{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:25:46Z","timestamp":1740176746462,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,3,7]],"date-time":"2020-03-07T00:00:00Z","timestamp":1583539200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,7]],"date-time":"2020-03-07T00:00:00Z","timestamp":1583539200000},"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":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1007\/s41060-020-00206-4","type":"journal-article","created":{"date-parts":[[2020,3,7]],"date-time":"2020-03-07T12:02:53Z","timestamp":1583582573000},"page":"135-159","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic parallelization of representative-based clustering algorithms for multicore cluster systems"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4933-6886","authenticated-orcid":false,"given":"Saiyedul","family":"Islam","sequence":"first","affiliation":[]},{"given":"Sundar","family":"Balasubramaniam","sequence":"additional","affiliation":[]},{"given":"Shruti","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Shikhar","family":"Brajesh","sequence":"additional","affiliation":[]},{"given":"Rohan","family":"Badlani","sequence":"additional","affiliation":[]},{"given":"Nitin","family":"Labhishetty","sequence":"additional","affiliation":[]},{"given":"Abhinav","family":"Baid","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1556-9905","authenticated-orcid":false,"given":"Poonam","family":"Goyal","sequence":"additional","affiliation":[]},{"given":"Navneet","family":"Goyal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,3,7]]},"reference":[{"unstructured":"(2019) Apache Mahout: scalable machine-learning and data-mining library. http:\/\/mahout.apache.org\/","key":"206_CR1"},{"issue":"7","key":"206_CR2","doi-asserted-by":"publisher","first-page":"622","DOI":"10.14778\/2180912.2180915","volume":"5","author":"B Bahmani","year":"2012","unstructured":"Bahmani, B., Moseley, B., Vattani, A., Kumar, R., Vassilvitskii, S.: Scalable k-means++. Proc VLDB Endow 5(7), 622\u2013633 (2012)","journal-title":"Proc VLDB Endow"},{"unstructured":"Benoit, N., Louise, S.: Kimble: a hierarchical intermediate representation for multi-grain parallelism. In: Workshop on Intermediate Representations, pp 21\u201328 (2011)","key":"206_CR3"},{"unstructured":"Berkeley: AMP camp two-Big Data Bootcamp Strata 2013. http:\/\/ampcamp.berkeley.edu\/exercises-strata-conf-2013 (2013)","key":"206_CR4"},{"unstructured":"Bondhugula, U., Hartono, A., Ramanujam, J., Sadayappan, P.: A practical automatic polyhedral program optimization system. In: ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) (2008)","key":"206_CR5"},{"issue":"1\u20132","key":"206_CR6","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/S0167-8191(96)00097-X","volume":"23","author":"T Brandes","year":"1997","unstructured":"Brandes, T., Chaumette, S., Counilh, M., Roman, J., Darte, A., Desprez, F., Mignot, J.: A set of integrated tools for the parallelization of applications using High Performance Fortran. Part I: HPFIT and the TransTOOL environment. Parallel Comput. 23(1\u20132), 71\u201387 (1997). https:\/\/doi.org\/10.1016\/S0167-8191(96)00097-X","journal-title":"Parallel Comput."},{"doi-asserted-by":"crossref","unstructured":"Brown, K.J., Sujeeth, A.K., Lee, H.J., Rompf, T., Chafi, H., Odersky, M., Olukotun, K.: A heterogeneous parallel framework for Domain-Specific Languages. In: 2011 International Conference on Parallel Architectures and Compilation Techniques, pp. 89\u2013100 (2011)","key":"206_CR7","DOI":"10.1109\/PACT.2011.15"},{"doi-asserted-by":"publisher","unstructured":"Buss, A., Papadopoulos, I., Pearce, O.: STAPL: standard template adaptive parallel library. In: 3rd Annual Haifa Experimental Systems Conference on-SYSTOR \u201910, ACM Press, New York, p. 1, https:\/\/doi.org\/10.1145\/1815695.1815713(2010)","key":"206_CR8","DOI":"10.1145\/1815695.1815713"},{"unstructured":"Danial, A.: CLOC-Count Lines of Code. https:\/\/github.com\/AlDanial\/cloc (2006)","key":"206_CR9"},{"issue":"1","key":"206_CR10","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1111\/j.1365-2966.2006.11287.x","volume":"375","author":"G De Lucia","year":"2006","unstructured":"De Lucia, G., Blaizot, J.: The hierarchical formation of the brightest cluster galaxies. Mon. Not. R. Astron. Soc. 375(1), 2\u201314 (2006)","journal-title":"Mon. Not. R. Astron. Soc."