{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:13:26Z","timestamp":1775326406589,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.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 Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2018,10,1]]},"DOI":"10.1109\/tpds.2018.2827055","type":"journal-article","created":{"date-parts":[[2018,4,16]],"date-time":"2018-04-16T20:40:35Z","timestamp":1523911235000},"page":"2176-2190","source":"Crossref","is-referenced-by-count":45,"title":["A Novel Data-Partitioning Algorithm for Performance Optimization of Data-Parallel Applications on Heterogeneous HPC Platforms"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4070-7468","authenticated-orcid":false,"given":"Hamidreza","family":"Khaleghzadeh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9181-3290","authenticated-orcid":false,"given":"Ravindranath Reddy","family":"Manumachu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9460-3897","authenticated-orcid":false,"given":"Alexey","family":"Lastovetsky","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-007-0148-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2004.10"},{"key":"ref33","first-page":"267","article-title":"An\n optimal scheduling scheme for tiling in distributed systems","author":"kyriakopoulos","year":"2007","journal-title":"IEEE Int Conf Cluster Computing"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304625"},{"key":"ref31","first-page":"56","article-title":"Automatic\n calibration of performance models on heterogeneous multicore architectures","author":"augonnet","year":"2009","journal-title":"Proc 3rd Workshop Highly Parallel Process Chip"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1145\/1594835.1504196","article-title":"Solving dense linear systems on platforms with multiple hardware accelerators","volume":"44","author":"quintana-ort\u00ed","year":"2009","journal-title":"SIGPLAN Not"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2005.45"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0743-7315(89)90021-X"},{"key":"ref35","first-page":"1","article-title":"Hypergraph-based dynamic load balancing for adaptive scientific computations","author":"catalyurek","year":"2007","journal-title":"Proc IEEE Int Parallel Distrib Process Symp"},{"key":"ref34","first-page":"59","article-title":"A unified\n algorithm for load-balancing adaptive scientific simulations","author":"schloegel","year":"2000","journal-title":"Proc ACM\/IEEE Conf Supercomputing"},{"key":"ref10","article-title":"OpenBLAS: An optimized BLAS library","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-009-0350-1"},{"key":"ref11","article-title":"FFTW: A fast, free c FFT library","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2007.06.001"},{"key":"ref13","first-page":"202","article-title":"High-performance computing on\n heterogeneous systems: Database queries on CPU and GPU","volume":"20","author":"ili?","year":"2010","journal-title":"High Perform Sci Comput Special Emphasis Current Capabilities Future Perspectives"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000163"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1007\/978-3-642-29737-3_50","article-title":"Column-based matrix partitioning for parallel matrix multiplication on heterogeneous processors based on\n functional performance models","volume":"7155","author":"clarke","year":"2012","journal-title":"Proc Euro-Par 2011 Parallel Processing Workshops"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2015.08.002"},{"key":"ref17","first-page":"417","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.101"},{"key":"ref19","first-page":"693","article-title":"Transparent application acceleration by intelligent scheduling of shared library calls on\n heterogeneous systems","author":"cola\u00e7o","year":"2013","journal-title":"Proc Int Conf Parallel Process Appl Math"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-017-2176-6"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1006\/jpdc.2000.1686","article-title":"Heterogeneous distribution of computations solving linear algebra problems on\n networks of heterogeneous computers","volume":"61","author":"kalinov","year":"2001","journal-title":"J Parallel Distrib Comput"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.12"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/71.963416"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006074864"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1145\/1353535.1346318","article-title":"Merge: A programming model for\n heterogeneous multi-core systems","volume":"42","author":"linderman","year":"2008","journal-title":"ACM SIGOPS Operating Syst Rev"},{"key":"ref5","article-title":"Data partitioning with a realistic performance model of networks of heterogeneous computers","author":"lastovetsky","year":"2004","journal-title":"Proc 18th Int Parallel Distrib Process Symp"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(90)90105-A"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2599527"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/40.6.356"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2608824"},{"key":"ref1","article-title":"Top500","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2613524"},{"key":"ref20","first-page":"203","article-title":"Heterogeneous sparse matrix computations on hybrid GPU\/CPU platforms","author":"cardellini","year":"2013","journal-title":"Proc Parallel Comput Accelerating Comput Sci Eng"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1155\/2005\/964902"},{"key":"ref48","article-title":"HPOPTA: Heterogeneous model-based data partitioning algorithm for optimization of data-parallel applications for\n performance","author":"khaleghzadeh","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-017-2141-4"},{"key":"ref47","first-page":"746","article-title":"Building\n the functional performance model of a processor","author":"lastovetsky","year":"2006","journal-title":"Proc ACM Symp Appl Comput"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2375202"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/12.956091"},{"key":"ref24","article-title":"XeonPhiOOC: Out-of-core package for\n out-of-core dgemm on Xeon Phi","author":"khaleghzadeh","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73940-1_27"},{"key":"ref23","article-title":"ZZGEMMOOC: Out-of-core package for\n out-of-core dgemm on GPU","author":"khaleghzadeh","year":"2017"},{"key":"ref44","first-page":"457","article-title":"Towards efficient decomposition and\n parallelization of MPDATA on hybrid CPU-GPU cluster","author":"wyrzykowski","year":"2013","journal-title":"Proc Int Conf Large-Scale Sci Comput"},{"key":"ref26","first-page":"1","article-title":"An efficient, model-based CPU-GPU\n heterogeneous FFT library","author":"ogata","year":"2008","journal-title":"Proc IEEE Int Symp Parallel Distrib Process"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513901"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0743-7315(03)00112-6"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/8458269\/08338082.pdf?arnumber=8338082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T10:35:27Z","timestamp":1643193327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8338082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,1]]},"references-count":48,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2018.2827055","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,1]]}}}