{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T04:20:15Z","timestamp":1666153215255},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s42514-020-00025-w","type":"journal-article","created":{"date-parts":[[2020,3,10]],"date-time":"2020-03-10T16:04:06Z","timestamp":1583856246000},"page":"67-80","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving the efficiency of HPC data movement on container-based virtual cluster"],"prefix":"10.1007","volume":"2","author":[{"given":"Dan","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,10]]},"reference":[{"key":"25_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al.: Tensorflow: a system for large-scale machine learning. In: 12th $$\\{$$USENIX$$\\}$$ Symposium on Operating Systems Design and Implementation ($$\\{$$OSDI$$\\}$$ 16), pp. 265\u2013283 (2016)"},{"issue":"1","key":"25_CR2","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1109\/35.815462","volume":"38","author":"Grenville Armitage","year":"2000","unstructured":"Armitage, Grenville: MPLs: the magic behind the myths [multiprotocol label switching]. Commun. Mag. IEEE 38(1), 124\u2013131 (2000)","journal-title":"Commun. Mag. IEEE"},{"key":"25_CR3","unstructured":"Burtsev, A., Srinivasan, K., Radhakrishnan, P., Voruganti, K., Goodson, G.R.: Fido: fast inter-virtual-machine communication for enterprise appliances. In: USENIX Annual Technical Conference, San Diego, CA (2009)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chai, L., Lai, P., Jin, H.-W., Panda, D.K.: Designing an efficient kernel-level and user-level hybrid approach for MPI intra-node communication on multi-core systems. In: Parallel Processing, 2008. ICPP\u201908. 37th International Conference on, pp. 222\u2013229. IEEE (2008)","DOI":"10.1109\/ICPP.2008.16"},{"issue":"2","key":"25_CR5","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1109\/TPDS.2010.76","volume":"22","author":"M den Burger","year":"2011","unstructured":"den Burger, M., Kielmann, T.: Collective receiver-initiated multicast for grid applications. Parallel Distrib. Syst. IEEE Trans. 22(2), 231\u2013244 (2011)","journal-title":"Parallel Distrib. Syst. IEEE Trans."},{"key":"25_CR6","unstructured":"Docker: https:\/\/www.docker.com\/ (2019). Accessed 22 Dec 2019"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Friedley, A., Bronevetsky, G., Hoefler, T., Lumsdaine, A.: Hybrid MPI: efficient message passing for multi-core systems. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. ACM, p. 18 (2013)","DOI":"10.1145\/2503210.2503294"},{"issue":"11","key":"25_CR9","doi-asserted-by":"publisher","first-page":"3079","DOI":"10.1109\/TPDS.2013.96","volume":"26","author":"Y Gong","year":"2013","unstructured":"Gong, Y., He, B., Zhong, J.: Network performance aware MPI collective communication operations in the cloud. IEEE Trans. Parallel Distrib. Syst. 26(11), 3079\u20133089 (2013)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Gong, Y., He, B., Li, D.: Finding constant from change: revisiting network performance aware optimizations on IAAS clouds. In: High Performance Computing, Networking, Storage and Analysis, SC14: International Conference for. IEEE, pp. 982\u2013993 (2014)","DOI":"10.1109\/SC.2014.85"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Graham, R.L., Shipman, G.: MPI support for multi-core architectures: Optimized shared memory collectives. In: Recent Advances in Parallel Virtual Machine and Message Passing Interface. Springer, pp. 130\u2013140 (2008)","DOI":"10.1007\/978-3-540-87475-1_21"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Gropp, W.: Mpich2: a new start for MPI implementations. In: Recent Advances in Parallel Virtual Machine and Message Passing Interface. Springer, p. 7 (2002)","DOI":"10.1007\/3-540-45825-5_5"},{"key":"25_CR12","unstructured":"Hanks, S., Meyer, D., Farinacci, D., Traina, P.: Generic routing encapsulation(GRE)RFC 1701 (2000)"},{"issue":"3","key":"25_CR13","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1109\/TPDS.2018.2867879","volume":"30","author":"D Huang","year":"2018","unstructured":"Huang, D., Liu, Q., Klasky, S., Wang, J., Choi, J.Y., Logan, J., Podhorszki, N.: Harnessing data movement in virtual clusters for in-situ execution. IEEE Trans. Parallel Distrib. Syst. 30(3), 615\u2013629 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"1","key":"25_CR14","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/TNSM.2015.2401568","volume":"12","author":"J Hwang","year":"2015","unstructured":"Hwang, J., Ramakrishnan, K.K., Wood, T.: Netvm: high performance and flexible networking using virtualization on commodity platforms. Netw. Serv. Manag. IEEE Trans. 12(1), 34\u201347 (2015)","journal-title":"Netw. Serv. Manag. IEEE Trans."