{"id":"https://openalex.org/W2164326463","doi":"https://doi.org/10.1145/1356052.1356055","title":"Cache efficient bidiagonalization using BLAS 2.5 operators","display_name":"Cache efficient bidiagonalization using BLAS 2.5 operators","publication_year":2008,"publication_date":"2008-05-01","ids":{"openalex":"https://openalex.org/W2164326463","doi":"https://doi.org/10.1145/1356052.1356055","mag":"2164326463"},"language":"en","primary_location":{"id":"doi:10.1145/1356052.1356055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1356052.1356055","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/A5083325748","display_name":"Gary Howell","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary W. Howell","raw_affiliation_strings":["North Carolina State University, Raleigh, NC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076825233","display_name":"James Demmel","orcid":"https://orcid.org/0000-0003-1145-3745"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James W. Demmel","raw_affiliation_strings":["University of California, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016710181","display_name":"Charles T. Fulton","orcid":"https://orcid.org/0000-0002-3430-1472"},"institutions":[{"id":"https://openalex.org/I106959904","display_name":"Florida Institute of Technology","ror":"https://ror.org/04atsbb87","country_code":"US","type":"education","lineage":["https://openalex.org/I106959904"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles T. Fulton","raw_affiliation_strings":["Florida Institute of Technology, Melbourne, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Florida Institute of Technology, Melbourne, FL","institution_ids":["https://openalex.org/I106959904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025834032","display_name":"Sven Hammarling","orcid":"https://orcid.org/0000-0003-3865-4897"},"institutions":[{"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sven Hammarling","raw_affiliation_strings":["University of Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001239429","display_name":"Karen Marmol","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Marmol","raw_affiliation_strings":["Harris Corporation, Melbourne, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harris Corporation, Melbourne, FL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1971,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94931282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"3","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9962000250816345,"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":0.9930999875068665,"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":0.7390696406364441},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7200590372085571},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6846378445625305},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5139786601066589},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47766146063804626},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4506809413433075},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4087316393852234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390696406364441},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7200590372085571},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6846378445625305},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5139786601066589},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47766146063804626},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4506809413433075},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4087316393852234},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1356052.1356055","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1356052.1356055","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"},{"id":"pmh:oai:eprints.maths.manchester.ac.uk.MIMS.EPrints:210","is_oa":false,"landing_page_url":"http://eprints.maths.manchester.ac.uk/210/1/bidiag23_03_06.pdf","pdf_url":"http://eprints.maths.manchester.ac.uk/210/1/bidiag23_03_06.pdf","source":{"id":"https://openalex.org/S4306400452","display_name":"MIMS EPrints (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"MIMS Preprint"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.106.7109","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.106.7109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.ma.man.ac.uk/210/01/covered/MIMS_ep2006_56.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.668.148","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.668.148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.ma.man.ac.uk/210/01/bidiag23_03_06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2823650346","display_name":"NGS:  Cache Efficient and Parallel Householder Bidiagonalization","funder_award_id":"0103642","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4357884192","display_name":"Comparative and Web-Enabled Virtual Screening (RMI)","funder_award_id":"1p20hg003900-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W349097221","https://openalex.org/W1537846056","https://openalex.org/W1542574673","https://openalex.org/W1552224009","https://openalex.org/W1621933882","https://openalex.org/W1918870341","https://openalex.org/W1981745143","https://openalex.org/W1989396323","https://openalex.org/W1999600349","https://openalex.org/W2005423095","https://openalex.org/W2021178437","https://openalex.org/W2039778940","https://openalex.org/W2041797552","https://openalex.org/W2053869601","https://openalex.org/W2070596272","https://openalex.org/W2072773380","https://openalex.org/W2073260424","https://openalex.org/W2078841894","https://openalex.org/W2085924714","https://openalex.org/W2087716616","https://openalex.org/W2097897435","https://openalex.org/W2122328435","https://openalex.org/W2135653967","https://openalex.org/W2149381887","https://openalex.org/W2164895445","https://openalex.org/W2798909945","https://openalex.org/W2897836668","https://openalex.org/W4229666556","https://openalex.org/W6645817467"],"related_works":["https://openalex.org/W2147122795","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W2167303720","https://openalex.org/W2109715593","https://openalex.org/W3161817247","https://openalex.org/W1918294866","https://openalex.org/W2012518269","https://openalex.org/W2068309140","https://openalex.org/W57688818"],"abstract_inverted_index":{"On":[0],"cache":[1],"based":[2],"computer":[3],"architectures":[4],"using":[5],"current":[6,103],"standard":[7],"algorithms,":[8],"Householder":[9,36],"bidiagonalization":[10,37,105],"requires":[11],"a":[12,39],"significant":[13],"portion":[14],"of":[15,33,38,57,62,77],"the":[16,31,58,63,75,102],"execution":[17,85],"time":[18],"for":[19,35],"computing":[20],"matrix":[21,64],"singular":[22],"values":[23],"and":[24,98],"vectors.":[25],"In":[26],"this":[27],"paper":[28],"we":[29],"reorganize":[30],"sequence":[32],"operations":[34,70],"general":[40],"m":[41],"\u00d7":[42],"n":[43],"matrix,":[44],"so":[45],"that":[46],"two":[47],"(_GEMV)":[48],"vector-matrix":[49],"multiplications":[50],"can":[51],"be":[52],"done":[53],"with":[54,101],"one":[55],"pass":[56],"unreduced":[59],"trailing":[60],"part":[61],"through":[65],"cache.":[66],"Two":[67],"new":[68],"BLAS":[69],"approximately":[71],"cut":[72],"in":[73],"half":[74],"transfer":[76],"data":[78],"from":[79],"main":[80],"memory":[81],"to":[82,89],"cache,":[83],"reducing":[84],"times":[86],"by":[87],"up":[88],"25":[90],"per":[91],"cent.":[92],"We":[93],"give":[94],"detailed":[95],"algorithm":[96],"descriptions":[97],"compare":[99],"timings":[100],"LAPACK":[104],"algorithm.":[106]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
