{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:43:46Z","timestamp":1775771026937,"version":"3.50.1"},"reference-count":216,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,8,3]],"date-time":"2019-08-03T00:00:00Z","timestamp":1564790400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,8,3]],"date-time":"2019-08-03T00:00:00Z","timestamp":1564790400000},"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":["Cluster Comput"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s10586-019-02960-y","type":"journal-article","created":{"date-parts":[[2019,8,3]],"date-time":"2019-08-03T10:02:37Z","timestamp":1564826557000},"page":"953-988","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Approaches of enhancing interoperations among high performance computing and big data analytics via augmentation"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7401-1827","authenticated-orcid":false,"given":"Ajeet Ram","family":"Pathak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manjusha","family":"Pandey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddharth S.","family":"Rautaray","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,3]]},"reference":[{"key":"2960_CR1","doi-asserted-by":"crossref","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. Commun. ACM 51 (2008)","DOI":"10.1145\/1327452.1327492"},{"key":"2960_CR2","volume-title":"Hadoop: The Definitive Guide","author":"T White","year":"2012","unstructured":"White, T.: Hadoop: The Definitive Guide. O\u2019Reilly Media, Inc., Newton (2012)"},{"key":"2960_CR3","unstructured":"Apache Spark. https:\/\/spark.apache.org . Accessed 22 Sep 2018"},{"key":"2960_CR4","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2699414","volume":"58","author":"DA Reed","year":"2015","unstructured":"Reed, D.A., Dongarra, J.: Exascale computing and big data. Commun. ACM 58, 56\u201368 (2015)","journal-title":"Commun. ACM"},{"key":"2960_CR5","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.jocs.2015.09.008","volume":"11","author":"E Elsebakhi","year":"2015","unstructured":"Elsebakhi, E., et al.: Large-scale machine learning based on functional networks for biomedical big data with high performance computing platforms. J. Comput. Sci. 11, 69\u201381 (2015)","journal-title":"J. Comput. Sci."},{"key":"2960_CR6","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.jocs.2014.12.001","volume":"6","author":"G Bianchini","year":"2015","unstructured":"Bianchini, G., Caymes-Scutari, P., M\u00e9ndez-Garabetti, M.: Evolutionary-Statistical System: a parallel method for improving forest fire spread prediction. J. Comput. Sci. 6, 58\u201366 (2015)","journal-title":"J. Comput. Sci."},{"key":"2960_CR7","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.compag.2012.08.007","volume":"89","author":"G Zhao","year":"2012","unstructured":"Zhao, G., Bryan, B.A., King, D., Song, X., Yu, Q.: Parallelization and optimization of spatial analysis for large scale environmental model data assembly. Comput. Electron. Agric. 89, 94\u201399 (2012)","journal-title":"Comput. Electron. Agric."},{"key":"2960_CR8","unstructured":"Bhangale, U.M., Kurte, K.R., Durbha, S.S., King, R.L., Younan, N.H.: Big data processing using HPC for remote sensing disaster data. In: Geoscience and Remote Sensing Symposium (IGARSS), 2016, pp. 5894\u20135897. IEEE International (2016)"},{"key":"2960_CR9","unstructured":"Worldwide high-performance data analysis forecast. https:\/\/www.marketresearchfuture.com\/reports\/high-performance-data-analytics-hpda-market-1828"},{"key":"2960_CR10","unstructured":"Cray Urika-XC. http:\/\/www.cray.com\/products\/analytics\/urika-xc . Accessed 27 Sep 2018"},{"key":"2960_CR11","unstructured":"Wrangler. https:\/\/portal.tacc.utexas.edu\/-\/introduction-to-wrangler . Accessed 27 Sep 2018"},{"key":"2960_CR12","unstructured":"HPCC. https:\/\/hpccsystems.com . Accessed 30 Sep 2018"},{"key":"2960_CR13","unstructured":"Bridges. https:\/\/www.psc.edu\/bridges . Accessed 30 Sep 2018"},{"key":"2960_CR14","unstructured":"ADIOS. https:\/\/www.exascaleproject.org\/project\/adios-framework-scientific-data-exascale-systems\/ . Accessed 7 Feb 2019"},{"key":"2960_CR15","unstructured":"CODAR. https:\/\/www.exascaleproject.org\/project\/codar-co-design-center-online-data-analysis-reduction-exascale\/ . Accessed 7 Feb 2019"},{"key":"2960_CR16","unstructured":"EXAFEL. https:\/\/www.exascaleproject.org\/project\/exafel-data-analytics-exascale-free-electron-lasers\/ . Accessed 7 Feb 2019"},{"key":"2960_CR17","unstructured":"ExaLearn Co-Design Center. https:\/\/www.exascaleproject.org\/ecp-announces-new-co-design-center-to-focus-on-exascale-machine-learning-technologies\/ . Accessed 7 Feb 2019"},{"key":"2960_CR18","unstructured":"Park, B.H., Hukerikar, S., Adamson, R., Engelmann, C.: Big data meets HPC log analytics: scalable approach to understanding systems at extreme scale. In: IEEE International Conference on Cluster Computing (CLUSTER), 2017, pp. 758\u2013765 (2017)"},{"key":"2960_CR19","doi-asserted-by":"crossref","unstructured":"Moise, D.: Experiences with performing MapReduce analysis of scientific data on HPC platforms. In: Proceedings of the ACM International Workshop on Data-Intensive Distributed Computing, pp. 11\u201318 (2016)","DOI":"10.1145\/2912152.2912154"},{"key":"2960_CR20","doi-asserted-by":"crossref","unstructured":"Fox, G.C., Qiu, J., Kamburugamuve, S., Jha, S., Luckow, A.: HPC-ABDS high performance computing enhanced Apache big data stack. In: 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 1057\u20131066 (2015)","DOI":"10.1109\/CCGrid.2015.122"},{"key":"2960_CR21","doi-asserted-by":"crossref","unstructured":"Fox, G., Qiu, J., Jha, S., Ekanayake, S., Kamburugamuve, S.: Big data, simulations and HPC convergence. In: Big Data Benchmarking, pp. 3\u201317. Springer (2015)","DOI":"10.1007\/978-3-319-49748-8_1"},{"key":"2960_CR22","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.compeleceng.2015.11.021","volume":"50","author":"J Veiga","year":"2016","unstructured":"Veiga, J., Exp\u00f3sito, R.R., Taboada, G.L., Touri\u00f1o, J.: Analysis and evaluation of MapReduce solutions on an HPC cluster. Comput. Electr. Eng. 50, 200\u2013216 (2016)","journal-title":"Comput. Electr. Eng."