{"id":"https://openalex.org/W2899387068","doi":"https://doi.org/10.1109/access.2018.2878271","title":"Performance Optimization of Multithreaded 2D Fast Fourier Transform on Multicore Processors Using Load Imbalancing Parallel Computing Method","display_name":"Performance Optimization of Multithreaded 2D Fast Fourier Transform on Multicore Processors Using Load Imbalancing Parallel Computing Method","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2899387068","doi":"https://doi.org/10.1109/access.2018.2878271","mag":"2899387068"},"language":"en","primary_location":{"id":"doi:10.1109/access.2018.2878271","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2878271","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2018.2878271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047980649","display_name":"Semyon Khokhriakov","orcid":null},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Semyon Khokhriakov","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin 4, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078230040","display_name":"Ravi Reddy Manumachu","orcid":"https://orcid.org/0000-0001-9181-3290"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Ravi Reddy Manumachu","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin 4, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9181-3290","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084068586","display_name":"Alexey Lastovetsky","orcid":"https://orcid.org/0000-0001-9460-3897"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Alexey Lastovetsky","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin 4, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin 4, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.9223,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.75783993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"64202","last_page":"64224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9800999760627747,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10232","display_name":"Optical Network Technologies","score":0.9724000096321106,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8587095737457275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8442077040672302},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7929353713989258},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7813990116119385},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5510290265083313},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.48995962738990784},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4594676196575165},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4501667618751526},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4300435781478882},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4247050881385803},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.41351810097694397},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27045708894729614},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18839862942695618}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8587095737457275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8442077040672302},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7929353713989258},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7813990116119385},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5510290265083313},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.48995962738990784},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4594676196575165},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4501667618751526},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4300435781478882},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4247050881385803},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.41351810097694397},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27045708894729614},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18839862942695618},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2018.2878271","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2878271","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:49ef654b57e8464480353840460506e2","is_oa":true,"landing_page_url":"https://doaj.org/article/49ef654b57e8464480353840460506e2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 6, Pp 64202-64224 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2018.2878271","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2018.2878271","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1766076957","display_name":"Meeting the Future Challenges of Heterogeneous and Extreme-Scale Parallel