{"id":"https://openalex.org/W544946","doi":"https://doi.org/10.1002/cpe.4330060703","title":"Matrix multiplication on the Intel Touchstone Delta","display_name":"Matrix multiplication on the Intel Touchstone Delta","publication_year":1994,"publication_date":"1994-10-01","ids":{"openalex":"https://openalex.org/W544946","doi":"https://doi.org/10.1002/cpe.4330060703","mag":"544946"},"language":"en","primary_location":{"id":"doi:10.1002/cpe.4330060703","doi":"https://doi.org/10.1002/cpe.4330060703","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.4330060703","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,"listed_in":["cwts-core"],"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"},"volume":null,"type":"article","is_traditional":true,"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/A5113657034","display_name":"Steven Huss\u2010Lederman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Huss\u2010Lederman","raw_affiliation_strings":["Supercomputing Research Center 17100 Science Drive Bowie, MD 20715-4300, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Supercomputing Research Center 17100 Science Drive Bowie, MD 20715-4300, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055484867","display_name":"Elaine M. Jacobson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elaine M. Jacobson","raw_affiliation_strings":["Supercomputing Research Center 17100 Science Drive Bowie, MD 20715-4300, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Supercomputing Research Center 17100 Science Drive Bowie, MD 20715-4300, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037768705","display_name":"Anna Tsao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anna Tsao","raw_affiliation_strings":["Supercomputing Research Center 17100 Science Drive Bowie, MD 20715-4300, USA","This research was done while the author was at Department of Mathematics, University of Maryland, College Park, MD 20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Supercomputing Research Center 17100 Science Drive Bowie, MD 20715-4300, USA","institution_ids":[]},{"raw_affiliation_string":"This research was done while the author was at Department of Mathematics, University of Maryland, College Park, MD 20742","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100459558","display_name":"Guodong Zhang","orcid":"https://orcid.org/0000-0003-4090-9123","observed_orcids":["https://orcid.org/0000-0003-4090-9123"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guodong Zhang","raw_affiliation_strings":["CONVEX Computer Corporation 3000 Waterview Parkway Richardson, TX 75083-3851, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CONVEX Computer Corporation 3000 Waterview Parkway Richardson, TX 75083-3851, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2846,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93394587,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":"6","issue":"7","first_page":"571","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9463000297546387,"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":0.9463000297546387,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.04859999939799309,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.0027000000700354576,"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/matrix-multiplication","display_name":"matrix multiplication","score":0.9940000176429749},{"id":"https://openalex.org/keywords/intel-touchstone-delta","display_name":"Intel Touchstone Delta","score":0.9169999957084656},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"distributed memory","score":0.6349999904632568},{"id":"https://openalex.org/keywords/message-passing","display_name":"message passing","score":0.7820000052452087},{"id":"https://openalex.org/keywords/parallel-algorithms","display_name":"parallel algorithms","score":0.6660000085830688},{"id":"https://openalex.org/keywords/communication-primitives","display_name":"communication primitives","score":0.746999979019165},{"id":"https://openalex.org/keywords/parallel-efficiency","display_name":"parallel efficiency","score":0.7649999856948853},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.8109999895095825},{"id":"https://openalex.org/keywords/data-layout","display_name":"data layout","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6708359122276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.658286452293396},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6573249101638794},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6241331100463867},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6071114540100098},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6053580045700073},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5664675235748291},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4578198194503784},{"id":"https://openalex.org/C85817219","wikidata":"https://www.wikidata.org/wiki/Q884772","display_name":"Block matrix","level":3,"score":0.4493662118911743},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.44616031646728516},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.371539831161499},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2901414632797241},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08283379673957825},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/cpe.4330060703","doi":"https://doi.org/10.1002/cpe.4330060703","is_oa":false,"landing_page_url":"https://doi.org/10.1002/cpe.4330060703","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,"listed_in":["cwts-core"],"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:10.1.1.47.7403","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.47.7403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-unix.mcs.anl.gov/prism/lib/techsrc/wn7.ps.Z","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.50.4324","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.50.4324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-unix.mcs.anl.gov/prism/lib/techsrc/wn14.ps.Z","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309398","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055"},{"id":"https://openalex.org/F4320309825","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W83590097","https://openalex.org/W133977063","https://openalex.org/W135834449","https://openalex.org/W200963352","https://openalex.org/W1484269629","https://openalex.org/W1524162954","https://openalex.org/W1528745880","https://openalex.org/W1532022113","https://openalex.org/W1547071828","https://openalex.org/W1559533846","https://openalex.org/W1591920523","https://openalex.org/W1598993252","https://openalex.org/W1947869163","https://openalex.org/W1984342881","https://openalex.org/W2000250112","https://openalex.org/W2002257715","https://openalex.org/W2058690191","https://openalex.org/W2082292996","https://openalex.org/W2165021839","https://openalex.org/W2170008263","https://openalex.org/W2253935813","https://openalex.org/W4205327951","https://openalex.org/W4230289604"],"related_works":["https://openalex.org/W2098885066","https://openalex.org/W2143151965","https://openalex.org/W1841951253","https://openalex.org/W2106438528","https://openalex.org/W2565436413","https://openalex.org/W2075711817","https://openalex.org/W1964711958","https://openalex.org/W2093608182","https://openalex.org/W1973589259","https://openalex.org/W2085681751"],"abstract_inverted_index":{"Abstract":[0],"Matrix":[1],"multiplication":[2,25],"is":[3,72],"a":[4,32,38],"key":[5],"primitive":[6],"in":[7,15,105],"block":[8],"matrix":[9,24,68,91],"algorithms":[10,26,47],"such":[11],"as":[12,83,85],"those":[13],"found":[14],"LAPACK.":[16],"We":[17,42,119],"present":[18,126],"results":[19,128],"from":[20],"our":[21],"study":[22],"of":[23,98,107],"on":[27,110],"the":[28,60,64],"Intel":[29],"Touchstone":[30],"Delta,":[31],"distributed":[33],"memory":[34],"message\u2010passing":[35],"architecture":[36],"with":[37,79,101],"two\u2010dimensional":[39],"mesh":[40,87,137],"topology.":[41],"analyze":[43],"and":[44,48,62,90,93,123,125,132],"compare":[45],"three":[46],"obtain":[49],"an":[50,114],"implementation,":[51],"BiMMeR,":[52],"that":[53,129],"uses":[54],"communication":[55],"primitives":[56],"highly":[57],"suited":[58],"to":[59,77],"Delta":[61],"exploits":[63],"single":[65],"node":[66],"assembly\u2010coded":[67],"multiplication.":[69],"Our":[70],"algorithm":[71],"completely":[73],"general,":[74],"i.e.":[75],"able":[76],"deal":[78],"various":[80],"data":[81],"layouts":[82],"well":[84],"arbitrary":[86],"aspect":[88],"ratios":[89],"dimensions,":[92],"has":[94],"achieved":[95],"parallel":[96],"efficiency":[97],"86":[99],"%,":[100],"overall":[102],"peak":[103],"performance":[104,127],"excess":[106],"8":[108],"Gflops":[109],"256":[111],"nodes":[112],"for":[113],"8800":[115,117],"\u00d7":[116],"matrix.":[118],"describe":[120],"BiMMeR's":[121],"design":[122],"implementation":[124],"demonstrate":[130],"scalability":[131],"robust":[133],"behavior":[134],"over":[135],"varying":[136],"topologies.":[138]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}
