{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:12:06Z","timestamp":1774591926741,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"publisher","award":["14\/IA\/2474"],"award-info":[{"award-number":["14\/IA\/2474"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2879228","type":"journal-article","created":{"date-parts":[[2018,11,12]],"date-time":"2018-11-12T19:36:11Z","timestamp":1542051371000},"page":"69075-69106","source":"Crossref","is-referenced-by-count":4,"title":["Parallel Data Partitioning Algorithms for Optimization of Data-Parallel Applications on Modern Extreme-Scale Multicore Platforms for Performance and Energy"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9181-3290","authenticated-orcid":false,"given":"Ravi Reddy","family":"Manumachu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Lastovetsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.1631"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1278177.1278182"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(89)90021-X"},{"key":"ref32","first-page":"56","article-title":"Automatic calibration of performance models on heterogeneous multicore architectures","author":"augonnet","year":"2009","journal-title":"Proc 3rd Workshop Highly Parallel Process Chip (HPPC)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1594835.1504196"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1353535.1346318"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-009-0350-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-007-0148-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2004.10"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2005.45"},{"key":"ref28","first-page":"1","article-title":"An efficient, model-based CPU-GPU heterogeneous FFT library","author":"ogata","year":"2008","journal-title":"Proc IEEE Int Symp Parallel Distrib Process (IPDPS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2017.2742513"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000163"},{"key":"ref1","author":"reddy","year":"2017","journal-title":"PARALEPH Parallel Data Partitioning Algorithms for Optimization of Data-Parallel Applications on Modern Extreme-Scale Multicore Platforms for Performance and Energy"},{"key":"ref20","first-page":"202","article-title":"High-performance computing on heterogeneous systems: Database queries on CPU and GPU","author":"ilic","year":"2010","journal-title":"High Performance Scientific Computing with Special Emphasis on Current Capabilities and Future Perspectives"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2015.08.002"},{"key":"ref21","first-page":"450","article-title":"Column-based matrix partitioning for parallel matrix multiplication on heterogeneous processors based on functional performance models","volume":"7155","author":"clarke","year":"2012","journal-title":"Proc Eur Conf Parallel Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.101"},{"key":"ref23","article-title":"Efficient computation of galois field expressions on hybrid CPU-GPU platforms","volume":"26","author":"radmanovi?","year":"2016","journal-title":"J Multiple-Valued Logic Soft Comput"},{"key":"ref26","first-page":"203","article-title":"Heterogeneous sparse matrix computations on hybrid GPU\/CPU platforms","author":"cardellini","year":"2013","journal-title":"Proc PARCO"},{"key":"ref25","first-page":"693","article-title":"Transparent application acceleration by intelligent scheduling of shared library calls on heterogeneous systems","author":"cola\u00e7o","year":"2013","journal-title":"Parallel Processing and Applied Mathematics"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.96"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2613524"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(90)90105-A"},{"key":"ref57","author":"reddy","year":"2016","journal-title":"HCLWattsUp API for Power and Energy Measurements Using WattsUp Pro Meter"},{"key":"ref56","article-title":"Report on exascale architecture roadmap in Japan","author":"kondo","year":"2012"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2004.07.007"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1133-x"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2715809"},{"key":"ref10","first-page":"129","article-title":"Smart cooling of data centers","volume":"2","author":"patel","year":"2003","journal-title":"Proc of Int Electron Pack Tech L Conf Exhib"},{"key":"ref11","first-page":"29:1","article-title":"Cool job allocation: Measuring the power savings of placing jobs at cooling-efficient locations in the data center","author":"bash","year":"2007","journal-title":"Proc USENIX Annu Tech Conf"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.281"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/I-SPAN.2009.22"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.231"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2013.06.028"},{"key":"ref15","year":"2016","journal-title":"OpenBLAS An Optimized BLAS Library"},{"key":"ref16","year":"2016","journal-title":"FFTW A Fast Free C FFT Library"},{"key":"ref17","year":"2016","journal-title":"Parallel FFTW"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2608824"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006074864"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.1997.1407"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4330030502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0045-7825(99)00241-8"},{"key":"ref5","first-page":"43","article-title":"A generic strategy for dynamic load balancing of distributed memory parallel computational mechanics using unstructured meshed","author":"arulananthan","year":"1998","journal-title":"Parallel Computational Fluid Dynamics Development and Applications of Parallel Technology"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.934155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2003.05.014"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-011-0648-7"},{"key":"ref9","first-page":"201","article-title":"HeteroPBLAS: A set of parallel basic linear algebra subprograms optimized for heterogeneous computational clusters","volume":"10","author":"reddy","year":"2009","journal-title":"Scalable Comput Pract Exp"},{"key":"ref46","first-page":"64","article-title":"Dynamic load balancing on dedicated heterogeneous systems","author":"galindo","year":"2008","journal-title":"Proc Eur Parallel Virtual Mach \/Message Passing Interface Users&#x2019; Group Meeting"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2004.07.005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-011-0594-4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-011-0595-3"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2076021.2048104"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2006.88"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2581122.2544141"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.30"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08532283.pdf?arnumber=8532283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:26:33Z","timestamp":1643243193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8532283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2879228","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}