{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:46:11Z","timestamp":1768311971317,"version":"3.49.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"crossref","award":["2016YFB1000403"],"award-info":[{"award-number":["2016YFB1000403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s10766-018-00623-w","type":"journal-article","created":{"date-parts":[[2018,12,31]],"date-time":"2018-12-31T23:35:50Z","timestamp":1546299350000},"page":"467-480","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Improving the Performance of Distributed MXNet with RDMA"],"prefix":"10.1007","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1079-3126","authenticated-orcid":false,"given":"Mingfan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxian","family":"Chi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,1]]},"reference":[{"key":"623_CR1","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.media.2016.06.032","volume":"33","author":"M Bruijne de","year":"2016","unstructured":"de Bruijne, M.: Machine learning approaches in medical image analysis: from detection to diagnosis. Med. Image. Anal. 33, 94\u201397 (2016). \n                    https:\/\/doi.org\/10.1016\/j.media.2016.06.032","journal-title":"Med. Image. Anal."},{"issue":"3","key":"623_CR2","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","volume":"13","author":"T Young","year":"2018","unstructured":"Young, T., Hazarika, D., Poria, S., Cambria, E.: Recent trends in deep learning based natural language processing. IEEE Comput. Intell. Mag. 13(3), 55\u201375 (2018). \n                    https:\/\/doi.org\/10.1109\/MCI.2018.2840738","journal-title":"IEEE Comput. Intell. Mag."},{"key":"623_CR3","doi-asserted-by":"publisher","unstructured":"P\u00e9rez, G., Arbel\u00e1ez, P.: Automated detection of lung nodules with three-dimensional convolutional neural networks. Proc. SPIE 10572, 10572-1-10572-10 (2017). \n                    https:\/\/doi.org\/10.1117\/12.2285954","DOI":"10.1117\/12.2285954"},{"key":"623_CR4","doi-asserted-by":"crossref","unstructured":"Huang G., Sun, Y., Liu, Z., Sedra, D.,Weinberger, K.Q.: Deep networks with stochastic depth. In: European Conference on Computer Vision, pp. 646\u2013661. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"623_CR5","doi-asserted-by":"crossref","unstructured":"You, Y., Zhang, Z., Hsieh, C., Demmel, J., Keutzer, K.: ImageNet training in minutes. CoRR. \n                    arXiv:1709.05011\n                    \n                   (2017)","DOI":"10.1145\/3225058.3225069"},{"key":"623_CR6","doi-asserted-by":"publisher","unstructured":"Grun, P., Hefty, S., Sur, S., Goodell, D., Russell, R.D., Pritchard, H., Squyres, J.M.: A brief introduction to the OpenFabrics interfaces: a new network API for maximizing high performance application efficiency. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 34\u201339 (2015). \n                    https:\/\/doi.org\/10.1109\/HOTI.2015.19","DOI":"10.1109\/HOTI.2015.19"},{"key":"623_CR7","unstructured":"Hintjens, P.: ZeroMQ: the guide. \n                    http:\/\/zguide.zeromq.org\/page:all\n                    \n                   (2010)"},{"issue":"4","key":"623_CR8","doi-asserted-by":"publisher","first-page":"2894","DOI":"10.1109\/COMST.2017.2746083","volume":"19","author":"P MacArthur","year":"2017","unstructured":"MacArthur, P., Liu, Q., Russell, R.D., Mizero, F., Veeraraghavan, M., Dennis, J.M.: An integrated tutorial on InfiniBand, verbs, and MPI. IEEE Commun. Surv. Tutorials 19(4), 2894\u20132926 (2017). \n                    https:\/\/doi.org\/10.1109\/COMST.2017.2746083","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"623_CR9","unstructured":"RDMA Consortium and others: Architectural specifications for RDMA over TCP\/IP (2009)"},{"key":"623_CR10","unstructured":"Li, M., Zhou, L.,Yang, Z., Li, A., Xia, F., Andersen, D.G., Smola, A.: Parameter server for distributed machine learning. In: Big Learning NIPS Workshop, vol. 6, p. 2 (2013)"},{"key":"623_CR11","doi-asserted-by":"publisher","unstructured":"Buyya, R., Cortes, T., Jin, H.: An introduction to the InfiniBand architecture. In: High Performance Mass Storage and Parallel I\/O: Technologies and Applications (2002). \n                    https:\/\/doi.org\/10.1109\/9780470544839.ch42","DOI":"10.1109\/9780470544839.ch42"},{"issue":"3","key":"623_CR12","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1023\/B:IJPP.0000029272.69895.c1","volume":"32","author":"J Liu","year":"2004","unstructured":"Liu, J., Wu, J., Panda, D.K.: High performance RDMA-based MPI implementation over InfiniBand. Int. J. Parallel Program. 