{"id":"https://openalex.org/W4408049841","doi":"https://doi.org/10.1145/3710848.3710897","title":"FlashFFTStencil: Bridging Fast Fourier Transforms to Memory-Efficient Stencil Computations on Tensor Core Units","display_name":"FlashFFTStencil: Bridging Fast Fourier Transforms to Memory-Efficient Stencil Computations on Tensor Core Units","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408049841","doi":"https://doi.org/10.1145/3710848.3710897"},"language":"en","primary_location":{"id":"doi:10.1145/3710848.3710897","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710897","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710897","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/10.1145/3710848.3710897","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102695664","display_name":"Haozhi Han","orcid":"https://orcid.org/0009-0004-3075-3385"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haozhi Han","raw_affiliation_strings":["Peking University, Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377529","display_name":"Kun Li","orcid":"https://orcid.org/0000-0002-1013-1325"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102777439","display_name":"Wei Cui","orcid":"https://orcid.org/0009-0005-9362-3585"},"institutions":[{"id":"https://openalex.org/I4210153468","display_name":"Microsoft (Canada)","ror":"https://ror.org/04xhxg104","country_code":"CA","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210153468"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wei Cui","raw_affiliation_strings":["Microsoft Research, Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Vancouver, Canada","institution_ids":["https://openalex.org/I4210153468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089673535","display_name":"Donglin Bai","orcid":"https://orcid.org/0000-0002-3655-8677"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donglin Bai","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Yiwei Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072946868","display_name":"Liang Yuan","orcid":"https://orcid.org/0000-0003-3406-2907"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yuan","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052630853","display_name":"Yifeng Chen","orcid":"https://orcid.org/0000-0002-2392-8472"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifeng Chen","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016255357","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0001-7520-9640"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Yunquan Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534161","display_name":"Ting Cao","orcid":"https://orcid.org/0000-0002-9107-013X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Cao","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438310","display_name":"Mao Yang","orcid":"https://orcid.org/0009-0009-6455-3898"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Yang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5102695664"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":13.6215,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98706177,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"355","last_page":"368"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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":0.9980999827384949,"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/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1908","display_name":"Geophysics"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/stencil","display_name":"Stencil","score":0.8644059300422668},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6623482704162598},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6158773303031921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5894336700439453},{"id":"https://openalex.org/keywords/out-of-core-algorithm","display_name":"Out-of-core algorithm","score":0.49744418263435364},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4759911298751831},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.45854452252388},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4093192517757416},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.400859534740448},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2986038327217102},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1960432529449463},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1227395236492157},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09133055806159973}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8644059300422668},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6623482704162598},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6158773303031921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5894336700439453},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.49744418263435364},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4759911298751831},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.45854452252388},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4093192517757416},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.400859534740448},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2986038327217102},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1960432529449463},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1227395236492157},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09133055806159973},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3710848.3710897","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710897","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710897","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:10.1145/3710848.3710897","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710897","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710897","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408049841.