{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:20:33Z","timestamp":1759134033526,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319699523"},{"type":"electronic","value":"9783319699530"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-69953-0_6","type":"book-chapter","created":{"date-parts":[[2018,3,19]],"date-time":"2018-03-19T10:54:32Z","timestamp":1521456872000},"page":"90-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Experiences of Converging Big Data Analytics Frameworks with High Performance Computing Systems"],"prefix":"10.1007","author":[{"given":"Peng","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfei","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiguang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,3,20]]},"reference":[{"issue":"7","key":"6_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-016-5588-7","volume":"59","author":"HH Fu","year":"2016","unstructured":"Fu, H.H., Liao, J.F., Yang, J.Z., Wang, L.N., Song, Z.Y., Huang, X.M., et al.: The Sunway TaihuLight supercomputer: system and applications. Sci. China Inf. Sci. 59(7), 1\u201316 (2016)","journal-title":"Sci. China Inf. Sci."},{"issue":"3","key":"6_CR2","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s11704-014-3501-3","volume":"8","author":"XK Liao","year":"2014","unstructured":"Liao, X.K., Xiao, L.Q., Yang, C.Q., Lu, Y.T.: Milkyway-2 supercomputer: system and application. Front. Comput. Sci. 8(3), 345\u2013356 (2014)","journal-title":"Front. Comput. Sci."},{"key":"6_CR3","unstructured":"Titan - Cray XK7 (2017). https:\/\/www.olcf.ornl.gov\/titan\/"},{"issue":"5","key":"6_CR4","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1007\/s11390-011-0184-1","volume":"26","author":"F Wang","year":"2011","unstructured":"Wang, F., Yang, C.Q., Du, Y.F., Chen, J., Yi, H.Z., Xu, W.X.: Optimizing Linpack benchmark on GPU-accelerated petascale supercomputer. J. Comput. Sci. Technol. 26(5), 854\u2013865 (2011)","journal-title":"J. Comput. Sci. Technol."},{"issue":"5","key":"6_CR5","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1007\/s11771-013-1602-z","volume":"20","author":"C Yang","year":"2013","unstructured":"Yang, C., Wu, Q., Tang, T., Wang, F., Xue, J.: Programming for scientific computing on peta-scale heterogeneous parallel systems. J. Cent. South Univ. 20(5), 1189\u20131203 (2013)","journal-title":"J. Cent. South Univ."},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"French, S., Zheng, Y., Romanowicz, B., Yelick, K.: Parallel Hessian assembly for seismic waveform inversion using global updates. In: IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 753\u2013762. IEEE (2015)","DOI":"10.1109\/IPDPS.2015.58"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Bhandarkar, M.: MapReduce programming with apache Hadoop. In: IEEE International Symposium on Parallel and Distributed Processing (IPDPS), p. 1 (2010)","DOI":"10.1109\/IPDPS.2010.5470377"},{"key":"6_CR8","unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., Mccauley, M.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: USENIX Conference on Networked Systems Design and Implementation, p. 2 (2012)"},{"issue":"7","key":"6_CR9","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.1016\/j.jpdc.2014.01.003","volume":"74","author":"K Kambatla","year":"2014","unstructured":"Kambatla, K., Kollias, G., Kumar, V., Grama, A.: Trends in big data analytics. J. Parallel Distrib. Comput. 74(7), 2561\u20132573 (2014)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"7","key":"6_CR10","doi-asserted-by":"publisher","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(7), 56\u201368 (2015)","journal-title":"Commun. ACM"},{"key":"6_CR11","unstructured":"NASA Center for Climate Simulation (2017). http:\/\/www.nasa.gov\/topics\/earth\/features\/climate-sim-center.html"},{"key":"6_CR12","unstructured":"InfiniBand Homepage (2017). http:\/\/www.infinibandta.org\/"},{"key":"6_CR13","unstructured":"Donovan, S., Kleen, A., Wilcox, M., Huizenga, G., Hutton, A.J.: Lustre: building a file system for 1,000-node clusters. In: Proceedings of the Linux Symposium, p. 9 (2003)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The Hadoop distributed file system. In: MASS Storage Systems and Technologies, pp. 1\u201310 (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Chaimov, N., Malony, A., Canon, S., Iancu, C., Ibrahim, K.Z., Srinivasan, J.: Scaling Spark on HPC systems. In: Proceedings of the 25th ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC), pp. 