},{"issue":"1","key":"206_CR11","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce. Commun. ACM 51(1), 107 (2008)","journal-title":"Commun. ACM"},{"doi-asserted-by":"publisher","unstructured":"Ekanayake, J., Pallickara, S., Fox, G.: MapReduce for data intensive scientific analyses. In: 2008 Fourth IEEE International Conference on eScience, Washington, pp. 277\u2013284, https:\/\/doi.org\/10.1109\/eScience.2008.59 (2008)","key":"206_CR12","DOI":"10.1109\/eScience.2008.59"},{"issue":"4","key":"206_CR13","doi-asserted-by":"publisher","first-page":"1619","DOI":"10.1111\/j.1365-2966.2008.13698.x","volume":"389","author":"AS Font","year":"2008","unstructured":"Font, A.S., Bower, R.G., McCarthy, I.G., Benson, A.J., Frenk, C.S., Helly, J.C.: The colours of satellite galaxies in groups and clusters. Mon. Not. R. Astron. Soc. 389(4), 1619\u20131629 (2008)","journal-title":"Mon. Not. R. Astron. Soc."},{"issue":"5","key":"206_CR14","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1145\/277652.277725","volume":"33","author":"M Frigo","year":"1998","unstructured":"Frigo, M., Leiserson, C.E., Randall, K.H.: The implementation of the Cilk-5 multithreaded language. ACM SIGPLAN Not. 33(5), 212\u2013223 (1998). https:\/\/doi.org\/10.1145\/277652.277725","journal-title":"ACM SIGPLAN Not."},{"issue":"1","key":"206_CR15","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.jpdc.2007.06.007","volume":"68","author":"L Glimcher","year":"2008","unstructured":"Glimcher, L., Jin, R., Agrawal, G.: Middleware for data mining applications on clusters and grids. J. Parallel Distrib. Comput. 68(1), 37\u201353 (2008)","journal-title":"J. Parallel Distrib. Comput."},{"doi-asserted-by":"crossref","unstructured":"Goyal, N., Balasubramaniam, S., Goyal, P., Islam, S., Sati, M.: A High Performance Computing framework for data mining. In: 2016 IEEE International Conference on High Performance Computing Workshops (HiPCW), IEEE, pp. 11\u201318 (2016a)","key":"206_CR16","DOI":"10.1109\/HiPCW.2016.010"},{"doi-asserted-by":"publisher","unstructured":"Goyal, P., Kumari, S., Singh, S., Kishore, V., Balasubramaniam, S.S., Goyal, N.: A parallel framework for grid-based bottom-up subspace clustering. In: Proceedings-3rd IEEE International Conference on Data Science and Advanced Analytics, DSAA 48, pp. 331\u2013340 (2016b). https:\/\/doi.org\/10.1109\/DSAA.2016.42","key":"206_CR17","DOI":"10.1109\/DSAA.2016.42"},{"doi-asserted-by":"crossref","unstructured":"Goyal, P., Kumari, S., Sharma, S., Balasubramaniam, S., Goyal, N.: Parallel SLINK for big data. Int. J. Data Sci. Anal. pp. 1\u201321 (2019)","key":"206_CR18","DOI":"10.1007\/s41060-019-00188-y"},{"key":"206_CR19","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2009.0053","author":"Y Gu","year":"2009","unstructured":"Gu, Y., Grossman, R.L.: Sector and sphere: the design and of a high-performance data cloud. Philos. Trans. R. Soc. A Math. Phys. Eng. Sci. (2009). https:\/\/doi.org\/10.1098\/rsta.2009.0053","journal-title":"Philos. Trans. R. Soc. A Math. Phys. Eng. Sci."},{"issue":"12","key":"206_CR20","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/2.546613","volume":"29","author":"M Hall","year":"1996","unstructured":"Hall, M., Anderson, J., Amarasinghe, S., Murphy, B., Bugnion, E., Lam, M.: Maximizing multiprocessor performance with the SUIF compiler. Computer 29(12), 84\u201389 (1996)","journal-title":"Computer"},{"key":"206_CR21","volume-title":"Elements of Software Science","author":"MH Halstead","year":"1977","unstructured":"Halstead, M.H.: Elements of Software Science. Elsevier, Amesterdam (1977)"},{"doi-asserted-by":"crossref","unstructured":"Husbands, P., Iancu, C., Yelick, K.: A performance analysis of the Berkeley UPC compiler. In: Proceedings of the 17th Annual International Conference on Supercomputing - ICS \u201903, ACM Press, New York, p. 63 (2003)","key":"206_CR22","DOI":"10.1145\/782814.782825"},{"issue":"2","key":"206_CR23","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1093\/ietisy\/e89-d.2.399","volume":"E89\u2013D","author":"M Ishihara","year":"2006","unstructured":"Ishihara, M., Honda, H., Sato, M.: Development and implementation of an interactive parallelization assistance tool for OpenMP: iPat\/OMP. IEICE Trans. Inf. Syst. E89\u2013D(2), 399\u2013407 (2006)","journal-title":"IEICE Trans. Inf. Syst."