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1559264847","https://openalex.org/W1561247983","https://openalex.org/W1979457157","https://openalex.org/W1987588924","https://openalex.org/W1987741783","https://openalex.org/W1993166652","https://openalex.org/W1996933093","https://openalex.org/W2011191879","https://openalex.org/W2039417226","https://openalex.org/W2049009664","https://openalex.org/W2055312318","https://openalex.org/W2057897376","https://openalex.org/W2063656563","https://openalex.org/W2074833026","https://openalex.org/W2077143534","https://openalex.org/W2132307955","https://openalex.org/W2134128809","https://openalex.org/W2151764765","https://openalex.org/W2154078685","https://openalex.org/W2296555911","https://openalex.org/W2296730406","https://openalex.org/W2315715336","https://openalex.org/W2325755933","https://openalex.org/W2528222261","https://openalex.org/W2730450744","https://openalex.org/W2889543163","https://openalex.org/W2902566644","https://openalex.org/W2903775786","https://openalex.org/W2913533776","https://openalex.org/W2922025187","https://openalex.org/W2936463352","https://openalex.org/W2962946415","https://openalex.org/W2963242393","https://openalex.org/W2983655274","https://openalex.org/W2984920043","https://openalex.org/W2996929894","https://openalex.org/W3045710976","https://openalex.org/W3099814709","https://openalex.org/W3130554079","https://openalex.org/W3132763358","https://openalex.org/W3147517636","https://openalex.org/W3175788003","https://openalex.org/W3196320218","https://openalex.org/W3205077974","https://openalex.org/W4213291363","https://openalex.org/W4255560897","https://openalex.org/W4283029140","https://openalex.org/W4283641593","https://openalex.org/W4308090436","https://openalex.org/W4309672181","https://openalex.org/W4321636636","https://openalex.org/W4321636661","https://openalex.org/W4366977677","https://openalex.org/W4367684987","https://openalex.org/W4376632753","https://openalex.org/W4381328365","https://openalex.org/W4385199271","https://openalex.org/W4391987273","https://openalex.org/W4405756205"],"related_works":["https://openalex.org/W2177020196","https://openalex.org/W1429949169","https://openalex.org/W3139770841","https://openalex.org/W4321617925","https://openalex.org/W4224944508","https://openalex.org/W2560781234","https://openalex.org/W1529356657","https://openalex.org/W2111914791","https://openalex.org/W3086863455","https://openalex.org/W2566489924"],"abstract_inverted_index":{"While":[0],"Tensor":[1],"Core":[2],"Units":[3],"(TCUs)":[4],"excel":[5],"in":[6,148],"AI":[7],"tasks,":[8],"their":[9],"application":[10],"to":[11,21,25,41,44,66,117],"HPC":[12,154],"algorithms":[13],"like":[14,164],"stencil":[15,37,46,81],"computations":[16,47,82],"faces":[17],"significant":[18],"challenges":[19],"due":[20],"sparsity,":[22],"which":[23],"leads":[24],"underutilization":[26],"and":[27,73,99,106,156],"exacerbates":[28],"memory-bound":[29],"limitations.":[30],"This":[31],"paper":[32],"introduces":[33],"FlashFFTStencil1,":[34],"a":[35,111,145],"memory-efficient":[36],"computing":[38],"system":[39],"designed":[40],"bridge":[42],"FFT":[43],"fully-dense":[45],"on":[48,61,77,94],"TCUs.":[49,165],"Aimed":[50],"at":[51],"bound":[52,132],"shifting,":[53,133],"FlashFFTStencil":[54,128,143],"comprises":[55],"three":[56],"key":[57],"techniques:":[58],"Kernel":[59],"Tailoring":[60],"HBM":[62],"fuses":[63],"distinct":[64],"kernels":[65],"enhance":[67],"parallelism":[68,101],"while":[69],"reducing":[70],"memory":[71,90],"transfer":[72],"footprint;":[74],"Architecture":[75],"Aligning":[76],"SMEM":[78],"restructures":[79],"FFT-based":[80],"into":[83],"dense":[84],"matrix":[85],"multiplications":[86],"tailored":[87],"for":[88],"shared":[89],"architecture;":[91],"Computation":[92],"Streamlining":[93],"TCU":[95,97],"optimizes":[96],"utilization":[98],"thread":[100],"by":[102,123],"minimizing":[103],"pipeline":[104],"stalls":[105],"maximizing":[107],"register":[108],"reuse.":[109],"Notably,":[110],"distinctive":[112],"extension":[113],"is":[114],"FlashFFTStencil's":[115],"ability":[116],"enable":[118],"theoretically":[119],"unrestricted":[120],"temporal":[121],"fusion":[122],"FFT.":[124],"Results":[125],"show":[126],"that":[127],"achieves":[129],"effective":[130],"sparsity-free":[131],"with":[134,159],"an":[135],"average":[136],"speedup":[137],"of":[138],"2.57x":[139],"over":[140],"the":[141,153],"state-of-the-art.":[142],"pioneers":[144],"new":[146],"era":[147],"unifying":[149],"computational":[150],"patterns":[151],"within":[152],"landscape":[155],"bridges":[157],"them":[158],"cutting-edge":[160],"AI-driven":[161],"hardware":[162],"innovations":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}