{"id":"https://openalex.org/W4321446133","doi":"https://doi.org/10.1145/3572848.3577477","title":"Generating Fast FFT Kernels on CPUs via FFT-Specific Intrinsics","display_name":"Generating Fast FFT Kernels on CPUs via FFT-Specific Intrinsics","publication_year":2023,"publication_date":"2023-02-21","ids":{"openalex":"https://openalex.org/W4321446133","doi":"https://doi.org/10.1145/3572848.3577477"},"language":"en","primary_location":{"id":"doi:10.1145/3572848.3577477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572848.3577477","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 SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","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/A5100380123","display_name":"Zhihao Li","orcid":"https://orcid.org/0000-0002-6149-0627"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhihao Li","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, Huawei Technologies Co., Ltd"],"affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, Huawei Technologies Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101816350","display_name":"Haipeng Jia","orcid":"https://orcid.org/0000-0002-9855-5367"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Jia","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS"],"affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001666028","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0002-2618-5088"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Zhang","raw_affiliation_strings":["SKLP, Institute of Computing, Technology, CAS"],"affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing, Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100582967","display_name":"Yuyan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuyan Sun","raw_affiliation_strings":["Huawei Technologies Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080114640","display_name":"Yiwei Zhang","orcid":"https://orcid.org/0000-0003-2050-572X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Zhang","raw_affiliation_strings":["SKLP, Institute of Computing, Technology, CAS"],"affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing, Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060305663","display_name":"Tun Chen","orcid":"https://orcid.org/0000-0003-3459-7960"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tun Chen","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS"],"affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100380123"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.308,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44252513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"427","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9984999895095825,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8573430776596069},{"id":"https://openalex.org/keywords/intrinsics","display_name":"Intrinsics","score":0.8425388336181641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7693551778793335},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7034125924110413},{"id":"https://openalex.org/keywords/split-radix-fft-algorithm","display_name":"Split-radix FFT algorithm","score":0.603263258934021},{"id":"https://openalex.org/keywords/prime-factor-fft-algorithm","display_name":"Prime-factor FFT algorithm","score":0.594419538974762},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5504962205886841},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46267077326774597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2787984013557434},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2356480062007904},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.16908729076385498},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11712080240249634},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.07608217000961304}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8573430776596069},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.8425388336181641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693551778793335},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7034125924110413},{"id":"https://openalex.org/C103755468","wikidata":"https://www.wikidata.org/wiki/Q17103599","display_name":"Split-radix FFT algorithm","level":5,"score":0.603263258934021},{"id":"https://openalex.org/C77928272","wikidata":"https://www.wikidata.org/wiki/Q7243214","display_name":"Prime-factor FFT algorithm","level":5,"score":0.594419538974762},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5504962205886841},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46267077326774597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2787984013557434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2356480062007904},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.16908729076385498},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11712080240249634},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.07608217000961304},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572848.3577477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572848.3577477","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 SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2102182691","https://openalex.org/W2983670846","https://openalex.org/W3010781441"],"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":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"algorithm-specific":[4],"instruction":[5],"(ASI)-based":[6],"fast":[7],"Fourier":[8],"transform":[9],"(FFT)":[10],"code":[11],"generation":[12],"framework,":[13],"named":[14],"FFTASI,":[15],"to":[16],"generate":[17],"unified":[18],"architecture":[19],"independent":[20],"butterfly":[21],"kernels":[22,29],"that":[23],"can":[24],"be":[25],"transformed":[26],"into":[27],"architecture-dependent":[28],"by":[30],"establishing":[31],"the":[32],"mapping":[33],"between":[34,48],"ASIs":[35],"and":[36,50],"architecture-specific":[37],"instructions":[38],"for":[39],"various":[40],"hardware":[41],"platforms.":[42],"FFTASI":[43],"strikes":[44],"a":[45],"good":[46],"balance":[47],"performance":[49],"productivity":[51],"on":[52],"CPUs.":[53]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}