{"id":"https://openalex.org/W4386718999","doi":"https://doi.org/10.1145/3605573.3605587","title":"GFFT: a Task Graph Based Fast Fourier Transform Optimization Framework","display_name":"GFFT: a Task Graph Based Fast Fourier Transform Optimization Framework","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386718999","doi":"https://doi.org/10.1145/3605573.3605587"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605587","pdf_url":null,"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 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3605573.3605587","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019136782","display_name":"Qinglin Lu","orcid":"https://orcid.org/0000-0002-8105-147X"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinglin Lu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, China"],"raw_orcid":"https://orcid.org/0000-0002-8105-147X","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102929620","display_name":"Xinyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, China"],"raw_orcid":"https://orcid.org/0000-0002-7345-2003","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695928","display_name":"Wenjing Ma","orcid":"https://orcid.org/0000-0002-1795-4498"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4391767820","display_name":"State Key Laboratory of Computer Science","ror":"https://ror.org/01hsx4r68","country_code":null,"type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818","https://openalex.org/I4391767820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Ma","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, China and State Key Laboratory of Computer Science, China"],"raw_orcid":"https://orcid.org/0000-0002-1795-4498","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, China and State Key Laboratory of Computer Science, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4391767820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054319371","display_name":"Yuwen Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwen Zhao","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, China and University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-4719-1049","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, China and University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046055268","display_name":"Daokun Chen","orcid":"https://orcid.org/0000-0003-2823-7213"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daokun Chen","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, China"],"raw_orcid":"https://orcid.org/0000-0003-2823-7213","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070636985","display_name":"Fangfang Liu","orcid":"https://orcid.org/0000-0001-7344-7493"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4391767820","display_name":"State Key Laboratory of Computer Science","ror":"https://ror.org/01hsx4r68","country_code":null,"type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818","https://openalex.org/I4391767820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangfang Liu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, China and State Key Laboratory of Computer Science, China"],"raw_orcid":"https://orcid.org/0000-0001-7344-7493","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, China and State Key Laboratory of Computer Science, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4391767820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019136782"],"corresponding_institution_ids":["https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":0.8977,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71472112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"513","last_page":"523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9846000075340271,"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":0.7126389741897583},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5124483704566956},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.5006144046783447},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4798526167869568},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33197277784347534},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.31283605098724365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14064189791679382},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05848437547683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126389741897583},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5124483704566956},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5006144046783447},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4798526167869568},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33197277784347534},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31283605098724365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14064189791679382},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05848437547683716},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605573.3605587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605587","pdf_url":null,"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 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3605573.3605587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3605573.3605587","pdf_url":null,"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 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1484558819","https://openalex.org/W1866830630","https://openalex.org/W1966904279","https://openalex.org/W1988888548","https://openalex.org/W2022028092","https://openalex.org/W2030799875","https://openalex.org/W2073671734","https://openalex.org/W2091782827","https://openalex.org/W2096070062","https://openalex.org/W2102182691","https://openalex.org/W2127391977","https://openalex.org/W2136952590","https://openalex.org/W2804032941","https://openalex.org/W2898200251","https://openalex.org/W2904838066","https://openalex.org/W2971002981","https://openalex.org/W2977289290","https://openalex.org/W2983670846","https://openalex.org/W3037749908","https://openalex.org/W3038006402","https://openalex.org/W3105888187","https://openalex.org/W4235537141","https://openalex.org/W6774015895"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2053286651","https://openalex.org/W2181743346","https://openalex.org/W2187401768","https://openalex.org/W2181413294","https://openalex.org/W2989452537","https://openalex.org/W2052122378","https://openalex.org/W2544423928","https://openalex.org/W2062023542"],"abstract_inverted_index":{"Fast":[0],"Fourier":[1],"Transform":[2],"(FFT)":[3],"is":[4],"a":[5,20,27,46,57,144],"widely":[6],"used":[7],"mathematical":[8],"tool":[9],"in":[10,66],"scientific":[11],"and":[12,15,37,69,93,117,134,157],"engineering":[13],"applications,":[14],"optimizing":[16],"its":[17],"performance":[18,89],"remains":[19],"challenging":[21],"problem.":[22],"This":[23],"paper":[24],"introduces":[25],"GFFT,":[26],"novel":[28],"task-graph-based":[29],"FFT":[30,55,60,107],"optimization":[31],"framework":[32],"that":[33,49,62,103],"leverages":[34],"modern":[35],"hardware":[36,51],"software":[38],"techniques":[39],"to":[40,53,78,87,115,119,127,136,155,159,167],"achieve":[41],"high-performance":[42],"computation.":[43],"GFFT":[44,83,104,148],"features":[45],"tuning":[47],"model":[48],"uses":[50],"parameters":[52],"optimize":[54],"decomposition,":[56],"bi-directional":[58],"recursive":[59],"algorithm":[61],"avoids":[63],"strided":[64],"load":[65],"SIMD":[67],"implementation,":[68],"several":[70],"graph":[71],"optimizers":[72],"inspired":[73],"by":[74],"deep":[75],"learning":[76],"frameworks":[77],"enhance":[79],"performance.":[80],"In":[81],"addition,":[82],"utilizes":[84],"task-based":[85],"parallelism":[86],"exploit":[88],"on":[90,121,129,138,161,169],"multi-core":[91,141],"processors":[92],"provide":[94],"potential":[95],"compatibility":[96],"with":[97,143,174],"heterogeneous":[98],"systems.":[99],"Experimental":[100],"results":[101],"demonstrate":[102],"outperforms":[105],"popular":[106],"frameworks,":[108],"achieving":[109],"an":[110,150],"average":[111,151],"speedup":[112,152],"of":[113,153],"1.17x":[114],"FFTW":[116,137,156],"1.27x":[118],"oneMKL":[120,160],"the":[122,130,139,162,170],"Intel":[123,163],"Xeon":[124,164],"processor,":[125,133,165],"1.18x":[126],"AOCL-FFTW":[128,168],"AMD":[131,171],"EPYC":[132,172],"2.11x":[135],"Sunway":[140],"processor":[142,173],"single":[145],"thread.":[146],"Additionally,":[147],"achieves":[149],"11.48x":[154],"1.41x":[158],"9.87x":[166],"16-threads.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
