{"id":"https://openalex.org/W2119809430","doi":"https://doi.org/10.1109/ipdps.2008.4536342","title":"Experiences in scaling scientific applications on current-generation quad-core processors","display_name":"Experiences in scaling scientific applications on current-generation quad-core processors","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2119809430","doi":"https://doi.org/10.1109/ipdps.2008.4536342","mag":"2119809430"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2008.4536342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","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/A5038062469","display_name":"Kevin Barker","orcid":"https://orcid.org/0000-0003-4947-0559"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin Barker","raw_affiliation_strings":["Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","Performance & Archit. Lab. (PAL), Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046929640","display_name":"Kei Davis","orcid":"https://orcid.org/0000-0002-4134-1798"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kei Davis","raw_affiliation_strings":["Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","Performance & Archit. Lab. (PAL), Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072223736","display_name":"Adolfy Hoisie","orcid":"https://orcid.org/0000-0001-7812-2946"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adolfy Hoisie","raw_affiliation_strings":["Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","Performance & Archit. Lab. (PAL), Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064935199","display_name":"Darren J. Kerbyson","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darren Kerbyson","raw_affiliation_strings":["Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","Performance & Archit. Lab. (PAL), Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078475557","display_name":"Michael Lang","orcid":"https://orcid.org/0000-0002-3498-6352"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Lang","raw_affiliation_strings":["Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","Performance & Archit. Lab. (PAL), Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060855642","display_name":"Scott Pakin","orcid":"https://orcid.org/0000-0002-5220-1985"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Pakin","raw_affiliation_strings":["Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","Performance & Archit. Lab. (PAL), Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008026936","display_name":"Jos\u00e9 Carlos Sancho","orcid":"https://orcid.org/0000-0002-6917-9155"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jose Carlos Sancho","raw_affiliation_strings":["Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","Performance & Archit. Lab. (PAL), Los Alamos, NM"],"affiliations":[{"raw_affiliation_string":"Performance and Architecture Lab (PAL), Los Alamos National Laboratory, USA","institution_ids":["https://openalex.org/I1343871089"]},{"raw_affiliation_string":"Performance & Archit. Lab. (PAL), Los Alamos, NM","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5038062469"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":3.4661,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.93011842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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":0.8402940630912781},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.8088163137435913},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8078352212905884},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6328591108322144},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6299629211425781},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5937231779098511},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5657362341880798},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4645300805568695},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.46059998869895935},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4385165572166443},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.43559741973876953},{"id":"https://openalex.org/keywords/yarn","display_name":"Yarn","score":0.41361871361732483},{"id":"https://openalex.org/keywords/clock-rate","display_name":"Clock rate","score":0.41283342242240906},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4099564850330353},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32033753395080566},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08742493391036987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8402940630912781},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.8088163137435913},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8078352212905884},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6328591108322144},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6299629211425781},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5937231779098511},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5657362341880798},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4645300805568695},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4385165572166443},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.43559741973876953},{"id":"https://openalex.org/C2778787235","wikidata":"https://www.wikidata.org/wiki/Q49007","display_name":"Yarn","level":2,"score":0.41361871361732483},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.41283342242240906},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4099564850330353},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32033753395080566},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08742493391036987},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","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/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:10.1109/ipdps.2008.4536342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W129935027","https://openalex.org/W1906159688","https://openalex.org/W2033263927","https://openalex.org/W2039231059","https://openalex.org/W2077828271","https://openalex.org/W2166997500","https://openalex.org/W2533204039","https://openalex.org/W6695275532"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2030340070","https://openalex.org/W4239672454","https://openalex.org/W4388580994","https://openalex.org/W2951241120","https://openalex.org/W2955750014","https://openalex.org/W2963673899","https://openalex.org/W1510302770","https://openalex.org/W3021853727"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,111,133],"present":[4],"an":[5,67],"initial":[6],"performance":[7,70,117,139],"evaluation":[8],"of":[9,29,46,51,56,71,116],"AMD":[10,18,99],"and":[11,20,48,53,95,105],"Intel's":[12],"first":[13],"quad-core":[14,63],"processor":[15,76,89,100],"offerings:":[16],"the":[17,21,27,82,87,98,124,136],"Barcelona":[19],"Intel":[22,88],"Xeon":[23],"X7350.":[24],"We":[25],"examine":[26],"suitability":[28],"these":[30],"processors":[31,64],"in":[32,69],"quad-socket":[33],"compute":[34],"nodes":[35],"as":[36],"building":[37],"blocks":[38],"for":[39],"large-scale":[40],"scientific":[41,59,109],"computing":[42],"clusters.":[43],"Our":[44],"analysis":[45],"intra-processor":[47],"intra-node":[49,106],"scalability":[50],"microbenchmarks":[52],"a":[54,91,114,129],"range":[55,115],"large-":[57],"scale":[58],"applications":[60,110],"indicates":[61],"that":[62,135],"can":[65],"deliver":[66],"improvement":[68],"up":[72,122],"to":[73,123],"4x":[74],"per":[75],"but":[77],"is":[78,140],"heavily":[79],"dependent":[80],"on":[81],"workload":[83],"being":[84],"processed.":[85],"While":[86],"has":[90,101],"higher":[92,102],"clock":[93],"rate":[94],"peak":[96],"performance,":[97],"memory":[103],"bandwidth":[104],"scalability.":[107],"The":[108],"analyzed":[112],"exhibit":[113],"improvements":[118],"from":[119],"only":[120],"3x":[121],"full":[125],"16x":[126],"speed-up":[127],"over":[128],"single":[130],"core.":[131],"Also,":[132],"note":[134],"maximum":[137],"node":[138],"not":[141],"necessarily":[142],"achieved":[143],"by":[144],"using":[145],"all":[146],"16":[147],"cores.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