},{"key":"2960_CR23","doi-asserted-by":"crossref","unstructured":"Xenopoulos, P., Daniel, J., Matheson, M., Sukumar, S.: Big data analytics on HPC architectures: performance and cost. In 2016 IEEE International Conference on Big Data (Big Data), pp. 2286\u20132295 (2016)","DOI":"10.1109\/BigData.2016.7840861"},{"key":"2960_CR24","doi-asserted-by":"crossref","unstructured":"Asaadi, H., Khaldi, D., Chapman, B.: A comparative survey of the HPC and big data paradigms: analysis and experiments. In: 2016 IEEE International Conference on Cluster Computing (CLUSTER), pp. 423\u2013432 (2016)","DOI":"10.1109\/CLUSTER.2016.21"},{"key":"2960_CR25","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1109\/TPDS.2016.2591947","volume":"28","author":"M Wasi-ur-Rahman","year":"2017","unstructured":"Wasi-ur-Rahman, M., Islam, N.S., Lu, X., Panda, D.K.D.K.: A comprehensive study of MapReduce over Lustre for intermediate data placement and shuffle strategies on HPC clusters. IEEE Trans. Parallel Distrib. Syst. 28, 633\u2013646 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2960_CR26","doi-asserted-by":"crossref","unstructured":"Usman, S., Mehmood, R., Katib, I.: Big data and HPC convergence: the cutting edge and outlook. In: Smart Societies, Infrastructure, Technologies and Applications, pp. 11\u201326. Springer (2018)","DOI":"10.1007\/978-3-319-94180-6_4"},{"key":"2960_CR27","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1177\/1094342018778123","volume":"32","author":"M Asch","year":"2018","unstructured":"Asch, M., et al.: Big data and extreme-scale computing: pathways to convergence-toward a shaping strategy for a future software and data ecosystem for scientific inquiry. Int. J. High Perform. Comput. Appl. 32, 435\u2013479 (2018)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"2960_CR28","unstructured":"The convergence of big data and extreme-scale HPC. https:\/\/www.hpcwire.com\/2018\/08\/31\/the-convergence-of-big-data-and-extreme-scale-hpc\/ . Accessed 22 Sep 2018"},{"key":"2960_CR29","doi-asserted-by":"crossref","unstructured":"Luckow, A., Paraskevakos, I., Chantzialexiou, G., Jha, S.: Hadoop on HPC: integrating Hadoop and pilot-based dynamic resource management. In: 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 1607\u20131616 (2016)","DOI":"10.1109\/IPDPSW.2016.166"},{"key":"2960_CR30","doi-asserted-by":"crossref","unstructured":"Ross, R.B., Thakur, R., et al.: PVFS: a parallel file system for Linux clusters. In: Proceedings of the 4th Annual Linux Showcase and Conference, pp. 391\u2013430 (2000)","DOI":"10.7551\/mitpress\/1556.003.0022"},{"key":"2960_CR31","unstructured":"Nagle, D., Serenyi, D., Matthews, A.: The Panasas ActiveScale storage cluster: delivering scalable high bandwidth storage. In: Proceedings of the 2004 ACM\/IEEE Conference on Supercomputing, p. 53 (2004)"},{"key":"2960_CR32","volume-title":"Managing NFS and NIS: Help for Unix System Administrators","author":"M Eisler","year":"2001","unstructured":"Eisler, M., Labiaga, R., Stern, H.: Managing NFS and NIS: Help for Unix System Administrators. O\u2019Reilly Media, Inc., Newton (2001)"},{"key":"2960_CR33","unstructured":"Schwan, P., et al.: Lustre: building a file system for 1000-node clusters. In: Proceedings of the 2003 Linux Symposium, vol. 2003, pp. 380\u2013386 (2003)"},{"key":"2960_CR34","unstructured":"Schmuck, F.B., Haskin, R.L.: GPFS: a shared-disk file system for large computing clusters. In: FAST, vol. 2 (2002)"},{"key":"2960_CR35","unstructured":"Gu, Y., Grossman, R.L., Szalay, A., Thakar, A.: Distributing the Sloan digital sky survey using UDT and sector. In: Second IEEE International Conference on e-Science and Grid Computing, 2006. e-Science\u201906, p. 56 (2006)"},{"key":"2960_CR36","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The Hadoop distributed file system. In: 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST), pp. 1\u201310 (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"2960_CR37","doi-asserted-by":"publisher","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.-T.: The Google file system. ACM 37 (2003). https:\/\/doi.org\/10.1145\/1165389.945450","DOI":"10.1145\/1165389.945450"},{"key":"2960_CR38","unstructured":"OpenMP. https:\/\/www.openmp.org . Accessed 20 Aug 2018"},{"key":"2960_CR39","unstructured":"MPICH. https:\/\/www.mpich.org . Accessed 20 Aug 2018"},{"key":"2960_CR40","unstructured":"MVAPICH. http:\/\/mvapich.cse.ohio-state.edu . Accessed 20 Aug 2018"},{"key":"2960_CR41","unstructured":"Exascale MPI. https:\/\/www.exascaleproject.org\/project\/exascale-mpi\/ . Accessed 2 Feb 2019"},{"key":"2960_CR42","unstructured":"OMPI-X. https:\/\/www.exascaleproject.org\/project\/ompi-x-open-mpi-exascale\/ . Accessed 2 Feb 2019"},{"key":"2960_CR43","unstructured":"OpenACC. https:\/\/www.openacc.org . Accessed 2 Feb 2019"},{"key":"2960_CR44","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1016\/j.future.2014.10.028","volume":"51","author":"F Zhang","year":"2015","unstructured":"Zhang, F., et al.: CloudFlow: a data-aware programming model for cloud workflow applications on modern HPC systems. Future Gener. Comput. Syst. 51, 98\u2013110 (2015)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR45","doi-asserted-by":"crossref","unstructured":"Venkata, M.G., Aderholdt, F., Parchman, Z.: SharP: Towards programming extreme-scale systems with hierarchical heterogeneous memory. In: 2017 46th International Conference on Parallel Processing Workshops (ICPPW), pp. 145\u2013154 (2017)","DOI":"10.1109\/ICPPW.2017.32"},{"key":"2960_CR46","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.future.2013.12.007","volume":"36","author":"Z Fadika","year":"2014","unstructured":"Fadika, Z., Dede, E., Govindaraju, M., Ramakrishnan, L.: MARIANE: using MapReduce in HPC environments. Future Gener. Comput. Syst. 36, 379\u2013388 (2014)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR47","unstructured":"Luckow, A., et al.: P*: a model of pilot-abstractions. CoRR (2012). http:\/\/arxiv.org\/abs\/1207.6644"},{"key":"2960_CR48","doi-asserted-by":"crossref","unstructured":"Neves, M.V., Ferreto, T., De Rose, C.: Scheduling MapReduce jobs in HPC clusters. In: Euro-Par 2012 Parallel Processing: 18th International Conference, Euro-Par 2012, Proceedings, pp. 179\u2013190. Springer, Berlin (2012)","DOI":"10.1007\/978-3-642-32820-6_19"},{"key":"2960_CR49","doi-asserted-by":"publisher","unstructured":"Sato, K., et al.: A user-level InfiniBand-based file system and checkpoint strategy for burst buffers. In: 2014 14th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 21\u201330 (2014). https:\/\/doi.org\/10.1109\/ccgrid.2014.24","DOI":"10.1109\/ccgrid.2014.24"},{"key":"2960_CR50","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/j.future.2004.11.016","volume":"22","author":"JT Daly","year":"2006","unstructured":"Daly, J.T.: A higher order estimate of the optimum checkpoint interval for restart dumps. Future Gener. Comput. Syst. 22, 303\u2013312 (2006)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR51","unstructured":"Pcocc. https:\/\/pcocc.readthedocs.io\/en\/latest\/ . Accessed 8 March 2019"},{"key":"2960_CR52","unstructured":"TrinityX. https:\/\/trinityx.eu . Accessed 8 March 2019"},{"key":"2960_CR53","unstructured":"OpenStack. https:\/\/www.openstack.org\/ . Accessed 8 March 2019"},{"key":"2960_CR54","unstructured":"Docker. https:\/\/www.docker.com . Accessed 8 March 2019"},{"key":"2960_CR55","unstructured":"Slurm elastic computing. https:\/\/slurm.schedmd.com\/elastic_computing.html . Accessed 8 March 2019"},{"key":"2960_CR56","unstructured":"Xen. https:\/\/xenproject.org . Accessed 8 March 2019"},{"key":"2960_CR57","unstructured":"VMware. https:\/\/www.vmware.com . Accessed 8 March 2019"},{"key":"2960_CR58","unstructured":"KVM. https:\/\/www.linux-kvm.org . Accessed 8 March 2019"},{"key":"2960_CR59","unstructured":"VirtualBox. https:\/\/www.virtualbox.org . Accessed 8 March 2019"},{"key":"2960_CR60","doi-asserted-by":"crossref","unstructured":"Regola, N., Ducom, J.