{"id":"https://openalex.org/W23390919","doi":"https://doi.org/10.1002/(sici)1096-9128(199709)9:9<837::aid-cpe267>3.0.co;2-2","title":"Parallel implementation of BLAS: general techniques for Level 3 BLAS","display_name":"Parallel implementation of BLAS: general techniques for Level 3 BLAS","publication_year":1997,"publication_date":"1997-09-01","ids":{"openalex":"https://openalex.org/W23390919","doi":"https://doi.org/10.1002/(sici)1096-9128(199709)9:9<837::aid-cpe267>3.0.co;2-2","mag":"23390919"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1096-9128(199709)9:9<837::aid-cpe267>3.0.co;2-2","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1096-9128(199709)9:9<837::aid-cpe267>3.0.co;2-2","pdf_url":null,"source":{"id":"https://openalex.org/S4210209928","display_name":"Concurrency Practice and Experience","issn_l":"1040-3108","issn":["1040-3108","1096-9128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency: Practice and Experience","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/A5047890137","display_name":"Almadena Chtchelkanova","orcid":null},"institutions":[{"id":"https://openalex.org/I12138139","display_name":"Austin College","ror":"https://ror.org/052k56z27","country_code":"US","type":"education","lineage":["https://openalex.org/I12138139"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Almadena Chtchelkanova","raw_affiliation_strings":["The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","institution_ids":["https://openalex.org/I12138139","https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062279572","display_name":"John A. Gunnels","orcid":"https://orcid.org/0000-0001-5110-190X"},"institutions":[{"id":"https://openalex.org/I12138139","display_name":"Austin College","ror":"https://ror.org/052k56z27","country_code":"US","type":"education","lineage":["https://openalex.org/I12138139"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Gunnels","raw_affiliation_strings":["The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","institution_ids":["https://openalex.org/I12138139","https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039664246","display_name":"Greg Morrow","orcid":null},"institutions":[{"id":"https://openalex.org/I12138139","display_name":"Austin College","ror":"https://ror.org/052k56z27","country_code":"US","type":"education","lineage":["https://openalex.org/I12138139"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Greg Morrow","raw_affiliation_strings":["The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","institution_ids":["https://openalex.org/I12138139","https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051184414","display_name":"James Overfelt","orcid":null},"institutions":[{"id":"https://openalex.org/I12138139","display_name":"Austin College","ror":"https://ror.org/052k56z27","country_code":"US","type":"education","lineage":["https://openalex.org/I12138139"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Overfelt","raw_affiliation_strings":["The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","University of Texas at Austin#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","institution_ids":["https://openalex.org/I12138139","https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061722569","display_name":"Robert A. Geijn","orcid":"https://orcid.org/0009-0004-6434-8492"},"institutions":[{"id":"https://openalex.org/I12138139","display_name":"Austin College","ror":"https://ror.org/052k56z27","country_code":"US","type":"education","lineage":["https://openalex.org/I12138139"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert A. van de Geijn","raw_affiliation_strings":["The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, College of Natural Sciences, Department of Computer Sciences, Taylor Hall 2124, Austin, Texas 78712-1188, USA","institution_ids":["https://openalex.org/I12138139","https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047890137"],"corresponding_institution_ids":["https://openalex.org/I12138139","https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.4287,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.65415208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":"9","first_page":"837","last_page":"857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9959999918937683,"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":0.8167396783828735},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6674110889434814},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6323333978652954},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5711668729782104},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5691626667976379},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.52152019739151},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.505915105342865},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4795936644077301},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.44485610723495483},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.341230183839798},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13161757588386536},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09795519709587097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167396783828735},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6674110889434814},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6323333978652954},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5711668729782104},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5691626667976379},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.52152019739151},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.505915105342865},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4795936644077301},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.44485610723495483},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.341230183839798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13161757588386536},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09795519709587097},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/(sici)1096-9128(199709)9:9<837::aid-cpe267>3.0.co;2-2","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1096-9128(199709)9:9<837::aid-cpe267>3.0.co;2-2","pdf_url":null,"source":{"id":"https://openalex.org/S4210209928","display_name":"Concurrency Practice and Experience","issn_l":"1040-3108","issn":["1040-3108","1096-9128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Concurrency: Practice and Experience","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.33.3672","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.3672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/ftp/pub/techreports/tr95-40.ps.Z","raw_type":"text"},{"id":"mag:23390919","is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=899270&coll=DL&dl=GUIDE","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2079658918","https://openalex.org/W2084379367","https://openalex.org/W1965833245","https://openalex.org/W145568931","https://openalex.org/W3145384893","https://openalex.org/W1988098298","https://openalex.org/W3091837582","https://openalex.org/W3195156891","https://openalex.org/W2020223986","https://openalex.org/W2340769696","https://openalex.org/W1585447259","https://openalex.org/W2905762035","https://openalex.org/W2950696620","https://openalex.org/W792389343","https://openalex.org/W2412152731","https://openalex.org/W2545915677","https://openalex.org/W2105626887","https://openalex.org/W1489544063","https://openalex.org/W2082306839","https://openalex.org/W2170783040"],"abstract_inverted_index":{"In":[0],"this":[1,71],"paper,":[2],"we":[3],"present":[4],"straightforward":[5],"techniques":[6,55],"for":[7,57,77],"a":[8,36],"highly":[9],"efficient,":[10],"scalable":[11],"implementation":[12,80],"of":[13,35,81],"common":[14],"matrix\u2013matrix":[15,38,59],"operations":[16],"generally":[17],"known":[18],"as":[19],"the":[20,54,58,93],"Level":[21,66],"3":[22,67],"Basic":[23],"Linear":[24],"Algebra":[25],"Subprograms":[26],"(BLAS).":[27],"This":[28],"work":[29,49],"builds":[30],"on":[31,92],"our":[32],"recent":[33],"discovery":[34],"parallel":[37,79],"multiplication":[39,60],"implementation,":[40],"which":[41],"has":[42],"yielded":[43],"superior":[44],"performance,":[45],"and":[46,69,84],"requires":[47],"little":[48],"space.":[50],"We":[51],"show":[52],"that":[53,86],"used":[56],"naturally":[61],"extend":[62],"to":[63],"all":[64],"important":[65],"BLAS":[68],"thus":[70],"approach":[72],"becomes":[73],"an":[74],"enabling":[75],"technology":[76],"efficient":[78],"these":[82],"routines":[83],"libraries":[85],"use":[87],"BLAS.":[88],"Representative":[89],"performance":[90],"results":[91],"Intel":[94],"Paragon":[95],"system":[96],"are":[97],"given.":[98],"\u00a9":[99],"1997":[100],"John":[101],"Wiley":[102],"&":[103],"Sons,":[104],"Ltd.":[105]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2016-06-24T00:00:00"}
