{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:06Z","timestamp":1740123546102,"version":"3.37.3"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2016,5,11]],"date-time":"2016-05-11T00:00:00Z","timestamp":1462924800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UID\/CEC\/04516\/2013"],"award-info":[{"award-number":["UID\/CEC\/04516\/2013"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,8]]},"DOI":"10.1007\/s11227-016-1721-z","type":"journal-article","created":{"date-parts":[[2016,5,11]],"date-time":"2016-05-11T08:52:34Z","timestamp":1462956754000},"page":"3366-3390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cache-conscious run-time decomposition of data parallel computations"],"prefix":"10.1007","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7958-9740","authenticated-orcid":false,"given":"Herv\u00e9","family":"Paulino","sequence":"first","affiliation":[]},{"given":"Nuno","family":"Delgado","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,5,11]]},"reference":[{"key":"1721_CR1","unstructured":"Apache Inc (2015) Apache hadoop. \n                        http:\/\/hadoop.apache.org\/"},{"key":"1721_CR2","doi-asserted-by":"crossref","unstructured":"Bauer M, Clark J, Schkufza E, Aiken A (2011) Programming the memory hierarchy revisited: supporting irregular parallelism in Sequoia. In: Proceedings of the 16th ACM SIGPLAN symposium on principles and practice of parallel programming, PPOPP 2011, ACM, pp 13\u201324","DOI":"10.1145\/1941553.1941558"},{"key":"1721_CR3","unstructured":"Biksh G et al (2006) Programming for parallelism and locality with hierarchically tiled arrays. In: Proceedings of the eleventh ACM SIGPLAN symposium on principles and practice of parallel programming (PPoPP 2006), pp 48\u201357"},{"issue":"1","key":"1721_CR4","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1021\/jo3008226","volume":"10","author":"R Chen","year":"2013","unstructured":"Chen R, Chen H (2013) Tiled-MapReduce: efficient and flexible MapReduce processing on multicore with tiling. TACO 10(1):3","journal-title":"TACO"},{"issue":"1","key":"1721_CR5","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) MapReduce: simplified data processing on large clusters. Commun ACM 51(1):107\u2013113","journal-title":"Commun ACM"},{"key":"1721_CR6","unstructured":"Elina (2012) Elina framework for distributed parallel computing in java. \n                        https:\/\/bitbucket.org\/hervepaulino\/elina\n                        \n                    . Last visited in February 2016"},{"key":"1721_CR7","doi-asserted-by":"crossref","unstructured":"Fatahalian K et al (2006) Sequoia: programming the memory hierarchy. In: Proceedings of the ACM\/IEEE SC2006 conference on high performance networking and computing. ACM Press, p\u00a083","DOI":"10.1109\/SC.2006.55"},{"key":"1721_CR8","doi-asserted-by":"crossref","unstructured":"Frigo M et al (1999) Cache-oblivious algorithms. In: 40th Annual symposium on foundations of computer science, FOCS \u201999, IEEE Computer Society, pp 285\u2013298","DOI":"10.1109\/SFFCS.1999.814600"},{"key":"1721_CR9","doi-asserted-by":"publisher","unstructured":"Paulino H, Marques E (2015) Heterogeneous programming with single operation multiple data. J Comput Syst Sci 81(1):16\u201337. doi:\n                        10.1016\/j.jcss.2014.06.021","DOI":"10.1016\/j.jcss.2014.06.021"},{"key":"1721_CR10","doi-asserted-by":"crossref","unstructured":"Kamil A, Yelick K (2014) Hierarchical computation in the SPMD programming model. In: Proceedings of the 26th international workshop on languages and compilers for parallel computing (LCPC 2013), vol 8664. LNCS. Springer, Berlin, pp 3\u201319","DOI":"10.1007\/978-3-319-09967-5_1"},{"key":"1721_CR11","unstructured":"Mao Y, Morris R, Kaashoek MF (2010) Optimizing MapReduce for multicore architectures. Technical report, Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology"},{"issue":"4","key":"1721_CR12","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1145\/233561.233564","volume":"18","author":"KS