-C.: Recommendations for virtualization technologies in high performance computing. In: 2010 IEEE Second International Conference on Cloud Computing Technology and Science, pp. 409\u2013416 (2010)","DOI":"10.1109\/CloudCom.2010.71"},{"key":"2960_CR61","first-page":"101","volume":"1","author":"EW Biederman","year":"2006","unstructured":"Biederman, E.W., Networx, L.: Multiple instances of the global Linux namespaces. Proc. Linux Symp. 1, 101\u2013112 (2006)","journal-title":"Proc. Linux Symp."},{"key":"2960_CR62","unstructured":"Cgroups. https:\/\/www.kernel.org\/doc\/Documentation\/cgroup-v1\/cgroups.txt . Accessed 10 March 2019"},{"key":"2960_CR63","unstructured":"Linux containers. https:\/\/linuxcontainers.org . Accessed 10 March 2019"},{"key":"2960_CR64","unstructured":"Linux-VServer. www.linux-vserver.org . Accessed 10 March 2019"},{"key":"2960_CR65","unstructured":"OpenVZ. https:\/\/openvz.org . Accessed 10 March 2019"},{"key":"2960_CR66","unstructured":"LXD Linux containers. https:\/\/linuxcontainers.org\/lxd\/introduction . Accessed 10 March 2019"},{"key":"2960_CR67","unstructured":"rkt-CoreOS. https:\/\/coreos.com\/rkt\/ . Accessed 10 March 2019"},{"key":"2960_CR68","doi-asserted-by":"crossref","first-page":"e0177459","DOI":"10.1371\/journal.pone.0177459","volume":"12","author":"GM Kurtzer","year":"2017","unstructured":"Kurtzer, G.M., Sochat, V., Bauer, M.W.: Singularity: scientific containers for mobility of compute. PLoS ONE 12, e0177459 (2017)","journal-title":"PLoS ONE"},{"key":"2960_CR69","unstructured":"Shifter. https:\/\/docs.nersc.gov\/programming\/shifter\/overview\/ . Accessed 14 March 2019"},{"key":"2960_CR70","doi-asserted-by":"crossref","unstructured":"Priedhorsky, R., Randles, T.: Charliecloud: unprivileged containers for user-defined software stacks in HPC. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p. 36 (2017","DOI":"10.1145\/3126908.3126925"},{"key":"2960_CR71","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1145\/1272998.1273025","volume":"41","author":"S Soltesz","year":"2007","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. ACM SIGOPS Oper. Syst. Rev. 41, 275\u2013287 (2007)","journal-title":"ACM SIGOPS Oper. Syst. Rev."},{"key":"2960_CR72","doi-asserted-by":"crossref","unstructured":"Julian, S., Shuey, M., Cook, S.: Containers in research: initial experiences with lightweight infrastructure. In: Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale, p. 25 (2016)","DOI":"10.1145\/2949550.2949562"},{"key":"2960_CR73","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.future.2016.08.025","volume":"68","author":"Z Kozhirbayev","year":"2017","unstructured":"Kozhirbayev, Z., Sinnott, R.O.: A performance comparison of container-based technologies for the cloud. Future Gener. Comput. Syst. 68, 175\u2013182 (2017)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR74","doi-asserted-by":"crossref","unstructured":"Medrano-Jaimes, F., Lozano-Rizk, J.E., Casta\u00f1eda-Avila, S., Rivera-Rodriguez, R.: Use of containers for high-performance computing. In: International Conference on Supercomputing in Mexico, pp. 24\u201332 (2018)","DOI":"10.1007\/978-3-030-10448-1_3"},{"key":"2960_CR75","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13673-017-0124-3","volume":"8","author":"JP Martin","year":"2018","unstructured":"Martin, J.P., Kandasamy, A., Chandrasekaran, K.: Exploring the support for high performance applications in the container runtime environment. Hum. Centric Comput. Inf. Sci. 8, 1 (2018)","journal-title":"Hum. Centric Comput. Inf. Sci."},{"key":"2960_CR76","unstructured":"Shafer, J.: I\/O virtualization bottlenecks in cloud computing today. In: Proceedings of the 2nd Conference on I\/O Virtualization, p. 5 (2010)"},{"key":"2960_CR77","volume-title":"Direct Device Assignment for Untrusted Fully-Virtualized Virtual Machines","author":"B-A Yassour","year":"2008","unstructured":"Yassour, B.-A., Ben-Yehuda, M., Wasserman, O.: Direct Device Assignment for Untrusted Fully-Virtualized Virtual Machines. IBM, Haifa (2008)"},{"key":"2960_CR78","unstructured":"Liu, J., Huang, W., Abali, B., Panda, D.K.: High performance VMM-bypass I\/O in virtual machines. In: USENIX Annual Technical Conference, General Track, pp. 29\u201342 (2006)"},{"key":"2960_CR79","unstructured":"SR-IOV. http:\/\/pcisig.com\/specifications\/iov\/single_root\/ . Accessed 14 March 2019"},{"key":"2960_CR80","doi-asserted-by":"crossref","unstructured":"Gugnani, S., Lu, X., Panda, D.K.: Performance characterization of Hadoop workloads on SR-IOV-enabled virtualized InfiniBand clusters. In: Proceedings of the 3rd IEEE\/ACM International Conference on Big Data Computing, Applications and Technologies, pp. 36\u201345 (2016)","DOI":"10.1145\/3006299.3006313"},{"key":"2960_CR81","doi-asserted-by":"crossref","unstructured":"Hillenbrand, M., Mauch, V., Stoess, J., Miller, K., Bellosa, F.: Virtual InfiniBand clusters for HPC clouds. In: Proceedings of the 2nd International Workshop on Cloud Computing Platforms, p. 9 (2012)","DOI":"10.1145\/2168697.2168706"},{"key":"2960_CR82","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1016\/j.jpdc.2013.01.013","volume":"73","author":"B Nicolae","year":"2013","unstructured":"Nicolae, B., Cappello, F.: BlobCR: virtual disk based checkpoint\u2013restart for HPC applications on IaaS clouds. J. Parallel Distrib. Comput. 73, 698\u2013711 (2013)","journal-title":"J. Parallel Distrib. Comput."},{"key":"2960_CR83","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.jss.2016.11.001","volume":"124","author":"J Ren","year":"2017","unstructured":"Ren, J., Qi, Y., Dai, Y., Xuan, Y., Shi, Y.: nOSV: a lightweight nested-virtualization VMM for hosting high performance computing on cloud. J. Syst. Softw. 124, 137\u2013152 (2017)","journal-title":"J. Syst. Softw."},{"key":"2960_CR84","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lu, X., Chakraborty, S., Panda, D.K. Slurm-V: extending Slurm for building efficient HPC cloud with SR-IOV and IVShmem. In: European Conference on Parallel Processing, pp. 349\u2013362 (2016)","DOI":"10.1007\/978-3-319-43659-3_26"},{"key":"2960_CR85","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s12145-016-0253-7","volume":"9","author":"HA Duran-Limon","year":"2016","unstructured":"Duran-Limon, H.A., Flores-Contreras, J., Parlavantzas, N., Zhao, M., Meulenert-Pe\u00f1a, A.: Efficient execution of the WRF model and other HPC applications in the cloud. Earth Sci. Inform. 9, 365\u2013382 (2016)","journal-title":"Earth Sci. Inform."},{"key":"2960_CR86","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1049\/iet-sen.2009.0091","volume":"5","author":"HA Duran-Limon","year":"2011","unstructured":"Duran-Limon, H.A., Siller, M., Blair, G.S., Lopez, A., Lombera-Landa, J.F.: Using lightweight virtual machines to achieve resource adaptation in middleware. IET Softw. 5, 229\u2013237 (2011)","journal-title":"IET Softw."},{"key":"2960_CR87","doi-asserted-by":"crossref","unstructured":"Yang, C.-T., Wang, H.-Y., Ou, W.-S., Liu, Y.-T., Hsu, C.