{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:03:32Z","timestamp":1774893812761,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584109","type":"print"},{"value":"9789819584116","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-8411-6_36","type":"book-chapter","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:10:35Z","timestamp":1774890635000},"page":"471-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving the\u00a0Energy Efficiency of\u00a0AI Clusters Through Variability-Aware Frequency Scaling and\u00a0Task Allocation"],"prefix":"10.1007","author":[{"given":"Yijia","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongxiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shixun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Calore, E., Gabbana, A., Schifano, S.F., Tripiccione, R.: Software and DVFS tuning for performance and energy-efficiency on intel KNL processors. J. Low Power Electron. Appl. 8(2) (2018)","DOI":"10.3390\/jlpea8020018"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Chasapis, D., Casas, M., Moret\u00f3, M., et\u00a0al.: Runtime-guided mitigation of manufacturing variability in power-constrained multi-socket NUMA nodes. In: Proceedings of the 2016 International Conference on Supercomputing. ICS \u201916, Association for Computing Machinery, New York, NY, USA (2016)","DOI":"10.1145\/2925426.2926279"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Gholkar, N., et\u00a0al.: PShifter: feedback-based dynamic power shifting within HPC jobs for performance. In: Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing, pp. 106\u2013117. HPDC \u201918, Association for Computing Machinery, New York, NY, USA (2018)","DOI":"10.1145\/3208040.3208047"},{"key":"36_CR4","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., et\u00a0al.: The llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"issue":"11","key":"36_CR5","doi-asserted-by":"publisher","first-page":"2494","DOI":"10.1109\/TPDS.2019.2917181","volume":"30","author":"J Guerreiro","year":"2019","unstructured":"Guerreiro, J., Ilic, A., Roma, N., Tom\u00e1s, P.: Modeling and decoupling the GPU power consumption for cross-domain DVFS. IEEE Trans. Parallel Distrib. Syst. 30(11), 2494\u20132506 (2019)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"36_CR6","doi-asserted-by":"crossref","unstructured":"Inadomi, Y., Patki, T., et\u00a0al.: Analyzing and mitigating the impact of manufacturing variability in power-constrained supercomputing. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. New York, USA (2015)","DOI":"10.1145\/2807591.2807638"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Jain, R., Tran, B., Chen, K., et\u00a0al.: PAL: a variability-aware policy for scheduling ml workloads in GPU clusters. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (2024)","DOI":"10.1109\/SC41406.2024.00032"},{"issue":"2","key":"36_CR8","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1109\/LCA.2024.3406038","volume":"23","author":"AK Kakolyris","year":"2024","unstructured":"Kakolyris, A.K., Masouros, D., Xydis, S., Soudris, D.: SLO-aware GPU DVFS for energy-efficient LLM inference serving. IEEE Comput. Archit. Lett. 23(2), 150\u2013153 (2024)","journal-title":"IEEE Comput. Archit. Lett."},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Kandiah, V., et al.: AccelWattch: a power modeling framework for modern GPUs. In: MICRO-54: 54th Annual IEEE\/ACM International Symposium on Microarchitecture, pp. 738\u2013753 (2021)","DOI":"10.1145\/3466752.3480063"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Liao, H., et al.: Ascend: a scalable and unified architecture for ubiquitous deep neural network computing: industry track paper. In: 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 789\u2013801 (2021)","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Marathe, A., Zhang, Y., Blanks, G., et\u00a0al.: An empirical survey of performance and energy efficiency variation on intel processors. In: Proceedings of the 5th International Workshop on Energy Efficient Supercomputing. E2SC\u201917 (2017)","DOI":"10.1145\/3149412.3149421"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Nath, R., Tullsen, D.: The crisp performance model for dynamic voltage and frequency scaling in a GPGPU. In: 2015 48th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 281\u2013293 (2015)","DOI":"10.1145\/2830772.2830826"},{"key":"36_CR13","unstructured":"Rajasekaran, S., Ghobadi, M., Akella, A.: CASSINI: network-aware job scheduling in machine learning clusters. In: 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24), pp. 1403\u20131420. Santa Clara, CA (2024)"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Sinha, P., Guliani, A., Jain, R., Tran, B., Sinclair, M.D., Venkataraman, S.: Not all GPUS are created equal: characterizing variability in large-scale, accelerator-rich systems. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. SC \u201922, IEEE Press (2022)","DOI":"10.1109\/SC41404.2022.00070"},{"issue":"12","key":"36_CR15","doi-asserted-by":"publisher","first-page":"2865","DOI":"10.1109\/TPDS.2020.3004623","volume":"31","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Chu, X.: GPGPU performance estimation with core and memory frequency scaling. IEEE Trans. Parallel Distrib. Syst. 31(12), 2865\u20132881 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Q., Li, L., Luo, W., Zhang, Y., Wang, B.: DSO: a GPU energy efficiency optimizer by fusing dynamic and static information. In: 2024 IEEE\/ACM 32nd International Symposium on Quality of Service (IWQoS), pp.\u00a01\u20136 (2024)","DOI":"10.1109\/IWQoS61813.2024.10682917"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, Y., Wei, F., et\u00a0al.: Using analytical performance\/power model and fine-grained DVFS to enhance ai accelerator energy efficiency. In: Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1, pp. 1118\u20131132. ASPLOS \u201925 (2025)","DOI":"10.1145\/3669940.3707231"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Yu, K., Yang, Y., Xiao, H., Chen, J.: An improved DVFS algorithm for energy-efficient real-time task scheduling. In: 2020 IEEE 22nd International Conference on High Performance Computing and Communications, pp. 263\u2013272 (2020)","DOI":"10.1109\/HPCC-SmartCity-DSS50907.2020.00033"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, H., Nukada, A., Liao, Q.: FCUFS: core-level frequency tuning for energy optimization on intel processors. In: 2024 IEEE International Conference on Cluster Computing (CLUSTER), pp. 214\u2013225 (2024)","DOI":"10.1109\/CLUSTER59578.2024.00026"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, Q., Lin, Z., Xu, P., Wang, B.: Improving GPU energy efficiency through an application-transparent frequency scaling policy with performance assurance. In: Proceedings of the Nineteenth European Conference on Computer Systems, pp. 769\u2013785. EuroSys \u201924 (2024)","DOI":"10.1145\/3627703.3629584"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8411-6_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:10:39Z","timestamp":1774890639000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8411-6_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584109","9789819584116"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8411-6_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"31 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}