{"id":"https://openalex.org/W2122283107","doi":"https://doi.org/10.1145/2597652.2597670","title":"Scaling up matrix computations on shared-memory manycore systems with 1000 CPU cores","display_name":"Scaling up matrix computations on shared-memory manycore systems with 1000 CPU cores","publication_year":2014,"publication_date":"2014-06-10","ids":{"openalex":"https://openalex.org/W2122283107","doi":"https://doi.org/10.1145/2597652.2597670","mag":"2122283107"},"language":"en","primary_location":{"id":"doi:10.1145/2597652.2597670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597652.2597670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM international conference on Supercomputing","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/A5032742296","display_name":"Fengguang Song","orcid":"https://orcid.org/0000-0001-7382-093X"},"institutions":[{"id":"https://openalex.org/I55769427","display_name":"Indiana University \u2013 Purdue University Indianapolis","ror":"https://ror.org/05gxnyn08","country_code":"US","type":"education","lineage":["https://openalex.org/I55769427","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengguang Song","raw_affiliation_strings":["Indiana University-Purdue University Indianapolis, Indianapolis, USA","Indiana University-Purdue University, Indianapolis, Indianapolis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University-Purdue University Indianapolis, Indianapolis, USA","institution_ids":["https://openalex.org/I55769427"]},{"raw_affiliation_string":"Indiana University-Purdue University, Indianapolis, Indianapolis, USA","institution_ids":["https://openalex.org/I55769427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee Knoxville, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2055,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.77680403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"342"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8628698587417603},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7012661695480347},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6017212867736816},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5578718781471252},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5422606468200684},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4963913559913635},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.49300047755241394},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.45916634798049927},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4549727439880371},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.4236070513725281},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41923829913139343},{"id":"https://openalex.org/keywords/single-core","display_name":"Single-core","score":0.4157763123512268},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3895907700061798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8628698587417603},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7012661695480347},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6017212867736816},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5578718781471252},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5422606468200684},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4963913559913635},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.49300047755241394},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.45916634798049927},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4549727439880371},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.4236070513725281},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41923829913139343},{"id":"https://openalex.org/C2780365336","wikidata":"https://www.wikidata.org/wiki/Q25047934","display_name":"Single-core","level":2,"score":0.4157763123512268},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3895907700061798},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2597652.2597670","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597652.2597670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.2525","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.2525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/utk/people/JackDongarra/PAPERS/ics14-song.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1480928214","https://openalex.org/W1519490651","https://openalex.org/W1750594686","https://openalex.org/W1938553034","https://openalex.org/W1982632559","https://openalex.org/W2025715322","https://openalex.org/W2043143850","https://openalex.org/W2058038604","https://openalex.org/W2059431371","https://openalex.org/W2064372914","https://openalex.org/W2074805288","https://openalex.org/W2095597068","https://openalex.org/W2124480634","https://openalex.org/W2128203141","https://openalex.org/W2132260309","https://openalex.org/W2153439050","https://openalex.org/W2157802978","https://openalex.org/W3083730481","https://openalex.org/W4229666556","https://openalex.org/W4231150350"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2142016460","https://openalex.org/W4205439893","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2185094550"],"abstract_inverted_index":{"While":[0],"the":[1,17,21,76,96,105,124,148,163,230],"growing":[2],"number":[3,131],"of":[4,20,49,107,132],"cores":[5,50,212],"per":[6],"chip":[7],"allows":[8],"researchers":[9],"to":[10,26,32,51,60,81,113,122,151,175,194,202,224,237],"solve":[11],"larger":[12],"scientific":[13],"and":[14,35,38,42,89,155,213,227],"engineering":[15],"problems,":[16],"parallel":[18,23,186],"efficiency":[19,187],"deployed":[22],"software":[24,37],"starts":[25],"decrease.":[27],"This":[28],"unscalability":[29,77],"problem":[30],"happens":[31],"both":[33],"vendor-provided":[34],"open-source":[36],"wastes":[39],"CPU":[40,211],"cycles":[41],"energy.":[43],"By":[44],"expecting":[45],"CPUs":[46],"with":[47,104,165],"hundreds":[48],"be":[52],"imminent,":[53],"we":[54,98,168],"have":[55,99],"designed":[56,100],"a":[57,108,130,138,142,180,215],"new":[58],"framework":[59,172,201,222],"perform":[61],"matrix":[62],"computations":[63],"for":[64],"massively":[65],"many":[66],"cores.":[67],"Our":[68,221],"performance":[69],"analysis":[70],"on":[71,141,162,179],"manycore":[72],"systems":[73],"shows":[74],"that":[75,126,170],"bottleneck":[78],"is":[79,121,173],"related":[80],"Non-Uniform":[82],"Memory":[83],"Access":[84],"(NUMA):":[85],"memory":[86,91,116],"bus":[87],"contention":[88],"remote":[90,143],"access":[92],"latency.":[93],"To":[94],"overcome":[95],"bottleneck,":[97],"NUMA-aware":[101],"tile":[102],"algorithms":[103],"help":[106],"dynamic":[109],"scheduling":[110],"runtime":[111,149],"system":[112,150,184,219],"minimize":[114],"NUMA":[115,144,159],"accesses.":[117],"The":[118],"main":[119],"idea":[120],"identify":[123],"data":[125,153],"is,":[127],"either":[128],"read":[129],"times":[133],"or":[134],"written":[135],"once":[136],"by":[137,235],"thread":[139],"resident":[140],"node,":[145],"then":[146],"utilize":[147],"conduct":[152],"caching":[154],"movement":[156],"between":[157],"different":[158],"nodes.":[160],"Based":[161],"experiments":[164],"QR":[166],"factorizations,":[167],"demonstrate":[169],"our":[171,200],"able":[174],"achieve":[176],"great":[177],"scalability":[178],"48-core":[181],"AMD":[182],"Opteron":[183],"(e.g.,":[185],"drops":[188],"only":[189],"3%":[190],"from":[191],"one":[192],"core":[193],"48":[195],"cores).":[196],"We":[197],"also":[198],"deploy":[199],"an":[203],"extreme-scale":[204],"shared-memory":[205],"SGI":[206],"machine":[207],"which":[208],"has":[209],"1024":[210],"runs":[214],"single":[216],"Linux":[217],"operating":[218],"image.":[220],"continues":[223],"scale":[225],"well,":[226],"can":[228],"outperform":[229],"vendor-optimized":[231],"Intel":[232],"MKL":[233],"library":[234],"up":[236],"750%.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}