-H.: On implementation of GPU virtualization using PCI pass-through. In: 4th IEEE International Conference on Cloud Computing Technology and Science Proceedings, pp. 711\u2013716 (2012)","DOI":"10.1109\/CloudCom.2012.6427531"},{"key":"2960_CR88","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/939460","author":"H Jo","year":"2013","unstructured":"Jo, H., Jeong, J., Lee, M., Choi, D.H.: Exploiting GPUs in virtual machine for BioCloud. Biomed. Res. Int. (2013). https:\/\/doi.org\/10.1155\/2013\/939460","journal-title":"Biomed. Res. Int."},{"key":"2960_CR89","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/s10586-018-2845-0","volume":"22","author":"J Prades","year":"2019","unstructured":"Prades, J., Rea\u00f1o, C., Silla, F.: On the effect of using rCUDA to provide CUDA acceleration to Xen virtual machines. Clust. Comput. 22, 185\u2013204 (2019)","journal-title":"Clust. Comput."},{"key":"2960_CR90","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1016\/j.future.2018.12.035","volume":"94","author":"I Mavridis","year":"2019","unstructured":"Mavridis, I., Karatza, H.: Combining containers and virtual machines to enhance isolation and extend functionality on cloud computing. Future Gener. Comput. Syst. 94, 674\u2013696 (2019)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR91","doi-asserted-by":"crossref","first-page":"6236","DOI":"10.1007\/s11227-018-2548-6","volume":"74","author":"R Gad","year":"2018","unstructured":"Gad, R., et al.: Zeroing memory deallocator to reduce checkpoint sizes in virtualized HPC environments. J. Supercomput. 74, 6236\u20136257 (2018)","journal-title":"J. Supercomput."},{"key":"2960_CR92","unstructured":"Trusted Computing Group. https:\/\/trustedcomputinggroup.org . Accessed 27 Feb 2019"},{"key":"2960_CR93","doi-asserted-by":"crossref","unstructured":"Goldman, K., Sailer, R., Pendarakis, D., Srinivasan, D.: Scalable integrity monitoring in virtualized environments. In: Proceedings of the Fifth ACM Workshop on Scalable Trusted Computing, pp. 73\u201378 (2010)","DOI":"10.1145\/1867635.1867647"},{"key":"2960_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, J., Lu, X., Panda, D.K.: Is singularity-based container technology ready for running MPI applications on HPC clouds? In: Proceedings of the 10th International Conference on Utility and Cloud Computing, pp. 151\u2013160 (2017)","DOI":"10.1145\/3147213.3147231"},{"key":"2960_CR95","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.future.2019.02.026","volume":"97","author":"M De Benedictis","year":"2019","unstructured":"De Benedictis, M., Lioy, A.: Integrity verification of Docker containers for a lightweight cloud environment. Future Gener. Comput. Syst. 97, 236\u2013246 (2019)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR96","first-page":"86","volume":"2016","author":"V Costan","year":"2016","unstructured":"Costan, V., Devadas, S.: Intel SGX explained. IACR Cryptol. ePrint Arch. 2016, 86 (2016)","journal-title":"IACR Cryptol. ePrint Arch."},{"key":"2960_CR97","unstructured":"Arnautov, S., et al.: SCONE: secure Linux containers with Intel SGX. In: 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI16), pp. 689\u2013703 (2016)"},{"key":"2960_CR98","unstructured":"Sailer, R., Zhang, X., Jaeger, T., Van Doorn, L.: Design and implementation of a TCG-based integrity measurement architecture. In: USENIX Security Symposium, vol. 13, pp. 223\u2013238 (2004)"},{"key":"2960_CR99","unstructured":"Sun, Y., et al.: Security namespace: making Linux security frameworks available to containers. In: 27th USENIX Security Symposium USENIX Security 18, pp. 1423\u20131439 (2018)"},{"key":"2960_CR100","unstructured":"AppArmor. https:\/\/www.novell.com\/developer\/ndk\/novell_apparmor.html . Accessed 27 Feb 2019"},{"key":"2960_CR101","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1007\/s10270-005-0079-0","volume":"4","author":"J B\u00e9zivin","year":"2005","unstructured":"B\u00e9zivin, J.: On the unification power of models. Softw. Syst. Model. 4, 171\u2013188 (2005)","journal-title":"Softw. Syst. Model."},{"key":"2960_CR102","doi-asserted-by":"crossref","unstructured":"Paraiso, F., Challita, S., Al-Dhuraibi, Y., Merle, P.: Model-driven management of docker containers. In: 2016 IEEE 9th International Conference on Cloud Computing (CLOUD), pp. 718\u2013725 (2016)","DOI":"10.1109\/CLOUD.2016.0100"},{"key":"2960_CR103","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.future.2018.01.022","volume":"83","author":"A P\u00e9rez","year":"2018","unstructured":"P\u00e9rez, A., Molt\u00f3, G., Caballer, M., Calatrava, A.: Serverless computing for container-based architectures. Future Gener. Comput. Syst. 83, 50\u201359 (2018)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR104","unstructured":"AWS Lambda. https:\/\/aws.amazon.com\/lambda . Accessed 1 March 2019"},{"key":"2960_CR105","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1007\/978-3-319-68066-8_13","volume-title":"Economics of Grids, Clouds, Systems, and Services","author":"V Medel","year":"2017","unstructured":"Medel, V., et al.: Client-side scheduling based on application characterization on Kubernetes. In: Pham, C., Altmann, J., Ba\u00f1ares, J.\u00c1. (eds.) Economics of Grids, Clouds, Systems, and Services, pp. 162\u2013176. Springer, Cham (2017)"},{"key":"2960_CR106","doi-asserted-by":"crossref","unstructured":"Yang, X., Liu, N., Feng, B., Sun, X.-H., Zhou, S.: PortHadoop: support direct HPC data processing in Hadoop. In: 2015 IEEE International Conference on Big Data (Big Data), pp. 223\u2013232 (2015)","DOI":"10.1109\/BigData.2015.7363759"},{"key":"2960_CR107","doi-asserted-by":"crossref","unstructured":"Ruan, G., Plale, B.: Horme: random access big data analytics. In: 2016 IEEE International Conference on Cluster Computing (CLUSTER), pp. 364\u2013373 (2016)","DOI":"10.1109\/CLUSTER.2016.27"},{"key":"2960_CR108","doi-asserted-by":"crossref","unstructured":"McAuley, J., Leskovec, J.: Hidden factors and hidden topics: understanding rating dimensions with review text. In: Proceedings of the 7th ACM Conference on Recommender Systems, pp. 165\u2013172 (2013)","DOI":"10.1145\/2507157.2507163"},{"key":"2960_CR109","doi-asserted-by":"crossref","unstructured":"Ren, K., Zheng, Q., Patil, S., Gibson, G.: IndexFS: scaling file system metadata performance with stateless caching and bulk insertion. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 237\u2013248 (2014)","DOI":"10.1109\/SC.2014.25"},{"key":"2960_CR110","doi-asserted-by":"crossref","unstructured":"Takatsu, F., Hiraga, K., Tatebe, O.: PPFS: a scale-out distributed file system for post-petascale systems. In: 2016 IEEE 18th International Conference on High Performance Computing and Communications, pp. 1477\u20131484 (2016)","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0210"},{"key":"2960_CR111","doi-asserted-by":"crossref","unstructured":"Islam, N.S., Lu, X., Wasi-ur-Rahman, M., Shankar, D., Panda, D.K.: Triple-H: a hybrid approach to accelerate HDFS on HPC clusters with heterogeneous storage architecture. In: 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 101\u2013110 (2015)","DOI":"10.1109\/CCGrid.2015.161"},{"key":"2960_CR112","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1145\/502059.502057","volume":"35","author":"M Welsh","year":"2001","unstructured":"Welsh, M., Culler, D., Brewer, E.: SEDA: an architecture for well-conditioned, scalable Internet services. ACM SIGOPS Oper. Syst. Rev. 35, 230\u2013243 (2001)","journal-title":"ACM SIGOPS Oper. Syst. Rev."