{"id":"https://openalex.org/W1968928637","doi":"https://doi.org/10.1145/2597652.2597669","title":"Input-adaptive parallel sparse fast fourier transform for stream processing","display_name":"Input-adaptive parallel sparse fast fourier transform for stream processing","publication_year":2014,"publication_date":"2014-06-10","ids":{"openalex":"https://openalex.org/W1968928637","doi":"https://doi.org/10.1145/2597652.2597669","mag":"1968928637"},"language":"en","primary_location":{"id":"doi:10.1145/2597652.2597669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597652.2597669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM international conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","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/A5100366889","display_name":"Shuo Chen","orcid":"https://orcid.org/0000-0003-3848-3397"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuo Chen","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452107","display_name":"Xiaoming Li","orcid":"https://orcid.org/0000-0001-5076-1885"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoming Li","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100366889"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.04877083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.9991999864578247,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9987000226974487,"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":0.9101482629776001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7009861469268799},{"id":"https://openalex.org/keywords/prime-factor-fft-algorithm","display_name":"Prime-factor FFT algorithm","score":0.6764817237854004},{"id":"https://openalex.org/keywords/split-radix-fft-algorithm","display_name":"Split-radix FFT algorithm","score":0.6616351008415222},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.6163778305053711},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5703864693641663},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5663579702377319},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.42734652757644653},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.337629109621048},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23803108930587769},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.16133740544319153},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.15542268753051758}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9101482629776001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009861469268799},{"id":"https://openalex.org/C77928272","wikidata":"https://www.wikidata.org/wiki/Q7243214","display_name":"Prime-factor FFT algorithm","level":5,"score":0.6764817237854004},{"id":"https://openalex.org/C103755468","wikidata":"https://www.wikidata.org/wiki/Q17103599","display_name":"Split-radix FFT algorithm","level":5,"score":0.6616351008415222},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.6163778305053711},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5703864693641663},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5663579702377319},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.42734652757644653},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.337629109621048},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23803108930587769},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.16133740544319153},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.15542268753051758},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2597652.2597669","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597652.2597669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6449945240","display_name":null,"funder_award_id":"FA9550-13-1-0213","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G7118665447","display_name":null,"funder_award_id":"1115771","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W148879656","https://openalex.org/W1501755821","https://openalex.org/W1575519488","https://openalex.org/W1966904279","https://openalex.org/W1986545790","https://openalex.org/W2012365979","https://openalex.org/W2022028092","https://openalex.org/W2031425559","https://openalex.org/W2053817819","https://openalex.org/W2102182691","https://openalex.org/W2107625832","https://openalex.org/W2123119012","https://openalex.org/W2152263739","https://openalex.org/W2904838066"],"related_works