{"id":"https://openalex.org/W4313408245","doi":"https://doi.org/10.1145/3577197","title":"Newly Released Capabilities in the Distributed-Memory SuperLU Sparse Direct Solver","display_name":"Newly Released Capabilities in the Distributed-Memory SuperLU Sparse Direct Solver","publication_year":2022,"publication_date":"2022-12-19","ids":{"openalex":"https://openalex.org/W4313408245","doi":"https://doi.org/10.1145/3577197"},"language":"en","primary_location":{"id":"doi:10.1145/3577197","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577197","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577197","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3577197","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 S. Li","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":"https://orcid.org/0000-0002-0747-698X","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006606232","display_name":"Paul Lin","orcid":"https://orcid.org/0000-0003-2128-0219"},"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":"Paul Lin","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":"https://orcid.org/0000-0003-2128-0219","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038051093","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0003-3750-1178"},"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":"Yang Liu","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":"https://orcid.org/0000-0003-3750-1178","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","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, Oak Ridge, TN"],"raw_orcid":"https://orcid.org/0000-0002-9432-5855","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7382,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91635647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"49","issue":"1","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.856724739074707},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7394769787788391},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7096512913703918},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5926833748817444},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5234241485595703},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.5146001577377319},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5125484466552734},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49021393060684204},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3832956850528717},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.375835120677948},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37017449736595154},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08790960907936096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.856724739074707},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7394769787788391},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7096512913703918},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5926833748817444},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5234241485595703},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.5146001577377319},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5125484466552734},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49021393060684204},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3832956850528717},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.375835120677948},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37017449736595154},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08790960907936096},{"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3577197","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577197","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577197","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"},{"id":"pmh:oai:osti.gov:1973357","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1973357","pdf_url":null,"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:10.1145/3577197","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577197","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577197","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"},"sustainable_development_goals":[],"awards":[{"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/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/G8253304997","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"}],"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/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4313408245.pdf","grobid_xml":"https://content.openalex.org/works/W4313408245.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W625657276","https://openalex.org/W1587659039","https://openalex.org/W2109828727","https://openalex.org/W2119623923","https://openalex.org/W2141331848","https://openalex.org/W2170111021","https://openalex.org/W2942021433","https://openalex.org/W2952013349","https://openalex.org/W3001467520","https://openalex.org/W3047208409","https://openalex.org/W3131110481","https://openalex.org/W3185393231"],"related_works":["https://openalex.org/W1604758548","https://openalex.org/W233983175","https://openalex.org/W2804126825","https://openalex.org/W1549048322","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W2271439649","https://openalex.org/W2011940952"],"abstract_inverted_index":{"We":[0,125],"present":[1],"the":[2,7,67,73,87,91,97,113,128,144,148],"new":[3,24,104],"features":[4,25],"available":[5],"in":[6,95,132],"recent":[8],"release":[9],"of":[10,119,143],"SuperLU_DIST":[11,15],",":[12],"Version":[13],"8.1.1.":[14],"is":[16],"a":[17,28],"distributed-memory":[18],"parallel":[19],"sparse":[20,150],"direct":[21],"solver.":[22],"The":[23],"include":[26],"(1)":[27],"3D":[29],"communication-avoiding":[30],"algorithm":[31,68],"framework":[32],"that":[33,56,127],"trades":[34],"off":[35],"inter-process":[36],"communication":[37],"for":[38,45],"selective":[39],"memory":[40,135],"duplication,":[41],"(2)":[42],"multi-GPU":[43],"support":[44],"both":[46,131],"NVIDIA":[47],"GPUs":[48],"and":[49,52,61,80,115,134,152],"AMD":[50],"GPUs,":[51],"(3)":[53],"mixed-precision":[54],"routines":[55],"perform":[57],"single-precision":[58],"LU":[59],"factorization":[60],"double-precision":[62],"iterative":[63],"refinement.":[64],"Apart":[65],"from":[66],"improvements,":[69],"we":[70,93],"also":[71],"modernized":[72],"software":[74],"build":[75],"system":[76],"to":[77,85,112,121],"use":[78],"CMake":[79],"Spack":[81],"package":[82],"installation":[83,88],"tools":[84],"simplify":[86],"procedure.":[89],"Throughout":[90],"article,":[92],"describe":[94],"detail":[96],"pertinent":[98],"performance-sensitive":[99],"parameters":[100],"associated":[101],"with":[102],"each":[103],"algorithmic":[105],"feature,":[106],"show":[107],"how":[108,120],"they":[109],"are":[110],"exposed":[111],"users,":[114],"give":[116],"general":[117],"guidance":[118],"set":[122],"these":[123],"parameters.":[124],"illustrate":[126],"solver\u2019s":[129],"performance":[130],"time":[133],"can":[136],"be":[137],"greatly":[138],"improved":[139],"after":[140],"systematic":[141],"tuning":[142],"parameters,":[145],"depending":[146],"on":[147],"input":[149],"matrix":[151],"underlying":[153],"hardware.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