},{"key":"2960_CR113","unstructured":"Wasi-ur-Rahman, M., Lu, X., Islam, N.S., Rajachandrasekar, R., Panda, D.K.: High-performance design of YARN MapReduce on modern HPC clusters with Lustre and RDMA. In: Parallel and Distributed Processing Symposium (IPDPS), 2015, pp. 291\u2013300. IEEE International (2015)"},{"key":"2960_CR114","doi-asserted-by":"crossref","unstructured":"Rahman, M.W., Lu, X., Islam, N.S., Rajachandrasekar, R., Panda, D.K.: MapReduce over Lustre: can RDMA-based approach benefit? In: Silva, F., Dutra, I., Santos Costa, V. (eds.) Euro-Par 2014 Parallel Processing: 20th International Conference. Proceedings, Porto, Portugal, 25\u201329 August 2014, pp. 644\u2013655. Springer (2014)","DOI":"10.1007\/978-3-319-09873-9_54"},{"key":"2960_CR115","doi-asserted-by":"crossref","unstructured":"Li, H., Ghodsi, A., Zaharia, M., Shenker, S., Stoica, I.: Tachyon: reliable, memory speed storage for cluster computing frameworks. In: Proceedings of the ACM Symposium on Cloud Computing, pp. 1\u201315 (2014)","DOI":"10.21236\/ADA611854"},{"key":"2960_CR116","doi-asserted-by":"crossref","unstructured":"Zhao, D., et al.: FusionFS: toward supporting data-intensive scientific applications on extreme-scale high-performance computing systems. In: 2014 IEEE International Conference on Big Data (Big Data), pp. 61\u201370 (2014)","DOI":"10.1109\/BigData.2014.7004214"},{"key":"2960_CR117","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.parco.2016.08.001","volume":"61","author":"P Xuan","year":"2017","unstructured":"Xuan, P., Ligon, W.B., Srimani, P.K., Ge, R., Luo, F.: Accelerating big data analytics on HPC clusters using two-level storage. Parallel Comput. 61, 18\u201334 (2017)","journal-title":"Parallel Comput."},{"key":"2960_CR118","doi-asserted-by":"crossref","unstructured":"Raynaud, T., Haque, R., Ait-Kaci, H.: CedCom: a high-performance architecture for Big Data applications. In: 2014 IEEE\/ACS 11th International Conference on Computer Systems and Applications (AICCSA), pp. 621\u2013632 (2014)","DOI":"10.1109\/AICCSA.2014.7073257"},{"key":"2960_CR119","doi-asserted-by":"crossref","unstructured":"Cheng, P., Lu, Y., Du, Y., Chen, Z.: Experiences of converging big data analytics frameworks with high performance computing systems. In: Yokota, R., Wu, W. (eds.) Supercomputing Frontiers, pp. 90\u2013106. Springer (2018)","DOI":"10.1007\/978-3-319-69953-0_6"},{"key":"2960_CR120","volume-title":"Accelerating Science with the NERSC Burst Buffer Early User Program","author":"W Bhimji","year":"2016","unstructured":"Bhimji, W., et al.: Accelerating Science with the NERSC Burst Buffer Early User Program. Lawrence National Laboratory, Berkeley (2016)"},{"key":"2960_CR121","unstructured":"Wang, T., Oral, S., Pritchard, M., Vasko, K., Yu, W.: Development of a burst buffer system for data-intensive applications. arXiv Prepr. arXiv1505.01765 (2015)"},{"key":"2960_CR122","unstructured":"Henseler, D., Landsteiner, B., Petesch, D., Wright, C., Wright, N.J.: Architecture and design of Cray DataWarp. In: Cray User Group, CUG (2016)"},{"key":"2960_CR123","doi-asserted-by":"crossref","unstructured":"Wang, T., Mohror, K., Moody, A., Sato, K., Yu, W.: An ephemeral burst-buffer file system for scientific applications. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p. 69 (2016)","DOI":"10.1109\/SC.2016.68"},{"key":"2960_CR124","doi-asserted-by":"crossref","unstructured":"Tang, K., et al.: Toward managing HPC burst buffers effectively: draining strategy to regulate bursty I\/O behavior. In: 2017 IEEE 25th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), pp. 87\u201398 (2017)","DOI":"10.1109\/MASCOTS.2017.35"},{"key":"2960_CR125","unstructured":"UnifyCR. https:\/\/www.exascaleproject.org\/project\/unifycr-file-system-burst-buffers\/ . Accessed 22 2019"},{"key":"2960_CR126","doi-asserted-by":"crossref","unstructured":"Islam, N.S., Shankar, D., Lu, X., Wasi-Ur-Rahman, M., Panda, D.K.: Accelerating I\/O performance of big data analytics on HPC clusters through RDMA-based key-value store. In: 2015 44th International Conference on Parallel Processing, pp. 280\u2013289 (2015)","DOI":"10.1109\/ICPP.2015.79"},{"key":"2960_CR127","doi-asserted-by":"crossref","unstructured":"Wang, Y., Goldstone, R., Yu, W., Wang, T.: Characterization and optimization of memory-resident MapReduce on HPC systems. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 799\u2013808 (2014)","DOI":"10.1109\/IPDPS.2014.87"},{"key":"2960_CR128","doi-asserted-by":"crossref","unstructured":"Yildiz, O., Zhou, A.C., Ibrahim, S.: Improving the effectiveness of burst buffers for big data processing in HPC systems with Eley. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER), pp. 87\u201391 (2017)","DOI":"10.1109\/CLUSTER.2017.73"},{"key":"2960_CR129","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.03.029","author":"O Yildiz","year":"2018","unstructured":"Yildiz, O., Zhou, A.C., Ibrahim, S.: Improving the effectiveness of burst buffers for big data processing in HPC systems with Eley. Future Gener. Comput. Syst. (2018). https:\/\/doi.org\/10.1016\/j.future.2018.03.029","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR130","doi-asserted-by":"crossref","unstructured":"Chaimov, N., et al.: Scaling Spark on HPC systems. In: Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing, pp. 97\u2013110 (2016)","DOI":"10.1145\/2907294.2907310"},{"key":"2960_CR131","doi-asserted-by":"crossref","unstructured":"Islam, N.S., Wasi-ur-Rahman, M., Lu, X., Panda, D.K.: High performance design for HDFS with byte-addressability of NVM and RDMA. In: Proceedings of the 2016 International Conference on Supercomputing, p. 8 (2016)","DOI":"10.1145\/2925426.2926290"},{"key":"2960_CR132","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: BurstMem: a high-performance burst buffer system for scientific applications. In: 2014 IEEE International Conference on Big Data (Big Data), pp. 71\u201379 (2014)","DOI":"10.1109\/BigData.2014.7004215"},{"key":"2960_CR133","unstructured":"Hadoop workload analysis. http:\/\/www.pdl.cmu.edu\/HLA\/index.shtml . Accessed 27 Feb 2018"},{"key":"2960_CR134","doi-asserted-by":"publisher","unstructured":"Liu, N., et al.: On the role of burst buffers in leadership-class storage systems. In 012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST), pp. 1\u201311 (2012). https:\/\/doi.org\/10.1109\/msst.2012.6232369","DOI":"10.1109\/msst.2012.6232369"},{"key":"2960_CR135","doi-asserted-by":"crossref","unstructured":"Wasi-ur-Rahman, M., Islam, N.S., Lu, X., Panda, D.K.: NVMD: non-volatile memory assisted design for accelerating MapReduce and DAG execution frameworks on HPC systems. In: IEEE International Conference on Big Data (Big Data), pp. 369\u2013374 (2017)","DOI":"10.1109\/BigData.2017.8257947"},{"key":"2960_CR136","unstructured":"Moving computation is cheaper than moving data. https:\/\/hadoop.apache.org\/docs\/r1.2.1\/hdfs_design.html . Accessed 22 Sep 2018"},{"key":"2960_CR137","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1002\/cpe.3125","volume":"26","author":"Q