{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:09:10Z","timestamp":1763190550045,"version":"3.45.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032104588","type":"print"},{"value":"9783032104595","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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\/978-3-032-10459-5_12","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:07:01Z","timestamp":1763190421000},"page":"143-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint Optimization of\u00a0Computation and\u00a0Communication Resources for\u00a0GPU Allocation in\u00a0Heterogeneous Clusters"],"prefix":"10.1007","author":[{"given":"Jiacheng","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Chu","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Gongming","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Gangyi","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"12_CR1","unstructured":"CIFAR-10 and CIFAR-100 datasets \u2014 cs.toronto.edu. https:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"12_CR2","unstructured":"examples\/word_language_model at main $$\\cdot $$ pytorch\/examples \u2014 github.com. https:\/\/github.com\/pytorch\/examples\/tree\/main\/word_language_model"},{"key":"12_CR3","unstructured":"NVIDIA Data Center GPU Resource Center \u2014 resources.nvidia.com. https:\/\/resources.nvidia.com\/l\/en-us-gpu"},{"key":"12_CR4","unstructured":"NVLink & NVSwitch for Advanced Multi-GPU Communication \u2014 nvidia.com. https:\/\/www.nvidia.com\/en-us\/data-center\/nvlink\/"},{"key":"12_CR5","unstructured":"torchtext.datasets \u2014 Torchtext 0.18.0 documentation \u2014 pytorch.org. https:\/\/pytorch.org\/text\/stable\/datasets.html#torchtext.datasets.WikiText2. Accessed 24 Apr 2025"},{"issue":"4","key":"12_CR6","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/1402946.1402967","volume":"38","author":"M Al-Fares","year":"2008","unstructured":"Al-Fares, M., Loukissas, A., Vahdat, A.: A scalable, commodity data center network architecture. ACM SIGCOMM Comput. Commun. Rev. 38(4), 63\u201374 (2008)","journal-title":"ACM SIGCOMM Comput. Commun. Rev."},{"issue":"2","key":"12_CR7","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.trb.2006.02.002","volume":"41","author":"B Bixby","year":"2007","unstructured":"Bixby, B.: The gurobi optimizer. Transp. Res. Part B 41(2), 159\u2013178 (2007)","journal-title":"Transp. Res. Part B"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Chaudhary, S., Ramjee, R., Sivathanu, M., Kwatra, N., Viswanatha, S.: Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning. In: Proceedings of the Fifteenth European Conference on Computer Systems, pp. 1\u201316 (2020)","DOI":"10.1145\/3342195.3387555"},{"issue":"3","key":"12_CR9","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1137\/S0097539700382820","volume":"35","author":"C Chekuri","year":"2005","unstructured":"Chekuri, C., Khanna, S.: A polynomial time approximation scheme for the multiple knapsack problem. SIAM J. Comput. 35(3), 713\u2013728 (2005)","journal-title":"SIAM J. Comput."},{"key":"12_CR10","unstructured":"Kingma, D.P., Welling, M.: Stochastic gradient VB and the variational auto-encoder. In: Second International Conference on Learning Representations, ICLR, vol.\u00a019, p.\u00a0121 (2014)"},{"key":"12_CR11","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1017\/CBO9781139177801.004","volume":"3","author":"A Krause","year":"2014","unstructured":"Krause, A., Golovin, D.: Submodular function maximization. Tractability 3, 71\u2013104 (2014)","journal-title":"Tractability"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Luo, L., Zhao, G., Xu, H., Xie, L., Xiong, Y.: Vita: virtual network topology-aware southbound message delivery in clouds. In: IEEE INFOCOM 2022-IEEE Conference on Computer Communications, pp. 630\u2013639. IEEE (2022)","DOI":"10.1109\/INFOCOM48880.2022.9796938"},{"key":"12_CR13","unstructured":"Merge, M.: IEEE standard for ethernet"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: Pipedream: generalized pipeline parallelism for DNN training. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles, pp. 1\u201315 (2019)","DOI":"10.1145\/3341301.3359646"},{"key":"12_CR15","unstructured":"Narayanan, D., Santhanam, K., Kazhamiaka, F., Phanishayee, A., Zaharia, M.: $$\\{$$Heterogeneity-Aware$$\\}$$ cluster scheduling policies for deep learning workloads. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2020), pp. 481\u2013498 (2020)"},{"issue":"3","key":"12_CR16","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1287\/moor.3.3.177","volume":"3","author":"GL Nemhauser","year":"1978","unstructured":"Nemhauser, G.L., Wolsey, L.A.: Best algorithms for approximating the maximum of a submodular set function. Math. Oper. Res. 3(3), 177\u2013188 (1978)","journal-title":"Math. Oper. Res."},{"issue":"2","key":"12_CR17","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.jpdc.2008.09.002","volume":"69","author":"P Patarasuk","year":"2009","unstructured":"Patarasuk, P., Yuan, X.: Bandwidth optimal all-reduce algorithms for clusters of workstations. J. Parallel Distrib. Comput. 69(2), 117\u2013124 (2009)","journal-title":"J. Parallel Distrib. Comput."},{"key":"12_CR18","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"12_CR19","unstructured":"Sergeev, A., Del\u00a0Balso, M.: Horovod: fast and easy distributed deep learning in tensorflow. arXiv preprint arXiv:1802.05799 (2018)"},{"issue":"1","key":"12_CR20","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1177\/1094342005051521","volume":"19","author":"R Thakur","year":"2005","unstructured":"Thakur, R., Rabenseifner, R., Gropp, W.: Optimization of collective communication operations in MPICH. Int. J. High Perform. Comput. Appl. 19(1), 49\u201366 (2005). https:\/\/doi.org\/10.1177\/1094342005051521","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10459-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:07:06Z","timestamp":1763190426000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10459-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9783032104588","9783032104595"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10459-5_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nha Trang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.npc-conference.com\/#\/npc2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}