{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:50:18Z","timestamp":1775069418742,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010246","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62372426"],"award-info":[{"award-number":["62372426"]}],"id":[{"id":"10.13039\/501100010246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010246","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62132019"],"award-info":[{"award-number":["62132019"]}],"id":[{"id":"10.13039\/501100010246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010246","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62102392"],"award-info":[{"award-number":["62102392"]}],"id":[{"id":"10.13039\/501100010246","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation of Jiangsu Province","award":["BK20210121"],"award-info":[{"award-number":["BK20210121"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Youth Innovation Promotion Association of the Chinese Academy of Science","award":["2023481"],"award-info":[{"award-number":["2023481"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tnet.2024.3404999","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T18:32:11Z","timestamp":1718649131000},"page":"4128-4143","source":"Crossref","is-referenced-by-count":4,"title":["ALEPH: Accelerating Distributed Training With eBPF-Based Hierarchical Gradient Aggregation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4400-2289","authenticated-orcid":false,"given":"Peng","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-4577","authenticated-orcid":false,"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1311-8908","authenticated-orcid":false,"given":"Gongming","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3805-4480","authenticated-orcid":false,"given":"Qianyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5871-9187","authenticated-orcid":false,"given":"Jiawei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4679-6572","authenticated-orcid":false,"given":"Chunming","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, State University of New York, Buffalo, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"ref4","volume-title":"AI and Compute","author":"Amodei","year":"2018"},{"key":"ref5","article-title":"Horovod: Fast and easy distributed deep learning in TensorFlow","author":"Sergeev","year":"2018","journal-title":"arXiv:1802.05799"},{"key":"ref6","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Networked Syst. Design Implement.","author":"Gu"},{"key":"ref7","first-page":"463","article-title":"A unified architecture for accelerating distributed DNN training in heterogeneous GPU\/CPU clusters","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Design Implement.","author":"Jiang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.09.002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00023"},{"key":"ref11","article-title":"Communication-efficient distributed deep learning: A comprehensive survey","author":"Tang","year":"2020","journal-title":"arXiv:2003.06307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737595"},{"key":"ref13","volume-title":"Allreduce","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/1094342005051521"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472888"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3229543.3229544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2947013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04083-x"},{"key":"ref19","article-title":"Massively distributed SGD: ImageNet\/ResNet-50 training in a flash","author":"Mikami","year":"2018","journal-title":"arXiv:1811.05233"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488756"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3028367"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378499"},{"key":"ref23","volume-title":"Amazon Elastic Compute Cloud (EC2)","year":"2024"},{"key":"ref24","first-page":"947","article-title":"Analysis of large-ScaleMulti-TenantGPU clusters for DNN training workloads","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Jeon"},{"key":"ref25","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Xiao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934908"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531476"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.07.040"},{"key":"ref29","volume-title":"EBPF Documentation","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267840"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1402958.1402968"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1851182.1851191"},{"key":"ref33","first-page":"741","article-title":"ATP: In-network aggregation for multi-tenant learning","volume-title":"Proc. 18th USENIX Symp. Networked Syst. Design Implement.","author":"Lao"},{"key":"ref34","article-title":"Scaling distributed machine learning with in-network aggregation","author":"Sapio","year":"2019","journal-title":"arXiv:1903.06701"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3452296.3472904"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2999096"},{"key":"ref37","first-page":"487","article-title":"BMC: Accelerating memcached using safe in-kernel caching and pre-stack processing","volume-title":"Proc. 18th USENIX Symp. Networked Syst. Design Implement.","author":"Ghigoff"},{"key":"ref38","volume-title":"VGG19","year":"2024"},{"key":"ref39","volume-title":"IFTOP","year":"2024"},{"key":"ref40","volume-title":"mpstat","year":"2024"},{"key":"ref41","first-page":"1","article-title":"400G and beyond: Coherent evolution to high-capacity inter data center links","volume-title":"Proc. Opt. Fiber Commun. Conf. Exhib. (OFC)","author":"Maniloff"},{"key":"ref42","first-page":"1267","article-title":"RDC: Energy-Efficient data center network congestion relief with topological reconfigurability at the edge","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Design Implement.","author":"Wang"},{"key":"ref43","volume-title":"Connectx-7 Product Brief","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s00446-002-0078-0"},{"key":"ref45","first-page":"259","article-title":"The BSD packet filter: A new architecture for user-level packet capture","volume-title":"Proc. USENIX Winter","volume":"46","author":"McCanne"},{"key":"ref46","volume-title":"Cilium","year":"2024"},{"key":"ref47","volume-title":"BPF and XDP Reference Guide","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1508293.1508303"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/NETSOFT.2019.8806651"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3281411.3281443"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref52","volume-title":"Byteps Performance When Training CNN","year":"2024"},{"key":"ref53","volume-title":"Dataloader","year":"2024"},{"key":"ref54","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI48845.2019.8965823"},{"key":"ref56","first-page":"181","article-title":"Poseidon: An efficient communication architecture for distributed deep learning on GPU clusters","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359642"},{"key":"ref58","volume-title":"An Instant Virtual Network on Your Laptop","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1402946.1402967"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787507"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/2934872.2934893"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-0000(74)80044-9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/0012-365X(75)90058-8"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2853587"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029621"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/90\/10720541\/10559845.pdf?arnumber=10559845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:37:06Z","timestamp":1729226226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10559845\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2024.3404999","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}