{"id":"https://openalex.org/W2028035197","doi":"https://doi.org/10.1145/2629641","title":"A Parallel Sparse Direct Solver via Hierarchical DAG Scheduling","display_name":"A Parallel Sparse Direct Solver via Hierarchical DAG Scheduling","publication_year":2014,"publication_date":"2014-10-27","ids":{"openalex":"https://openalex.org/W2028035197","doi":"https://doi.org/10.1145/2629641","mag":"2028035197"},"language":"en","primary_location":{"id":"doi:10.1145/2629641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2629641","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"},"type":"article","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/A5076399048","display_name":"Kyungjoo Kim","orcid":"https://orcid.org/0000-0003-1241-1934"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyungjoo Kim","raw_affiliation_strings":["The University of Texas at Austin","The University of Texas, at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas, at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036842144","display_name":"Victor Eijkhout","orcid":"https://orcid.org/0000-0002-8094-5738"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Eijkhout","raw_affiliation_strings":["The University of Texas at Austin","The University of Texas, at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"The University of Texas, at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076399048"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":5.6708,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96232205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"41","issue":"1","first_page":"1","last_page":"27"},"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":0.9986000061035156,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8486498594284058},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.829641580581665},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5968515276908875},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.49729254841804504},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4959438741207123},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4851166009902954},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.47571784257888794},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.42037510871887207},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2626035511493683},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.14017626643180847},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10023549199104309},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.09594810009002686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486498594284058},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.829641580581665},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5968515276908875},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.49729254841804504},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4959438741207123},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4851166009902954},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.47571784257888794},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.42037510871887207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2626035511493683},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.14017626643180847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10023549199104309},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.09594810009002686},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2629641","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2629641","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1307015062","display_name":null,"funder_award_id":"0904907, ACI-1148125/1340293","funder_id":"https://openalex.org/F4320337563","funder_display_name":"Division of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320337563","display_name":"Division of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W25664821","https://openalex.org/W181225834","https://openalex.org/W226825246","https://openalex.org/W635768826","https://openalex.org/W1520639991","https://openalex.org/W1581078542","https://openalex.org/W1600065697","https://openalex.org/W1973166496","https://openalex.org/W1982355466","https://openalex.org/W1986834688","https://openalex.org/W1992935334","https://openalex.org/W1993879252","https://openalex.org/W1998276913","https://openalex.org/W2002257715","https://openalex.org/W2003105834","https://openalex.org/W2010150079","https://openalex.org/W2013459285","https://openalex.org/W2019111678","https://openalex.org/W2019527978","https://openalex.org/W2026139385","https://openalex.org/W2031990962","https://openalex.org/W2034036349","https://openalex.org/W2038205735","https://openalex.org/W2043246824","https://openalex.org/W2047196981","https://openalex.org/W2058374962","https://openalex.org/W2063675347","https://openalex.org/W2066784028","https://openalex.org/W2070299075","https://openalex.org/W2071166325","https://openalex.org/W2079777558","https://openalex.org/W2081114193","https://openalex.org/W2086794688","https://openalex.org/W2090129250","https://openalex.org/W2101501830","https://openalex.org/W2104861744","https://openalex.org/W2112865524","https://openalex.org/W2118341515","https://openalex.org/W2124405500","https://openalex.org/W2124480634","https://openalex.org/W2127144731","https://openalex.org/W2143133118","https://openalex.org/W2150871235","https://openalex.org/W2152786407","https://openalex.org/W2154281337","https://openalex.org/W2163041510","https://openalex.org/W2163360863","https://openalex.org/W2242157770","https://openalex.org/W2298969531","https://openalex.org/W2353286494","https://openalex.org/W2555826189","https://openalex.org/W2596290099","https://openalex.org/W2605732856","https://openalex.org/W3023536296","https://openalex.org/W3104001151","https://openalex.org/W4297831128"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2731094954","https://openalex.org/W2789273959","https://openalex.org/W2155261584","https://openalex.org/W4302345037","https://openalex.org/W2952978498","https://openalex.org/W2584231425","https://openalex.org/W233983175","https://openalex.org/W2355089277","https://openalex.org/W3046406417"],"abstract_inverted_index":{"We":[0,81],"present":[1],"a":[2,83,96,152],"parallel":[3,34,76,84,97,165],"sparse":[4,42,166,184],"direct":[5,167,185],"solver":[6,85,168],"for":[7,171],"multicore":[8],"architectures":[9],"based":[10,86],"on":[11,87,100],"Directed":[12],"Acyclic":[13],"Graph":[14],"(DAG)":[15],"scheduling.":[16],"Recently,":[17],"DAG":[18],"scheduling":[19,66,145,156],"has":[20,50],"become":[21],"popular":[22],"in":[23,64,69,139],"advanced":[24],"Dense":[25],"Linear":[26],"Algebra":[27],"libraries":[28],"due":[29],"to":[30,41,51,78,117,146],"its":[31,39],"efficient":[32],"asynchronous":[33],"execution":[35],"of":[36,57],"tasks.":[37,60],"However,":[38],"application":[40],"matrix":[43],"problems":[44,174],"is":[45,135,169],"more":[46],"challenging":[47],"as":[48],"it":[49],"deal":[52],"with":[53],"an":[54],"enormous":[55],"number":[56],"highly":[58],"irregular":[59],"This":[61],"typically":[62],"results":[63],"substantial":[65],"overhead":[67],"both":[68],"time":[70],"and":[71,158,161],"space,":[72],"which":[73],"causes":[74],"overall":[75],"performance":[77],"be":[79],"suboptimal.":[80],"describe":[82],"two-level":[88,143,149],"task":[89,144],"parallelism:":[90],"tasks":[91,106,124],"are":[92,107,125,131],"first":[93],"generated":[94],"from":[95,137,176],"tree":[98],"traversal":[99],"the":[101,148,172,177],"assembly":[102],"tree;":[103],"next,":[104],"those":[105],"further":[108],"refined":[109],"by":[110,114],"using":[111],"algorithms":[112],"-":[113,115],"blocks":[116],"gain":[118],"fine-grained":[119,123],"parallelism.":[120,150],"The":[121,163],"resulting":[122],"asynchronously":[126],"executed":[127],"after":[128],"their":[129],"dependencies":[130],"analyzed.":[132],"Our":[133],"approach":[134],"distinct":[136],"others":[138],"that":[140],"we":[141,154],"adopt":[142],"mirror":[147],"As":[151],"result,":[153],"reduce":[155],"overhead,":[157],"increase":[159],"efficiency":[160],"flexibility.":[162],"proposed":[164],"evaluated":[170],"particular":[173],"arising":[175],"hp":[178],"-Finite":[179],"Element":[180],"Method":[181],"where":[182],"conventional":[183],"solvers":[186],"do":[187],"not":[188],"scale":[189],"well.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}