{"id":"https://openalex.org/W2115139836","doi":"https://doi.org/10.1177/109434209601000403","title":"Local Basic Linear Algebra Subroutines (LBLAS) for the CM-5/5E","display_name":"Local Basic Linear Algebra Subroutines (LBLAS) for the CM-5/5E","publication_year":1996,"publication_date":"1996-12-01","ids":{"openalex":"https://openalex.org/W2115139836","doi":"https://doi.org/10.1177/109434209601000403","mag":"2115139836"},"language":"en","primary_location":{"id":"doi:10.1177/109434209601000403","is_oa":false,"landing_page_url":"https://doi.org/10.1177/109434209601000403","pdf_url":null,"source":{"id":"https://openalex.org/S4210228336","display_name":"The International Journal of Supercomputer Applications and High Performance Computing","issn_l":"1078-3482","issn":["1078-3482"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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 Supercomputer Applications and High Performance Computing","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/A5086696314","display_name":"David A. Kramer","orcid":"https://orcid.org/0000-0003-2434-3764"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Kramer","raw_affiliation_strings":["THINKING MACHINES CORPORATION, CAMBRIDGE, MA 02138"],"affiliations":[{"raw_affiliation_string":"THINKING MACHINES CORPORATION, CAMBRIDGE, MA 02138","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027003862","display_name":"S. Lennart Johnsson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Lennart Johnsson","raw_affiliation_strings":["THINKING MACHINES CORPORATION, AND HARVARD UNIVERSITY,\rCAMBRIDGE, MA 02138","THINKING MACHINES CORPORATION, AND HARVARD UNIVERSITY,#R#CAMBRIDGE, MA 02138"],"affiliations":[{"raw_affiliation_string":"THINKING MACHINES CORPORATION, AND HARVARD UNIVERSITY,\rCAMBRIDGE, MA 02138","institution_ids":[]},{"raw_affiliation_string":"THINKING MACHINES CORPORATION, AND HARVARD UNIVERSITY,#R#CAMBRIDGE, MA 02138","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089920438","display_name":"Yu Hu","orcid":"https://orcid.org/0000-0002-6045-5045"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Hu","raw_affiliation_strings":["AIKEN COMPUTATION LAB, HARVARD UNIVERSITY, CAMBRIDGE,\rMA 02138","AIKEN COMPUTATION LAB, HARVARD UNIVERSITY, CAMBRIDGE,#R#MA 02138"],"affiliations":[{"raw_affiliation_string":"AIKEN COMPUTATION LAB, HARVARD UNIVERSITY, CAMBRIDGE,\rMA 02138","institution_ids":[]},{"raw_affiliation_string":"AIKEN COMPUTATION LAB, HARVARD UNIVERSITY, CAMBRIDGE,#R#MA 02138","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086696314"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4017,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70005444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"4","first_page":"300","last_page":"335"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9988999962806702,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983000159263611,"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/subroutine","display_name":"Subroutine","score":0.9286155700683594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8524736166000366},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.689748227596283},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6337884068489075},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5148107409477234},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.499359130859375},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.49387675523757935},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4442235827445984},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4168063998222351},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.359585702419281},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32811301946640015},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31931787729263306},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.2718816101551056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10302937030792236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08470699191093445}],"concepts":[{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.9286155700683594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8524736166000366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.689748227596283},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6337884068489075},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5148107409477234},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.499359130859375},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.49387675523757935},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4442235827445984},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4168063998222351},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.359585702419281},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32811301946640015},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31931787729263306},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2718816101551056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10302937030792236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08470699191093445},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/109434209601000403","is_oa":false,"landing_page_url":"https://doi.org/10.1177/109434209601000403","pdf_url":null,"source":{"id":"https://openalex.org/S4210228336","display_name":"The International Journal of Supercomputer Applications and High Performance Computing","issn_l":"1078-3482","issn":["1078-3482"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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 Supercomputer Applications and High Performance Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W584037522","https://openalex.org/W1984342881","https://openalex.org/W1988425770","https://openalex.org/W1991286031","https://openalex.org/W2002257715","https://openalex.org/W2006384005","https://openalex.org/W2009018110","https://openalex.org/W2014830932","https://openalex.org/W2037540668","https://openalex.org/W2038469228","https://openalex.org/W2043456428","https://openalex.org/W2050120391","https://openalex.org/W2057711597","https://openalex.org/W2084231858","https://openalex.org/W2146406121","https://openalex.org/W3007497337"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W2391861012","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W2488336788","https://openalex.org/W1495480229","https://openalex.org/W4239025233","https://openalex.org/W2012309011","https://openalex.org/W179067477","https://openalex.org/W2995265122"],"abstract_inverted_index":{"The":[0,18,94,119],"Connection":[1],"Machine":[2],"Scientific":[3],"Software":[4],"Library":[5],"(CMSSL)":[6],"is":[7,96],"a":[8,32,80,115],"library":[9,102],"of":[10,24,52,62,68,86,104,113,121],"scientific":[11],"routines":[12],"designed":[13],"for":[14],"distributed":[15,116,125],"memory":[16,117,126],"architectures.":[17],"basic":[19],"linear":[20],"algebra":[21],"subroutines":[22],"(BLAS)":[23],"the":[25,47,53,63,87,97,107],"CMSSL":[26,95],"have":[27,73],"been":[28,74],"imple":[29],"mented":[30],"as":[31],"two-level":[33],"structure":[34],"to":[35,39,59,78],"exploit":[36],"optimizations":[37],"local":[38,54,58],"nodes":[40],"and":[41,50,71,82,110],"across":[42],"nodes.":[43],"This":[44],"paper":[45],"presents":[46],"implementation":[48],"considerations":[49],"performance":[51,101],"BLAS,":[55],"or":[56],"BLAS":[57,123],"each":[60],"node":[61,91],"system.":[64],"A":[65],"wide":[66],"variety":[67],"loop":[69],"structures":[70],"unrollings":[72],"implemented":[75],"in":[76,90,130],"order":[77],"achieve":[79],"uniform":[81],"high":[83,100],"performance,":[84],"irrespective":[85],"data":[88,108],"layout":[89],"mem":[92],"ory.":[93],"only":[98],"existing":[99],"capable":[103],"supporting":[105],"both":[106],"parallel":[109],"message-passing":[111],"modes":[112],"programming":[114],"computer.":[118],"implications":[120],"implementing":[122],"on":[124],"computers":[127],"are":[128],"considered":[129],"this":[131],"light.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}