Liu","year":"2014","unstructured":"Liu, Q., et al.: Hello ADIOS: the challenges and lessons of developing leadership class I\/O frameworks. Concurr. Comput. Pract. Exp. 26, 1453\u20131473 (2014)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"2960_CR138","unstructured":"Klasky, S., et al.: In situ data processing for extreme-scale computing. In: Proceedings of SciDAC (2011)"},{"key":"2960_CR139","unstructured":"ALPINE Project. https:\/\/www.exascaleproject.org\/project\/alpine-algorithms-infrastructure-situ-visualization-analysis\/ . Accessed 7 Feb 2019"},{"key":"2960_CR140","doi-asserted-by":"crossref","unstructured":"Foster, I., et al.: Computing just what you need: online data analysis and reduction at extreme scales. In: European Conference on Parallel Processing, pp. 3\u201319 (2017)","DOI":"10.1109\/HiPC.2017.00042"},{"key":"2960_CR141","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1080\/17445760.2011.638294","volume":"27","author":"G Mackey","year":"2012","unstructured":"Mackey, G., Sehrish, S., Mitchell, C., Bent, J., Wang, J.: USFD: a unified storage framework for SOAR HPC scientific workflows. Int. J. Parallel Emerg. Distrib. Syst. 27, 347\u2013367 (2012)","journal-title":"Int. J. Parallel Emerg. Distrib. Syst."},{"key":"2960_CR142","unstructured":"EZ. https:\/\/www.exascaleproject.org\/project\/ez-fast-effective-parallel-error-bounded-exascale-lossy-compression-scientific-data\/ . Accessed 7 Feb 2019"},{"key":"2960_CR143","doi-asserted-by":"crossref","unstructured":"Tao, D., Di, S., Chen, Z., Cappello, F.: Significantly improving lossy compression for scientific data sets based on multidimensional prediction and error-controlled quantization. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 1129\u20131139 (2017)","DOI":"10.1109\/IPDPS.2017.115"},{"key":"2960_CR144","doi-asserted-by":"crossref","first-page":"2069","DOI":"10.1007\/s11227-016-1904-7","volume":"73","author":"SW Son","year":"2017","unstructured":"Son, S.W., Sehrish, S., Liao, W., Oldfield, R., Choudhary, A.: Reducing I\/O variability using dynamic I\/O path characterization in petascale storage systems. J. Supercomput. 73, 2069\u20132097 (2017)","journal-title":"J. Supercomput."},{"key":"2960_CR145","doi-asserted-by":"crossref","unstructured":"Wang, T., Oral, S., Pritchard, M., Wang, B., Yu, W.: TRIO: burst buffer based I\/O orchestration. In: 2015 IEEE International Conference on Cluster Computing, pp. 194\u2013203 (2015)","DOI":"10.1109\/CLUSTER.2015.38"},{"key":"2960_CR146","doi-asserted-by":"crossref","unstructured":"Kougkas, A., Dorier, M., Latham, R., Ross, R., Sun, X.-H.: Leveraging burst buffer coordination to prevent I\/O interference. In: 2016 IEEE 12th International Conference on e-Science (e-Science), pp. 371\u2013380 (2016)","DOI":"10.1109\/eScience.2016.7870922"},{"key":"2960_CR147","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.parco.2018.01.004","volume":"76","author":"X Zhang","year":"2018","unstructured":"Zhang, X., Jiang, S., Diallo, A., Wang, L.: IR+: removing parallel I\/O interference of MPI programs via data replication over heterogeneous storage devices. Parallel Comput. 76, 91\u2013105 (2018)","journal-title":"Parallel Comput."},{"key":"2960_CR148","doi-asserted-by":"crossref","unstructured":"Han, J., et al.: Accelerating a burst buffer via user-level I\/O isolation. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER), pp. 245\u2013255 (2017)","DOI":"10.1109\/CLUSTER.2017.60"},{"key":"2960_CR149","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TPDS.2015.2389262","volume":"27","author":"C Xu","year":"2016","unstructured":"Xu, C., et al.: Exploiting analytics shipping with virtualized MapReduce on HPC backend storage servers. IEEE Trans. Parallel Distrib. Syst. 27, 185\u2013196 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"2960_CR150","doi-asserted-by":"crossref","unstructured":"da Silva, R.F., Callaghan, S., Deelman, E.: On the use of burst buffers for accelerating data-intensive scientific workflows. In: Proceedings of the 12th Workshop on Workflows in Support of Large-Scale Science, p. 2 (2017)","DOI":"10.1145\/3150994.3151000"},{"key":"2960_CR151","doi-asserted-by":"crossref","unstructured":"Dreher, M., Raffin, B.: A flexible framework for asynchronous in situ and in transit analytics for scientific simulations. In: 2014 14th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 277\u2013286 (2014)","DOI":"10.1109\/CCGrid.2014.92"},{"key":"2960_CR152","doi-asserted-by":"crossref","unstructured":"Malitsky, N.: Bringing the HPC reconstruction algorithms to Big Data platforms. In: 2016 New York Scientific Data Summit (NYSDS), pp. 1\u20138 (2016)","DOI":"10.1109\/NYSDS.2016.7747818"},{"key":"2960_CR153","unstructured":"OpenFabrics. http:\/\/www.openfabrics.org\/ . Accessed 22 Sep 2018"},{"key":"2960_CR154","doi-asserted-by":"crossref","unstructured":"Wasi-ur-Rahman, M., et al.: High-performance RDMA-based design of Hadoop MapReduce over InfiniBand. In: 2013 IEEE 27th International Parallel and Distributed Processing Symposium Workshops and PhD Forum (IPDPSW), pp. 1908\u20131917 (2013)","DOI":"10.1109\/IPDPSW.2013.238"},{"key":"2960_CR155","doi-asserted-by":"crossref","unstructured":"Rahman, M.W., Lu, X., Islam, N.S., Panda, D.K.: HOMR: a hybrid approach to exploit maximum overlapping in MapReduce over high performance interconnects. In: Proceedings of the 28th ACM International Conference on Supercomputing, pp. 33\u201342 (2014)","DOI":"10.1145\/2597652.2597684"},{"key":"2960_CR156","unstructured":"High Performance Data Analytics: Experiences of Porting the Apache Hama Graph Analytics Framework to an HPC InfiniBand Connected Cluster (White Paper). https:\/\/gdmissionsystems.com\/-\/media\/General-Dynamics\/Cyber-and-Electronic-Warfare-Systems\/PDF\/Brochures\/high-performance-data-analytics-whitepaper-2015.ashx"},{"key":"2960_CR157","doi-asserted-by":"crossref","unstructured":"Li, M., Lu, X., Hamidouche, K., Zhang, J., Panda, D.K.: Mizan-RMA: accelerating Mizan graph processing framework with MPI RMA. In: IEEE 23rd International Conference on High Performance Computing (HiPC), 42\u201351 (2016)","DOI":"10.1109\/HiPC.2016.015"},{"key":"2960_CR158","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Designing MPI library with on-demand paging (ODP) of InfiniBand: challenges and benefits. In: SC\u201916: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 433\u2013443 (2016)","DOI":"10.1109\/SC.2016.36"},{"key":"2960_CR159","doi-asserted-by":"crossref","unstructured":"Lu, X., Wang, B., Zha, L., Xu, Z.: Can MPI benefit Hadoop and MapReduce applications? In: 2011 40th International Conference on Parallel Processing Workshops, pp. 371\u2013379 (2011)","DOI":"10.1109\/ICPPW.2011.56"},{"key":"2960_CR160","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xu, C., Li, X., Yu, W.: JVM-bypass for efficient Hadoop shuffling. In 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, pp. 569\u2013578 (2013)","DOI":"10.1109\/IPDPS.2013.13"},{"key":"2960_CR161","unstructured":"Sur, S., Wang, H., Huang, J., Ouyang, X., Panda, D.K.: Can high-performance interconnects benefit Hadoop distributed file system? In: Workshop on Micro Architectural Support for Virtualization, Data Center Computing, and Clouds (MASVDC). Held in Conjunction with MICRO (2010)"},{"key":"2960_CR162","doi-asserted-by":"crossref","unstructured":"Jose, J., et al.: Memcached design on high performance RDMA capable interconnects. In: 2011 International Conference on Parallel Processing, pp. 743\u2013752 (2011)","DOI":"10.1109\/ICPP.2011.37"},{"key":"2960_CR163","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 (2010)","DOI":"10.1145\/2020373.2020378"},{"key":"2960_CR164","doi-asserted-by":"crossref","unstructured":"Islam, N.S., et al.: 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 (2012)","DOI":"10.1109\/SC.2012.65"},{"key":"2960_CR165","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: High-performance design of HBase with RDMA over InfiniBand. