{"id":"https://openalex.org/W4416203815","doi":"https://doi.org/10.1145/3712285.3759772","title":"TurboFNO: High-Performance Fourier Neural Operator with Fused FFT-GEMM-iFFT on GPU","display_name":"TurboFNO: High-Performance Fourier Neural Operator with Fused FFT-GEMM-iFFT on GPU","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416203815","doi":"https://doi.org/10.1145/3712285.3759772"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759772","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 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759772","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":false,"raw_author_name":"Shixun Wu","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0001-8637-3307","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, 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":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0002-2688-8058","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, 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":["University of California Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0009-0002-9628-3326","affiliations":[{"raw_affiliation_string":"University of California Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100513379","display_name":"Yue Zhu","orcid":"https://orcid.org/0009-0009-2273-5618"},"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":"Yue Zhu","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0009-0009-2273-5618","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiyang Hu","orcid":"https://orcid.org/0009-0005-8299-6124"},"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":"Haiyang Hu","raw_affiliation_strings":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0009-0005-8299-6124","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"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":["University of California, Riverside, Riverside, USA"],"raw_orcid":"https://orcid.org/0000-0003-2578-4940","affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"991","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5663999915122986,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5663999915122986,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.08429999649524689,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.04149999842047691,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.8718000054359436},{"id":"https://openalex.org/keywords/split-radix-fft-algorithm","display_name":"Split-radix FFT algorithm","score":0.5702000260353088},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5630999803543091},{"id":"https://openalex.org/keywords/prime-factor-fft-algorithm","display_name":"Prime-factor FFT algorithm","score":0.5109000205993652},{"id":"https://openalex.org/keywords/twiddle-factor","display_name":"Twiddle factor","score":0.46129998564720154},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.42239999771118164}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8718000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591999769210815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.621399998664856},{"id":"https://openalex.org/C103755468","wikidata":"https://www.wikidata.org/wiki/Q17103599","display_name":"Split-radix FFT algorithm","level":5,"score":0.5702000260353088},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C77928272","wikidata":"https://www.wikidata.org/wiki/Q7243214","display_name":"Prime-factor FFT algorithm","level":5,"score":0.5109000205993652},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C4697666","wikidata":"https://www.wikidata.org/wiki/Q7857913","display_name":"Twiddle factor","level":5,"score":0.46129998564720154},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.2833000123500824},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759772","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 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759772","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759772","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 International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1810694562","https://openalex.org/W1977146182","https://openalex.org/W2028146845","https://openalex.org/W2073773252","https://openalex.org/W2086748522","https://openalex.org/W2110455005","https://openalex.org/W2120145199","https://openalex.org/W2161516432","https://openalex.org/W2502191402","https://openalex.org/W2915802156","https://openalex.org/W2954698171","https://openalex.org/W3081168214","https://openalex.org/W3185424780","https://openalex.org/W4283835962","https://openalex.org/W4292218920","https://openalex.org/W4319069056","https://openalex.org/W4367859812","https://openalex.org/W4372272640","https://openalex.org/W4384705353","https://openalex.org/W4386763993","https://openalex.org/W4387008005","https://openalex.org/W4388666897","https://openalex.org/W4388855658","https://openalex.org/W4389127811","https://openalex.org/W4389459420","https://openalex.org/W4391093839","https://openalex.org/W4393183862","https://openalex.org/W4400409887","https://openalex.org/W4404133321","https://openalex.org/W4404780808","https://openalex.org/W4405755896","https://openalex.org/W4406014313","https://openalex.org/W4408049837","https://openalex.org/W4408049841","https://openalex.org/W4411074661","https://openalex.org/W7084107549"],"related_works":[],"abstract_inverted_index":{"Fourier":[0,20],"Neural":[1],"Operators":[2],"(FNO)":[3],"are":[4],"widely":[5],"used":[6],"for":[7],"learning":[8],"partial":[9],"differential":[10],"equation":[11],"solution":[12],"operators.":[13],"However,":[14],"FNO":[15],"lacks":[16],"architecture-aware":[17],"optimizations,with":[18],"its":[19],"layers":[21],"executing":[22],"FFT,":[23],"filtering,":[24],"GEMM,":[25],"zero":[26],"padding,":[27],"and":[28,37,60,76,89,102,147,171],"iFFT":[29,150],"as":[30],"separate":[31],"stages,":[32],"incurring":[33],"multiple":[34],"kernel":[35,51,81],"launches":[36],"significant":[38],"global":[39],"memory":[40,95,132,138],"traffic.":[41],"We":[42,56],"propose":[43,106],"TurboFNO,":[44],"the":[45,72,100,118,123,149],"first":[46,57],"fully":[47],"fused":[48],"FFT-GEMM-iFFT":[49],"GPU":[50,165],"with":[52,122],"built-in":[53,84],"FFT":[54,59,80,101,108,143],"optimizations.":[55],"develop":[58],"GEMM":[61,103,146,153],"kernels":[62],"from":[63,156],"scratch,":[64],"achieving":[65],"performance":[66],"comparable":[67],"to":[68,92,135,145,151,175],"or":[69],"faster":[70],"than":[71],"closed-source":[73],"SOTA":[74],"cuBLAS":[75],"cuFFT.":[77],"Additionally,":[78,127],"our":[79],"integrates":[82],"a":[83,112],"high-frequency":[85],"truncation,":[86],"input":[87],"zero-padding,":[88],"pruning":[90],"feature":[91],"avoid":[93],"additional":[94],"copy":[96],"kernels.":[97],"To":[98],"fuse":[99],"workloads,":[104],"we":[105,128],"an":[107,162],"variant":[109],"in":[110,125],"which":[111],"single":[113],"thread":[114],"block":[115],"iterates":[116],"over":[117],"hidden":[119],"dimension,":[120],"aligning":[121],"k-loop":[124],"GEMM.":[126],"design":[129],"two":[130],"shared":[131,157],"swizzling":[133],"patterns":[134],"achieve":[136],"100%":[137],"bank":[139],"utilization":[140],"when":[141],"forwarding":[142],"output":[144],"enabling":[148],"retrieve":[152],"results":[154],"directly":[155],"memory.":[158],"Experimental":[159],"result":[160],"on":[161],"NVIDIA":[163],"A100":[164],"shows":[166],"TurboFNO":[167],"outperforms":[168],"PyTorch,":[169],"cuBLAS,":[170],"cuFFT":[172],"by":[173],"up":[174],"150%.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-12T00:00:00"}