{"id":"https://openalex.org/W2116288740","doi":"https://doi.org/10.1109/ispass.2005.1430566","title":"Partitioning Multi-Threaded Processors with a Large Number of Threads","display_name":"Partitioning Multi-Threaded Processors with a Large Number of Threads","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2116288740","doi":"https://doi.org/10.1109/ispass.2005.1430566","mag":"2116288740"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2005.1430566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2005.1430566","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 Performance Analysis of Systems and Software, 2005. ISPASS 2005.","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":null,"display_name":"A. El-Moursy","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. El-Moursy","raw_affiliation_strings":["Departments of Electrical and Computer Engineering and of Computer Science, University of Rochester, USA","Dept. of Electr. & Comput. Eng.,, Rochester Univ., NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Electrical and Computer Engineering and of Computer Science, University of Rochester, USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng.,, Rochester Univ., NY","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100882757","display_name":"Rajeev Garg","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Garg","raw_affiliation_strings":["Departments of Electrical and Computer Engineering and of Computer Science, University of Rochester, USA","Dept. of Electr. & Comput. Eng.,, Rochester Univ., NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Electrical and Computer Engineering and of Computer Science, University of Rochester, USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng.,, Rochester Univ., NY","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009386140","display_name":"David H. Albonesi","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.H. Albonesi","raw_affiliation_strings":["Computer Systems Laboratory, Cornell University, USA","University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Systems Laboratory, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013232946","display_name":"Sandhya Dwarkadas","orcid":"https://orcid.org/0000-0003-2631-8191"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Dwarkadas","raw_affiliation_strings":["Departments of Electrical and Computer Engineering and of Computer Science, University of Rochester, USA","Cornell University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departments of Electrical and Computer Engineering and of Computer Science, University of Rochester, USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"112","last_page":"123"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8300455212593079},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.688223123550415},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6448051929473877},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.6287371516227722},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6023850440979004},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.49883365631103516},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.44912150502204895},{"id":"https://openalex.org/keywords/branch-predictor","display_name":"Branch predictor","score":0.44788262248039246},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.4315645396709442},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.41553497314453125},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.4125669002532959},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3997144103050232},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36628973484039307},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.3626693785190582},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.33036696910858154},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.32696235179901123},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2682199478149414}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300455212593079},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.688223123550415},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6448051929473877},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.6287371516227722},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6023850440979004},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.49883365631103516},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.44912150502204895},{"id":"https://openalex.org/C168522837","wikidata":"https://www.wikidata.org/wiki/Q679552","display_name":"Branch predictor","level":2,"score":0.44788262248039246},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.4315645396709442},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.41553497314453125},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.4125669002532959},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3997144103050232},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36628973484039307},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3626693785190582},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.33036696910858154},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.32696235179901123},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2682199478149414},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ispass.2005.1430566","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2005.1430566","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 