{"id":"https://openalex.org/W3024918586","doi":"https://doi.org/10.1007/s11227-020-03340-9","title":"Applying the swept rule for solving explicit partial differential equations on heterogeneous computing systems","display_name":"Applying the swept rule for solving explicit partial differential equations on heterogeneous computing systems","publication_year":2020,"publication_date":"2020-05-30","ids":{"openalex":"https://openalex.org/W3024918586","doi":"https://doi.org/10.1007/s11227-020-03340-9","mag":"3024918586"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-020-03340-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-020-03340-9","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11227-020-03340-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031187329","display_name":"Daniel J. Magee","orcid":"https://orcid.org/0000-0001-9152-3656"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]},{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel J. Magee","raw_affiliation_strings":["School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, OR, USA","Los Alamos National Laboratory, Los Alamos, USA","School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043737683","display_name":"Anthony S. Walker","orcid":"https://orcid.org/0000-0002-0616-6998"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony S. Walker","raw_affiliation_strings":["School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, OR, USA","School of Mechanical, Industrial and Manufacturing Engineering, Oregon State University, Corvallis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"School of Mechanical, Industrial and Manufacturing Engineering, Oregon State University, Corvallis, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083534268","display_name":"Kyle E. Niemeyer","orcid":"https://orcid.org/0000-0003-4425-7097"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle E. Niemeyer","raw_affiliation_strings":["School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, OR, USA","[OREGON STATE UNIVERSITY]"],"raw_orcid":"https://orcid.org/0000-0003-4425-7097","affiliations":[{"raw_affiliation_string":"School of Mechanical, Industrial, and Manufacturing Engineering, Oregon State University, Corvallis, OR, USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"[OREGON STATE UNIVERSITY]","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083534268"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08807006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"77","issue":"2","first_page":"1976","last_page":"1997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9966999888420105,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8263429999351501},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.750320553779602},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7178802490234375},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7105233669281006},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6910882592201233},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6408209204673767},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5874649882316589},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5096442699432373},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49601826071739197},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4448525607585907},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.433616042137146},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4122133255004883},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4021247625350952},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09653070569038391}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263429999351501},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.750320553779602},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7178802490234375},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7105233669281006},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6910882592201233},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6408209204673767},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5874649882316589},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5096442699432373},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49601826071739197},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4448525607585907},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.433616042137146},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4122133255004883},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4021247625350952},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09653070569038391},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11227-020-03340-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-020-03340-9","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1811.08282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.08282","pdf_url":"https://arxiv.org/pdf/1811.08282","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":"mag:3024918586","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.08282.pdf","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,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1811.08282","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.08282","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s11227-020-03340-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-020-03340-9","pdf_url":null,"source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G2536900113","display_name":"SWEPT