{"id":"https://openalex.org/W2952013349","doi":"https://doi.org/10.1145/3330345.3330357","title":"A communication-avoiding 3D sparse triangular solver","display_name":"A communication-avoiding 3D sparse triangular solver","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2952013349","doi":"https://doi.org/10.1145/3330345.3330357","mag":"2952013349"},"language":"en","primary_location":{"id":"doi:10.1145/3330345.3330357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330345.3330357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/1558528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048170299","display_name":"Piyush Sao","orcid":"https://orcid.org/0000-0002-9432-5855"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piyush Sao","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014168997","display_name":"Ramakrishnan Kannan","orcid":"https://orcid.org/0000-0002-5852-4806"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramakrishnan Kannan","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006873445","display_name":"Xiaoye Sherry Li","orcid":"https://orcid.org/0000-0002-0747-698X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoye Sherry Li","raw_affiliation_strings":["Lawrence Berkeley National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016738770","display_name":"Richard Vuduc","orcid":"https://orcid.org/0000-0003-2178-138X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Vuduc","raw_affiliation_strings":["Georgia Institute of technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4808,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80944543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9991999864578247,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/solver","display_name":"Solver","score":0.8186070919036865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7291767597198486},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.534841001033783},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5334019660949707},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5313065052032471},{"id":"https://openalex.org/keywords/planar","display_name":"Planar","score":0.48053795099258423},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4679865837097168},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4551905691623688},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.45104479789733887},{"id":"https://openalex.org/keywords/sparse-grid","display_name":"Sparse grid","score":0.44904178380966187},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.44229868054389954},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4214279055595398},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3985234797000885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17311573028564453},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.0680030882358551}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.8186070919036865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291767597198486},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.534841001033783},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5334019660949707},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5313065052032471},{"id":"https://openalex.org/C134786449","wikidata":"https://www.wikidata.org/wiki/Q3391255","display_name":"Planar","level":2,"score":0.48053795099258423},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4679865837097168},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4551905691623688},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.45104479789733887},{"id":"https://openalex.org/C156439662","wikidata":"https://www.wikidata.org/wiki/Q7573793","display_name":"Sparse grid","level":2,"score":0.44904178380966187},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.44229868054389954},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4214279055595398},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3985234797000885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17311573028564453},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0680030882358551},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3330345.3330357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330345.3330357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1558528","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1558528","pdf_url":"https://www.osti.gov/servlets/purl/1558528","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":"pmh:oai:osti.gov:1558528","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1558528","pdf_url":"https://www.osti.gov/servlets/purl/1558528","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},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"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/G3232922872","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3997560910","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G4327825534","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G454454283","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4865274590","display_name":null,"funder_award_id":"1710371","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5726405315","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G6129992089","display_name":null,"funder_award_id":"DE-AC05-","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"},{"id":"https://openalex.org/G6495930337","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6864165199","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G7995982022","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/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","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"},{"id":"https://openalex.org/G8943143067","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320316892","funder_display_name":"UT-Battelle"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320316892","display_name":"UT-Battelle","ror":"https://ror.org/04nza6677"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952013349.pdf","grobid_xml":"https://content.openalex.org/works/W2952013349.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1538076361","https://openalex.org/W1640020431","https://openalex.org/W1880110930","https://openalex.org/W1907157228","https://openalex.org/W1968235986","https://openalex.org/W1978564754","https://openalex.org/W1993274656","https://openalex.org/W2012715759","https://openalex.org/W2036498563","https://openalex.org/W2066166631","https://openalex.org/W2127144731","https://openalex.org/W2137541800","https://openalex.org/W2145194992","https://openalex.org/W2153024623","https://openalex.org/W2162241008","https://openalex.org/W2235832317","https://openalex.org/W2483598939","https://openalex.org/W2538561686","https://openalex.org/W2585804629","https://openalex.org/W2785452945","https://openalex.org/W2887674375","https://openalex.org/W2887752250","https://openalex.org/W2887905332","https://openalex.org/W2964337156","https://openalex.org/W3105937213","https://openalex.org/W4238938416","https://openalex.org/W4253282397","https://openalex.org/W6822168629"],"related_works":["https://openalex.org/W2091883426","https://openalex.org/W2174948646","https://openalex.org/W3173235360","https://openalex.org/W2024017047","https://openalex.org/W4318256793","https://openalex.org/W2594370889","https://openalex.org/W2390720471","https://openalex.org/W2051410394","https://openalex.org/W1600789676","https://openalex.org/W2134327945"],"abstract_inverted_index":{"We":[0,68,118],"present":[1,69],"a":[2,16,48,96,127],"novel":[3],"distributed":[4],"memory":[5],"algorithm":[6,79,121,150],"to":[7,72],"improve":[8],"the":[9,13,24,63,74,90,106,146,158],"strong":[10],"scalability":[11],"of":[12,15,27,60,77,98,110,142],"solution":[14],"sparse":[17,33,41,85,160],"triangular":[18,42,86,134],"system.":[19],"This":[20],"operation":[21],"appears":[22],"in":[23,124],"solve":[25,135],"phase":[26],"direct":[28],"methods":[29],"for":[30,102,122,153,157],"solving":[31],"general":[32],"linear":[34],"systems,":[35],"Ax":[36],"=":[37],"b.":[38],"Our":[39,132],"3D":[40,49,84,114,133],"solver":[43,87],"employs":[44],"several":[45],"techniques,":[46],"including":[47],"MPI":[50],"process":[51],"grid,":[52],"elimination":[53],"tree":[54],"parallelism,":[55],"and":[56,80,100,113,155],"data":[57],"replication,":[58],"all":[59],"which":[61],"reduce":[62,89],"per-process":[64,91],"communication":[65,75,92],"when":[66,137],"combined.":[67],"analytical":[70],"models":[71],"understand":[73],"cost":[76],"our":[78,83,120],"show":[81],"that":[82],"can":[88],"volume":[93],"asymptotically":[94],"by":[95,151],"factor":[97],"O(n1/4)":[99],"O(n1/6)":[101],"problems":[103],"arising":[104],"from":[105],"finite":[107],"element":[108],"discretizations":[109],"2D":[111,149],"\"planar\"":[112],"\"non-planar\"":[115],"PDEs,":[116],"respectively.":[117,162],"implement":[119],"use":[123],"SuperLU_DIST3D,":[125],"using":[126],"hybrid":[128],"MPI+OpenMP":[129],"programming":[130],"model.":[131],"algorithm,":[136],"run":[138],"on":[139],"12k":[140],"cores":[141],"Cray":[143],"XC30,":[144],"outperforms":[145],"current":[147],"state-of-the-art":[148],"7.2x":[152],"planar":[154],"2.7x":[156],"non-planar":[159],"matrices,":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-21T07:57:09.225873","created_date":"2025-10-10T00:00:00"}