McKinley","year":"1996","unstructured":"McKinley KS, Carr S, Tseng CW (1996) Improving data locality with loop transformations. ACM Trans Program Lang Syst 18(4):424\u2013453","journal-title":"ACM Trans Program Lang Syst"},{"key":"1721_CR13","doi-asserted-by":"crossref","unstructured":"Quintin JN, Wagner F (2010) Hierarchical work-stealing. In: Euro-Par 2010\u2014parallel processing, 16th international Euro-Par conference, vol 6271. Lecture notes in computer science. Springer, Berlin, pp 217\u2013229","DOI":"10.1007\/978-3-642-15277-1_21"},{"key":"1721_CR14","doi-asserted-by":"crossref","unstructured":"Ranger C, Raghuraman R, Penmetsa A, Bradski GR, Kozyrakis C (2007) Evaluating MapReduce for multi-core and multiprocessor systems. In: 13st International conference on high-performance computer architecture (HPCA-13 2007), ACM, pp 13\u201324","DOI":"10.1109\/HPCA.2007.346181"},{"key":"1721_CR15","doi-asserted-by":"crossref","unstructured":"Saramago J et al (2012) Towards an adaptable middleware for parallel computing in heterogeneous environments. In: 2012 IEEE international conference on cluster computing workshops, CLUSTER workshops 2012, IEEE, pp 143\u2013151","DOI":"10.1109\/ClusterW.2012.36"},{"key":"1721_CR16","doi-asserted-by":"crossref","unstructured":"Talbot J, Yoo RM, Kozyrakis C (2011) Phoenix++: modular MapReduce for shared-memory systems. In: Proceedings of the second international workshop on MapReduce and its applications (MapReduce \u201911). ACM, pp 9\u201316","DOI":"10.1145\/1996092.1996095"},{"key":"1721_CR17","doi-asserted-by":"crossref","unstructured":"Treichler S, Bauer M, Aiken A (2013) Language support for dynamic, hierarchical data partitioning. In: Proceedings of the 2013 ACM SIGPLAN international conference on object oriented programming systems languages and applications, OOPSLA 2013, part of SPLASH 2013, ACM, pp 495\u2013514","DOI":"10.1145\/2509136.2509545"},{"key":"1721_CR18","doi-asserted-by":"crossref","unstructured":"Wang L, Merchant S, El-Ghazawi T (2011) Exploiting hierarchical parallelism using UPC. In: Proceedings of the 2011 IEEE international symposium on parallel and distributed processing workshops and PhD forum (IPDPS Workshops \u201911). IEEE Computer Society, pp 1216\u20131224","DOI":"10.1109\/IPDPS.2011.273"},{"key":"1721_CR19","doi-asserted-by":"crossref","unstructured":"Yan Y et al (2010) Hierarchical place trees: a portable abstraction for task parallelism and data movement. In: Proceedings of the 22nd international conference on languages and compilers for parallel computing (LCPC\u201909). Springer, Berlin, pp 172\u2013187","DOI":"10.1007\/978-3-642-13374-9_12"},{"key":"1721_CR20","doi-asserted-by":"crossref","unstructured":"Zhang Y (2013) HJ-Hadoop: an optimized MapReduce runtime for multi-core systems. In: Conference on systems, programming, and applications: software for humanity, SPLASH \u201913\u2014companion volume. ACM, pp 111\u2013112","DOI":"10.1145\/2508075.2514875"},{"key":"1721_CR21","doi-asserted-by":"crossref","unstructured":"Zheng G et al (2010) Hierarchical load balancing for Charm++ applications on large supercomputers. In: Proceedings of the 2010 39th international conference on parallel processing workshops (ICPP\u2019 10 workshops). IEEE Computer Society, pp 436\u2013444","DOI":"10.1109\/ICPPW.2010.65"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-016-1721-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1721-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1721-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1721-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T06:40:48Z","timestamp":1559371248000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-016-1721-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5,11]]},"references-count":21,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["1721"],"URL":"https:\/\/doi.org\/10.1007\/s11227-016-1721-z","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2016,5,11]]}}}