{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T22:27:41Z","timestamp":1649111261455},"reference-count":11,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,12,13]],"date-time":"2018-12-13T00:00:00Z","timestamp":1544659200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11227-018-2724-8","type":"journal-article","created":{"date-parts":[[2018,12,13]],"date-time":"2018-12-13T10:21:24Z","timestamp":1544696484000},"page":"1654-1669","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Analytical Communication Performance Models as a metric in the partitioning of data-parallel kernels on heterogeneous platforms"],"prefix":"10.1007","volume":"75","author":[{"given":"Juan A.","family":"Rico-Gallego","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan C.","family":"D\u00edaz-Mart\u00edn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carmen","family":"Calvo-Jurado","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Moreno-\u00c1lvarez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan L.","family":"Garc\u00eda-Zapata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,13]]},"reference":[{"issue":"10","key":"2724_CR1","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1109\/71.963416","volume":"12","author":"O Beaumont","year":"2001","unstructured":"Beaumont O, Boudet V, Rastello F, Robert Y (2001) Matrix multiplication on heterogeneous platforms. IEEE Trans Parallel Distrib Syst 12(10):1033\u20131051","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"2724_CR2","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/s11227-014-1207-9","volume":"69","author":"D Clarke","year":"2014","unstructured":"Clarke D, Zhong Z, Rychkov V, Lastovetsky A (2014) FuPerMod: a software tool for the optimization of data-parallel applications on heterogeneous platforms. J Supercomput 69:61\u201369","journal-title":"J Supercomput"},{"key":"2724_CR3","doi-asserted-by":"crossref","unstructured":"Dongarra J, Pineau JF, Robert Y, Vivien F (2008) Matrix product on heterogeneous master-worker platforms. In: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, ACM, New York, NY, USA, PPoPP \u201908, pp 53\u201362","DOI":"10.1145\/1345206.1345217"},{"issue":"4","key":"2724_CR5","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1006\/jpdc.2000.1686","volume":"61","author":"A Kalinov","year":"2001","unstructured":"Kalinov A, Lastovetsky A (2001) Heterogeneous distribution of computations solving linear algebra problems on networks of heterogeneous computers. J Parallel Distrib Comput 61(4):520\u2013535","journal-title":"J Parallel Distrib Comput"},{"key":"2724_CR6","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-642-14122-5_13","volume-title":"Euro-Par 2009\u2014parallel processing workshops","author":"A Lastovetsky","year":"2010","unstructured":"Lastovetsky A, Reddy R (2010) Distributed data partitioning for heterogeneous processors based on partial estimation of their functional performance models. In: Lin HX, Alexander M, Forsell M, Kn\u00fcpfer A, Prodan R, Sousa L, Streit A (eds) Euro-Par 2009\u2014parallel processing workshops. Springer, Berlin, pp 91\u2013101"},{"key":"2724_CR7","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1002\/cpe.3609","volume":"28","author":"T Malik","year":"2016","unstructured":"Malik T, Rychkov V, Lastovetsky A (2016) Network-aware optimization of communications for parallel matrix multiplication on hierarchical HPC platforms. Concurr Comput Pract Exp 28:802\u2013821","journal-title":"Concurr Comput Pract Exp"},{"key":"2724_CR8","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.parco.2015.02.006","volume":"46","author":"JA Rico-Gallego","year":"2015","unstructured":"Rico-Gallego JA, D\u00edaz-Mart\u00edn JC (2015) \n                    \n                      \n                    \n                    $$\\tau $$\n                    \n                      \n                        \u03c4\n                      \n                    \n                  -Lop: modeling performance of shared memory MPI. Parallel Comput 46:14\u201331","journal-title":"Parallel Comput"},{"key":"2724_CR9","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.future.2016.02.021","volume":"61","author":"JA Rico-Gallego","year":"2016","unstructured":"Rico-Gallego JA, D\u00edaz-Mart\u00edn JC, Lastovetsky AL (2016) Extending \n                    \n                      \n                    \n                    $$\\tau $$\n                    \n                      \n                        \u03c4\n                      \n                    \n                  -lop to model concurrent MPI communications in multicore clusters. Future Gener Comput Syst 61:66\u201382","journal-title":"Future Gener Comput Syst"},{"issue":"11","key":"2724_CR10","doi-asserted-by":"publisher","first-page":"3215","DOI":"10.1109\/TPDS.2017.2715809","volume":"28","author":"JA Rico-Gallego","year":"2017","unstructured":"Rico-Gallego JA, Lastovetsky AL, D\u00edaz-Mart\u00edn JC (2017) Model-based estimation of the communication cost of hybrid data-parallel applications on heterogeneous clusters. IEEE Trans Parallel Distrib Syst 28(11):3215\u20133228","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"2724_CR4","unstructured":"van de Geijn RA, Watts J (1995) SUMMA: scalable universal matrix multiplication algorithm. Technical Report, Austin, TX, USA"},{"key":"2724_CR11","doi-asserted-by":"publisher","first-page":"2506","DOI":"10.1109\/TC.2014.2375202","volume":"64","author":"Z Zhong","year":"2015","unstructured":"Zhong Z, Rychkov V, Lastovetsky A (2015) Data partitioning on multicore and multi-GPU platforms using functional performance models. IEEE Trans Comput 64:2506\u20132518","journal-title":"IEEE Trans Comput"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2724-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-018-2724-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2724-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,12,12]],"date-time":"2019-12-12T19:13:10Z","timestamp":1576177990000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-018-2724-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,13]]},"references-count":11,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["2724"],"URL":"https:\/\/doi.org\/10.1007\/s11227-018-2724-8","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,13]]},"assertion":[{"value":"13 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}