{"id":"https://openalex.org/W1998492046","doi":"https://doi.org/10.1145/1065895.1065898","title":"Automatic blocking of QR and LU factorizations for locality","display_name":"Automatic blocking of QR and LU factorizations for locality","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W1998492046","doi":"https://doi.org/10.1145/1065895.1065898","mag":"1998492046"},"language":"en","primary_location":{"id":"doi:10.1145/1065895.1065898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065895.1065898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 workshop on Memory system performance  - MSP '04","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/15013895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101413850","display_name":"Qing Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Yi","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA","Lawrence Livermore National            Laboratory, Livermore, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National            Laboratory, Livermore, CA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084197997","display_name":"Ken Kennedy","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ken Kennedy","raw_affiliation_strings":["Rice University, Houston, TX","Rice University (Houston, TX)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University, Houston, TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University (Houston, TX)","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017918038","display_name":"Haihang You","orcid":"https://orcid.org/0000-0003-1432-827X"},"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":"Haihang You","raw_affiliation_strings":["University of Tennessee, Knoxville, TN","University of Tennessee, Knoxville, TN;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, Knoxville, TN;","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069239197","display_name":"Keith Seymour","orcid":"https://orcid.org/0000-0003-0850-2745"},"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":"Keith Seymour","raw_affiliation_strings":["University of Tennessee, Knoxville, TN","University of Tennessee, Knoxville, TN;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, Knoxville, TN;","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, Knoxville, TN","University of Tennessee, Knoxville, TN;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, TN","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"University of Tennessee, Knoxville, TN;","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8551,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84391793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8447955846786499},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7937285900115967},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7678209543228149},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7126824855804443},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.6877461075782776},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.6327141523361206},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6075610518455505},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6054387092590332},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5915343165397644},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.545546293258667},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.44471102952957153},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4354328215122223},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.41273632645606995},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38458728790283203},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.3553953170776367},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3322996497154236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33039987087249756},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11919912695884705},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11047405004501343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447955846786499},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7937285900115967},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7678209543228149},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7126824855804443},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.6877461075782776},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.6327141523361206},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6075610518455505},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6054387092590332},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5915343165397644},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.545546293258667},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.44471102952957153},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4354328215122223},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.41273632645606995},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38458728790283203},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3553953170776367},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3322996497154236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33039987087249756},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11919912695884705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11047405004501343},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/1065895.1065898","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065895.1065898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 workshop on Memory system performance  - MSP '04","raw_type":"proceedings-article"},{"id":"pmh:info:ark/67531/metadc1404945","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc1404945/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Presented at: The Second ACM SIGPLAN Workshop on Memory System Performance, Washington , DC, United States, Jun 08 - Jun 08, 2004","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.3632","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.3632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icl.cs.utk.edu/news_pub/submissions/msp04-yi.pdf","raw_type":"text"},{"id":"pmh:oai:osti.gov:15013895","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/15013895","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},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/e2458d74-c117-43ef-a672-2cbdd597844c","is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/ACMmsp/msp2004.html#YiKYSD04","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yi, Q, Kennedy, K, You, H, Seymour, K & Dongarra, J 2004, Automatic blocking of QR and LU factorizations for locality. in Proceedings of the ACM SIGPLAN Workshop on Memory System Performance, MSP 2004|Proc. ACM SIGPLAN Workshop Mem. Syst. Perform., MSP. Association for Computing Machinery, pp. 12-22, 2nd ACM SIGPLAN Workshop on Memory Systems Performance, MSP 2004, Washington, DC, 1/07/04. https://doi.org/10.1145/1065895.1065898","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.atira.dk:publications/e2458d74-c117-43ef-a672-2cbdd597844c","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/e2458d74-c117-43ef-a672-2cbdd597844c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yi, Q, Kennedy, K, You, H, Seymour, K & Dongarra, J 2004, Automatic blocking of QR and LU factorizations for locality. in Proceedings of the ACM SIGPLAN Workshop on Memory System Performance, MSP 2004|Proc. ACM SIGPLAN Workshop Mem. Syst. Perform., MSP. Association for Computing Machinery, pp. 12-22, 2nd ACM SIGPLAN Workshop on Memory Systems Performance, MSP 2004, Washington, DC, 1/07/04. https://doi.org/10.1145/1065895.1065898","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:osti.gov:15013895","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/15013895","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1491410022","https://openalex.org/W1494930385","https://openalex.org/W1500117749","https://openalex.org/W1536051636","https://openalex.org/W1545258949","https://openalex.org/W1560132800","https://openalex.org/W1605045777","https://openalex.org/W1964354616","https://openalex.org/W2042629708","https://openalex.org/W2046351222","https://openalex.org/W2068326054","https://openalex.org/W2069738303","https://openalex.org/W2073866852","https://openalex.org/W2089799314","https://openalex.org/W2098220211","https://openalex.org/W2108315152","https://openalex.org/W2119609467","https://openalex.org/W2138007781","https://openalex.org/W2152320213","https://openalex.org/W2152960970","https://openalex.org/W2158158791","https://openalex.org/W2168846776","https://openalex.org/W2169282672","https://openalex.org/W3004256893"],"related_works":["https://openalex.org/W2021525945","https://openalex.org/W1998492046","https://openalex.org/W2023965391","https://openalex.org/W3095040987","https://openalex.org/W2013417994","https://openalex.org/W4225552076","https://openalex.org/W4290725151","https://openalex.org/W2025529701","https://openalex.org/W4388311419","https://openalex.org/W2119370163"],"abstract_inverted_index":{"QR":[0,54,131],"and":[1,59,132,149,168],"LU":[2,60,133],"factorizations":[3],"for":[4,129,173],"dense":[5],"matrices":[6,38],"are":[7,13],"important":[8],"linear":[9,78],"algebra":[10,79],"computations":[11,23],"that":[12,142],"widely":[14],"used":[15],"in":[16,47,160],"scientific":[17],"applications.":[18],"To":[19],"efficiently":[20],"perform":[21],"these":[22,75,89],"on":[24,36,56],"modern":[25],"computers,":[26],"the":[27,42,72,97,151,174],"factorization":[28,61],"algorithms":[29,62],"need":[30],"to":[31,39,116,125],"be":[32,102,144],"blocked":[33,86,94],"when":[34],"operating":[35],"large":[37],"effectively":[40],"exploit":[41],"deep":[43],"cache":[44],"hierarchy":[45],"prevalent":[46],"today's":[48],"computer":[49],"memory":[50],"systems.":[51],"Because":[52],"both":[53,130,162],"(based":[55],"Householder":[57],"transformations)":[58],"contain":[63],"complex":[64],"loop":[65,120],"structures,":[66],"few":[67],"compilers":[68],"can":[69,101,143],"fully":[70],"automate":[71],"blocking":[73,110,140],"of":[74,88,96,108,153],"algorithms.":[76],"Though":[77],"libraries":[80],"such":[81,104],"as":[82,105],"LAPACK":[83],"provides":[84],"manually":[85,157],"implementations":[87],"algorithms,":[90],"by":[91,146],"automatically":[92],"generating":[93],"versions":[95,155,159],"computations,":[98],"more":[99],"benefit":[100],"gained":[103],"automatic":[106],"adaptation":[107],"different":[109,139],"strategies.":[111],"This":[112],"paper":[113],"demonstrates":[114],"how":[115],"apply":[117],"an":[118],"aggressive":[119],"transformation":[121],"technique,":[122],"dependence":[123],"hoisting,":[124],"produce":[126],"efficient":[127],"blockings":[128],"with":[134,156],"partial":[135],"pivoting.":[136],"We":[137],"present":[138],"strategies":[141],"generated":[145],"our":[147],"optimizer":[148],"compare":[150],"performance":[152],"auto-blocked":[154],"tuned":[158,172],"LAPACK,":[161],"using":[163],"reference":[164],"BLAS,":[165],"ATLAS":[166],"BLAS":[167,170],"native":[169],"specially":[171],"underlying":[175],"machine":[176],"architectures.":[177]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
