{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:06:34Z","timestamp":1730225194219,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/hipcw.2018.8634318","type":"proceedings-article","created":{"date-parts":[[2019,2,7]],"date-time":"2019-02-07T23:57:00Z","timestamp":1549583820000},"page":"8-17","source":"Crossref","is-referenced-by-count":2,"title":["Performance Optimization of Multithreaded 2D FFT on Multicore Processors: Challenges and Solution Approaches"],"prefix":"10.1109","author":[{"given":"Semyon","family":"Khokhriakov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995937"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810128"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/978-3-319-58667-0_11","article-title":"gearshifft - the fft benchmark suite for heterogeneous platforms","author":"steinbach","year":"2017","journal-title":"High Performance Computing"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2015.12.001"},{"journal-title":"HCLFFT Novel model-based methods for performance optimization of 2D discrete Fourier transform on multicore processors","year":"2018","author":"khokhriakov","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/PARCOMPTECH.2015.7084519"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpdc.2014.03.009","article-title":"Optimized FFT computations on heterogeneous platforms with application to the Poisson equation","volume":"74","author":"wu","year":"2014","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref11","first-page":"64","article-title":"Cache optimization for coarse grain task parallel processing using inter-array padding","author":"ishizaka","year":"2003","journal-title":"International Workshop on Languages and Compilers for Parallel Computing"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1290520.1290522"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1145\/2908080.2908123","article-title":"Effective padding of multidimensional arrays to avoid cache conflict misses","author":"hong","year":"2016","journal-title":"Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079080"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2599527"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2608824"},{"key":"ref17","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 Transactions on Computers"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2827055"},{"journal-title":"Fastest Fourier transform in the west","year":"2018","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(01)00120-X"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2011.08.007"},{"journal-title":"Parallel fft-2d in heterogeneous systems","year":"0","author":"almeida","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2015.2460242"},{"journal-title":"Intel MKL FFT - fast fourier transforms","year":"2018","author":"corporation","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2015.10.024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2015.09.005"},{"journal-title":"Optimized FFT Routines for AMD Graphics Processors","year":"2018","key":"ref8"},{"journal-title":"Optimized FFT Routines for NVIDIA Graphics Processors","year":"2018","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2015.2444240"},{"journal-title":"Intel QuickPath Interconnect","year":"2008","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907569"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/11082748X"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2013.08.028"},{"key":"ref21","first-page":"1","article-title":"2DECOMP and FFT - a highly scalable 2D decomposition library and FFT interface","author":"li","year":"2010","journal-title":"Cray User Group Conference CUG 2010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199807)10:8<583::AID-CPE327>3.0.CO;2-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-015-1018-0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2012.12.002"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370639"}],"event":{"name":"2018 IEEE 25th International Conference on High Performance Computing Workshops (HiPCW)","start":{"date-parts":[[2018,12,17]]},"location":"Bengaluru, India","end":{"date-parts":[[2018,12,20]]}},"container-title":["2018 IEEE 25th International Conference on High Performance Computing Workshops (HiPCW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8620958\/8634014\/08634318.pdf?arnumber=8634318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T22:14:22Z","timestamp":1643235262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8634318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/hipcw.2018.8634318","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}