{"id":"https://openalex.org/W1973825452","doi":"https://doi.org/10.1145/1274971.1275011","title":"Scheduling FFT computation on SMP and multicore systems","display_name":"Scheduling FFT computation on SMP and multicore systems","publication_year":2007,"publication_date":"2007-06-17","ids":{"openalex":"https://openalex.org/W1973825452","doi":"https://doi.org/10.1145/1274971.1275011","mag":"1973825452"},"language":"en","primary_location":{"id":"doi:10.1145/1274971.1275011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1275011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual international conference on Supercomputing","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/A5101391095","display_name":"Ayaz Ali","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayaz Ali","raw_affiliation_strings":["University of Houston, Houston, TX","University of Houston , Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Houston , Houston, TX","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073745784","display_name":"Lennart Johnsson","orcid":"https://orcid.org/0000-0003-0337-879X"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lennart Johnsson","raw_affiliation_strings":["University of Houston, Houston, TX","University of Houston , Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Houston , Houston, TX","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058655155","display_name":"Jaspal Subhlok","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaspal Subhlok","raw_affiliation_strings":["University of Houston, Houston, TX","University of Houston , Houston, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Houston , Houston, TX","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9962999820709229,"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":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8627475500106812},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.822191596031189},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.7866494059562683},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6937110424041748},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5631651878356934},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.5479450821876526},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.515861451625824},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49921655654907227},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.49740341305732727},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4933599531650543},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.478620707988739},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4724443554878235},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.4715835154056549},{"id":"https://openalex.org/keywords/posix-threads","display_name":"POSIX Threads","score":0.4603016972541809},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15253034234046936},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14009755849838257},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11251956224441528},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.08188384771347046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8627475500106812},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.822191596031189},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.7866494059562683},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6937110424041748},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5631651878356934},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.5479450821876526},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.515861451625824},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49921655654907227},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.49740341305732727},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4933599531650543},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.478620707988739},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4724443554878235},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.4715835154056549},{"id":"https://openalex.org/C41138395","wikidata":"https://www.wikidata.org/wiki/Q928112","display_name":"POSIX Threads","level":3,"score":0.4603016972541809},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15253034234046936},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14009755849838257},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11251956224441528},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.08188384771347046},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1274971.1275011","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1275011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.572.3380","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.572.3380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vgrads.rice.edu/publications/pdfs/Computing_FFT_on_Multicore_Manycore.pdf/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W850271438","https://openalex.org/W1555915743","https://openalex.org/W1866830630","https://openalex.org/W1972057882","https://openalex.org/W1990860452","https://openalex.org/W2045836768","https://openalex.org/W2060469182","https://openalex.org/W2061171222","https://openalex.org/W2089592348","https://openalex.org/W2102182691","https://openalex.org/W2134572726","https://openalex.org/W2136952590","https://openalex.org/W2146236588","https://openalex.org/W2164197394","https://openalex.org/W2166395705"],"related_works":["https://openalex.org/W1993191611","https://openalex.org/W2338363223","https://openalex.org/W2479014312","https://openalex.org/W1583465708","https://openalex.org/W1511134614","https://openalex.org/W1981758122","https://openalex.org/W105894385","https://openalex.org/W1993711049","https://openalex.org/W2544282943","https://openalex.org/W2097285270"],"abstract_inverted_index":{"Increased":[0],"complexity":[1],"of":[2,12,32,37,119,144,158,163,168,173,181,196],"memory":[3,15,45],"systems":[4],"to":[5,23,61,105,110,140],"ameliorate":[6],"the":[7,10,35,59,79,83,92,117,128,142,156,182,190,201,210],"gap":[8],"between":[9,209],"speed":[11],"processors":[13,197],"and":[14,42,160,189,212],"has":[16],"made":[17],"it":[18],"increasingly":[19],"harder":[20],"for":[21,91,147,186,192],"compilers":[22,80],"optimize":[24],"an":[25,123],"arbitrary":[26],"code":[27],"within":[28],"a":[29,88,166,206],"palatable":[30],"amount":[31],"time.":[33],"With":[34],"emergence":[36],"multicore":[38],"(CMP),":[39],"multiprocessor":[40,46],"(SMP)":[41],"hybrid":[43],"shared":[44],"architectures,":[47],"achieving":[48],"high":[49,63,99],"e":[50,64,100],"ciency":[51,65,101],"is":[52,122,130,177,198],"becoming":[53],"even":[54,126],"more":[55],"challenging.":[56],"To":[57],"address":[58],"challenge":[60],"achieve":[62],"in":[66,81,132],"performance":[67,157,172,207],"critical":[68],"applications,":[69],"domain":[70],"speci":[71],"c":[72],"frameworks":[73],"have":[74,86],"been":[75],"developed":[76,87],"that":[77,97,180],"aid":[78],"scheduling":[82],"computations.":[84],"We":[85,154],"portable":[89],"framework":[90],"Fast":[93],"Fourier":[94],"Transform":[95],"(FFT)":[96],"achieves":[98],"by":[102,113],"automatically":[103],"adapting":[104],"various":[106],"architectural":[107],"features.":[108],"Adapting":[109],"parallel":[111,148,174],"architectures":[112],"searching":[114],"through":[115],"all":[116],"combinations":[118],"schedules":[120,146,176],"(plans)":[121],"expensive":[124],"task,":[125],"when":[127],"search":[129],"conducted":[131],"parallel.":[133],"In":[134,200],"this":[135],"paper,":[136],"we":[137,203],"develop":[138],"heuristics":[139],"simplify":[141],"generation":[143],"better":[145],"FFT":[149,164,175,188],"computations":[150],"on":[151,165],"CMP/SMP":[152],"systems.":[153],"evaluate":[155],"OpenMP":[159],"PThreads":[161],"implementations":[162],"number":[167,195],"latest":[169],"architectures.":[170],"The":[171],"compared":[178],"with":[179],"best":[183],"plan":[184],"generated":[185],"sequential":[187],"speedup":[191],"di":[193],"erent":[194],"reported.":[199],"end,":[202],"also":[204],"present":[205],"comparison":[208],"UHFFT":[211],"FFTW":[213],"implementations.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}