{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:22:12Z","timestamp":1783041732964,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515010113"],"award-info":[{"award-number":["2025A1515010113"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["PCL2025A08"],"award-info":[{"award-number":["PCL2025A08"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["PCL2025A11"],"award-info":[{"award-number":["PCL2025A11"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2024LZH012"],"award-info":[{"award-number":["ZR2024LZH012"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Future Generation Computer Systems"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.future.2026.108596","type":"journal-article","created":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T16:06:10Z","timestamp":1778861170000},"page":"108596","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Concord: A GPU cluster scheduler with enhanced interference profiling and asymmetric job packing"],"prefix":"10.1016","volume":"183","author":[{"given":"Xinhua","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6876-1795","authenticated-orcid":false,"given":"Weiwei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijie","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.future.2026.108596_b1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.future.2026.108596_b2","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.future.2026.108596_b3","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.future.2026.108596_b4","article-title":"High-performance computing and big data: Emerging trends in advanced computing systems for data-intensive applications","author":"Gathu","year":"2024","journal-title":"J. Adv. Comput. Syst."},{"key":"10.1016\/j.future.2026.108596_b5","unstructured":"Qinghao Hu, Peng Sun, Shengen Yan, Yonggang Wen, Characterization and prediction of deep learning workloads in large-scale gpu datacenters, in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2021."},{"key":"10.1016\/j.future.2026.108596_b6","doi-asserted-by":"crossref","unstructured":"Qizhen Weng, Wencong Xiao, Yinghao Yu, Wei Wang, Cheng Wang, Jian He, Yong Li, MLaaS in the wild: Workload analysis and scheduling in Large-Scale heterogeneous GPU clusters, in: USENIX Symposium on Networked Systems Design and Implementation, 2022.","DOI":"10.21203\/rs.3.rs-2266264\/v1"},{"key":"10.1016\/j.future.2026.108596_b7","doi-asserted-by":"crossref","DOI":"10.1145\/2898442.2898444","article-title":"Borg, omega, and kubernetes: Lessons learned from three container-management systems over a decade","author":"Burns","year":"2016","journal-title":"Queue"},{"key":"10.1016\/j.future.2026.108596_b8","doi-asserted-by":"crossref","unstructured":"Vinod Kumar Vavilapalli, Arun C. Murthy, Chris Douglas, Sharad Agarwal, Mahadev Konar, Robert Evans, Thomas Graves, Jason Lowe, Hitesh Shah, Siddharth Seth, Bikas Saha, Carlo Curino, Apache Hadoop YARN: yet another resource negotiator, in: Proceedings of the Annual Symposium on Cloud Computing, ISBN: 9781450324281, 2013.","DOI":"10.1145\/2523616.2523633"},{"key":"10.1016\/j.future.2026.108596_b9","doi-asserted-by":"crossref","DOI":"10.1145\/2954679.2872388","article-title":"Interference management for distributed parallel applications in consolidated clusters","author":"Han","year":"2016","journal-title":"ACM SIGPLAN Not."},{"key":"10.1016\/j.future.2026.108596_b10","unstructured":"Wencong Xiao, Romil Bhardwaj, Ramachandran Ramjee, Muthian Sivathanu, Nipun Kwatra, Zhenhua Han, Pratyush Patel, Xuan Peng, Hanyu Zhao, Quanlu Zhang, Fan Yang, Gandiva: Introspective cluster scheduling for deep learning, in: USENIX Symposium on Operating Systems Design and Implementation, 2018."},{"key":"10.1016\/j.future.2026.108596_b11","unstructured":"Ting-An Yeh, Hung-Hsin Chen, Jerry Chou, KubeShare: A framework to manage GPUs as first-class and shared resources in container cloud, in: Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing, 2020."},{"key":"10.1016\/j.future.2026.108596_b12","unstructured":"Qinghao Hu, Meng Zhang, Peng Sun, Yonggang Wen, Tianwei Zhang, Lucid: A non-intrusive, scalable and interpretable scheduler for deep learning training jobs, in: Proceedings of the ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2023."},{"key":"10.1016\/j.future.2026.108596_b13","article-title":"Horus: Interference-aware and prediction-based scheduling in deep learning systems","author":"Yeung","year":"2021","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.future.2026.108596_b14","unstructured":"Myeongjae Jeon, Shivaram Venkataraman, Amar Phanishayee, Junjie Qian, Analysis of Large-Scale Multi-Tenant GPU clusters for DNN training workloads, in: USENIX Annual Technical Conference, 2019."