{"id":"https://openalex.org/W4408049837","doi":"https://doi.org/10.1145/3710848.3710853","title":"TurboFFT: Co-Designed High-Performance and Fault-Tolerant Fast Fourier Transform on GPUs","display_name":"TurboFFT: Co-Designed High-Performance and Fault-Tolerant Fast Fourier Transform on GPUs","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408049837","doi":"https://doi.org/10.1145/3710848.3710853"},"language":"en","primary_location":{"id":"doi:10.1145/3710848.3710853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710853","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710853","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710853","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075806978","display_name":"Shixun Wu","orcid":"https://orcid.org/0000-0001-8637-3307"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shixun Wu","raw_affiliation_strings":["UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035339023","display_name":"Yujia Zhai","orcid":"https://orcid.org/0000-0002-2688-8058"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujia Zhai","raw_affiliation_strings":["UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705519","display_name":"Jinyang Liu","orcid":"https://orcid.org/0000-0003-0177-502X"},"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":"Jinyang Liu","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779661","display_name":"Jiajun Huang","orcid":"https://orcid.org/0000-0001-5092-3987"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Huang","raw_affiliation_strings":["UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071045650","display_name":"Zizhe Jian","orcid":"https://orcid.org/0009-0005-2079-8130"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhe Jian","raw_affiliation_strings":["UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109906601","display_name":"H. L. Dai","orcid":"https://orcid.org/0009-0002-9628-3326"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huangliang Dai","raw_affiliation_strings":["UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103124363","display_name":"Sheng Di","orcid":"https://orcid.org/0000-0002-9935-5674"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Di","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["UC Riverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5075806978"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":2.9249,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.90082779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"70","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11005","display_name":"Radiation Effects in Electronics","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955999851226807,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7365734577178955},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6993569135665894},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5664968490600586},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.49574002623558044},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.42292168736457825},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.13485702872276306},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06389111280441284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7365734577178955},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6993569135665894},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5664968490600586},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.49574002623558044},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.42292168736457825},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.13485702872276306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06389111280441284},{"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:10.1145/3710848.3710853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710853","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710853","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3710848.3710853","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710853","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710853","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408049837.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1541483005","https://openalex.org/W1573878051","https://openalex.org/W1576341769","https://openalex.org/W1629908538","https://openalex.org/W1986905947","https://openalex.org/W1995746640","https://openalex.org/W1997843200","https://openalex.org/W2023856022","https://openalex.org/W2034593585","https://openalex.org/W2042544282","https://openalex.org/W2043483139","https://openalex.org/W2052455844","https://openalex.org/W2061043348","https://openalex.org/W2091067307","https://openalex.org/W2105524676","https://openalex.org/W2130449268","https://openalex.org/W2134320686","https://openalex.org/W2134572726","https://openalex.org/W2150981663","https://openalex.org/W2152211247","https://openalex.org/W2156514327","https://openalex.org/W2158612529","https://openalex.org/W2170196949","https://openalex.org/W2292469857","https://openalex.org/W2296204683","https://openalex.org/W2647773517","https://openalex.org/W2767260595","https://openalex.org/W2767321582","https://openalex.org/W2767694495","https://openalex.org/W2769166900","https://openalex.org/W2788316508","https://openalex.org/W2798289565","https://openalex.org/W3102927675","https://openalex.org/W3105862567","https://openalex.org/W3140366478","https://openalex.org/W3164390940","https://openalex.org/W3171842021","https://openalex.org/W3201073812","https://openalex.org/W4367859812","https://openalex.org/W4372272640","https://openalex.org/W4388666897","https://openalex.org/W4389459420","https://openalex.org/W4393183862","https://openalex.org/W4400409887"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"GPU-based":[0],"fast":[1],"Fourier":[2],"transform":[3],"(FFT)":[4],"is":[5,177],"extremely":[6],"important":[7],"for":[8,44,130,209],"scientific":[9],"computing":[10],"and":[11,23,47,58,92,113,165,187,212],"signal":[12],"processing.":[13],"However,":[14],"we":[15,36,53,82],"find":[16],"the":[17,24,74,90,102,117,147],"inefficiency":[18],"of":[19,26,197,204],"existing":[20],"FFT":[21,41,119],"libraries":[22],"absence":[25],"fault":[27,49,80,86,175,192],"tolerance":[28,87,176,193],"against":[29],"soft":[30],"error.":[31],"To":[32],"address":[33,101],"these":[34],"issues,":[35],"introduce":[37],"TurboFFT,":[38],"a":[39,67,107,166],"new":[40],"prototype":[42,60],"co-designed":[43],"high":[45],"performance":[46,71],"online":[48,136],"tolerance.":[50],"For":[51,79],"FFT,":[52],"propose":[54],"an":[55,160,195],"architecture-aware,":[56],"padding-free,":[57],"template-based":[59],"to":[61,73,95,122,126,179,182,199],"maximize":[62],"hardware":[63],"resource":[64],"utilization,":[65],"achieving":[66],"competitive":[68],"or":[69,180],"superior":[70],"compared":[72],"state-of-the-art":[75],"closed-source":[76],"library,":[77],"cuFFT.":[78],"tolerance,":[81],"1)":[83],"explore":[84],"algorithm-based":[85],"(ABFT)":[88],"at":[89],"thread":[91],"threadblock":[93],"levels":[94],"reduce":[96],"additional":[97,139,155],"memory":[98,141],"footprint,":[99],"2)":[100],"error":[103,205],"propagation":[104],"by":[105],"introducing":[106],"two-side":[108,133],"ABFT":[109,152],"with":[110,153,191],"location":[111],"encoding,":[112],"3)":[114],"further":[115],"modify":[116],"threadblock-level":[118,149],"from":[120],"1-transaction":[121],"multi-transaction":[123,144],"in":[124,151],"order":[125],"bring":[127],"more":[128],"parallelism":[129],"ABFT.":[131],"Our":[132],"strategy":[134],"enables":[135],"correction":[137],"without":[138,174],"global":[140],"while":[142],"our":[143],"design":[145],"averages":[146],"expensive":[148],"reduction":[150],"zero":[154],"operations.":[156],"Experimental":[157],"results":[158],"on":[159],"NVIDIA":[161],"A100":[162],"server":[163],"GPU":[164,170],"Tesla":[167],"Turing":[168],"T4":[169],"demonstrate":[171],"that":[172],"TurboFFT":[173,190],"comparable":[178],"up":[181],"300%":[183],"faster":[184],"than":[185],"cuFFT":[186],"outperforms":[188],"VkFFT.":[189],"maintains":[194],"overhead":[196],"7%":[198],"15%,":[200],"even":[201],"under":[202],"tens":[203],"injections":[206],"per":[207],"minute":[208],"both":[210],"FP32":[211],"FP64.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