},{"key":"25_CR15","unstructured":"Kamil, S., Shalf, J., Oliker, L., Skinner, D.: Understanding ultra-scale application communication requirements. In: Workload Characterization Symposium, 2005. Proceedings of the IEEE International. IEEE, pp. 178\u2013187 (2005)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Kandalla, K., Subramoni, H., Vishnu, A., Panda, D.K.: Designing topology-aware collective communication algorithms for large scale infiniband clusters: case studies with scatter and gather. In: Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW), 2010 IEEE International Symposium on. IEEE, pp. 1\u20138 (2010)","DOI":"10.1109\/IPDPSW.2010.5470853"},{"key":"25_CR17","unstructured":"Karonis, N.T., De\u00a0Supinski, B.R., Foster, I., Gropp, W., Lusk, E., Bresnahan, J.: Exploiting hierarchy in parallel computer networks to optimize collective operation performance. In: Parallel and Distributed Processing Symposium, 2000. IPDPS 2000. Proceedings. 14th International. IEEE, pp. 377\u2013384 (2000)"},{"issue":"8","key":"25_CR18","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1145\/329366.301116","volume":"34","author":"Thilo Kielmann","year":"1999","unstructured":"Kielmann, Thilo, Hofman, Rutger\u00a0FH, Bal, Henri\u00a0E, Plaat, Aske, Bhoedjang, Raoul\u00a0AF: Magpie: MPI\u2019s collective communication operations for clustered wide area systems. ACM Sigplan Notices 34(8), 131\u2013140 (1999)","journal-title":"ACM Sigplan Notices"},{"key":"25_CR19","unstructured":"Koponen, T., Amidon, K., Balland, P., Casado, M., Chanda, A., Fulton, B., Ganichev, I., Gross, J., Gude, N., Ingram, P., et al.: Network virtualization in multi-tenant datacenters. In: USENIX NSDI (2014)"},{"key":"25_CR20","unstructured":"Kubernetes: http:\/\/kubernetes.io\/ (2019). Accessed 22 Dec 2019"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Kwon, Y., Nunley, D., Gardner, J.P.: Magdalena B., Bill, H., Sarah, L.. Scalable clustering algorithm for N-body simulations in a shared-nothing cluster. Technical Report, University of Washington, Seattle, WA (2009)","DOI":"10.1007\/978-3-642-13818-8_11"},{"issue":"1\u20132","key":"25_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00450-010-0115-3","volume":"25","author":"P Lai","year":"2010","unstructured":"Lai, P., Sur, S., Panda, D.K.: Designing truly one-sided MPI-2 RMA intra-node communication on multi-core systems. Comput. Sci. Res. Dev. 25(1\u20132), 3\u201314 (2010)","journal-title":"Comput. Sci. Res. Dev."},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Li, S., Hoefler, T., Snir, M.: Numa-aware shared-memory collective communication for MPI. In: Proceedings of the 22nd International Aymposium on High-Performance Parallel and Distributed Computing, ACM, pp. 85\u201396 (2013)","DOI":"10.1145\/2462902.2462903"},{"issue":"19","key":"25_CR24","doi-asserted-by":"publisher","first-page":"195004","DOI":"10.1103\/PhysRevLett.88.195004","volume":"88","author":"Z Lin","year":"2002","unstructured":"Lin, Z., Ethier, S., Hahm, T.S., Tang, W.M.: Size scaling of turbulent transport in magnetically confined plasmas. Phys. Rev. Lett. 88(19), 195004 (2002)","journal-title":"Phys. Rev. Lett."},{"key":"25_CR25","unstructured":"Linux Container: https:\/\/linuxcontainers.org\/ (2018). Accessed 22 Sept 2019"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Ma, T., Herault, T., Bosilca, G., Dongarra, J.J.: Process distance-aware adaptive MPI collective communications. In: Cluster Computing (CLUSTER), 2011 IEEE International Conference on. IEEE, pp. 196\u2013204 (2011)","DOI":"10.1109\/CLUSTER.2011.30"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Mahalingam, M., Dutt, D., Duda, K., Agarwal, P., Kreeger, L., Sridhar, T., Bursell, M., Wright, C.: Virtual extensible local area network (vxlan): a framework for overlaying virtualized layer 2 networks over layer 3 networks. Technical Report (2014)","DOI":"10.17487\/rfc7348"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Mamidala, A.R., Kumar, R., De, D., Panda, D.K : MPI collectives on modern multicore clusters: performance optimizations and communication characteristics. In: Cluster Computing and the Grid, 2008. CCGRID\u201908. 8th IEEE International Symposium on. IEEE, pp. 130\u2013137 (2008)","DOI":"10.1109\/CCGRID.2008.87"},{"key":"25_CR29","unstructured":"Probe\u2019s Marmot and Susitna Clusters: http:\/\/nmc-probe.org (2017). Accessed 12 May 2017"},{"key":"25_CR30","unstructured":"Ram, K.K., Cox, A.L., Chadha, M., Rixner, S., Barr, T.W., Smith, R., Rixner, S.: Hyper-switch: a scalable software virtual switching architecture. In: USENIX Annual Technical Conference, pp. 13\u201324 (2013)"},{"issue":"1","key":"25_CR31","first-page":"55","volume":"10","author":"R Reussner","year":"2002","unstructured":"Reussner, R., Sanders, P., Tr\u00e4ff, J.L.: Skampi: a comprehensive benchmark for public benchmarking of MPI. Sci. Program. 