{"id":"https://openalex.org/W2914973124","doi":"https://doi.org/10.1109/hipcw.2018.8634318","title":"Performance Optimization of Multithreaded 2D FFT on Multicore Processors: Challenges and Solution Approaches","display_name":"Performance Optimization of Multithreaded 2D FFT on Multicore Processors: Challenges and Solution Approaches","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914973124","doi":"https://doi.org/10.1109/hipcw.2018.8634318","mag":"2914973124"},"language":"en","primary_location":{"id":"doi:10.1109/hipcw.2018.8634318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw.2018.8634318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 25th International Conference on High Performance Computing Workshops (HiPCW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, 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, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, 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, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, 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":null,"apc_paid":null,"fwci":0.6609,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65483419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"74","issue":null,"first_page":"8","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9771999716758728,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.9128879308700562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.787060022354126},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6528236865997314},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6486347913742065},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.4166223406791687},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35225337743759155},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16363796591758728}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9128879308700562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787060022354126},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6528236865997314},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6486347913742065},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.4166223406791687},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35225337743759155},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16363796591758728}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw.2018.8634318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw.2018.8634318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 25th International Conference on High Performance Computing Workshops (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W79587924","https://openalex.org/W1046360519","https://openalex.org/W1510522826","https://openalex.org/W1647609603","https://openalex.org/W1810866258","https://openalex.org/W1966416130","https://openalex.org/W1967802285","https://openalex.org/W1979796968","https://openalex.org/W1984005572","https://openalex.org/W2002555321","https://openalex.org/W2011544816","https://openalex.org/W2028899550","https://openalex.org/W2042478655","https://openalex.org/W2043591914","https://openalex.org/W2072375667","https://openalex.org/W2074570088","https://openalex.org/W2097999418","https://openalex.org/W2111320011","https://openalex.org/W2115400927","https://openalex.org/W2120119701","https://openalex.org/W2122405433","https://openalex.org/W2272797324","https://openalex.org/W2415800180","https://openalex.org/W2508492666","https://openalex.org/W2519627041","https://openalex.org/W2587758664","https://openalex.org/W2618868084","https://openalex.org/W2748740248","https://openalex.org/W2801415324","https://openalex.org/W3017247523","https://openalex.org/W3103952756","https://openalex.org/W6630753849"],"related_works":["https://openalex.org/W2083992893","https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126","https://openalex.org/W2079303253","https://openalex.org/W2104702637","https://openalex.org/W4248099758","https://openalex.org/W2979015021"],"abstract_inverted_index":{"Fast":[0],"Fourier":[1,76],"transform":[2],"(FFT)":[3],"is":[4,33,160,197,202],"a":[5,91,249],"key":[6],"routine":[7],"employed":[8],"in":[9,48,66,79,158,175],"application":[10],"domains":[11],"such":[12,51],"as":[13,52],"molecular":[14],"dynamics,":[15,18],"computational":[16],"fluid":[17],"signal":[19],"processing,":[20,22],"image":[21],"and":[23,56,86,113,144,151,264],"condition":[24],"monitoring":[25],"systems.":[26],"Its":[27],"performance":[28,41,70,111,131,153,192,215,236,242,262],"on":[29,90,227,244],"latest":[30],"multicore":[31,95,246],"platforms":[32,50,181],"therefore":[34,114],"of":[35,72,98,127,154,193,213,237,241],"paramount":[36],"concern":[37],"to":[38,129,224,259],"the":[39,69,106,133,138,149,176,190,211,214,234,261],"high":[40],"computing":[42],"community.":[43],"The":[44,125],"inherent":[45],"complexities":[46],"however":[47],"these":[49],"severe":[53,222],"resource":[54],"contention":[55],"non-uniform":[57],"memory":[58],"access":[59],"(NUMA)":[60],"pose":[61],"formidable":[62],"challenges.":[63],"We":[64,146,185,253],"study":[65],"this":[67],"work":[68],"profiles":[71],"multithreaded":[73],"2D":[74,134],"fast":[75],"transforms":[77],"provided":[78],"three":[80,107,139,255],"highly":[81],"optimized":[82],"packages,":[83],"FFTW-2.1.5,":[84,155],"FFTW-3.3.7,":[85,200],"Intel":[87,93,194,218],"MKL":[88,195,219],"FFT":[89,135,196,220,238],"modern":[92,245],"Haswell":[94],"processor":[96],"consisting":[97],"thirty-six":[99],"cores.":[100],"First,":[101],"we":[102,230],"show":[103,187],"that":[104,148,165,188,232],"all":[105],"routines":[108,136],"demonstrate":[109,147],"drastic":[110,183],"variations":[112,216,243,263],"their":[115,122],"average":[116,128,150,191,235],"performances":[117],"are":[118,141,221],"considerably":[119],"lower":[120],"than":[121,162,199],"peak":[123,130,152],"performances.":[124],"ratio":[126],"for":[132,206,217],"from":[137],"packages":[140],"40%,":[142],"30%,":[143],"24%.":[145],"last":[156],"updated":[157],"1999,":[159],"better":[161,198],"FFTW-3.3.7":[163,205],"suggesting":[164],"extensive":[166],"machine":[167],"optimization":[168],"using":[169],"architecture-specific":[170],"techniques":[171],"can":[172],"be":[173],"harmful":[174],"long":[177],"run":[178],"since":[179],"hardware":[180],"undergo":[182],"changes.":[184],"also":[186],"while":[189],"it":[201],"outperformed":[203],"by":[204,239],"many":[207],"problem":[208],"sizes.":[209],"Also":[210],"width":[212],"compared":[223],"FFTW-3.3.7.":[225],"Based":[226],"our":[228],"study,":[229],"conclude":[231],"improving":[233],"removal":[240],"processors":[247],"constitutes":[248],"tremendous":[250],"research":[251],"challenge.":[252],"propose":[254],"possible":[256],"solution":[257],"approaches":[258],"remove":[260],"suggest":[265],"future":[266],"directions.":[267]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
