{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T10:43:27Z","timestamp":1779014607643,"version":"3.51.4"},"reference-count":50,"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.2018.2878271","type":"journal-article","created":{"date-parts":[[2018,10,30]],"date-time":"2018-10-30T15:12:50Z","timestamp":1540912370000},"page":"64202-64224","source":"Crossref","is-referenced-by-count":11,"title":["Performance Optimization of Multithreaded 2D Fast Fourier Transform on Multicore Processors Using Load Imbalancing Parallel Computing Method"],"prefix":"10.1109","volume":"6","author":[{"given":"Semyon","family":"Khokhriakov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9181-3290","authenticated-orcid":false,"given":"Ravi Reddy","family":"Manumachu","sequence":"additional","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":"10.1007\/s11227-009-0350-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-007-0148-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1353535.1346318"},{"key":"ref32","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006074864"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2013.08.028"},{"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":"56","article-title":"Automatic calibration of performance models on heterogeneous multicore architectures","author":"augonnet","year":"2009","journal-title":"Proc Eur Conf Parallel Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1594835.1504196"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/11082748X"},{"key":"ref27","year":"2018","journal-title":"Parallel FFTW"},{"key":"ref29","first-page":"1","article-title":"2DECOMP and FFT&#x2014;A highly scalable 2D decomposition library and FFT interface","author":"li","year":"2010","journal-title":"Proc Cray User Group Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2015.2444240"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907569"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2015.10.024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810128"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2015.12.001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.03.009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995937"},{"key":"ref26","year":"2018","journal-title":"Fastest Fourier transform in the west"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PARCOMPTECH.2015.7084519"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079080"},{"key":"ref10","year":"2001","journal-title":"Hypertransport"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2608824"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2005.05.007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2827055"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000163"},{"key":"ref14","author":"lastovetsky","year":"2011","journal-title":"Design and implementation of self-adaptable parallel algorithms for scientific computing on highly heterogeneous HPC platforms"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199807)10:8<583::AID-CPE327>3.0.CO;2-3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370639"},{"key":"ref17","first-page":"551","article-title":"Parallel FFT-2D in heterogeneous systems","author":"almeida","year":"2005","journal-title":"Proc 23rd Multi-Conf Appl Inform Int Conf Parallel Distrib Comput Netw (IASTED)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(01)00120-X"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.12.002"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2011.08.007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2460242"},{"key":"ref6","year":"2018","journal-title":"Intel MKL FFT&#x2014;Fast Fourier Transforms"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2015.09.005"},{"key":"ref8","year":"2018","journal-title":"Optimized FFT Routines for AMD Graphics Processors"},{"key":"ref7","year":"2018","journal-title":"Optimized FFT Routines for NVIDIA Graphics Processors"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908123"},{"key":"ref9","year":"2008","journal-title":"Intel QuickPath Interconnect"},{"key":"ref46","author":"khokhriakov","year":"2018","journal-title":"HCLFFT Software Library for Performance Optimization of 2D Discrete Fourier Transform on Multicore Processors"},{"key":"ref45","first-page":"160","article-title":"Bi-objective optimization of data-parallel applications on homogeneous multicore clusters for performance and energy","volume":"64","author":"reddy","year":"2017","journal-title":"IEEE Trans Comput"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1290520.1290522"},{"key":"ref47","first-page":"64","article-title":"Cache optimization for coarse grain task parallel processing using inter-array padding","author":"ishizaka","year":"2003","journal-title":"Proc Int Workshop Lang Compil Parallel Comput"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303051"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON.2016.7777889"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2599527"},{"key":"ref43","article-title":"Model-based optimization of MPDATA on Intel Xeon Phi through load imbalancing","author":"lastovetsky","year":"2015","journal-title":"CoRR"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08515025.pdf?arnumber=8515025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:39:13Z","timestamp":1641987553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8515025\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2878271","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}