{"id":"https://openalex.org/W2122515712","doi":"https://doi.org/10.1109/ipdps.2004.1303000","title":"SRUMMA: a matrix multiplication algorithm suitable for clusters and scalable shared memory systems","display_name":"SRUMMA: a matrix multiplication algorithm suitable for clusters and scalable shared memory systems","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2122515712","doi":"https://doi.org/10.1109/ipdps.2004.1303000","mag":"2122515712"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2004.1303000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-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/A5111940913","display_name":"Manoj Krishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Krishnan","raw_affiliation_strings":["Computational Sciences & Mathematics, Pacific Northwest National Laboratory, USA","Computational Sci. & Math., Pacific Northwest Nat. Lab., Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Computational Sciences & Mathematics, Pacific Northwest National Laboratory, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Computational Sci. & Math., Pacific Northwest Nat. Lab., Washington, DC, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047131679","display_name":"Jarek Nieplocha","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Nieplocha","raw_affiliation_strings":["Computational Sciences & Mathematics, Pacific Northwest National Laboratory, USA","Computational Sci. & Math., Pacific Northwest Nat. Lab., Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Computational Sciences & Mathematics, Pacific Northwest National Laboratory, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Computational Sci. & Math., Pacific Northwest Nat. Lab., Washington, DC, USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111940913"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":3.1691,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.91363747,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"70","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994000196456909,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9973999857902527,"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":0.8272885680198669},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8134288191795349},{"id":"https://openalex.org/keywords/myrinet","display_name":"Myrinet","score":0.7913107872009277},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7193173766136169},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.6341066360473633},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6274049282073975},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6222611665725708},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5453883409500122},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4665500819683075},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.45120537281036377},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.4389289319515228},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.4267407953739166},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3954430818557739},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3502911329269409},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.2017829716205597},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10674852132797241},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08942720293998718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272885680198669},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8134288191795349},{"id":"https://openalex.org/C2780601250","wikidata":"https://www.wikidata.org/wiki/Q1863181","display_name":"Myrinet","level":3,"score":0.7913107872009277},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7193173766136169},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.6341066360473633},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6274049282073975},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6222611665725708},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5453883409500122},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4665500819683075},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.45120537281036377},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.4389289319515228},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4267407953739166},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3954430818557739},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3502911329269409},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2017829716205597},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10674852132797241},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08942720293998718},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdps.2004.1303000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.115.7146","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.115.7146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hpc.pnl.gov/projects/srumma/srumma-ipdps04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.78.71","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.78.71","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.emsl.pnl.gov/docs/parsoft/armci/publications/srumma.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W74523810","https://openalex.org/W1535437188","https://openalex.org/W1559533846","https://openalex.org/W1580435966","https://openalex.org/W1598993252","https://openalex.org/W1604065341","https://openalex.org/W1813030236","https://openalex.org/W1861151562","https://openalex.org/W1964711958","https://openalex.org/W1966234748","https://openalex.org/W1968748303","https://openalex.org/W1984788566","https://openalex.org/W1985926973","https://openalex.org/W2006096882","https://openalex.org/W2029342163","https://openalex.org/W2036678384","https://openalex.org/W2045741647","https://openalex.org/W2056999868","https://openalex.org/W2082292996","https://openalex.org/W2084809569","https://openalex.org/W2093608182","https://openalex.org/W2098885066","https://openalex.org/W2120785304","https://openalex.org/W2121609535","https://openalex.org/W2134439087","https://openalex.org/W2135653967","https://openalex.org/W2143151965","https://openalex.org/W2148979214","https://openalex.org/W2154806371","https://openalex.org/W2156189380","https://openalex.org/W2199463396","https://openalex.org/W2541014599","https://openalex.org/W2601133358","https://openalex.org/W2798909945","https://openalex.org/W3136479147","https://openalex.org/W4231150350","https://openalex.org/W6634569203","https://openalex.org/W6639223761","https://openalex.org/W6677972753","https://openalex.org/W6679959440","https://openalex.org/W6680915648","https://openalex.org/W6682136429","https://openalex.org/W7048807060"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W2043670592","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2159192094","https://openalex.org/W2122515712"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"We":[4],"describe":[5],"a":[6,12,119],"novel":[7],"parallel":[8,43,95],"algorithm":[9,111],"that":[10,22],"implements":[11],"dense":[13],"matrix":[14,44,96,120,139],"multiplication":[15,45,97,140],"operation":[16],"with":[17],"algorithmic":[18],"efficiency":[19],"equivalent":[20],"to":[21],"of":[23,51,93,122,129],"Cannon's":[24],"algorithm.":[25],"It":[26],"is":[27],"suitable":[28],"for":[29,118],"clusters":[30,68,143],"and":[31,54,72,134],"scalable":[32],"shared":[33,52,73,135],"memory":[34,53,56,74,136],"systems.":[35],"The":[36,64,127],"current":[37],"approach":[38],"differs":[39],"from":[40,86],"the":[41,48,87,90,94,102,106,109],"other":[42],"algorithms":[46,98],"by":[47],"explicit":[49],"use":[50],"remote":[55],"access":[57],"(RMA)":[58],"communication":[59,137],"rather":[60],"than":[61,116],"message":[62],"passing.":[63],"experimental":[65],"results":[66],"on":[67,105,124,138,142],"(IBM":[69],"SP,":[70],"Linux-Myrinet)":[71],"systems":[75],"(SGI":[76],"Altix,":[77,108],"Cray":[78],"XI)":[79],"demonstrate":[80],"consistent":[81],"performance":[82,141],"advantages":[83],"over":[84],"pdgemm":[85,117],"ScaLAPACK/PBBLAS":[88],"suite,":[89],"leading":[91],"implementation":[92],"used":[99],"today.":[100],"In":[101],"best":[103],"case":[104],"SGI":[107],"new":[110],"performs":[112],"20":[113],"times":[114],"better":[115],"size":[121],"1000":[123],"128":[125],"processors.":[126],"impact":[128],"zero-copy":[130],"nonblocking":[131],"RMA":[132],"communications":[133],"are":[144],"investigated.":[145]},"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":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}