{"id":"https://openalex.org/W4386709677","doi":"https://doi.org/10.1145/3605573.3605606","title":"O(N) distributed direct factorization of structured dense matrices using runtime systems.","display_name":"O(N) distributed direct factorization of structured dense matrices using runtime systems.","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386709677","doi":"https://doi.org/10.1145/3605573.3605606"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065317117","display_name":"Sameer Deshmukh","orcid":"https://orcid.org/0000-0002-5615-1399"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sameer Deshmukh","raw_affiliation_strings":["School of Computing, Tokyo Institute of Technology, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5615-1399","affiliations":[{"raw_affiliation_string":"School of Computing, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024747717","display_name":"Rio Yokota","orcid":"https://orcid.org/0000-0001-7573-7873"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rio Yokota","raw_affiliation_strings":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7573-7873","affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010055736","display_name":"George Bosilca","orcid":"https://orcid.org/0000-0003-2411-8495"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Bosilca","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee at Knoxville, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2411-8495","affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee at Knoxville, United States of America","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114229330","display_name":"Qinxiang Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Qinxiang Ma","raw_affiliation_strings":["School of Computing, Tokyo Institute of Technology, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7329-1756","affiliations":[{"raw_affiliation_string":"School of Computing, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10572","display_name":"Geophysical and Geoelectrical Methods","score":0.9902999997138977,"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"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9796000123023987,"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":0.690678060054779},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.6059698462486267},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5896203517913818},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5873873233795166},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.5396192073822021},{"id":"https://openalex.org/keywords/incomplete-lu-factorization","display_name":"Incomplete LU factorization","score":0.5327337384223938},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5141294598579407},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5082542300224304},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.49225035309791565},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3995485007762909},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3318617641925812},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24930158257484436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.690678060054779},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.6059698462486267},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5896203517913818},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5873873233795166},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.5396192073822021},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.5327337384223938},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5141294598579407},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5082542300224304},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.49225035309791565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3995485007762909},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3318617641925812},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24930158257484436},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3605573.3605606","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5938650130","display_name":"Construction of numerical linear algebra based on lattice H-matrices and its high-performance implementation on modern architectures","funder_award_id":"21H03447","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G720495953","display_name":"Application of Unconventional Linear Algebra Techniques to Continuous Learning in Supergiant Neural Networks","funder_award_id":"20K20624","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7645965464","display_name":"Fast and accurate eigenvalue calculations by hierarchical low-rank approximation and its application to large-scale electronic structure calculations","funder_award_id":"23K24854","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1973786815","https://openalex.org/W2069045162","https://openalex.org/W2093529653","https://openalex.org/W2160774872","https://openalex.org/W2168612748","https://openalex.org/W2183835152","https://openalex.org/W2188296733","https://openalex.org/W2983126917","https://openalex.org/W3114973229","https://openalex.org/W4285503969","https://openalex.org/W4321636779"],"related_works":["https://openalex.org/W2078637543","https://openalex.org/W2063952346","https://openalex.org/W2381435995","https://openalex.org/W2584547575","https://openalex.org/W1987177655","https://openalex.org/W1509943448","https://openalex.org/W2526784484","https://openalex.org/W2050448951","https://openalex.org/W4246966070","https://openalex.org/W2127144731"],"abstract_inverted_index":{"Structured":[0],"dense":[1,34,125],"matrices":[2,28,139],"result":[3],"from":[4,37,141],"boundary":[5],"integral":[6],"problems":[7,162],"in":[8,16],"electrostatics":[9],"and":[10,12,119,130],"geostatistics,":[11],"also":[13],"Schur":[14],"complements":[15],"sparse":[17],"preconditioners":[18],"such":[19,27,48],"as":[20],"multi-frontal":[21],"methods.":[22],"Exploiting":[23],"the":[24,31,73,110,161],"structure":[25],"of":[26,124,145,152],"can":[29,54],"reduce":[30],"time":[32,137],"for":[33,96,138,154,159],"direct":[35,126],"factorization":[36,136],"O(N3)":[38],"to":[39,133,149],"O(N).":[40],"The":[41,64],"Hierarchically":[42],"Semi-Separable":[43],"(HSS)":[44],"matrix":[45,51],"is":[46,67],"one":[47],"low":[49,127],"rank":[50,128],"format":[52],"that":[53,87,163],"be":[55],"factorized":[56],"using":[57],"a":[58,83,94,142],"Cholesky-like":[59],"algorithm":[60,66],"called":[61],"ULV":[62],"factorization.":[63],"HSS-ULV":[65,111],"highly":[68],"parallel":[69],"because":[70],"it":[71],"removes":[72],"dependency":[74],"on":[75,147],"trailing":[76],"sub-matrices":[77],"at":[78],"each":[79],"HSS":[80,91],"level.":[81],"However,":[82],"key":[84],"merge":[85],"step":[86],"links":[88],"two":[89],"successive":[90],"levels":[92],"remains":[93],"challenge":[95],"efficient":[97],"parallelization.":[98],"In":[99],"this":[100],"paper,":[101],"we":[102,164],"use":[103],"an":[104],"asynchronous":[105],"runtime":[106],"system":[107],"PaRSEC":[108],"with":[109,117],"algorithm.":[112],"We":[113],"compare":[114],"our":[115],"work":[116],"STRUMPACK":[118],"LORAPO,":[120],"both":[121],"state-of-the-art":[122],"implementations":[123],"factorization,":[129],"achieve":[131],"up":[132,148],"2x":[134],"better":[135,157],"arising":[140],"diverse":[143],"set":[144],"applications":[146],"128":[150],"nodes":[151],"Fugaku":[153],"similar":[155],"or":[156],"accuracy":[158],"all":[160],"survey.":[165]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}