{"id":"https://openalex.org/W4402733233","doi":"https://doi.org/10.1177/10943420241281050","title":"Numerical eigen-spectrum slicing, accurate orthogonal eigen-basis, and mixed-precision eigenvalue refinement using OpenMP data-dependent tasks and accelerator offload","display_name":"Numerical eigen-spectrum slicing, accurate orthogonal eigen-basis, and mixed-precision eigenvalue refinement using OpenMP data-dependent tasks and accelerator offload","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4402733233","doi":"https://doi.org/10.1177/10943420241281050"},"language":"en","primary_location":{"id":"doi:10.1177/10943420241281050","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420241281050","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://www.osti.gov/biblio/2447519","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"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":true,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","MIT Lincoln Lab, LLS, CMIT Lincoln Laboratory, Lexington, MA,USA"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"MIT Lincoln Lab, LLS, CMIT Lincoln Laboratory, Lexington, MA,USA","institution_ids":["https://openalex.org/I4210122954"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022214330","display_name":"Anthony M. Castaldo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210088951","display_name":"Synopsys (United States)","ror":"https://ror.org/013by2m91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210088951"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Castaldo","raw_affiliation_strings":["Technical Development, Synopsys, Inc., Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Technical Development, Synopsys, Inc., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210088951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062373552","display_name":"Yaohung M. Tsai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaohung M Tsai","raw_affiliation_strings":["ML Compilers and AI Accelerators, Meta, Inc., Menlo Park, CA,USA"],"affiliations":[{"raw_affiliation_string":"ML Compilers and AI Accelerators, Meta, Inc., Menlo Park, CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107438805","display_name":"Daniel Mishler","orcid":null},"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":"Daniel Mishler","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","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/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"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Applied Mathematics, University of Manchester, Manchester,UK","Computer Science and Mathematics, Oak Ridge National Laboratory, Oak Ridge, TN,USA","Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Applied Mathematics, University of Manchester, Manchester,UK","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Computer Science and Mathematics, Oak Ridge National Laboratory, Oak Ridge, TN,USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073990539"],"corresponding_institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":0.3719,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.64512214,"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":"671","last_page":"691"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9990000128746033,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9990000128746033,"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":0.9970999956130981,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/slicing","display_name":"Slicing","score":0.7704858779907227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727454662322998},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.6897317171096802},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.650196373462677},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6098892688751221},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5942201614379883},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.5759560465812683},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4933578073978424},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.41908320784568787},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3517230153083801},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20623260736465454},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12766161561012268}],"concepts":[{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.7704858779907227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727454662322998},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.6897317171096802},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.650196373462677},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6098892688751221},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5942201614379883},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5759560465812683},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4933578073978424},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41908320784568787},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3517230153083801},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20623260736465454},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12766161561012268},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/10943420241281050","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420241281050","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:osti.gov:2447519","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2447519","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":"pmh:oai:osti.gov:2447519","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2447519","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},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G1514730378","display_name":null,"funder_award_id":"2004541","funder_id":"https://openalex.org/F4320332169","funder_display_name":"Directorate for Computer and Information Science and Engineering"},{"id":"https://openalex.org/G3646891343","display_name":null,"funder_award_id":"FA8750-19-2-1000","funder_id":"https://openalex.org/F4320338249","funder_display_name":"Air Force Civil Engineer Center"},{"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/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338249","display_name":"Air Force Civil Engineer Center","ror":"https://ror.org/006gmme17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W111941793","https://openalex.org/W1581582143","https://openalex.org/W1982811641","https://openalex.org/W2003009527","https://openalex.org/W2005498993","https://openalex.org/W2014090447","https://openalex.org/W2014209007","https://openalex.org/W2032608160","https://openalex.org/W2044540053","https://openalex.org/W2072396164","https://openalex.org/W2087891564","https://openalex.org/W2088415187","https://openalex.org/W2104110430","https://openalex.org/W2107857731","https://openalex.org/W2119522963","https://openalex.org/W2156779053","https://openalex.org/W2157237396","https://openalex.org/W2168612748","https://openalex.org/W2289184339","https://openalex.org/W2529375688","https://openalex.org/W2626680996","https://openalex.org/W2800481425","https://openalex.org/W2887881931","https://openalex.org/W2950745813","https://openalex.org/W2982181895","https://openalex.org/W2983126917","https://openalex.org/W3021029305","https://openalex.org/W3100418870","https://openalex.org/W3194256796","https://openalex.org/W4205295188","https://openalex.org/W4229666556","https://openalex.org/W4239881334","https://openalex.org/W4384705357"],"related_works":["https://openalex.org/W2393746923","https://openalex.org/W2972496411","https://openalex.org/W4239223006","https://openalex.org/W3033662781","https://openalex.org/W2137530048","https://openalex.org/W2360869927","https://openalex.org/W2050876785","https://openalex.org/W2074642116","https://openalex.org/W3164401656","https://openalex.org/W2392031372"],"abstract_inverted_index":{"Performing":[0],"a":[1,13,23],"variety":[2],"of":[3,25,29,51],"numerical":[4,40,79,122],"computations":[5],"efficiently":[6],"and,":[7],"at":[8],"the":[9,38,128,133],"same":[10],"time,":[11],"in":[12],"portable":[14],"fashion":[15],"requires":[16],"both":[17],"an":[18],"overarching":[19],"design":[20],"followed":[21],"by":[22,83],"number":[24],"implementation":[26],"strategies.":[27],"All":[28],"these":[30],"are":[31],"exemplified":[32],"below":[33],"as":[34],"we":[35],"present":[36,95],"transitioning":[37],"PLASMA":[39],"library":[41],"from":[42,131],"relying":[43],"on":[44],"dependence-driven":[45],"large":[46],"tasks":[47],"to":[48,57],"achieving":[49],"utilization":[50],"fine":[52,105],"grain":[53],"tasking":[54,107],"and":[55,70,76,99,111,121,136],"offload":[56,112],"hardware":[58,84],"accelerators":[59],"while":[60],"keeping":[61],"its":[62],"core":[63],"dependence":[64],"sets:":[65],"OpenMP":[66],"source":[67,88,135],"code":[68],"pragmas":[69],"runtime":[71],"for":[72,108,113],"most":[73],"system-level":[74],"functionality":[75],"basic":[77],"low-level":[78],"kernels":[80],"provided":[81],"directly":[82],"vendors":[85],"or":[86],"open":[87,134],"projects":[89],"with":[90],"vendor":[91],"contributions.":[92],"We":[93,117],"also":[94],"new":[96],"algorithmic":[97],"methods":[98],"their":[100],"efficient":[101],"parallel":[102],"implementations":[103],"including":[104],"grained":[106],"eigen-spectrum":[109],"slicing":[110],"mixed-precision":[114],"eigenvalue":[115],"refinement.":[116],"provide":[118],"performance,":[119],"scaling,":[120],"results":[123],"showing":[124],"sizable":[125],"gains":[126],"over":[127],"available":[129],"solutions":[130],"either":[132],"vendor-provided":[137],"packages.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}