":["https://openalex.org/W2031343199","https://openalex.org/W2356814585","https://openalex.org/W2977460836","https://openalex.org/W2144412928","https://openalex.org/W4362564158","https://openalex.org/W2155491755","https://openalex.org/W2154006536","https://openalex.org/W2348800014","https://openalex.org/W1820187807","https://openalex.org/W2365391860"],"abstract_inverted_index":{"Fast":[0],"Fourier":[1,31,205,222],"Transform":[2],"(FFT)":[3],"is":[4,73,88,172,304,331],"frequently":[5],"invoked":[6],"in":[7,19,65,119,166,311],"stream":[8,120,167],"processing,":[9,168],"e.g.,":[10],"calculating":[11],"the":[12,22,29,66,70,77,90,93,96,110,114,129,157,160,180,184,188,193,220,243,261,266,269,273],"spectral":[13,181],"representation":[14,182],"of":[15,28,79,128,183,228,249,254,334],"audio/video":[16],"frames,":[17],"and":[18,113,125,137,146,169,246,258,271,289,299,313,355,360,373],"many":[20],"cases":[21],"inputs":[23,47,118,316],"are":[24,48,62],"sparse,":[25],"i.e.,":[26,293],"most":[27],"inputs'":[30],"coefficients":[32,223],"being":[33],"zero.":[34],"Many":[35],"sparse":[36,59,82,104,139,189,198,210,282,339,345],"FFT":[37,60,83,105,190,283,308,346],"algorithms":[38,71,106],"have":[39],"been":[40],"proposed":[41],"to":[42,50,134,143,155,163,174,186,217,242,328,353],"improve":[43,256],"FFT's":[44],"efficiency":[45],"when":[46,170],"known":[49],"be":[51,175,233],"sparse.":[52],"However,":[53],"like":[54],"their":[55],"\"dense\"":[56],"counterparts,":[57],"existing":[58,103],"implementations":[61,309],"input":[63,111,132,162,244,274,343],"oblivious":[64],"sense":[67],"that":[68,141,200],"how":[69],"work":[72],"not":[74],"affected":[75],"by":[76,107,212],"value":[78],"input.":[80,195],"The":[81],"computation":[84,94,191],"on":[85,95,192,285,347],"one":[86],"frame":[87],"exactly":[89],"same":[91],"as":[92],"next":[97],"frame.":[98],"This":[99],"paper":[100],"improves":[101],"upon":[102],"simultaneously":[108],"exploiting":[109],"sparsity":[112],"similarity":[115,130,158],"between":[116,131,159],"adjacent":[117],"processing.":[121],"Our":[122,302],"algorithm":[123,208,238,303],"detects":[124],"takes":[126],"advantage":[127],"samples":[133],"automatically":[135],"design":[136],"customize":[138],"filters":[140,216],"lead":[142],"better":[144],"parallelism":[145,257],"performance.":[147,259],"More":[148],"specifically,":[149],"we":[150,177],"develop":[151],"an":[152,332],"efficient":[153],"heuristic":[154,263],"detect":[156,265],"current":[161,194],"its":[164],"predecessor":[165,185],"it":[171],"found":[173],"similar,":[176],"novelly":[178],"use":[179],"accelerate":[187],"Given":[196],"a":[197,225],"signal":[199],"has":[201,239],"only":[202],"$k$":[203],"non-zero":[204,221],"coefficients,":[206],"our":[207,237,280,320,342,377],"utilizes":[209],"approximation":[211],"tuning":[213],"several":[214],"adaptive":[215,344],"efficiently":[218],"package":[219],"into":[224],"small":[226],"number":[227],"bins":[229],"which":[230,255,330],"can":[231,264],"then":[232],"estimated":[234],"accurately.":[235],"Therefore,":[236],"runtime":[240],"sub-linear":[241],"size":[245,318],"gets":[247],"rid":[248],"recursive":[250],"coefficient":[251],"estimation,":[252],"both":[253,310],"Furthermore,":[260,341],"new":[262],"discontinuities":[267],"inside":[268],"streams":[270],"resumes":[272],"adaptation":[275],"very":[276],"quickly.":[277],"We":[278],"evaluate":[279],"input-adaptive":[281],"implementation":[284,322],"Intel":[286],"i7":[287],"CPU":[288,379],"three":[290],"NVIDIA":[291,294],"GPUs,":[292],"GeForce":[295],"GTX480,":[296],"Tesla":[297,300,348],"C2070":[298],"C2075.":[301],"faster":[305],"than":[306,337],"previous":[307],"theory":[312],"implementation.":[314],"For":[315],"with":[317],"N=2^{24},":[319],"parallel":[321],"outperforms":[323],"FFTW":[324],"for":[325],"k":[326],"up":[327,352],"2^{18},":[329],"order":[333],"magnitude":[335],"higher":[336],"prior":[338],"algorithms.":[340],"C2075":[349],"GPU":[350],"achieves":[351],"77.2x":[354],"29.3x":[356],"speedups":[357,366],"over":[358,376],"1-thread":[359],"4-thread":[361],"FFTW,":[362],"10.7x,":[363],"6.4x,":[364],"5.2x":[365],"against":[367],"sFFT":[368,370],"1.0,":[369],"2.0,":[371],"CUFFT,":[372],"6.9x":[374],"speedup":[375],"sequential":[378],"performance,":[380],"respectively.":[381]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}