{"id":"https://openalex.org/W7166094640","doi":"https://doi.org/10.1145/3815572.3815762","title":"A Performance-Portable, Massively Parallel Distributed Nonuniform FFT","display_name":"A Performance-Portable, Massively Parallel Distributed Nonuniform FFT","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166094640","doi":"https://doi.org/10.1145/3815572.3815762"},"language":null,"primary_location":{"id":"doi:10.1145/3815572.3815762","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815572.3815762","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 Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3815572.3815762","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5096147970","display_name":"Paul Fischill","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paul Fischill","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0005-9850-9415","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057790835","display_name":"Andreas Adelmann","orcid":"https://orcid.org/0000-0002-7230-7007"},"institutions":[{"id":"https://openalex.org/I2802229908","display_name":"Paul Scherrer Institute","ror":"https://ror.org/03eh3y714","country_code":"CH","type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I2802229908"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Adelmann","raw_affiliation_strings":["Paul Scherrer Institute, Villigen, Switzerland and ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-7230-7007","affiliations":[{"raw_affiliation_string":"Paul Scherrer Institute, Villigen, Switzerland and ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I2802229908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011706235","display_name":"Sriramkrishnan Muralikrishnan","orcid":"https://orcid.org/0000-0002-5494-1880"},"institutions":[{"id":"https://openalex.org/I171892758","display_name":"Forschungszentrum J\u00fclich","ror":"https://ror.org/02nv7yv05","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I171892758"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sriramkrishnan Muralikrishnan","raw_affiliation_strings":["Forschungszentrum J\u00fclich, J\u00fclich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5494-1880","affiliations":[{"raw_affiliation_string":"Forschungszentrum J\u00fclich, J\u00fclich, Germany","institution_ids":["https://openalex.org/I171892758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8313562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.4487999975681305,"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"}},"topics":[{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.4487999975681305,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.09759999811649323,"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/T10232","display_name":"Optical Network Technologies","score":0.025100000202655792,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.5378999710083008},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.42579999566078186},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.3257000148296356},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.30660000443458557},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.27459999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.633400022983551},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45350000262260437},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41100001335144043},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3815572.3815762","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815572.3815762","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 Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3815572.3815762","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815572.3815762","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 Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1561562988","https://openalex.org/W1737669150","https://openalex.org/W1963792518","https://openalex.org/W1965060209","https://openalex.org/W1998152471","https://openalex.org/W2002199481","https://openalex.org/W2010122118","https://openalex.org/W2012300893","https://openalex.org/W2078794610","https://openalex.org/W2080236984","https://openalex.org/W2090690379","https://openalex.org/W2099944953","https://openalex.org/W2112164060","https://openalex.org/W2131768055","https://openalex.org/W2140980608","https://openalex.org/W2296520333","https://openalex.org/W2503127310","https://openalex.org/W2792765611","https://openalex.org/W2957081506","https://openalex.org/W2973391561","https://openalex.org/W3003966688","https://openalex.org/W3036255981","https://openalex.org/W3093203959","https://openalex.org/W3176102465","https://openalex.org/W3211315168","https://openalex.org/W4246652625","https://openalex.org/W4391759261","https://openalex.org/W4396529508","https://openalex.org/W4402314313","https://openalex.org/W4414882796","https://openalex.org/W6893197023","https://openalex.org/W6911441642"],"related_works":[],"abstract_inverted_index":{"The":[0],"nonuniform":[1],"fast":[2],"Fourier":[3,163],"transform":[4],"(NUFFT)":[5],"enables":[6],"spectral":[7,187],"methods":[8],"for":[9,51,73],"problems":[10],"with":[11,15,159],"irregularly":[12],"spaced":[13],"samples,":[14],"applications":[16],"in":[17],"medical":[18],"imaging,":[19],"molecular":[20],"dynamics,":[21],"and":[22,62,69,77,118,165,172],"kinetic":[23,179],"plasma":[24,180],"simulations.":[25],"Existing":[26],"GPU":[27],"implementations":[28],"are":[29],"limited":[30],"to":[31,37,125,151,161,186],"shared-memory":[32],"execution,":[33],"restricting":[34],"problem":[35],"sizes":[36],"what":[38],"fits":[39],"on":[40,60,110,169],"a":[41,134],"single":[42],"node.":[43],"We":[44,65,147],"present":[45],"the":[46,85,89,130,138,149],"first":[47],"distributed,":[48],"performance-portable":[49],"NUFFT":[50,92,143],"heterogeneous":[52],"supercomputers.":[53],"Our":[54,79],"Kokkos-based":[55,101],"implementation":[56,102],"runs":[57],"without":[58],"modification":[59],"NVIDIA":[61],"AMD":[63,105],"GPUs.":[64,106,127],"develop":[66],"multiple":[67],"spreading":[68,80],"interpolation":[70],"kernels":[71,81],"optimized":[72],"different":[74],"accuracy":[75,144],"requirements":[76],"architectures.":[78],"match":[82],"or":[83],"exceed":[84],"single-GPU":[86],"throughput":[87],"of":[88,137,156],"state-of-the-art":[90],"CUDA-based":[91],"library":[93],"cuFINUFFT":[94],"at":[95,182],"production":[96],"particle":[97,188],"densities,":[98],"while":[99],"our":[100],"additionally":[103],"supports":[104],"Strong":[107],"scaling":[108,123],"experiments":[109],"Alps":[111],"(NVIDIA":[112,116],"GH200),":[113],"JUWELS":[114],"Booster":[115],"A100),":[117],"LUMI":[119],"(AMD":[120],"MI250X)":[121],"demonstrate":[122],"up":[124,160],"1024":[126],"At":[128],"scale,":[129],"distributed":[131,176],"FFT":[132],"is":[133],"significant":[135],"part":[136],"total":[139],"runtime,":[140],"making":[141],"higher":[142],"less":[145],"expensive.":[146],"apply":[148],"method":[150],"massively":[152],"parallel":[153],"Particle-in-Fourier":[154],"simulations":[155,181],"Landau":[157],"damping":[158],"10243":[162],"modes":[164],"8.6":[166],"billion":[167],"particles":[168],"Alps,":[170],"JUWELS,":[171],"LUMI,":[173],"demonstrating":[174],"that":[175],"NUFFTs":[177],"enable":[178],"resolutions":[183],"previously":[184],"inaccessible":[185],"methods.":[189]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-27T00:00:00"}