},{"doi-asserted-by":"crossref","unstructured":"Islam, S., Balasubramaniam, S., Goyal, P., Sati, M., Goyal, N.: A domain specific language for clustering. In: Padmanabhan K., Krishna P.R., Parida L. (eds) Distributed Computing and Internet Technology. ICDCIT 2017. Lecture Notes in Computer Science, vol. 10109, pp 231\u2013234. Springer, Cham (2017)","key":"206_CR24","DOI":"10.1007\/978-3-319-50472-8_19"},{"doi-asserted-by":"crossref","unstructured":"Islam, S., Balasubramaniam, S., Gupta, S., Brajesh, S., Badlani, R., Labhishetty, N., Baid, A., Goyal, P., Goyal, N.: Pattern-based automatic parallelization of representative-based clustering algorithms. In: 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), IEEE, pp. 99\u2013108 (2018)","key":"206_CR25","DOI":"10.1109\/DSAA.2018.00020"},{"doi-asserted-by":"crossref","unstructured":"Islam, S., Balasubramaniam, S., Goyal, P., Sultana, A., Bhutani, L., Raje, S., Goyal, N.: A rapid prototyping approach for High Performance Density-based clustering. In: IEEE 6th International Conference on Data Science and Advanced Analytics (DSAA), IEEE, Washington (2019)","key":"206_CR26","DOI":"10.1109\/DSAA.2019.00041"},{"doi-asserted-by":"crossref","unstructured":"Islam, S., Goyal, N., Balasubramaniam, S., Goyal, P., Agarwal, A., Rathore, K.S., Singh, N.: Rapid prototyping of hierarchical agglomerative clustering algorithms for distributed systems. In: IEEE International Conference on Big Data (Big Data), IEEE, Los Angeles (2019)","key":"206_CR27","DOI":"10.1109\/BigData47090.2019.9006390"},{"unstructured":"Jubertie, S.: Metrics-calculator. https:\/\/github.com\/sjubertie\/metrics-calculator (2015)","key":"206_CR28"},{"doi-asserted-by":"publisher","unstructured":"Kang, U., Tsourakakis, C.E., Faloutsos, C.: PEGASUS: A peta-scale graph mining system-implementation and observations. In: Proceedings-IEEE International Conference on Data Mining (ICDM), pp. 229\u2013238, https:\/\/doi.org\/10.1109\/ICDM.2009.14 (2009)","key":"206_CR29","DOI":"10.1109\/ICDM.2009.14"},{"unstructured":"Kocaguneli, E., Tosun, A., Bener, A.B., Turhan, B., Caglayan, B.: Prest: an intelligent software metrics extraction, analysis and defect prediction tool. In: Proceedings of the 21st International Conference on Software Engineering & Knowledge Engineering (SEKE\u20192009), Boston, 1\u20133 July 2009, Knowledge Systems Institute Graduate School, pp. 637\u2013642 (2009)","key":"206_CR30"},{"issue":"6","key":"206_CR31","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1145\/1273442.1250759","volume":"42","author":"M Kulkarni","year":"2007","unstructured":"Kulkarni, M., Pingali, K., Walter, B., Ramanarayanan, G., Bala, K., Chew, L.P.: Optimistic parallelism requires abstractions. ACM SIGPLAN Not 42(6), 211 (2007)","journal-title":"ACM SIGPLAN Not"},{"doi-asserted-by":"crossref","unstructured":"Kumari, S., Maheshwari, A., Goyal, P., Goyal, N.: Parallel framework for efficient k-means clustering. In: Proceedings of the 8th Annual ACM India Conference on-Compute \u201915, ACM Press, New York, pp. 63\u201371 (2015)","key":"206_CR32","DOI":"10.1145\/2835043.2835060"},{"unstructured":"Liao, W.k.: Parallel K-means data clustering. http:\/\/www.ece.northwestern.edu\/~wkliao\/Kmeans\/index.html (2005)","key":"206_CR33"},{"issue":"4","key":"206_CR34","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/s41060-018-0100-7","volume":"6","author":"T Meng","year":"2018","unstructured":"Meng, T., Yuan, B.: Parallel edge-based visual assessment of cluster tendency on GPU. Int. J. Data Sci. Anal. 6(4), 287\u2013295 (2018)","journal-title":"Int. J. Data Sci. Anal."