{"id":"https://openalex.org/W4401826682","doi":"https://doi.org/10.1177/10943420241268200","title":"Batched sparse direct solver design and evaluation in SuperLU_DIST","display_name":"Batched sparse direct solver design and evaluation in SuperLU_DIST","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401826682","doi":"https://doi.org/10.1177/10943420241268200"},"language":"en","primary_location":{"id":"doi:10.1177/10943420241268200","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420241268200","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt20h717s9/qt20h717s9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088105630","display_name":"Wajih Boukaram","orcid":"https://orcid.org/0000-0002-2958-9344"},"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":"Wajih Boukaram","raw_affiliation_strings":["Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046043219","display_name":"Yuxi Hong","orcid":"https://orcid.org/0000-0002-0741-6602"},"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":"Yuxi Hong","raw_affiliation_strings":["Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","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":["Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014452980","display_name":"Tianyi Shi","orcid":"https://orcid.org/0000-0003-0848-4778"},"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":"Tianyi Shi","raw_affiliation_strings":["Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","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":true,"raw_author_name":"Xiaoye S Li","raw_affiliation_strings":["Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006873445"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.358,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62858298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"38","issue":"6","first_page":"585","last_page":"598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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":0.9914000034332275,"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/solver","display_name":"Solver","score":0.8278934955596924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314645051956177},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.620705783367157},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6181079745292664},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6059602499008179},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5478798747062683},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5361101031303406},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.5242193937301636},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4635336399078369},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4113613963127136},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37568655610084534},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3307842016220093},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.26643800735473633},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18519151210784912},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16785606741905212},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08946466445922852}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.8278934955596924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314645051956177},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.620705783367157},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6181079745292664},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6059602499008179},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5478798747062683},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5361101031303406},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.5242193937301636},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4635336399078369},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4113613963127136},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37568655610084534},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3307842016220093},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.26643800735473633},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18519151210784912},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16785606741905212},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08946466445922852},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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},{"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/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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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":3,"locations":[{"id":"doi:10.1177/10943420241268200","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420241268200","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt20h717s9","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/20h717s9","pdf_url":"https://escholarship.org/content/qt20h717s9/qt20h717s9.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The International Journal of High Performance Computing Applications, vol 38, iss 6","raw_type":"article"},{"id":"pmh:ark:/13030/qt20h717s9","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"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:escholarship.org:ark:/13030/qt20h717s9","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/20h717s9","pdf_url":"https://escholarship.org/content/qt20h717s9/qt20h717s9.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The International Journal of High Performance Computing Applications, vol 38, iss 6","raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401826682.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2046140068","https://openalex.org/W2067418541","https://openalex.org/W2162322364","https://openalex.org/W2249637006","https://openalex.org/W2469975815","https://openalex.org/W2516389007","https://openalex.org/W2611897209","https://openalex.org/W4285609454","https://openalex.org/W4297677512","https://openalex.org/W4313408245","https://openalex.org/W4322576898","https://openalex.org/W4388664805"],"related_works":["https://openalex.org/W233983175","https://openalex.org/W1604758548","https://openalex.org/W2804126825","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W1549048322","https://openalex.org/W2015141752","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W4321636545"],"abstract_inverted_index":{"Over":[0],"the":[1,9,27,60,63,67,88,92,98,104,148],"course":[2],"of":[3,26,62,91,97,134,147],"interactions":[4],"with":[5,108,118],"various":[6],"application":[7],"teams,":[8],"need":[10],"for":[11,29,51],"batched":[12,47,68,77,128,139],"sparse":[13,33,48,54,82,129],"linear":[14,34],"algebra":[15,35],"functions":[16],"has":[17],"emerged":[18],"in":[19],"order":[20],"to":[21],"make":[22],"more":[23],"efficient":[24],"use":[25],"GPUs":[28],"many":[30,110],"small":[31,111],"and":[32,74,142],"problems.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"present":[41],"our":[42,126],"recent":[43],"work":[44],"on":[45],"a":[46,75,138],"direct":[49,130],"solver":[50,131,141],"GPUs.":[52],"The":[53,81],"LU":[55],"factorization":[56],"is":[57,85,132],"computed":[58,86],"by":[59,87],"levels":[61],"elimination":[64],"tree,":[65],"leveraging":[66],"dense":[69],"operations":[70,102],"at":[71],"each":[72],"level":[73,89],"new":[76,127],"Scatter":[78],"GPU":[79],"kernel.":[80],"triangular":[83,99],"solve":[84],"sets":[90],"directed":[93],"acyclic":[94],"graph":[95],"(DAG)":[96],"matrix.":[100],"Batched":[101],"overcome":[103],"large":[105],"overhead":[106],"associated":[107],"launching":[109],"kernels.":[112],"For":[113],"medium":[114],"sized":[115],"matrix":[116],"batches":[117],"not-so-small":[119],"bandwidth,":[120],"using":[121],"an":[122],"NVIDIA":[123],"A100":[124],"GPU,":[125],"orders":[133],"magnitude":[135],"faster":[136],"than":[137,145],"banded":[140],"uses":[143],"less":[144],"one-tenth":[146],"memory.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}