TIME-SPACE DOMAIN DECOMPOSITION RULE FOR BREAKING THE LATENCY BARRIER IN 20 YEARS, ENGINEERS WILL NOT SIMPLY BE DOING CFD ANALYSIS. THEYLL BE S","funder_award_id":"NNX15AU66A","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"}],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W766918198","https://openalex.org/W1506424797","https://openalex.org/W1820706094","https://openalex.org/W1991531168","https://openalex.org/W2012630580","https://openalex.org/W2017587301","https://openalex.org/W2033130314","https://openalex.org/W2048520013","https://openalex.org/W2072706249","https://openalex.org/W2104373803","https://openalex.org/W2145194992","https://openalex.org/W2154786353","https://openalex.org/W2159138721","https://openalex.org/W2278971702","https://openalex.org/W2414060363","https://openalex.org/W2428569594","https://openalex.org/W2461259506","https://openalex.org/W2570788611","https://openalex.org/W2594128612","https://openalex.org/W2767138068","https://openalex.org/W2768347146","https://openalex.org/W2771281485","https://openalex.org/W2781691429","https://openalex.org/W2962919798","https://openalex.org/W3152199537","https://openalex.org/W4393751350","https://openalex.org/W6911461940"],"related_works":["https://openalex.org/W2583390085","https://openalex.org/W3032663520","https://openalex.org/W2071542942","https://openalex.org/W3005892215","https://openalex.org/W2949001880","https://openalex.org/W647925487","https://openalex.org/W3022257248","https://openalex.org/W2766544779","https://openalex.org/W2006349425","https://openalex.org/W2240204032","https://openalex.org/W2599987010","https://openalex.org/W963568387","https://openalex.org/W2185053320","https://openalex.org/W2499620565","https://openalex.org/W2899353149","https://openalex.org/W2099212158","https://openalex.org/W2092241121","https://openalex.org/W2273704862","https://openalex.org/W2503230463","https://openalex.org/W244682305"],"abstract_inverted_index":{"Applications":[0],"that":[1,50,106,216],"exploit":[2],"the":[3,20,30,37,53,59,73,115,167,179,183,191,198,202],"architectural":[4],"details":[5],"of":[6,29,46,55,76,161,173,201],"high-performance":[7],"computing":[8],"(HPC)":[9],"systems":[10,65,215],"have":[11],"become":[12,86],"increasingly":[13],"invaluable":[14],"in":[15,33,58,81],"academia":[16],"and":[17,79,85,125,170,186,189,208],"industry":[18],"over":[19,149],"past":[21],"two":[22,139,150],"decades.":[23],"The":[24,92,155],"most":[25],"important":[26],"hardware":[27],"development":[28],"last":[31],"decade":[32],"HPC":[34,127],"has":[35],"been":[36],"general":[38],"purpose":[39],"graphics":[40],"processing":[41],"unit":[42],"(GPGPU),":[43],"a":[44,82,87,98,134,159,171],"class":[45],"massively":[47,212],"parallel":[48,213],"devices":[49],"now":[51],"contributes":[52],"majority":[54],"computational":[56],"power":[57],"top":[60],"500":[61],"supercomputers.":[62],"As":[63],"these":[64],"grow,":[66],"small":[67],"costs":[68],"such":[69],"as":[70],"latency\u2014due":[71],"to":[72,90,108,133,163,175],"fixed":[74],"cost":[75],"memory":[77],"accesses":[78],"communication\u2014accumulate":[80],"large":[83],"simulation":[84],"significant":[88],"barrier":[89],"performance.":[91],"swept":[93,116,156,203],"time-space":[94],"decomposition":[95,136],"rule":[96,117,157,204],"is":[97],"communication-avoiding":[99],"technique":[100],"for":[101,166,178,205],"time-stepping":[102],"stencil":[103],"update":[104],"formulas":[105],"attempts":[107],"reduce":[109],"latency":[110,219],"costs.":[111,220],"This":[112],"work":[113,187],"extends":[114],"by":[118],"targeting":[119],"heterogeneous,":[120],"CPU/GPU":[121],"architectures":[122],"representing":[123],"current":[124],"future":[126],"systems.":[128],"We":[129],"compare":[130],"our":[131],"approach":[132],"naive":[135],"scheme":[137],"with":[138,190],"test":[140],"equations":[141,207],"using":[142,182],"an":[143],"MPI+CUDA":[144],"pattern":[145],"on":[146,211],"40":[147],"processes":[148],"nodes":[151],"containing":[152],"one":[153],"GPU.":[154],"produces":[158],"factor":[160,172],"1.9":[162],"23":[164],"speedup":[165,177],"heat":[168],"equation":[169],"1.1":[174],"2.0":[176],"Euler":[180],"equations,":[181],"same":[184],"processors":[185],"distribution,":[188],"best":[192],"possible":[193],"configurations.":[194],"These":[195],"results":[196],"show":[197],"potential":[199],"effectiveness":[200],"different":[206],"numerical":[209],"schemes":[210],"compute":[214],"incur":[217],"substantial":[218]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}