{"id":"https://openalex.org/W4308090249","doi":"https://doi.org/10.1109/hpec55821.2022.9926333","title":"A High Throughput Hardware Accelerator for FFTW Codelets: A First Look","display_name":"A High Throughput Hardware Accelerator for FFTW Codelets: A First Look","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4308090249","doi":"https://doi.org/10.1109/hpec55821.2022.9926333"},"language":"en","primary_location":{"id":"doi:10.1109/hpec55821.2022.9926333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5091539370","display_name":"Larry Tang","orcid":"https://orcid.org/0009-0000-7749-6196"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Larry Tang","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429226","display_name":"Siyuan Chen","orcid":"https://orcid.org/0000-0001-7774-2430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Chen","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069328293","display_name":"Keshav Harisrikanth","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keshav Harisrikanth","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003023334","display_name":"Guanglin Xu","orcid":"https://orcid.org/0009-0007-7743-9088"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanglin Xu","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377660","display_name":"Ken Mai","orcid":"https://orcid.org/0000-0002-9096-8757"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Mai","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062806943","display_name":"Franz Franchetti","orcid":"https://orcid.org/0000-0002-3529-8973"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franz Franchetti","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091539370"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.4462,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59067925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9860000014305115,"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"}},"topics":[{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9860000014305115,"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/T10299","display_name":"Photonic and Optical Devices","score":0.9797999858856201,"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"}},{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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":0.7941814661026001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7451831102371216},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.64141446352005},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6357442140579224},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6221038103103638},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.49902915954589844},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.48728787899017334},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4394574463367462},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4143350124359131},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4126591384410858},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41020750999450684},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38374394178390503},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3787321448326111},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3249611258506775},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21788600087165833},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11952078342437744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.06397199630737305}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.7941814661026001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451831102371216},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.64141446352005},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6357442140579224},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6221038103103638},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.49902915954589844},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.48728787899017334},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4394574463367462},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4143350124359131},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4126591384410858},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41020750999450684},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38374394178390503},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3787321448326111},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3249611258506775},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21788600087165833},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11952078342437744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.06397199630737305},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec55821.2022.9926333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4327521644","https://openalex.org/W2978884468","https://openalex.org/W3132558499","https://openalex.org/W2005846134","https://openalex.org/W2168413811","https://openalex.org/W2369237035","https://openalex.org/W2948041274","https://openalex.org/W4226515754","https://openalex.org/W2087878472","https://openalex.org/W4367355863"],"abstract_inverted_index":{"The":[0,57,100],"Fast":[1],"Fourier":[2],"Transform":[3],"(FFT)":[4],"is":[5,59,103,112],"a":[6,51,79,84,92,109,115],"critical":[7],"computation":[8,72],"for":[9,96,131],"numerous":[10],"applications":[11],"in":[12,36,114],"science":[13],"and":[14,22,108,127],"engineering.":[15],"Its":[16],"implementation":[17],"has":[18],"been":[19],"widely":[20],"studied":[21],"optimized":[23],"on":[24,78],"various":[25],"computing":[26],"platforms,":[27],"with":[28],"the":[29,33,46,62,76,124],"FFTW":[30,47,66,97],"library":[31,48,69],"becoming":[32],"standard":[34],"interface":[35],"HPC.":[37],"In":[38],"this":[39,88],"work,":[40],"we":[41,90],"propose":[42],"hardware":[43,58,102],"acceleration":[44],"of":[45,123],"by":[49],"putting":[50],"software":[52,68],"code":[53],"let":[54],"into":[55],"hardware.":[56],"exposed":[60],"to":[61],"user":[63],"through":[64],"an":[65],"-compatible":[67],"while":[70],"actual":[71],"takes":[73],"place":[74],"behind":[75],"scenes":[77],"custom":[80],"accelerator.":[81],"To":[82],"demonstrate":[83],"first":[85],"look":[86],"at":[87],"idea,":[89],"design":[91],"high":[93],"throughput":[94],"accelerator":[95],"twiddle":[98],"codelets.":[99],"FFT":[101],"automatically":[104],"generated":[105],"using":[106],"SPIRAL":[107],"test":[110,125],"chip":[111,126],"fabricated":[113],"TSMC":[116],"28nm":[117],"process.":[118],"We":[119],"provide":[120],"measured":[121],"results":[122],"discuss":[128],"many":[129],"opportunities":[130],"future":[132],"work.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
