{"id":"https://openalex.org/W2124224644","doi":"https://doi.org/10.1109/pccc.2013.6742796","title":"A hybrid GPU/CPU FFT library for large FFT problems","display_name":"A hybrid GPU/CPU FFT library for large FFT problems","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2124224644","doi":"https://doi.org/10.1109/pccc.2013.6742796","mag":"2124224644"},"language":"en","primary_location":{"id":"doi:10.1109/pccc.2013.6742796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2013.6742796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 32nd International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://udspace.udel.edu/bitstreams/3d81b1ab-87da-4379-ab3b-7b3c716b7ba9/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100366892","display_name":"Shuo Chen","orcid":"https://orcid.org/0009-0008-5912-4178"},"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":"Shuo Chen","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Delaware, Newark, DE","Dept. of Electr. & Comput. Eng., Univ. of Delaware, Newark, DE, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Delaware, Newark, DE","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452126","display_name":"Xiaoming Li","orcid":"https://orcid.org/0000-0002-3059-9793"},"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":["Dept. of Electrical and Computer Engineering, University of Delaware, Newark, DE","Dept. of Electr. & Comput. Eng., Univ. of Delaware, Newark, DE, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Delaware, Newark, DE","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.7173,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.67684887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9950000047683716,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8868120312690735},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8754608631134033},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.761363685131073},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.4867141544818878},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4634520709514618},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4549235701560974},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.45246174931526184},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.26794302463531494},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12061098217964172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8868120312690735},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8754608631134033},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.761363685131073},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.4867141544818878},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4634520709514618},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4549235701560974},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.45246174931526184},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26794302463531494},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12061098217964172}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pccc.2013.6742796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pccc.2013.6742796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 32nd International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:udspace.udel.edu:19716/12800","is_oa":true,"landing_page_url":"http://udspace.udel.edu/handle/19716/12800","pdf_url":"https://udspace.udel.edu/bitstreams/3d81b1ab-87da-4379-ab3b-7b3c716b7ba9/download","source":{"id":"https://openalex.org/S4377196565","display_name":"Library, Museums and Press - UDSpace (University of Delaware)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I86501945","host_organization_name":"University of Delaware","host_organization_lineage":["https://openalex.org/I86501945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:udspace.udel.edu:19716/12800","is_oa":true,"landing_page_url":"http://udspace.udel.edu/handle/19716/12800","pdf_url":"https://udspace.udel.edu/bitstreams/3d81b1ab-87da-4379-ab3b-7b3c716b7ba9/download","source":{"id":"https://openalex.org/S4377196565","display_name":"Library, Museums and Press - UDSpace (University of Delaware)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I86501945","host_organization_name":"University of Delaware","host_organization_lineage":["https://openalex.org/I86501945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2124224644.pdf","grobid_xml":"https://content.openalex.org/works/W2124224644.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1631114303","https://openalex.org/W1966904279","https://openalex.org/W1967802285","https://openalex.org/W2009516879","https://openalex.org/W2022028092","https://openalex.org/W2061171222","https://openalex.org/W2074570088","https://openalex.org/W2102182691","https://openalex.org/W2107483876","https://openalex.org/W2108600626","https://openalex.org/W2108792719","https://openalex.org/W2114927422","https://openalex.org/W2123119012","https://openalex.org/W2164197394","https://openalex.org/W2171473263","https://openalex.org/W2904838066","https://openalex.org/W3004184795","https://openalex.org/W3147878143","https://openalex.org/W6684857869"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2088078730","https://openalex.org/W2400763249","https://openalex.org/W1482063109","https://openalex.org/W2043940072","https://openalex.org/W2249399447","https://openalex.org/W2745443495","https://openalex.org/W2115229350"],"abstract_inverted_index":{"Graphic":[0],"Processing":[1],"Units":[2],"(GPU)":[3],"has":[4],"been":[5],"proved":[6],"to":[7,12,51,75,85,117],"be":[8],"a":[9,57,71,99],"promising":[10],"platform":[11],"accelerate":[13],"large":[14,150],"size":[15,31],"Fast":[16],"Fourier":[17],"Transform":[18],"(FFT)":[19],"computation.":[20],"However,":[21],"GPU":[22,44,50,81,94,110],"performance":[23,141],"is":[24,66,136,159],"severely":[25],"restricted":[26],"by":[27],"the":[28,33],"limited":[29],"memory":[30],"and":[32,80,89,109,111,120,126,143,161,168,175],"low":[34],"bandwidth":[35],"of":[36,64,107],"data":[37],"transfer":[38],"through":[39],"PCI":[40],"channel.":[41],"Additionally,":[42],"current":[43],"based":[45],"FFT":[46,114,151],"implementation":[47],"only":[48],"uses":[49],"compute,":[52],"but":[53],"employs":[54],"CPU":[55,79,108],"as":[56],"mere":[58],"memory-transfer":[59],"controller.":[60],"The":[61],"computing":[62],"power":[63],"CPUs":[65],"wasted.":[67],"This":[68,96],"paper":[69],"proposes":[70],"hybrid":[72],"parallel":[73],"framework":[74],"use":[76],"both":[77],"multi-core":[78],"in":[82,131],"heterogeneous":[83],"systems":[84],"compute":[86],"large-scale":[87],"2D":[88],"3D":[90],"FFTs":[91],"that":[92,103],"exceed":[93],"memory.":[95],"work":[97],"introduces":[98],"flexible":[100],"partitioning":[101],"scheme":[102],"enables":[104],"concurrent":[105],"execution":[106],"integrates":[112],"several":[113],"decomposition":[115],"paradigms":[116],"tailor":[118],"computation":[119],"communication.":[121],"Moreover,":[122],"our":[123,149],"library":[124,152],"exposes":[125],"exploits":[127],"previously":[128],"overlooked":[129],"parallelism":[130],"FFT.":[132],"Optimal":[133],"load":[134],"balancing":[135],"automatically":[137],"achieved":[138],"from":[139],"effective":[140],"modeling":[142],"empirical":[144],"tuning":[145],"process.":[146],"On":[147],"average,":[148],"on":[153],"GeForce":[154],"GTX480,":[155],"Tesla":[156],"C2070,":[157],"C2075":[158],"121%":[160],"145%":[162],"faster":[163],"than":[164],"4-thread":[165],"SSE-enabled":[166],"FFTW":[167],"Intel":[169],"MKL,":[170],"with":[171],"max":[172],"speedups":[173],"4.61":[174],"2.81,":[176],"respectively.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}