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium, pp. 774\u2013785 (2012)","DOI":"10.1109\/IPDPS.2012.74"},{"key":"2960_CR166","doi-asserted-by":"crossref","unstructured":"Lu, X., et al.: High-performance design of Hadoop RPC with RDMA over InfiniBand. In: 2013 42nd International Conference on Parallel Processing, pp. 641\u2013650 (2013)","DOI":"10.1109\/ICPP.2013.78"},{"key":"2960_CR167","doi-asserted-by":"crossref","unstructured":"Islam, N.S., Lu, X., Rahman, M.W., Panda, D.K.: SOR-HDFS: a SEDA-based approach to maximize overlapping in RDMA-enhanced HDFS. In: Proceedings of the 23rd International Symposium on High-Performance Parallel and Distributed Computing, pp. 261\u2013264 (2014)","DOI":"10.1145\/2600212.2600715"},{"key":"2960_CR168","doi-asserted-by":"crossref","unstructured":"Lu, X., Rahman, M.W.U., Islam, N., Shankar, D., Panda, D.K.: Accelerating Spark with RDMA for big data processing: early experiences. In: 2014 IEEE 22nd Annual Symposium on High-Performance Interconnects, pp. 9\u201316 (2014)","DOI":"10.1109\/HOTI.2014.15"},{"key":"2960_CR169","doi-asserted-by":"crossref","unstructured":"Islam, N.S., Lu, X., Wasi-ur-Rahman, M., Panda, D.K.: Can parallel replication benefit Hadoop distributed file system for high performance interconnects? In: 2013 IEEE 21st Annual Symposium on High-Performance Interconnects, pp. 75\u201378 (2013)","DOI":"10.1109\/HOTI.2013.24"},{"key":"2960_CR170","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.micpro.2018.05.009","volume":"61","author":"M Katevenis","year":"2018","unstructured":"Katevenis, M., et al.: Next generation of Exascale-class systems: ExaNeSt Project and the status of its interconnect and storage development. Microprocess. Microsyst. 61, 58\u201371 (2018)","journal-title":"Microprocess. Microsyst."},{"key":"2960_CR171","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.future.2016.04.003","volume":"72","author":"F Zahid","year":"2017","unstructured":"Zahid, F., Gran, E.G., Bogda\u0144ski, B., Johnsen, B.D., Skeie, T.: Efficient network isolation and load balancing in multi-tenant HPC clusters. Future Gener. Comput. Syst. 72, 145\u2013162 (2017)","journal-title":"Future Gener. Comput. Syst."},{"key":"2960_CR172","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.jpdc.2016.07.001","volume":"108","author":"J Wang","year":"2017","unstructured":"Wang, J., et al.: SideIO: a side I\/O system framework for hybrid scientific workflow. J. Parallel Distrib. Comput. 108, 45\u201358 (2017)","journal-title":"J. Parallel Distrib. Comput."},{"key":"2960_CR173","doi-asserted-by":"crossref","unstructured":"Huang, D., et al.: UNIO: a unified I\/O system framework for hybrid scientific workflow. In: Second International Conference on Cloud Computing and Big Data in Asia, pp. 99\u2013114 (2015)","DOI":"10.1007\/978-3-319-28430-9_8"},{"key":"2960_CR174","unstructured":"Hadoop on demand. https:\/\/svn.apache.org\/repos\/asf\/hadoop\/common\/tags\/release-0.17.1\/docs\/hod.html . Accessed 22 Sep 2018"},{"key":"2960_CR175","unstructured":"Magpie. https:\/\/github.com\/LLNL\/magpie . Accessed 22 Sep 2018"},{"key":"2960_CR176","doi-asserted-by":"crossref","unstructured":"Moody, W.C., Ngo, L.B., Duffy, E., Apon, A.: JUMMP: job uninterrupted maneuverable MapReduce platform. In: 2013 IEEE International Conference on Cluster Computing (CLUSTER), pp. 1\u20138 (2013)","DOI":"10.1109\/CLUSTER.2013.6702650"},{"key":"2960_CR177","unstructured":"Krishnan, S., Tatineni, M., Baru, C.: myHadoop-Hadoop-on-Demand on Traditional HPC Resources. San Diego Supercomputer Center Technical Report. TR-2011-2. University of California, San Diego (2011)"},{"key":"2960_CR178","doi-asserted-by":"crossref","unstructured":"Lu, T., et al.: Canopus: a paradigm shift towards elastic extreme-scale data analytics on HPC storage. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER), pp. 58\u201369 (2017)","DOI":"10.1109\/CLUSTER.2017.62"},{"key":"2960_CR179","unstructured":"EXAHDF5. https:\/\/www.exascaleproject.org\/project\/exahdf5-delivering-efficient-parallel-o-exascale-computing-systems\/ . Accessed 7 Feb 2019"},{"key":"2960_CR180","doi-asserted-by":"publisher","unstructured":"Mercier, M., Glesser, D., Georgiou, Y., Richard, O.: Big data and HPC collocation: using HPC idle resources for Big Data analytics. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 347\u2013352 (2017). https:\/\/doi.org\/10.1109\/bigdata.2017.8257944","DOI":"10.1109\/bigdata.2017.8257944"},{"key":"2960_CR181","unstructured":"Turilli, M., Santcroos, M., Jha, S.: A comprehensive perspective on the pilot-job abstraction. CoRR (2015). http:\/\/arxiv.org\/abs\/1508.04180"},{"key":"2960_CR182","unstructured":"Merzky, A., Santcroos, M., Turilli, M., Jha, S.: RADICAL-Pilot: scalable execution of heterogeneous and dynamic workloads on supercomputers. CoRR (2015). http:\/\/arxiv.org\/abs\/1512.08194"},{"key":"2960_CR183","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.softx.2015.03.001","volume":"1","author":"A Merzky","year":"2015","unstructured":"Merzky, A., Weidner, O., Jha, S.: SAGA: a standardized access layer to heterogeneous distributed computing infrastructure. SoftwareX 1, 3\u20138 (2015)","journal-title":"SoftwareX"},{"key":"2960_CR184","unstructured":"SAGA-Hadoop. https:\/\/github.com\/drelu\/saga-hadoop . Accessed 22 Sep 2018"},{"key":"2960_CR185","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.jpdc.2017.11.004","volume":"120","author":"MW Rahman","year":"2018","unstructured":"Rahman, M.W., Islam, N.S., Lu, X., Shankar, D., Panda, D.K.: MR-Advisor: a comprehensive tuning, profiling, and prediction tool for MapReduce execution frameworks on HPC clusters. J. Parallel Distrib. Comput. 120, 237\u2013250 (2018)","journal-title":"J. Parallel Distrib. Comput."},{"key":"2960_CR186","doi-asserted-by":"crossref","unstructured":"Jin, H., Ji, J., Sun, X.