32(3), 167\u2013198 (2004). \n                    https:\/\/doi.org\/10.1023\/B:IJPP.0000029272.69895.c1","journal-title":"Int. J. Parallel Program."},{"key":"623_CR13","doi-asserted-by":"crossref","unstructured":"Islam, N.S., Rahman, M.W., Jose, J., Rajachandrasekar, R., Wang, H., Subramoni, H., Murthy, C., Panda, D.K.: High performance RDMA-based design of HDFS over InfiniBand. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, p. 35. IEEE Computer Society Press (2012)","DOI":"10.1109\/SC.2012.65"},{"key":"623_CR14","doi-asserted-by":"crossref","unstructured":"Jose, J., Subramoni, H., Luo, M., Zhang, M., Huang, J., Wasi-ur Rahman, M., Islam, N.S., Ouyang, X., Wang, H., Sur, S., et al.: Memcached design on high performance rdma capable interconnects. In: 2011 International Conference on Parallel Processing (ICPP), pp. 743\u2013752. IEEE (2011)","DOI":"10.1109\/ICPP.2011.37"},{"key":"623_CR15","doi-asserted-by":"crossref","unstructured":"Jose, J., Luo, M., Sur, S., Panda, D.K.: Unifying UPC and MPI runtimes: experience with MVAPICH. In: Proceedings of the Fourth Conference on Partitioned Global Address Space Programming Model, p. 5. ACM (2010)","DOI":"10.1145\/2020373.2020378"},{"key":"623_CR16","doi-asserted-by":"publisher","unstructured":"Jia, C., Liu, J., Jin, X., Lin, H., An, 412 H., Han, W., Wu, Z., Chi, M.: Improving the performance of distributed TensorFlow with RDMA. Int. J. Parallel Program. 46(4), 674\u2013685 (2018). \n                    https:\/\/doi.org\/10.1007\/s10766-017-0520-3","DOI":"10.1007\/s10766-017-0520-3"},{"key":"623_CR17","doi-asserted-by":"crossref","unstructured":"Lu, X., Islam, NS.,Wasi-Ur-Rahman, M., Jose, J., Subramoni, H.,Wang, H., Panda, D.K.: High-performance design of Hadoop RPC with RDMA over InfiniBand. In: 2013 42nd International Conference on Parallel Processing (ICPP), pp 641\u2013650. IEEE (2013)","DOI":"10.1109\/ICPP.2013.78"},{"key":"623_CR18","unstructured":"Mitchell, C., Geng, Y., Li, J.: Using one-sided RDMA reads to build a fast, CPU-efficient key-value store. In: USENIX Annual Technical Conference, pp. 103\u2013114 (2013)"},{"key":"623_CR19","unstructured":"Zhang, H., Zheng, Z., Xu, S., Dai, W., Ho, Q., Liang, X., Hu, Z., Wei, J., Xie, P., Xing, E.P.: Poseidon: an efficient communication architecture for distributed deep learning on GPU clusters. arXiv preprint \n                    arXiv:1706.03292\n                    \n                   (2017)"},{"key":"623_CR20","unstructured":"Mamidala, A.R., Kollias, G., Ward, C., Artico, F.: MXNET-MPI: embedding MPI parallelism in parameter server task model for scaling deep learning. ArXiv e-prints \n                    arXiv:1801.03855\n                    \n                  . \n                    http:\/\/adsabs.harvard.edu\/abs\/2018arXiv180103855M\n                    \n                   (2018)"},{"key":"623_CR21","unstructured":"Liu, J., Jiang,W.,Wyckoff, P., Panda, D.K., Ashton, D., Buntinas, D., Gropp,W., Toonen, B.: In: 18th International Parallel and Distributed Processing Symposium, 2004 (IEEE, 2004), p. 16"},{"key":"623_CR22","unstructured":"Pandya, A.A.: TCP\/IP processor and engine using RDMA (2008). US Patent 7,376,755"},{"issue":"4","key":"623_CR23","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1145\/2740070.2626299","volume":"44","author":"A Kalia","year":"2015","unstructured":"Kalia, A., Kaminsky, M., Andersen, D.G.: Using RDMA efficiently for key-value services. ACM SIGCOMM Comput. Commun. Rev. 44(4), 295\u2013306 (2015)","journal-title":"ACM SIGCOMM Comput. Commun. Rev."}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-018-00623-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-018-00623-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-018-00623-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:46:35Z","timestamp":1577839595000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-018-00623-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,1]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["623"],"URL":"https:\/\/doi.org\/10.1007\/s10766-018-00623-w","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1,1]]},"assertion":[{"value":"18 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 January 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}