},{"issue":"34","key":"206_CR35","first-page":"1","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng, X., Bradley, J., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., Freeman, J., Tsai, D.B., Amde, M., Owen, S., Xin, D., Xin, R., Franklin, M.J., Zadeh, R., Zaharia, M., Talwalkar, A.: MLlib: machine learning in Apache Spark. J. Mach. Learn. Res. 17(34), 1\u20137 (2016)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"206_CR36","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1145\/1118890.1118892","volume":"37","author":"M Mernik","year":"2005","unstructured":"Mernik, M., Heering, J., Sloane, A.M.: When and how to develop domain-specific languages. ACM Comput. Surv. 37(4), 316\u2013344 (2005)","journal-title":"ACM Comput. Surv."},{"doi-asserted-by":"crossref","unstructured":"Patwary, M.A., Palsetia, D., Agrawal, A., Liao, W.k., Manne, F., Choudhary, A.: A new scalable parallel DBSCAN algorithm using the disjoint-set data structure. In: International Conference on High Performance Computing, Networking, Storage and Analysis, Los Alamitos, pp. 62:1\u201362:11 (2012)","key":"206_CR37","DOI":"10.1109\/SC.2012.9"},{"unstructured":"Pop, S., Cohen, A., Bastoul, C., Girbal, S., Silber, G.A., Vasilache, N.: GRAPHITE polyhedral analyses and optimizations for GCC. GCC Developer\u2019s Summit, pp. 179\u2013197 (2006)","key":"206_CR38"},{"unstructured":"Ributzka, J.: Open64 compiler and tools. https:\/\/sourceforge.net\/projects\/open64\/?source=navbar (2000)","key":"206_CR39"},{"issue":"3\u20134","key":"206_CR40","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s41060-016-0027-9","volume":"1","author":"S Salloum","year":"2016","unstructured":"Salloum, S., Dautov, R., Chen, X., Peng, P.X., Huang, J.Z.: Big data analytics on Apache Spark. Int. J. Data Sci. Anal. 1(3\u20134), 145\u2013164 (2016)","journal-title":"Int. J. Data Sci. Anal."},{"doi-asserted-by":"crossref","unstructured":"Saraswat, V.V.A., Sarkar, V., von Praun, C., Praun, C.V.: X10: concurrent programming for modern architectures. In: Proceedings of the 12th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming-PPoPP \u201907, ACM Press, New York, p. 271 (2007)","key":"206_CR41","DOI":"10.1145\/1229428.1229483"},{"issue":"7042","key":"206_CR42","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1038\/nature03597","volume":"435","author":"V Springel","year":"2005","unstructured":"Springel, V.: Simulations of the formation, evolution and clustering of galaxies and quasars. Nature 435(7042), 629\u201336 (2005)","journal-title":"Nature"},{"unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauley, M., Franklin, M.J., Shenker, S., Stoica, I.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: 9th USENIX Conference on Networked Systems Design and Implementation, Berkeley, p. 2 (2012)","key":"206_CR43"},{"key":"206_CR44","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810114","volume-title":"Data Mining and Analysis: Fundamental Concepts and Algorithms","author":"MJ Zaki","year":"2014","unstructured":"Zaki, M.J., Wagner Meira, J.: Data Mining and Analysis: Fundamental Concepts and Algorithms. Cambridge University Press, New York (2014)"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-020-00206-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41060-020-00206-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-020-00206-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,7]],"date-time":"2021-03-07T00:17:33Z","timestamp":1615076253000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s41060-020-00206-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,7]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["206"],"URL":"https:\/\/doi.org\/10.1007\/s41060-020-00206-4","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"type":"print","value":"2364-415X"},{"type":"electronic","value":"2364-4168"}],"subject":[],"published":{"date-parts":[[2020,3,7]]},"assertion":[{"value":"2 January 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}