{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:14:12Z","timestamp":1779174852013,"version":"3.51.4"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpds.2023.3267943","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T18:15:21Z","timestamp":1681755321000},"page":"1-14","source":"Crossref","is-referenced-by-count":9,"title":["TurboMGNN: Improving Concurrent GNN Training Tasks on GPU With Fine-Grained Kernel Fusion"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0814-0919","authenticated-orcid":false,"given":"Wenchao","family":"Wu","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8451-8656","authenticated-orcid":false,"given":"Xuanhua","family":"Shi","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5671-0576","authenticated-orcid":false,"given":"Ligang","family":"He","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Warwick, Coventry, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-7605","authenticated-orcid":false,"given":"Hai","family":"Jin","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Big Data Technology and System, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"515","article-title":"GNNAdvisor: An adaptive and efficient runtime system for GNN acceleration on GPUs","author":"wang","year":"2021","journal-title":"Proc 15th USENIX Symp Operating Syst Des Implementation"},{"key":"ref35","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441585"},{"key":"ref34","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"ref37","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456247"},{"key":"ref36","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3332466.3374546"},{"key":"ref33","article-title":"Graph2Seq: Graph to sequence learning with attention-based neural networks","author":"xu","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3293883.3295712"},{"key":"ref32","first-page":"579","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"chen","year":"2018","journal-title":"Proc 13th USENIX Conf Operating Syst Des Implementation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449884"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3065737"},{"key":"ref39","article-title":"How powerful are graph neural networks?","author":"xu","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456233"},{"key":"ref38","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356143"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600222"},{"key":"ref24","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015"},{"key":"ref46","first-page":"881","article-title":"RAMMER: Enabling holistic deep learning compiler optimizations with rtasks","author":"ma","year":"2020","journal-title":"Proc 14th USENIX Conf Operating Syst Des Implementation"},{"key":"ref23","year":"2013"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref26","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006359"},{"key":"ref25","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Conf Operating Syst Des Implementation"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.14778\/2904483.2904488"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807184"},{"key":"ref42","year":"2022"},{"key":"ref41","year":"2022"},{"key":"ref22","year":"2013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"ref21","first-page":"17","article-title":"PowerGraph: Distributed graph-parallel computation on natural graphs","author":"gonzalez","year":"2012","journal-title":"Proc 10th USENIX Conf Operating Syst Des Implementation"},{"key":"ref43","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.15"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600227"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3399730"},{"key":"ref8","article-title":"Fast graph representation learning with PyTorch geometric","author":"fey","year":"2019"},{"key":"ref7","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3133691"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3210-2"},{"key":"ref6","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3014632"},{"key":"ref40","article-title":"Graph attention networks","author":"veli?kovi?","year":"2017"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/4359390\/10103627.pdf?arnumber=10103627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T21:30:49Z","timestamp":1683927049000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10103627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3267943","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}