","unstructured":"NVIDIA. [Apr 6, 2022]. NVIDIA V100 Tensor Core GPU. Internet:\/\/www.nvidia.com\/en-us\/data-center\/v100\/([Apr 6, 2022])."},{"key":"e_1_3_2_1_26_1","unstructured":"NVIDIA. [Sep 11 2020]. CUDA Toolkit. Internet:developer.nvidia.com\/cuda-toolkit([Sep 11 2020])."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"T. Patki Z. Frye H. Bhatia F. Di Natale J. Glosli H. Ingolfsson and B. Rountree. 2019. Comparing GPU Power and Frequency Capping: A Case Study with the MuMMI Workflow. In 2019 IEEE\/ACM Workflows in Support of Large-Scale Science (WORKS). 31\u201339.","DOI":"10.1109\/WORKS49585.2019.00009"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465009"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops PhD Forum. 947\u2013953","author":"Rountree B.","unstructured":"B. Rountree, D.\u00a0H. Ahn, B.\u00a0R. de Supinski, D.\u00a0K. Lowenthal, and M. Schulz. 2012. Beyond DVFS: A First Look at Performance Under a Hardware-Enforced Power Bound. In Proceedings of the 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops PhD Forum. 947\u2013953."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 957\u2013966","author":"Sakamoto R.","unstructured":"R. Sakamoto, T. Cao, M. Kondo, K. Inoue, M. Ueda, T. Patki, D. Ellsworth, B. Rountree, and M. Schulz. 2017. Production Hardware Overprovisioning: Real-World Performance Optimization Using an Extensible Power-Aware Resource Management Framework. In Proceedings of the 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 957\u2013966."},{"key":"e_1_3_2_1_31_1","volume-title":"Studying Thermal Management for Graphics-Processor Architectures. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). 54\u201365","author":"Sheaffer J.W.","unstructured":"J.W. Sheaffer, K. Skadron, and D.P. Luebke. 2005. Studying Thermal Management for Graphics-Processor Architectures. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). 54\u201365."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCSim.2015.7237023"},{"key":"e_1_3_2_1_33_1","volume-title":"Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing","author":"Stratton J.A.","year":"2012","unstructured":"J.A. Stratton, C. Rodrigues, I.J. Sung, N. Obeid, L.W. Chang, N. Anssari, G.D. Liu, and W.W. Hwu. 2012. Parboil: A Revised Benchmark Suite for Scientific and Commercial Throughput Computing. Center for Reliable and High-Performance Computing (2012)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2013.269"},{"key":"e_1_3_2_1_35_1","volume-title":"Variation-Aware Application Scheduling and Power Management for Chip Multiprocessors. In 2008 International Symposium on Computer Architecture (ISCA). 363\u2013374","author":"Teodorescu R.","unstructured":"R. Teodorescu and J. Torrellas. 2008. Variation-Aware Application Scheduling and Power Management for Chip Multiprocessors. In 2008 International Symposium on Computer Architecture (ISCA). 363\u2013374."},{"key":"e_1_3_2_1_36_1","unstructured":"The University of Tokyo. [Apr 5 2022]. Wisteria\/BDEC-01 Supercomputer System. Internet:\/\/www.cc.u-tokyo.ac.jp\/en\/supercomputer\/wisteria\/service\/([Apr 5 2022])."},{"key":"e_1_3_2_1_37_1","volume-title":"TSUBAME Computing Services. Internet:\/\/www.t3.gsic.titech.ac.jp\/en([Apr 5","author":"Tokyo Institute of Technology. [Apr 5, 2022].","year":"2022","unstructured":"Tokyo Institute of Technology. [Apr 5, 2022]. TSUBAME Computing Services. Internet:\/\/www.t3.gsic.titech.ac.jp\/en([Apr 5, 2022])."},{"key":"e_1_3_2_1_38_1","volume-title":"JUNE 2021","year":"2021","unstructured":"TOP500. 2021. JUNE 2021. Internet:\/\/www.top500.org\/lists\/top500\/2021\/06\/(2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2687001"},{"key":"e_1_3_2_1_40_1","volume-title":"7nm Technology. Internet:www.tsmc.com\/japanese\/dedicatedFoundry\/technology\/logic\/l_7nm([Apr 11","author":"TSMC.","year":"2022","unstructured":"TSMC. [Apr 11, 2022]. 7nm Technology. Internet:www.tsmc.com\/japanese\/dedicatedFoundry\/technology\/logic\/l_7nm([Apr 11, 2022])."},{"key":"e_1_3_2_1_41_1","first-page":"941","article-title":"Energy wall for exascale supercomputing","volume":"35","author":"Wang Z.","year":"2016","unstructured":"Z. Wang, Y. Tang, Juan Chen, Jingling Xue, Yun Zhou, and Y. Dong. 2016. Energy wall for exascale supercomputing. Computing and Informatics 35 (2016), 941\u2013962.","journal-title":"Computing and Informatics"}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","location":"Bordeaux France","acronym":"ICPP '22"},"container-title":["Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545084","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:44Z","timestamp":1750186964000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545084"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":40,"alternative-id":["10.1145\/3545008.3545084","10.1145\/3545008"],"URL":"https:\/\/doi.org\/10.1145\/3545008.3545084","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}