-H., Chen, Y., Thakur, R.: CHAIO: enabling HPC applications on data-intensive file systems. In: 2012 41st International Conference on Parallel Processing, pp. 369\u2013378 (2012)","DOI":"10.1109\/ICPP.2012.1"},{"key":"2960_CR187","doi-asserted-by":"crossref","unstructured":"Aupy, G., Gainaru, A., Le F\u00e8vre, V.: Periodic I\/O scheduling for super-computers. In: International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems, pp. 44\u201366 (2017)","DOI":"10.1007\/978-3-319-72971-8_3"},{"key":"2960_CR188","doi-asserted-by":"crossref","unstructured":"Gao, C., Ren, R., Cai, H.: GAI: a centralized tree-based scheduler for machine learning workload in large shared clusters. In: International Conference on Algorithms and Architectures for Parallel Processing, pp. 611\u2013629 (2018)","DOI":"10.1007\/978-3-030-05054-2_46"},{"key":"2960_CR189","unstructured":"Ekanayake, S., Kamburugamuve, S., Fox, G.C.: SPIDAL Java: high performance data analytics with Java and MPI on large multicore HPC clusters. In: Proceedings of 24th High Performance Computing Symposium (2016)"},{"key":"2960_CR190","unstructured":"NVIDIA NCCL. https:\/\/developer.nvidia.com\/nccl . Accessed 22 Sep 2018"},{"key":"2960_CR191","doi-asserted-by":"crossref","unstructured":"Wickramasinghe, U.S., Bronevetsky, G., Lumsdaine, A., Friedley, A.: Hybrid MPI: a case study on the Xeon Phi platform. In: ACM Proceedings of the 4th International Workshop on Runtime and Operating Systems for Supercomputers, pp. 6:1\u20136:8 (2014)","DOI":"10.1145\/2612262.2612267"},{"key":"2960_CR192","unstructured":"DATALIB. https:\/\/www.exascaleproject.org\/project\/datalib-data-libraries-services-enabling-exascale-science\/ . Accessed 7 Feb 2019"},{"key":"2960_CR193","doi-asserted-by":"publisher","unstructured":"Gittens, A., et al.: Matrix factorizations at scale: a comparison of scientific data analytics in Spark and C +MPI using three case studies. In: 2016 IEEE International Conference on Big Data (Big Data), pp. 204\u2013213 (2016). https:\/\/doi.org\/10.1109\/bigdata.2016.7840606","DOI":"10.1109\/bigdata.2016.7840606"},{"key":"2960_CR194","doi-asserted-by":"crossref","unstructured":"Jha, S., Qiu, J., Luckow, A., Mantha, P., Fox, G.C.: A tale of two data-intensive paradigms: applications, abstractions, and architectures. In: 2014 IEEE International Congress on Big Data (BigData Congress), pp. 645\u2013652 (2014)","DOI":"10.1109\/BigData.Congress.2014.137"},{"key":"2960_CR195","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.procs.2015.07.286","volume":"53","author":"JL Reyes-Ortiz","year":"2015","unstructured":"Reyes-Ortiz, J.L., Oneto, L., Anguita, D.: Big data analytics in the cloud: Spark on Hadoop vs MPI\/OpenMP on Beowulf. Procedia Comput. Sci. 53, 121\u2013130 (2015)","journal-title":"Procedia Comput. Sci."},{"key":"2960_CR196","doi-asserted-by":"crossref","first-page":"901","DOI":"10.14778\/3090163.3090168","volume":"10","author":"M Anderson","year":"2017","unstructured":"Anderson, M., et al.: Bridging the gap between HPC and Big Data frameworks. Proc. VLDB Endow. 10, 901\u2013912 (2017)","journal-title":"Proc. VLDB Endow."},{"key":"2960_CR197","doi-asserted-by":"crossref","unstructured":"Guo, Y., Bland, W., Balaji, P., Zhou, X.: Fault tolerant MapReduce-MPI for HPC clusters. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p. 34 (2015)","DOI":"10.1145\/2807591.2807617"},{"key":"2960_CR198","unstructured":"SCR. https:\/\/computation.llnl.gov\/projects\/scalable-checkpoint-restart-for-mpi . Accessed 22 Sep 2018"},{"key":"2960_CR199","doi-asserted-by":"crossref","unstructured":"Moody, A., Bronevetsky, G., Mohror, K., De Supinski, B.R.: Design, modeling, and evaluation of a scalable multi-level checkpointing system. In: SC\u201910: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201311 (2010)","DOI":"10.1109\/SC.2010.18"},{"key":"2960_CR200","doi-asserted-by":"crossref","unstructured":"Rajachandrasekar, R., Moody, A., Mohror, K., Panda, D.K.: A 1\u00a0PB\/s file system to checkpoint three million MPI tasks. In: Proceedings of the 22nd International Symposium on High-Performance Parallel and Distributed Computing, pp. 143\u2013154 (2013)","DOI":"10.1145\/2462902.2462908"},{"key":"2960_CR201","unstructured":"VeloC. https:\/\/www.exascaleproject.org\/project\/veloc-low-overhead-transparent-multilevel-checkpoint-restart\/ . Accessed 7 Feb 2019"},{"key":"2960_CR202","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.jpdc.2014.09.005","volume":"76","author":"Y You","year":"2015","unstructured":"You, Y., et al.: Scaling support vector machines on modern HPC platforms. J. Parallel Distrib. Comput. 76, 16\u201331 (2015)","journal-title":"J. Parallel Distrib. Comput."},{"key":"2960_CR203","unstructured":"TeraSort. http:\/\/sortbenchmark.org . Accessed 22 Sep 2018"},{"key":"2960_CR204","unstructured":"Ahmad, F., Lee, S., Thottethodi, M., Vijaykumar, T.N.: PUMA: Purdue MapReduce benchmarks suite (2012)"},{"key":"2960_CR205","unstructured":"IOZone benchmark. http:\/\/www.iozone.org . Accessed 22 Sep 2018"},{"key":"2960_CR206","unstructured":"Shan, H., Shalf, J.: Using IOR to analyze the I\/O performance for HPC platforms. In: Cray User Group Conference 2007, Seattle, WA, USA (2007)"},{"key":"2960_CR207","doi-asserted-by":"crossref","unstructured":"Huang, S., Huang, J., Dai, J., Xie, T., Huang, B.: The HiBench benchmark suite: characterization of the MapReduce-based data analysis. In: New Frontiers in Information and Software as Services, pp. 209\u2013228 (2011)","DOI":"10.1007\/978-3-642-19294-4_9"},{"key":"2960_CR208","doi-asserted-by":"crossref","unstructured":"Huang, S., Huang, J., Dai, J., Xie, T., Huang, B.: The HiBench benchmark suite: characterization of the MapReduce-based data analysis. In: IEEE 26th International Conference on Data Engineering Workshops (ICDEW), pp. 41\u201351 (2010)","DOI":"10.1109\/ICDEW.2010.5452747"},{"key":"2960_CR209","unstructured":"Gao, W., et al.: BigDataBench: a dwarf-based big data and AI benchmark suite. CoRR (2018). http:\/\/arxiv.org\/abs\/1802.08254"},{"key":"2960_CR210","unstructured":"OSU HiBD-benchmark. http:\/\/hibd.cse.ohio-state.edu . Accessed 22 Sep 2018"},{"key":"2960_CR211","unstructured":"HPL\u2014a portable implementation of the high-performance Linpack benchmark for distributed-memory computers. http:\/\/www.netlib.org\/benchmark\/hpl\/"},{"key":"2960_CR212","unstructured":"Graph500. https:\/\/graph500.org\/ . Accessed 22 Sep 2018"},{"key":"2960_CR213","unstructured":"BLAST. https:\/\/blast.ncbi.nlm.nih.gov\/Blast.cgi . Accessed 22 Sep 2018"},{"key":"2960_CR214","unstructured":"GridMix. https:\/\/hadoop.apache.org\/docs\/r1.2.1\/gridmix.html . Accessed 22 Sep 2018"},{"key":"2960_CR215","unstructured":"Parallel Workload Archive. http:\/\/www.cs.huji.ac.il\/labs\/parallel\/workload\/ . Accessed 22 Sep 2018"},{"key":"2960_CR216","unstructured":"Albrecht, J.: Challenges for the LHC Run 3: Computing and Algorithms. (2016)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02960-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-02960-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02960-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T17:30:38Z","timestamp":1721583038000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-02960-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,3]]},"references-count":216,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["2960"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-02960-y","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,3]]},"assertion":[{"value":"22 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}