{"id":"https://openalex.org/W2100988782","doi":"https://doi.org/10.1109/ipdps.2011.93","title":"A Communication-Avoiding, Hybrid-Parallel, Rank-Revealing Orthogonalization Method","display_name":"A Communication-Avoiding, Hybrid-Parallel, Rank-Revealing Orthogonalization Method","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2100988782","doi":"https://doi.org/10.1109/ipdps.2011.93","mag":"2100988782"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2011.93","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2011.93","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Parallel &amp; Distributed Processing Symposium","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071661180","display_name":"Mark Frederick Hoemmen","orcid":null},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Hoemmen","raw_affiliation_strings":["Scalable Algorithms Department, Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scalable Algorithms Department, Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I192454743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071661180"],"corresponding_institution_ids":["https://openalex.org/I192454743"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"966","last_page":"977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9994000196456909,"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"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/orthogonalization","display_name":"Orthogonalization","score":0.887861967086792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8140292167663574},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7689694166183472},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.6542206406593323},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.6101254820823669},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5586298704147339},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5019919872283936},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3712192177772522},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.16937607526779175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1404038667678833}],"concepts":[{"id":"https://openalex.org/C47559304","wikidata":"https://www.wikidata.org/wiki/Q1702189","display_name":"Orthogonalization","level":2,"score":0.887861967086792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8140292167663574},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7689694166183472},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.6542206406593323},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.6101254820823669},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5586298704147339},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5019919872283936},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3712192177772522},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.16937607526779175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1404038667678833},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2011.93","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2011.93","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Parallel &amp; Distributed Processing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W57462620","https://openalex.org/W1522703524","https://openalex.org/W1825216778","https://openalex.org/W1863162408","https://openalex.org/W1907157228","https://openalex.org/W2001135345","https://openalex.org/W2014724759","https://openalex.org/W2016279572","https://openalex.org/W2022916138","https://openalex.org/W2029665502","https://openalex.org/W2040425799","https://openalex.org/W2066349733","https://openalex.org/W2073955633","https://openalex.org/W2074361019","https://openalex.org/W2086666883","https://openalex.org/W2088307891","https://openalex.org/W2145194992","https://openalex.org/W2165439482","https://openalex.org/W3016205154","https://openalex.org/W3029019225","https://openalex.org/W6638601623"],"related_works":["https://openalex.org/W2897260157","https://openalex.org/W2533759852","https://openalex.org/W2109456519","https://openalex.org/W2279936185","https://openalex.org/W2556526093","https://openalex.org/W2007138219","https://openalex.org/W2026512611","https://openalex.org/W324598049","https://openalex.org/W1985165680","https://openalex.org/W4245497162"],"abstract_inverted_index":{"Orthogonalization":[0],"consumes":[1],"much":[2],"of":[3,7,25,58,135,157,165,198,214],"the":[4,42,79,101,155,192,211,215,224],"run":[5],"time":[6],"many":[8],"iterative":[9,119],"methods":[10],"for":[11,99,114,121,154],"solving":[12],"sparse":[13],"linear":[14],"systems":[15],"and":[16,44,46,66,71,93,141,144,147,219],"eigenvalue":[17],"problems.":[18],"Commonly":[19],"used":[20],"algorithms,":[21],"such":[22],"as":[23,82,187],"variants":[24],"Gram-Schmidt":[26],"or":[27,128,201],"Householder":[28,83],"QR,":[29],"have":[30,131],"performance":[31],"dominated":[32],"by":[33],"communication.":[34],"Here,":[35],"\"communication\"":[36],"includes":[37],"both":[38,139],"data":[39,67],"movement":[40,68],"between":[41,48,64,69],"CPU":[43,70],"memory,":[45],"messages":[47,63],"processors":[49,65],"in":[50,87,117,210,223],"parallel.":[51],"Our":[52,150,194],"Tall":[53],"Skinny":[54],"QR":[55,84],"(TSQR)":[56],"family":[57],"algorithms":[59],"requires":[60],"asymptotically":[61],"fewer":[62],"memory":[72],"than":[73,96],"typical":[74],"orthogonalization":[75],"methods,":[76,120],"yet":[77],"achieves":[78,196],"same":[80],"accuracy":[81],"factorization.":[85],"Furthermore,":[86],"block":[88,105,118],"orthogonalizations,":[89],"TSQR":[90,136],"is":[91,152,207],"faster":[92],"more":[94,202],"accurate":[95],"existing":[97,123],"approaches":[98,124],"orthogonalizing":[100,158],"vectors":[102],"within":[103],"each":[104],"(\"normalization\").":[106],"TSQR's":[107],"rank-revealing":[108],"capability":[109],"also":[110],"makes":[111],"it":[112],"useful":[113],"detecting":[115],"deflation":[116],"which":[122],"sacrifice":[125],"performance,":[126],"accuracy,":[127],"both.":[129],"We":[130],"implemented":[132],"a":[133,159],"version":[134],"that":[137],"exploits":[138],"distributed-memory":[140],"shared-memory":[142,170,184],"parallelism,":[143],"supports":[145,182],"real":[146],"complex":[148],"arithmetic.":[149],"implementation":[151,195],"optimized":[153],"case":[156],"small":[160],"number":[161],"(5":[162],"--":[163],"20)":[164],"very":[166],"long":[167],"vectors.":[168],"The":[169],"parallel":[171],"component":[172],"uses":[173],"Intel's":[174],"Threading":[175],"Building":[176],"Blocks,":[177],"though":[178],"its":[179],"modular":[180],"design":[181],"other":[183],"programming":[185],"models":[186],"well,":[188],"including":[189],"computation":[190],"on":[191],"GPU.":[193],"speedups":[197],"2":[199],"times":[200],"over":[203],"competing":[204],"orthogonalizations.":[205],"It":[206],"available":[208],"now":[209],"development":[212],"branch":[213],"Trilinos":[216],"software":[217],"package,":[218],"will":[220],"be":[221],"included":[222],"10.8":[225],"release.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