},{"key":"10.1016\/j.future.2026.108596_b15","doi-asserted-by":"crossref","unstructured":"Christina Delimitrou, Christos Kozyrakis, Paragon: QoS-aware scheduling for heterogeneous datacenters, in: Proceedings of the ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2013.","DOI":"10.1145\/2451116.2451125"},{"key":"10.1016\/j.future.2026.108596_b16","doi-asserted-by":"crossref","unstructured":"Jason Mars, Lingjia Tang, Robert Hundt, Kevin Skadron, Bubble-up: Increasing utilization in modern warehouse scale computers via sensible co-locations, in: Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture, 2011.","DOI":"10.1145\/2155620.2155650"},{"key":"10.1016\/j.future.2026.108596_b17","doi-asserted-by":"crossref","DOI":"10.1145\/2508148.2485974","article-title":"Bubble-flux: Precise online qos management for increased utilization in warehouse scale computers","author":"Yang","year":"2013","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"10.1016\/j.future.2026.108596_b18","series-title":"IEEE International Parallel and Distributed Processing Symposium","article-title":"Themis: Predicting and reining in application-level slowdown on spatial multitasking GPUs","author":"Zhao","year":"2019"},{"key":"10.1016\/j.future.2026.108596_b19","unstructured":"Juncheng Gu, Mosharaf Chowdhury, Kang G. Shin, Tiresias: A GPU cluster manager for distributed deep learning, in: USENIX Symposium on Networked Systems Design and Implementation, 2019."},{"key":"10.1016\/j.future.2026.108596_b20","unstructured":"AutoML, AutoML. http:\/\/www.ml4aad.org\/automl\/."},{"key":"10.1016\/j.future.2026.108596_b21","doi-asserted-by":"crossref","unstructured":"Foteini Strati, Xianzhe Ma, Ana Klimovic, Orion: Interference-aware, fine-grained GPU sharing for ML applications, in: Proceedings of the Nineteenth European Conference on Computer Systems, 2024.","DOI":"10.1145\/3627703.3629578"},{"key":"10.1016\/j.future.2026.108596_b22","unstructured":"NVIDIA, Multi-Process Service. https:\/\/docs.nvidia.com\/deploy\/mps."},{"key":"10.1016\/j.future.2026.108596_b23","unstructured":"NVIDIA, Multi-Instance GPU. https:\/\/www.nvidia.com\/en-us\/technologies\/multi-instance-gpu\/."},{"key":"10.1016\/j.future.2026.108596_b24","doi-asserted-by":"crossref","unstructured":"Bowen Zhang, Yuhang Wang, Zhuozhao Li, BOER: Enhancing Resource Utilization for Deep Learning Inference with Hybrid Spatial GPU Sharing, in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2025.","DOI":"10.1145\/3712285.3759857"},{"key":"10.1016\/j.future.2026.108596_b25","unstructured":"Deepak Narayanan, Keshav Santhanam, Fiodar Kazhamiaka, Amar Phanishayee, Matei Zaharia, Heterogeneity-Aware cluster scheduling policies for deep learning workloads, in: USENIX Symposium on Operating Systems Design and Implementation, 2020."},{"key":"10.1016\/j.future.2026.108596_b26","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2016","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.future.2026.108596_b27","series-title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"10.1016\/j.future.2026.108596_b28","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.future.2026.108596_b29","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2017","journal-title":"Int. Conf. Learn. Represent."},{"key":"10.1016\/j.future.2026.108596_b30","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/W16-3210","article-title":"Multi30k: Multilingual english-german image descriptions","author":"Elliott","year":"2016","journal-title":"In Proc. the 5th Work. Vis. Lang."},{"key":"10.1016\/j.future.2026.108596_b31","doi-asserted-by":"crossref","unstructured":"Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Searching for mobilenetv3, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"10.1016\/j.future.2026.108596_b32","doi-asserted-by":"crossref","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, Imagenet: A large-scale hierarchical image database, in: IEEE Conference on Computer Vision and Pattern Recognition, 2009.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"10.1016\/j.future.2026.108596_b33","doi-asserted-by":"crossref","unstructured":"Charles R. Qi, Hao Su, Pointnet: Deep learning on point sets for 3d classification and segmentation, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017.","DOI":"10.1109\/CVPR.2017.16"},{"key":"10.1016\/j.future.2026.108596_b34","series-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015"},{"key":"10.1016\/j.future.2026.108596_b35","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016."