{"id":"https://openalex.org/W2922025187","doi":"https://doi.org/10.1145/3295816.3295817","title":"Performance analysis and autotuning setup of the cuFFT library","display_name":"Performance analysis and autotuning setup of the cuFFT library","publication_year":2018,"publication_date":"2018-11-04","ids":{"openalex":"https://openalex.org/W2922025187","doi":"https://doi.org/10.1145/3295816.3295817","mag":"2922025187"},"language":"en","primary_location":{"id":"doi:10.1145/3295816.3295817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295816.3295817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems","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/A5068360342","display_name":"David St\u0159el\u00e1k","orcid":"https://orcid.org/0000-0003-4513-4718"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"David St\u0159el\u00e1k","raw_affiliation_strings":["Masaryk University Brno, Czech Republic CNB CSIC Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Masaryk University Brno, Czech Republic CNB CSIC Madrid, Spain","institution_ids":["https://openalex.org/I21449261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089216324","display_name":"Ji\u0159\u00ed Filipovi\u010d","orcid":"https://orcid.org/0000-0002-5703-9673"},"institutions":[{"id":"https://openalex.org/I21449261","display_name":"Masaryk University","ror":"https://ror.org/02j46qs45","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21449261"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ji\u0159\u00ed Filipovi\u010d","raw_affiliation_strings":["Masaryk University Brno, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Masaryk University Brno, Czech Republic","institution_ids":["https://openalex.org/I21449261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068360342"],"corresponding_institution_ids":["https://openalex.org/I21449261"],"apc_list":null,"apc_paid":null,"fwci":2.3684,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89145845,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.998199999332428,"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"}},{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9977999925613403,"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":0.9429652690887451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800586819648743},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6892868280410767},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.634042501449585},{"id":"https://openalex.org/keywords/split-radix-fft-algorithm","display_name":"Split-radix FFT algorithm","score":0.5655161738395691},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5433294773101807},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4795210659503937},{"id":"https://openalex.org/keywords/prime-factor-fft-algorithm","display_name":"Prime-factor FFT algorithm","score":0.4631940722465515},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.379446417093277},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3178616166114807},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.30332618951797485},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10403051972389221},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.09347397089004517}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.9429652690887451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800586819648743},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6892868280410767},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.634042501449585},{"id":"https://openalex.org/C103755468","wikidata":"https://www.wikidata.org/wiki/Q17103599","display_name":"Split-radix FFT algorithm","level":5,"score":0.5655161738395691},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5433294773101807},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4795210659503937},{"id":"https://openalex.org/C77928272","wikidata":"https://www.wikidata.org/wiki/Q7243214","display_name":"Prime-factor FFT algorithm","level":5,"score":0.4631940722465515},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.379446417093277},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3178616166114807},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.30332618951797485},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10403051972389221},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.09347397089004517},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3295816.3295817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295816.3295817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on AutotuniNg and aDaptivity AppRoaches for Energy efficient HPC Systems","raw_type":"proceedings-article"}],"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/W1528905581","https://openalex.org/W1658472922","https://openalex.org/W1809752932","https://openalex.org/W2014606598","https://openalex.org/W2096070062","https://openalex.org/W2102182691","https://openalex.org/W2106788917","https://openalex.org/W2107483876","https://openalex.org/W2108600626","https://openalex.org/W2296555911","https://openalex.org/W2430551657","https://openalex.org/W2587758664","https://openalex.org/W2796505725","https://openalex.org/W4236989128","https://openalex.org/W4313180950"],"related_works":["https://openalex.org/W2031343199","https://openalex.org/W2977460836","https://openalex.org/W2356814585","https://openalex.org/W2144412928","https://openalex.org/W2113951268","https://openalex.org/W4362564158","https://openalex.org/W1984254719","https://openalex.org/W2144032791","https://openalex.org/W2185259940","https://openalex.org/W2012363129"],"abstract_inverted_index":{"Fast":[0],"Fourier":[1],"transform":[2],"(FFT)":[3],"has":[4,22],"many":[5,38],"applications.":[6],"It":[7],"is":[8,43],"often":[9,61],"one":[10],"of":[11,20,79],"the":[12,64,85,101,107],"most":[13],"computationally":[14],"demanding":[15],"kernels,":[16],"so":[17],"a":[18,77],"lot":[19],"attention":[21,99],"been":[23],"invested":[24],"into":[25],"tuning":[26],"its":[27],"performance":[28],"on":[29],"various":[30],"hardware":[31],"devices.":[32],"However,":[33],"FFT":[34,65,90],"libraries":[35],"have":[36],"usually":[37],"possible":[39],"settings":[40,50,93,104],"and":[41],"it":[42],"not":[44,96],"always":[45],"easy":[46],"to":[47,83,88,100],"deduce":[48],"which":[49,103],"should":[51],"be":[52],"used":[53],"for":[54,67],"optimal":[55],"performance.":[56],"In":[57],"practice,":[58],"we":[59,69],"can":[60,70],"slightly":[62],"modify":[63],"settings,":[66],"example,":[68],"pad":[71],"or":[72],"crop":[73],"input":[74],"data.":[75],"Surprisingly,":[76],"majority":[78],"state-of-the-art":[80],"papers":[81],"focus":[82],"answer":[84],"question":[86,102],"how":[87],"implement":[89],"under":[91],"given":[92],"but":[94],"do":[95],"pay":[97],"much":[98],"result":[105],"in":[106],"fastest":[108],"computation.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