Computing","funder_award_id":"14/IA/2474","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W79587924","https://openalex.org/W1510522826","https://openalex.org/W1647609603","https://openalex.org/W1705453322","https://openalex.org/W1810866258","https://openalex.org/W1966416130","https://openalex.org/W1967802285","https://openalex.org/W1979796968","https://openalex.org/W1984005572","https://openalex.org/W2003094427","https://openalex.org/W2005659209","https://openalex.org/W2011544816","https://openalex.org/W2028899550","https://openalex.org/W2030129803","https://openalex.org/W2042478655","https://openalex.org/W2043591914","https://openalex.org/W2072375667","https://openalex.org/W2074570088","https://openalex.org/W2097999418","https://openalex.org/W2102624126","https://openalex.org/W2109426995","https://openalex.org/W2111320011","https://openalex.org/W2115400927","https://openalex.org/W2116367043","https://openalex.org/W2120119701","https://openalex.org/W2122405433","https://openalex.org/W2123031400","https://openalex.org/W2125980577","https://openalex.org/W2137789117","https://openalex.org/W2166417226","https://openalex.org/W2171473263","https://openalex.org/W2272797324","https://openalex.org/W2278129015","https://openalex.org/W2291749214","https://openalex.org/W2415800180","https://openalex.org/W2508492666","https://openalex.org/W2519627041","https://openalex.org/W2562411185","https://openalex.org/W2618868084","https://openalex.org/W2748740248","https://openalex.org/W2801415324","https://openalex.org/W3103952756","https://openalex.org/W4244789640","https://openalex.org/W4251173935","https://openalex.org/W4295162670","https://openalex.org/W6603261376","https://openalex.org/W6630753849","https://openalex.org/W6684857869","https://openalex.org/W6695135304","https://openalex.org/W6696726799"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W1980880153","https://openalex.org/W2083992893","https://openalex.org/W2068975988","https://openalex.org/W2955328870","https://openalex.org/W2166713816"],"abstract_inverted_index":{"Fast":[0],"Fourier":[1],"transform":[2],"(FFT)":[3],"is":[4,33],"a":[5,88,161,192,216,240],"key":[6],"routine":[7],"employed":[8],"in":[9,46,72],"application":[10],"domains":[11],"such":[12,49],"as":[13,50,197],"molecular":[14],"dynamics,":[15,18],"computational":[16],"fluid":[17],"signal":[19,218,233],"processing,":[20,22],"image":[21],"and":[23,54,79,109,138,176,180,229,253,263,265,268,278,282,292,294,297,307],"condition":[24],"monitoring":[25],"systems.":[26],"Its":[27],"performance":[28,65,107,125,146,158,205],"on":[29,87,150,236,239],"modern":[30,89,151,241],"multicore":[31,92,152,244],"platforms":[32,48],"therefore":[34],"of":[35,67,95,123,147,157,203,206,215,220,247],"paramount":[36],"concern":[37],"to":[38],"the":[39,64,102,127,132,144,155,199,204,207,231,251,266,295],"high-performance":[40],"computing":[41,190],"community.":[42],"The":[43,121,185,280],"inherent":[44],"complexities":[45],"these":[47],"severe":[51],"resource":[52],"contention":[53],"non-uniform":[55],"memory":[56],"access,":[57],"however,":[58],"pose":[59],"formidable":[60],"challenges.":[61],"We":[62,98,140],"study":[63],"profiles":[66],"multithreaded":[68],"2D":[69,128,148,183,213],"FFTs":[70],"provided":[71],"three":[73,103,133],"highly":[74],"optimized":[75],"packages,":[76],"FFTW-2.1.5,":[77],"FFTW-3.3.7,":[78],"Intel":[80,90,242,273,302],"Math":[81],"Kernel":[82],"Library":[83],"(Intel":[84],"MKL)":[85],"FFT,":[86],"Haswell":[91,243],"processor":[93],"consisting":[94,246],"36":[96,248],"cores.":[97],"show":[99],"that":[100,142],"all":[101],"routines":[104,130],"exhibit":[105],"drastic":[106],"variations,":[108],"hence,":[110],"their":[111,118],"average":[112,145,252,267,281,296],"performances":[113],"are":[114,135,261,276,290,305],"considerably":[115],"lower":[116],"than":[117],"peak":[119],"performances.":[120],"ratios":[122],"average-topeak":[124],"for":[126,182,257,286],"FFT":[129,149,275,304],"from":[131],"packages":[134],"40%,":[136],"30%,":[137],"24%.":[139],"conclude":[141],"improving":[143],"processors":[153,208],"by":[154],"removal":[156],"variations":[159],"constitutes":[160],"tremendous":[162],"research":[163],"challenge.":[164],"To":[165],"address":[166],"this":[167],"challenge,":[168],"we":[169],"propose":[170],"two":[171],"novel":[172],"optimization":[173],"methods,":[174],"PFFT-FPM":[175,258],"PFFT-FPM-PAD,":[177],"specifically":[178],"designed":[179],"implemented":[181],"FFT.":[184],"methods":[186],"employ":[187],"model-based":[188],"parallel":[189],"using":[191,225,259,272,288,301],"load-imbalancing":[193],"technique.":[194],"They":[195],"take":[196],"inputs,":[198],"discrete":[200],"3D":[201],"functions":[202],"against":[209],"problem":[210],"size,":[211],"compute":[212],"DFT":[214],"complex":[217],"matrix":[219],"size":[221],"N":[222,224],"\u00d7":[223],"p":[226],"abstract":[227],"processors,":[228],"output":[230],"transformed":[232],"matrix.":[234],"Based":[235],"our":[237],"experiments":[238],"server":[245],"physical":[249],"cores,":[250],"maximum":[254,269,283,298],"speedups":[255,270,284,299],"observed":[256,271,285,300],"FFTW-3.3.7":[260,289],"1.9\u00d7":[262],"6.8\u00d7,":[264],"MKL":[274,303],"1.3\u00d7":[277],"2\u00d7.":[279],"PFFT-FPM-PAD":[287],"2\u00d7":[291],"9.4\u00d7,":[293],"1.4\u00d7":[306],"5.9\u00d7.":[308]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}