{"id":"https://openalex.org/W2012282434","doi":"https://doi.org/10.1109/iiswc.2010.5650174","title":"Performance of multi-process and multi-thread processing on multi-core SMT processors","display_name":"Performance of multi-process and multi-thread processing on multi-core SMT processors","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2012282434","doi":"https://doi.org/10.1109/iiswc.2010.5650174","mag":"2012282434"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc.2010.5650174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2010.5650174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on Workload Characterization (IISWC'10)","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/A5101774031","display_name":"Hiroshi Inoue","orcid":"https://orcid.org/0000-0002-8238-0371"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Hiroshi Inoue","raw_affiliation_strings":["IBM Research, Tokyo Research Laboratory, Kanagawa, Japan","IBM Research - Tokyo, Kanagawa-ken 242-0001 Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research - Tokyo, Kanagawa-ken 242-0001 Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006642369","display_name":"Toshio Nakatani","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Toshio Nakatani","raw_affiliation_strings":["IBM Research, Tokyo Research Laboratory, Kanagawa, Japan","IBM Research - Tokyo, Kanagawa-ken 242-0001 Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, Tokyo Research Laboratory, Kanagawa, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research - Tokyo, Kanagawa-ken 242-0001 Japan#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9991999864578247,"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":0.8490520715713501},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8118184208869934},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.7399301528930664},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7056033611297607},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6804493069648743},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6025202870368958},{"id":"https://openalex.org/keywords/allocator","display_name":"Allocator","score":0.5667977333068848},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.5165928602218628},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.4753824472427368},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.47504687309265137},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.4524215757846832},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.4487341046333313},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39462602138519287},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.36482951045036316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8490520715713501},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8118184208869934},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.7399301528930664},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7056033611297607},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6804493069648743},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6025202870368958},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.5667977333068848},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.5165928602218628},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.4753824472427368},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.47504687309265137},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.4524215757846832},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.4487341046333313},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39462602138519287},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.36482951045036316}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iiswc.2010.5650174","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2010.5650174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on Workload Characterization (IISWC'10)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.207.5216","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.207.5216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.trl.ibm.com/trl/people/inouehrs/pdf/IISWC2010_inoue.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.4300000071525574,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2022740893","https://openalex.org/W2095594115","https://openalex.org/W2100506425","https://openalex.org/W2120230074","https://openalex.org/W2149085464","https://openalex.org/W2165500483","https://openalex.org/W2182205977","https://openalex.org/W2465756754","https://openalex.org/W2467941640","https://openalex.org/W2532326028","https://openalex.org/W2545500460","https://openalex.org/W3142147837","https://openalex.org/W6681764175","https://openalex.org/W6685712386","https://openalex.org/W6720124463","https://openalex.org/W6728936925"],"related_works":["https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W1974923383","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2090306017","https://openalex.org/W2003336045"],"abstract_inverted_index":{"Many":[0],"modern":[1],"high-performance":[2],"processors":[3],"support":[4],"multiple":[5,12,68,72,166],"hardware":[6,81,224],"threads":[7,36,73,225],"in":[8,37,74,99],"the":[9,28,53,60,117,126,131,150,162,174,199,223,229,233,240,246],"form":[10],"of":[11,23,30,80,133,173,198,222],"cores":[13,31,167],"and":[14,34,70,85,93,109,136,207,243],"SMT":[15,35,55,86,122,192],"(Simultaneous":[16],"Multi-Threading).":[17],"Hence":[18],"achieving":[19],"good":[20],"performance":[21,51,61,247],"scalability":[22,62,84,123],"programs":[24],"with":[25,63],"respect":[26],"to":[27,48,125,155,186,239],"numbers":[29],"(core":[32,83],"scalability)":[33,41],"one":[38,75],"core":[39,145,200],"(SMT":[40],"is":[42,196,202],"critical.":[43],"To":[44,170],"identify":[45],"a":[46,94,179,183,227],"way":[47],"achieve":[49,142],"higher":[50],"on":[52,77,101,190,226],"multi-core":[54,191],"processors,":[56],"this":[57],"paper":[58],"compares":[59],"two":[64,78,102],"parallelization":[65],"models":[66,141],"(using":[67],"processes":[69],"using":[71,220],"process)":[76],"types":[79],"parallelism":[82],"scalability).":[87],"We":[88,114,147],"tested":[89],"standard":[90],"Java":[91],"benchmarks":[92],"real-world":[95],"server":[96],"program":[97],"written":[98],"PHP":[100,184],"platforms,":[103],"Sun's":[104],"UltraSPARC":[105],"T1":[106],"(Niagara)":[107],"processor":[108,217],"Intel's":[110],"Xeon":[111],"(Nehalem)":[112],"processor.":[113],"show":[115,148],"that":[116,149,201],"multi-thread":[118,151],"model":[119,128,152,164],"achieves":[120],"better":[121],"compared":[124,238],"multi-process":[127,163],"by":[129,236,248],"reducing":[130],"number":[132],"cache":[134],"misses":[135,160,189,235],"DTLB":[137,159,188,234],"misses.":[138],"However":[139],"both":[140,175],"roughly":[143],"equal":[144],"scalability.":[146],"generates":[153],"up":[154],"7.4":[156],"times":[157],"more":[158],"than":[161],"when":[165],"are":[168],"used.":[169],"take":[171],"advantage":[172],"models,":[176],"we":[177],"implemented":[178],"memory":[180,209,213],"allocator":[181,195,231],"for":[182,215],"runtime":[185],"reduce":[187],"processors.":[193],"The":[194],"aware":[197],"running":[203],"each":[204,216],"software":[205],"thread":[206],"allocates":[208],"blocks":[210],"from":[211],"same":[212],"page":[214],"core.":[218],"When":[219],"all":[221],"Niagara,":[228],"core-aware":[230],"reduces":[232],"46.7%":[237],"default":[241],"allocator,":[242],"it":[244],"improves":[245],"3.0%.":[249]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}