},{"key":"10.1016\/j.future.2026.108596_b36","unstructured":"Alex Krizhevsky, The CIFAR10 Dataset. https:\/\/www.cs.toronto.edu."},{"key":"10.1016\/j.future.2026.108596_b37","unstructured":"Chenxi Liu, Barret Zoph, Progressive Neural Architecture Search, in: European Conference on Computer Vision, 2018."},{"key":"10.1016\/j.future.2026.108596_b38","article-title":"Survey on SVM and their application in image classification","author":"Chandra","year":"2021","journal-title":"Int. J. Inf. Technol."},{"key":"10.1016\/j.future.2026.108596_b39","doi-asserted-by":"crossref","unstructured":"Tianqi Chen, Carlos Guestrin, Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, 2016.","DOI":"10.1145\/2939672.2939785"},{"key":"10.1016\/j.future.2026.108596_b40","doi-asserted-by":"crossref","DOI":"10.1057\/9780230509993","article-title":"Classification and regression by randomforest","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"10.1016\/j.future.2026.108596_b41","doi-asserted-by":"crossref","unstructured":"Wenyan Chen, Zizhao Mo, Huanle Xu, Kejiang Ye, Interference-aware multiplexing for deep learning in gpu clusters: A middleware approach, in: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2023.","DOI":"10.1145\/3581784.3607060"},{"key":"10.1016\/j.future.2026.108596_b42","article-title":"SARS: Towards minimizing average coflow completion time in MapReduce systems","author":"Wang","year":"2024","journal-title":"Comput. Netw."},{"key":"10.1016\/j.future.2026.108596_b43","doi-asserted-by":"crossref","unstructured":"Shulai Zhang, Quan Chen, Weihao Cui, Han Zhao, Chunyu Xue, Zhen Zheng, Wei Lin, Minyi Guo, Improving GPU sharing performance through adaptive bubbleless spatial-temporal sharing, in: Proceedings of the European Conference on Computer Systems, 2025.","DOI":"10.1145\/3689031.3696070"},{"key":"10.1016\/j.future.2026.108596_b44","doi-asserted-by":"crossref","unstructured":"Rajat Phull, Cheng-Hong Li, Kunal Rao, Hari Cadambi, Interference-driven resource management for GPU-based heterogeneous clusters, in: Proceedings of the International Symposium on High-Performance Parallel and Distributed Computing, 2012.","DOI":"10.1145\/2287076.2287091"},{"key":"10.1016\/j.future.2026.108596_b45","doi-asserted-by":"crossref","unstructured":"Wenyan Chen, Chengzhi Lu, Huanle Xu, Kejiang Ye, Chengzhong Xu, Multiplexing Dynamic Deep Learning Workloads with SLO-awareness in GPU Clusters, in: Proceedings of the Twentieth European Conference on Computer Systems, 2025.","DOI":"10.1145\/3689031.3696074"},{"key":"10.1016\/j.future.2026.108596_b46","doi-asserted-by":"crossref","DOI":"10.1007\/s11227-022-04682-2","article-title":"Kubegpu: efficient sharing and isolation mechanisms for GPU resource management in container cloud: W. Shen et al.","author":"Shen","year":"2023","journal-title":"J. Supercomput."},{"key":"10.1016\/j.future.2026.108596_b47","unstructured":"Jing Gu, Shengbo Song, Ying Li, Hanmei Luo, GaiaGPU: Sharing GPUs in container clouds, in: 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications, 2018."},{"key":"10.1016\/j.future.2026.108596_b48","doi-asserted-by":"crossref","DOI":"10.1007\/s11227-024-06849-5","article-title":"A fine-grained GPU sharing and job scheduling for deep learning jobs on the cloud","author":"Chung","year":"2025","journal-title":"J. Supercomput."},{"key":"10.1016\/j.future.2026.108596_b49","unstructured":"ONNX, Open Neural Network Exchange. https:\/\/github.com\/onnx."},{"key":"10.1016\/j.future.2026.108596_b50","series-title":"2026 IEEE International Symposium on High Performance Computer Architecture","article-title":"AUM: Unleashing the efficiency potential of shared processors with accelerator units for LLM serving","author":"Wang","year":"2026"}],"container-title":["Future Generation Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X2600230X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167739X2600230X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:11:23Z","timestamp":1783041083000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167739X2600230X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"alternative-id":["S0167739X2600230X"],"URL":"https:\/\/doi.org\/10.1016\/j.future.2026.108596","relation":{},"ISSN":["0167-739X"],"issn-type":[{"value":"0167-739X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Concord: A GPU cluster scheduler with enhanced interference profiling and asymmetric job packing","name":"articletitle","label":"Article Title"},{"value":"Future Generation Computer Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.future.2026.108596","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108596"}}