97\u2013110 (2016)","DOI":"10.1145\/2907294.2907310"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Y., Goldstone, R., Yu, W., Wang, T.: Characterization and optimization of memory-resident MapReduce on HPC systems. In: IEEE International Symposium on Parallel and Distributed Processing (IPDPS), pp. 799\u2013808 (2014)","DOI":"10.1109\/IPDPS.2014.87"},{"key":"6_CR17","unstructured":"Maltzahn, C., Molinaestolano, E., Khurana, A., Nelson, A.J., Brandt, S.A., Weil, S.: Ceph as a scalable alternative to the Hadoop distributed file system. The Magazine of USENIX and SAGE, pp. 38\u201349 (2010)"},{"key":"6_CR18","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: IEEE International Conference on Big Data, pp. 223\u2013232 (2015)","DOI":"10.1109\/BigData.2015.7363759"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Fadika, Z., Dede, E., Govindaraju, M., Ramakrishnan, L.: MARIANE: MApReduce implementation adapted for HPC environments. In: International Conference on Grid Computing, pp. 82\u201389 (2011)","DOI":"10.1109\/Grid.2011.20"},{"key":"6_CR20","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":"10.1145\/2670979.2670985"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Uta, A., Sandu, A., Costache, S., Kielmann, T.: Scalable in-memory computing. In: International Symposium on Cluster, Cloud and Grid Computing, pp. 805\u2013810 (2015)","DOI":"10.1109\/CCGrid.2015.106"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Zhao, D., Zhang, Z., Zhou, X., Li, T.: FusionFS: toward supporting data-intensive scientific applications on extreme-scale high-performance computing systems. In: IEEE International Conference on Big Data, pp. 61\u201370 (2014)","DOI":"10.1109\/BigData.2014.7004214"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Katz, D.S., Wozniak, J.M., Espinosa, A.: Design and analysis of data management in scalable parallel scripting. In: International Conference on High PERFORMANCE Computing, Networking, Storage and Analysis, pp. 1\u201311 (2012)","DOI":"10.1109\/SC.2012.44"},{"key":"6_CR24","unstructured":"IOzone Filesystem Benchmark (2017). http:\/\/www.iozone.org\/"},{"key":"6_CR25","unstructured":"MDTest Metadata Benchmark (2017). https:\/\/github.com\/MDTEST-LANL\/mdtest"},{"key":"6_CR26","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: International Conference on Data Engineering Workshops, pp. 41\u201351 (2010)","DOI":"10.1109\/ICDEW.2010.5452747"},{"key":"6_CR27","unstructured":"Hadoop Adapter for Lustre (HAL) (2017). https:\/\/github.com\/intel-hpdd\/lustre-connector-for-hadoop"},{"issue":"1","key":"6_CR28","first-page":"652","volume":"2","author":"H Hu","year":"2017","unstructured":"Hu, H., Wen, Y., Chua, T.S., Li, X.: Toward scalable systems for big data analytics: a technology tutorial. IEEE Access 2(1), 652\u2013687 (2017)","journal-title":"IEEE Access"},{"issue":"12","key":"6_CR29","first-page":"1793","volume":"11","author":"SN Brohi","year":"2016","unstructured":"Brohi, S.N., Bamiah, M.A., Brohi, M.N.: Identifying and analyzing the transient and permanent barriers for big data. J. Eng. Sci. Technol. 11(12), 1793\u20131807 (2016)","journal-title":"J. Eng. Sci. Technol."},{"issue":"8","key":"6_CR30","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1109\/JPROC.2011.2155130","volume":"99","author":"KM Tolle","year":"2011","unstructured":"Tolle, K.M., Tansley, D.S.W., Hey, A.J.G.: The fourth paradigm: data-intensive scientific discovery [point of view]. Proc. IEEE 99(8), 1334\u20131337 (2011)","journal-title":"Proc. IEEE"},{"key":"6_CR31","doi-asserted-by":"crossref","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: IEEE International Symposium on Parallel and Distributed Processing (IPDPS), pp. 291\u2013300 (2015)","DOI":"10.1109\/IPDPS.2015.83"},{"key":"6_CR32","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.parco.2016.08.001","volume":"61","author":"P Xuan","year":"2016","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 (2016)","journal-title":"Parallel Comput."}],"container-title":["Lecture Notes in Computer Science","Supercomputing Frontiers"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-69953-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,12]],"date-time":"2019-10-12T23:53:58Z","timestamp":1570924438000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-69953-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319699523","9783319699530"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-69953-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}