{"id":"https://openalex.org/W2951378879","doi":"https://doi.org/10.1145/3330345.3330356","title":"Least squares solvers for distributed-memory machines with GPU accelerators","display_name":"Least squares solvers for distributed-memory machines with GPU accelerators","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2951378879","doi":"https://doi.org/10.1145/3330345.3330356","mag":"2951378879"},"language":"en","primary_location":{"id":"doi:10.1145/3330345.3330356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330356","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330356","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"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":"Jakub Kurzak","raw_affiliation_strings":["University of Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104910026","display_name":"Mark Gates","orcid":"https://orcid.org/0000-0003-2996-1641"},"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":"Mark Gates","raw_affiliation_strings":["University of Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022931436","display_name":"Ali Charara","orcid":"https://orcid.org/0000-0002-9509-7794"},"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":"Ali Charara","raw_affiliation_strings":["University of Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087711762","display_name":"Asim YarKhan","orcid":"https://orcid.org/0000-0002-3901-9695"},"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":"Asim YarKhan","raw_affiliation_strings":["University of Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"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":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9940000176429749,"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":0.8353963494300842},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.8141347765922546},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6486358642578125},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.621436595916748},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4913875162601471},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4872507154941559},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.47031915187835693},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4484335780143738},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.43668797612190247},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4273245930671692},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4165889620780945},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.3811255395412445},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.2972589433193207},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24530917406082153},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23144826292991638},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21054714918136597},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08764377236366272},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.07339048385620117}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353963494300842},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.8141347765922546},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6486358642578125},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.621436595916748},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4913875162601471},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4872507154941559},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.47031915187835693},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4484335780143738},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.43668797612190247},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4273245930671692},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4165889620780945},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3811255395412445},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2972589433193207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24530917406082153},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23144826292991638},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21054714918136597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08764377236366272},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.07339048385620117},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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:10.1145/3330345.3330356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330356","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"}],"best_oa_location":{"id":"doi:10.1145/3330345.3330356","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3330345.3330356","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3330345.3330356","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"},"sustainable_development_goals":[],"awards":[{"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/G2366088775","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G3049477530","display_name":null,"funder_award_id":"Contract No. DE-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/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/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4957472368","display_name":null,"funder_award_id":". DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6486853205","display_name":null,"funder_award_id":"Contract No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"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/G6911681599","display_name":null,"funder_award_id":"No. DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"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/G8794501934","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320337674","funder_display_name":"Wind Energy Technologies Office"},{"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"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320337674","display_name":"Wind Energy Technologies Office","ror":null},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951378879.pdf","grobid_xml":"https://content.openalex.org/works/W2951378879.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W47427672","https://openalex.org/W54170965","https://openalex.org/W1516000274","https://openalex.org/W1574975504","https://openalex.org/W1946080187","https://openalex.org/W1986334759","https://openalex.org/W1999664467","https://openalex.org/W2021817036","https://openalex.org/W2028122240","https://openalex.org/W2030167104","https://openalex.org/W2032052535","https://openalex.org/W2073260424","https://openalex.org/W2100893446","https://openalex.org/W2104373803","https://openalex.org/W2108634150","https://openalex.org/W2124480634","https://openalex.org/W2157237396","https://openalex.org/W2240679564","https://openalex.org/W3100417409","https://openalex.org/W4231150350","https://openalex.org/W4241072847"],"related_works":["https://openalex.org/W3163773192","https://openalex.org/W2522245970","https://openalex.org/W4205760564","https://openalex.org/W2500257945","https://openalex.org/W278443433","https://openalex.org/W2007578977","https://openalex.org/W2021525945","https://openalex.org/W1973739845","https://openalex.org/W2061048205","https://openalex.org/W4239025233"],"abstract_inverted_index":{"This":[0],"work":[1,35,53,90],"presents":[2,108],"an":[3],"implementation":[4,50,105],"of":[5,20,81,99],"a":[6,55,79],"linear":[7,41],"least":[8],"squares":[9],"solver":[10],"for":[11,23,88],"distributed-memory":[12],"machines":[13],"with":[14],"GPU":[15],"accelerators,":[16],"developed":[17],"as":[18,67,78],"part":[19],"the":[21,31,34,44,49,52,59,76,97,100,104,109],"Software":[22],"Linear":[24],"Algebra":[25],"Targeting":[26],"Exascale":[27],"(SLATE)":[28],"package.":[29],"From":[30,48],"algorithmic":[32],"standpoint,":[33,51],"leverages":[36],"recent":[37],"advances":[38],"in":[39],"dense":[40],"algebra,":[42],"specifically":[43],"communication-avoiding":[45],"QR":[46],"factorization.":[47],"represents":[54],"sharp":[56],"departure":[57],"from":[58],"traditional":[60],"conventions":[61],"established":[62],"by":[63],"legacy":[64],"packages,":[65],"such":[66],"LAPACK":[68],"and":[69,84,107],"ScaLAPACK.":[70],"It":[71],"is":[72],"based":[73],"on":[74],"representing":[75],"matrix":[77],"collection":[80],"individual":[82],"tiles,":[83],"using":[85],"batch":[86],"operations":[87],"offloading":[89],"to":[91],"accelerators.":[92],"The":[93],"article":[94],"lays":[95],"out":[96],"principles":[98],"new":[101],"approach,":[102],"discusses":[103],"details":[106],"performance":[110],"results.":[111]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