10(1), 55\u201365 (2002)","journal-title":"Sci. Program."},{"issue":"3","key":"25_CR32","doi-asserted-by":"publisher","first-page":"033623","DOI":"10.1103\/PhysRevA.65.033623","volume":"65","author":"GL Salmond","year":"2002","unstructured":"Salmond, G.L., Holmes, C.A., Milburn, G.J.: Dynamics of a strongly driven two-component Bose\u2013Einstein condensate. Phys. Rev. A 65(3), 033623 (2002)","journal-title":"Phys. Rev. A"},{"key":"25_CR33","unstructured":"Sergeev, A., Balso, M.D.: Horovod: fast and easy distributed deep learning in tensorflow. arXiv:1802.05799 (2018)"},{"key":"25_CR34","doi-asserted-by":"crossref","unstructured":"Sistare, S., Vandevaart, R., Loh, E.: Optimization of MPI collectives on clusters of large-scale SMP\u2019s. In: Proceedings of the 1999 ACM\/IEEE Conference on Supercomputing, ACM, p.\u00a023 (1999)","DOI":"10.1145\/331532.331555"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Soltesz, S., P\u00f6tzl, H., Fiuczynski, M.E., Bavier, A., Peterson, L.: Container-based operating system virtualization: a scalable, high-performance alternative to hypervisors. In: ACM SIGOPS Operating Systems Review, vol. 41. ACM, pp. 275\u2013287 (2007)","DOI":"10.1145\/1272998.1273025"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Subramoni, H., Kandalla, K., Vienne, J., Sur, S., Barth, B., Tomko, K., Mclay, R., Schulz, K., Panda, D.K: Design and evaluation of network topology-\/speed-aware broadcast algorithms for infiniband clusters. In: Cluster Computing (CLUSTER), 2011 IEEE International Conference on. IEEE, pp. 317\u2013325 (2011)","DOI":"10.1109\/CLUSTER.2011.43"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Subramoni, H., Potluri, S., Kandalla, K., Barth, B., Vienne, J., Keasler, J., Tomko, K., Schulz, K., Moody, A., Panda, D.K: Design of a scalable infiniband topology service to enable network-topology-aware placement of processes. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. IEEE Computer Society Press, p. 70 (2012)","DOI":"10.1109\/SC.2012.47"},{"key":"25_CR38","unstructured":"Sundararaj, A., Gupta, A., Dinda, P., et\u00a0al.: Increasing application performance in virtual environments through run-time inference and adaptation. In: High Performance Distributed Computing, 2005. HPDC-14. Proceedings. 14th IEEE International Symposium on. IEEE (2005), pp. 47\u201358 (2005)"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Thakur, R., Gropp, W.D.: Improving the performance of collective operations in MPICH. In: Recent Advances in Parallel Virtual Machine and Message Passing Interface. Springer, pp. 257\u2013267 (2003)","DOI":"10.1007\/978-3-540-39924-7_38"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Trahay, F., Denis, A., Aumage, O., Namyst, R.: Improving reactivity and communication overlap in MPI using a generic i\/o manager. In: Recent Advances in Parallel Virtual Machine and Message Passing Interface. Springer, pp. 170\u2013177 (2007)","DOI":"10.1007\/978-3-540-75416-9_27"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Vazhkudai, S.S., de\u00a0Supinski, B.R., Bland, Arthur\u00a0S., Geist, A., Sexton, J., Kahle, J., Zimmer, C.J., Atchley, S., Oral, S., Maxwell, D.E. et\u00a0al.: The design, deployment, and evaluation of the coral pre-exascale systems. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis. IEEE Press, p.\u00a052 (2018)","DOI":"10.1109\/SC.2018.00055"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Wang, B., Ethier, S., Tang, W., Williams, T., Ibrahim, K.Z., Madduri, K., Williams, S., Oliker, L.: Kinetic turbulence simulations at extreme scale on leadership-class systems. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. ACM, p.\u00a082 (2013)","DOI":"10.1145\/2503210.2503258"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Xavier, M.G., Neves, M.V., Rossi, F.D, Ferreto, T.C, Lange, T., De Rose, C.A.F: Performance evaluation of container-based virtualization for high performance computing environments. In: Parallel, Distributed and Network-Based Processing (PDP), 2013 21st Euromicro International Conference on. IEEE, pp. 233\u2013240 (2013)","DOI":"10.1109\/PDP.2013.41"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-020-00025-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s42514-020-00025-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-020-00025-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T06:12:46Z","timestamp":1666073566000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s42514-020-00025-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["25"],"URL":"https:\/\/doi.org\/10.1007\/s42514-020-00025-w","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]},"assertion":[{"value":"1 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}