{"id":"https://openalex.org/W7223092907","doi":"https://doi.org/10.48550/arxiv.2610.28372","title":"Fast and scalable multi-GPU sliced FFT solvers for asymptotically compatible discretizations of 3D nonlocal diffusion problems","display_name":"Fast and scalable multi-GPU sliced FFT solvers for asymptotically compatible discretizations of 3D nonlocal diffusion problems","publication_year":2026,"publication_date":"2026-10-20","ids":{"openalex":"https://openalex.org/W7223092907","doi":"https://doi.org/10.48550/arxiv.2610.28372"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.28372","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28372","pdf_url":"https://arxiv.org/pdf/2610.28372","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.28372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159173181","display_name":"Yulong Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yulong","raw_affiliation_strings":["School of Mathematics and Statistics , and National Center for Applied Mathematics in Hubei , Wuhan University , Wuhan 430072 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , and National Center for Applied Mathematics in Hubei , Wuhan University , Wuhan 430072 , China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159170026","display_name":"Jiale Meng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Jiale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159193193","display_name":"Zhenlin Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210139958","display_name":"Beijing Computational Science Research Center","ror":"https://ror.org/04tavf782","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139958"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Zhenlin","raw_affiliation_strings":["Co-corresponding author . Beijing Computational Science Research Center , Beijing , 100193 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Co-corresponding author . Beijing Computational Science Research Center , Beijing , 100193 , China","institution_ids":["https://openalex.org/I4210139958"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159219226","display_name":"Jiwei Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Jiwei","raw_affiliation_strings":["Co-corresponding author. School of Mathematics and Statistics , and Hubei Key Laboratory of Computational Science , Wuhan University , Wuhan 430072 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Co-corresponding author. School of Mathematics and Statistics , and Hubei Key Laboratory of Computational Science , Wuhan University , Wuhan 430072 , China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10514","display_name":"Numerical methods in engineering","score":0.5228999853134155,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10514","display_name":"Numerical methods in engineering","score":0.5228999853134155,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3107999861240387,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.052400000393390656,"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/peridynamics","display_name":"peridynamics","score":0.8100000023841858},{"id":"https://openalex.org/keywords/nonlocal-diffusion","display_name":"nonlocal diffusion","score":0.9879999756813049},{"id":"https://openalex.org/keywords/multi-gpu-computing","display_name":"multi-GPU computing","score":0.8999999761581421},{"id":"https://openalex.org/keywords/multigrid-preconditioning","display_name":"multigrid preconditioning","score":0.9959999918937683},{"id":"https://openalex.org/keywords/parallel-scalability","display_name":"parallel scalability","score":0.35899999737739563}],"concepts":[{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.7089999914169312},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6342999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003000140190125},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.588100016117096},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.5666999816894531},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5038999915122986},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49779999256134033},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4271000027656555},{"id":"https://openalex.org/C181330731","wikidata":"https://www.wikidata.org/wiki/Q2068418","display_name":"Finite difference","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.35920000076293945},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C77928272","wikidata":"https://www.wikidata.org/wiki/Q7243214","display_name":"Prime-factor FFT algorithm","level":5,"score":0.33640000224113464},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3075999915599823},{"id":"https://openalex.org/C205951836","wikidata":"https://www.wikidata.org/wiki/Q1147751","display_name":"Finite difference method","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C181789720","wikidata":"https://www.wikidata.org/wiki/Q4812191","display_name":"Asymptotically optimal algorithm","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C203739276","wikidata":"https://www.wikidata.org/wiki/Q1780355","display_name":"Machine epsilon","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.28372","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28372","pdf_url":"https://arxiv.org/pdf/2610.28372","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.28372","doi":"https://doi.org/10.48550/arxiv.2610.28372","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.28372","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.28372","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28372","pdf_url":"https://arxiv.org/pdf/2610.28372","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223092907.pdf","grobid_xml":"https://content.openalex.org/works/W7223092907.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W1272383281","https://openalex.org/W4416017756"],"related_works":["https://openalex.org/W7220980864","https://openalex.org/W3120508029","https://openalex.org/W4393281752","https://openalex.org/W4280528130","https://openalex.org/W4360617672","https://openalex.org/W2903069957","https://openalex.org/W2021104567","https://openalex.org/W2171120359","https://openalex.org/W2071739952","https://openalex.org/W2082311763"],"abstract_inverted_index":{"Large-scale":[0],"3D":[1,72,191],"peridynamic":[2,192],"transient":[3,151],"diffusion":[4],"simulations":[5],"are":[6],"constrained":[7],"by":[8,70],"the":[9,30,41,49,60,65,120,168],"computational":[10],"cost":[11],"and":[12,22,45,90,123],"memory":[13,143],"requirements":[14],"of":[15,132,142,158,190],"nonlocal":[16],"interactions.":[17],"We":[18,74],"propose":[19],"a":[20,76,92,172,183],"fast":[21,188],"scalable":[23,184],"multi-GPU":[24,185],"sliced":[25,104,180],"FFT":[26,52,181],"algorithm":[27,50],"based":[28],"on":[29,110,119,134],"recently":[31],"developed":[32],"asymptotically":[33],"compatible":[34],"finite":[35,46],"difference":[36],"(ACFD)":[37],"scheme.":[38],"By":[39],"exploiting":[40],"discrete":[42],"operator's":[43],"structure":[44],"interaction":[47],"range,":[48],"combines":[51],"acceleration":[53],"with":[54,114,139,153],"local":[55,169],"inter-GPU":[56],"communication.":[57],"It":[58],"preserves":[59],"ACFD":[61],"scheme":[62],"while":[63],"avoiding":[64],"global":[66],"data":[67],"redistribution":[68],"required":[69],"full":[71,117],"FFTs.":[73],"build":[75],"matrix-free":[77],"GPU":[78],"conjugate":[79],"gradient":[80],"(CG)":[81],"solver,":[82],"use":[83],"multigrid":[84],"preconditioning":[85],"to":[86],"reduce":[87],"iteration":[88],"counts,":[89],"introduce":[91],"human-audited":[93],"configuration":[94],"agent":[95],"for":[96,116,187],"efficient":[97],"cross-level":[98],"configuration.":[99],"Strong-scaling":[100],"tests":[101],"show":[102],"that":[103,179],"FFT-CG":[105,118],"achieves":[106],"93.2%":[107],"parallel":[108],"efficiency":[109],"eight":[111,135],"GPUs,":[112],"compared":[113],"28.2%":[115],"same":[121],"problem":[122],"hardware.":[124],"The":[125,145],"framework":[126],"supports":[127],"approximately":[128,154],"10.29":[129],"billion":[130,156],"degrees":[131,157],"freedom":[133],"RTX":[136],"4090":[137],"GPUs":[138],"24":[140],"GB":[141],"each.":[144],"insulated":[146],"penny-shaped":[147],"cutout":[148],"benchmark":[149],"demonstrates":[150,165],"simulation":[152],"8.58":[155],"freedom.":[159],"Three-dimensional":[160],"star-shaped":[161],"interface":[162],"evolution":[163],"further":[164],"convergence":[166],"toward":[167],"solution":[170],"in":[171],"nonlinear":[173],"phase-field":[174],"problem.":[175],"These":[176],"results":[177],"demonstrate":[178],"provides":[182],"approach":[186],"computation":[189],"diffusion.":[193]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-22T00:00:00"}