{"id":"https://openalex.org/W3163545840","doi":"https://doi.org/10.1145/3468267.3470613","title":"Solving DWF dirac equation using multi-splitting preconditioned conjugate gradient with tensor cores on NVIDIA GPUs","display_name":"Solving DWF dirac equation using multi-splitting preconditioned conjugate gradient with tensor cores on NVIDIA GPUs","publication_year":2021,"publication_date":"2021-07-05","ids":{"openalex":"https://openalex.org/W3163545840","doi":"https://doi.org/10.1145/3468267.3470613","mag":"3163545840"},"language":"en","primary_location":{"id":"doi:10.1145/3468267.3470613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3468267.3470613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3468267.3470613","source":null,"license":null,"license_id":null,"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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3468267.3470613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiqun Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiqun Tu","raw_affiliation_strings":["NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"M. A. Clark","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. A. Clark","raw_affiliation_strings":["NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chulwoo Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chulwoo Jung","raw_affiliation_strings":["Brookhaven National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"last","author":{"id":null,"display_name":"Robert D. Mawhinney","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert D. Mawhinney","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8169,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64048761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9984999895095825,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10271","display_name":"Seismic Imaging and Inversion Techniques","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.8187000155448914},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.6532999873161316},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5206000208854675},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5040000081062317},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.49140000343322754},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.4498000144958496},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.39629998803138733},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3903999924659729}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.8187000155448914},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.6532999873161316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533000230789185},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C89408827","wikidata":"https://www.wikidata.org/wiki/Q855169","display_name":"Biconjugate gradient method","level":5,"score":0.37070000171661377},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3659999966621399},{"id":"https://openalex.org/C50820777","wikidata":"https://www.wikidata.org/wiki/Q213723","display_name":"Hypercube","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C120553275","wikidata":"https://www.wikidata.org/wiki/Q4903720","display_name":"Biconjugate gradient stabilized method","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30979999899864197},{"id":"https://openalex.org/C91394653","wikidata":"https://www.wikidata.org/wiki/Q5161159","display_name":"Conjugate residual method","level":4,"score":0.30649998784065247},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C44274781","wikidata":"https://www.wikidata.org/wiki/Q6497132","display_name":"Lattice reduction","level":4,"score":0.2542000114917755}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3468267.3470613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3468267.3470613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3468267.3470613","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.05615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05615","pdf_url":"https://arxiv.org/pdf/2104.05615","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,"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":"pmh:oai:osti.gov:2333678","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2333678","pdf_url":"https://www.osti.gov/servlets/purl/2333678","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"doi:10.1145/3468267.3470613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3468267.3470613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3468267.3470613","source":null,"license":null,"license_id":null,"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":[{"id":"https://openalex.org/G121915436","display_name":null,"funder_award_id":"DEAC05- 00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1528409558","display_name":null,"funder_award_id":"No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G203625172","display_name":null,"funder_award_id":"DE--AC05--00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G241279073","display_name":null,"funder_award_id":"DE\u2010SC0012704","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2988778103","display_name":null,"funder_award_id":"DE-AC05?","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3049477530","display_name":null,"funder_award_id":"Contract No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G357145406","display_name":null,"funder_award_id":"DE-SC-0012704","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G3850097093","display_name":null,"funder_award_id":"No. DE-SC0012704","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4972998915","display_name":null,"funder_award_id":"Contract No: DESC0012704","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5633341255","display_name":null,"funder_award_id":"No. DE-SC0012704","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5765906131","display_name":null,"funder_award_id":"SC0012704.","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6486853205","display_name":null,"funder_award_id":"Contract No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G6733788163","display_name":null,"funder_award_id":"Contract No. DE-SC0012704","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G6846386583","display_name":"THEORETICAL HIGH ENERGY PHYSICS","funder_award_id":"DESC0011941","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6911681599","display_name":null,"funder_award_id":"No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7463374569","display_name":null,"funder_award_id":"SC0012704","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3163545840.pdf","grobid_xml":"https://content.openalex.org/works/W3163545840.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1730313211","https://openalex.org/W1970261865","https://openalex.org/W1976798627","https://openalex.org/W1984450486","https://openalex.org/W1986289864","https://openalex.org/W1986609007","https://openalex.org/W2027257397","https://openalex.org/W2032576830","https://openalex.org/W2057309399","https://openalex.org/W2059448777","https://openalex.org/W2060823693","https://openalex.org/W2074846139","https://openalex.org/W2106833662","https://openalex.org/W2124904639","https://openalex.org/W2126271681","https://openalex.org/W2155216327","https://openalex.org/W2155967869","https://openalex.org/W2316564661","https://openalex.org/W2555146563","https://openalex.org/W3022212232","https://openalex.org/W3037606462","https://openalex.org/W3130633441"],"related_works":[],"abstract_inverted_index":{"We":[0,88],"show":[1],"that":[2,57],"using":[3],"the":[4,11,23,28,41,45,50,62,86,90,105,111],"multi-splitting":[5],"algorithm":[6],"as":[7],"a":[8,72],"preconditioner":[9,46],"for":[10,85,118],"domain":[12],"wall":[13],"Dirac":[14],"linear":[15],"operator,":[16],"arising":[17],"in":[18,49],"lattice":[19],"QCD,":[20],"effectively":[21],"reduces":[22],"inter-node":[24,128],"communication":[25,129],"cost,":[26],"at":[27,100],"expense":[29],"of":[30],"performing":[31],"more":[32,121],"on-node":[33,122],"floating":[34],"point":[35],"and":[36,61,83,124],"memory":[37,125],"operations.":[38],"Correctly":[39],"including":[40],"boundary":[42],"snake":[43],"terms,":[44],"is":[47,55,68,80],"implemented":[48],"QUDA":[51],"framework,":[52],"where":[53],"it":[54],"found":[56],"utilizing":[58],"kernel":[59],"fusion":[60],"tensor":[63],"cores":[64],"on":[65],"NVIDIA":[66],"GPUs":[67],"necessary":[69],"to":[70,95],"achieve":[71],"sufficiently":[73],"performant":[74],"preconditioner.":[75,87,112],"A":[76],"reduced-dimension":[77],"(reduced-Ls)":[78],"strategy":[79],"also":[81],"proposed":[82],"tested":[84],"find":[89],"method":[91,114],"achieves":[92],"lower":[93],"time":[94],"solution":[96],"than":[97,127],"regular":[98],"CG":[99],"high":[101],"node":[102],"count":[103],"despite":[104],"additional":[106],"local":[107],"computational":[108],"requirements":[109],"from":[110],"This":[113],"could":[115],"be":[116],"useful":[117],"supercomputers":[119],"with":[120],"flops":[123],"bandwidth":[126],"bandwidth.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2021-05-24T00:00:00"}