Performance Analysis of Systems and Software, 2005. ISPASS 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.121.1475","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.121.1475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csl.cornell.edu/~albonesi/research/papers/ispass05_1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.2710","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.2710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.rochester.edu/u/sandhya/papers/ispass05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1608995421","https://openalex.org/W2006610758","https://openalex.org/W2032094184","https://openalex.org/W2035872164","https://openalex.org/W2058997312","https://openalex.org/W2084619442","https://openalex.org/W2101084218","https://openalex.org/W2102081731","https://openalex.org/W2102727118","https://openalex.org/W2106625514","https://openalex.org/W2114421447","https://openalex.org/W2116020886","https://openalex.org/W2118532220","https://openalex.org/W2120230074","https://openalex.org/W2122939826","https://openalex.org/W2127000835","https://openalex.org/W2129548165","https://openalex.org/W2130838728","https://openalex.org/W2138351227","https://openalex.org/W2138708064","https://openalex.org/W2140200206","https://openalex.org/W2143322909","https://openalex.org/W2145871983","https://openalex.org/W2147796461","https://openalex.org/W2147943147","https://openalex.org/W2153536983","https://openalex.org/W2154512574","https://openalex.org/W2158398871","https://openalex.org/W2161864047","https://openalex.org/W2249344705","https://openalex.org/W2294451725","https://openalex.org/W2296006986","https://openalex.org/W2532467869","https://openalex.org/W3140903683","https://openalex.org/W3142147837","https://openalex.org/W3148484433","https://openalex.org/W4235505870","https://openalex.org/W4235861380","https://openalex.org/W4236258190","https://openalex.org/W4237941914","https://openalex.org/W4247115961","https://openalex.org/W4247264372","https://openalex.org/W4251468890","https://openalex.org/W4251852027","https://openalex.org/W4252062241","https://openalex.org/W4253401904","https://openalex.org/W4253546582","https://openalex.org/W6636146310","https://openalex.org/W6679308475","https://openalex.org/W6680696677","https://openalex.org/W6681022782","https://openalex.org/W6681352259","https://openalex.org/W6792941224","https://openalex.org/W6793277613","https://openalex.org/W6817363484"],"related_works":["https://openalex.org/W2118532220","https://openalex.org/W4240807263","https://openalex.org/W2366153089","https://openalex.org/W2913446311","https://openalex.org/W1532726325","https://openalex.org/W2354938433","https://openalex.org/W1576844086","https://openalex.org/W2150450196","https://openalex.org/W1558769186","https://openalex.org/W1965694280"],"abstract_inverted_index":{"Today's":[0],"general-purpose":[1],"processors":[2,116,254,262],"are":[3],"increasingly":[4],"using":[5],"multithreading":[6],"in":[7,169],"order":[8],"to":[9,117,131],"better":[10],"leverage":[11],"the":[12,48,60,137,147,156,165,178,185,188,193,199,205,209,248,268],"additional":[13],"on-chip":[14],"real":[15],"estate":[16],"available":[17],"with":[18,34],"each":[19,80],"technology":[20],"generation.":[21],"Simultaneous":[22],"multi-threading":[23],"(SMT)":[24],"was":[25],"originally":[26],"proposed":[27],"as":[28,162,164],"a":[29,65,72,106,170,219,245,258,263],"large":[30,215],"dynamic":[31],"superscalar":[32],"processor":[33,46,70,97,221],"monolithic":[35,216],"hardware":[36],"structures":[37,50,63],"shared":[38],"among":[39,51,196],"all":[40],"threads.":[41,197],"Inters":[42],"hyper-threaded":[43],"Pentium":[44],"4":[45],"partitions":[47],"queue":[49],"two":[52],"threads,":[53,83],"demonstrating":[54],"more":[55,237,241],"balanced":[56],"performance":[57,180,226],"by":[58,64,183],"reducing":[59],"hoarding":[61],"of":[62,77,103,140,143,187,204,230,232,260],"single":[66],"thread.":[67],"IBM's":[68],"Power5":[69],"is":[71,181,208],"2-way":[73],"chip":[74],"multiprocessor":[75],"(CMP)":[76],"SMT":[78,217,234,251],"processors,":[79,218],"supporting":[81],"2":[82],"which":[84],"significantly":[85],"reduces":[86],"design":[87,120,138],"complexity":[88],"and":[89,114,124,145,154,159,192,239,252],"can":[90],"improve":[91],"power":[92,122,242],"efficiency.":[93],"This":[94],"paper":[95],"examines":[96],"partitioning":[98,144],"options":[99],"for":[100,267],"larger":[101],"numbers":[102],"threads":[104],"on":[105,227],"chip.":[107],"While":[108],"growing":[109],"transistor":[110],"budgets":[111],"permit":[112],"four":[113],"eight-thread":[115],"be":[118],"designed,":[119],"complexity,":[121],"dissipation,":[123],"wire":[125],"scaling":[126],"limitations":[127],"create":[128],"significant":[129,202],"barriers":[130],"their":[132],"actual":[133],"realization.":[134],"We":[135,175],"explore":[136],"choices":[139],"sharing,":[141],"or":[142],"distributing,":[146],"front":[148],"end":[149],"(instruction":[150],"cache,":[151],"instruction":[152],"fetch,":[153],"dispatch),":[155],"execution":[157,194],"units":[158],"associated":[160],"state,":[161],"well":[163],"L1":[166,189],"Dcache":[167,190],"banks,":[168],"clustered":[171],"multi-threaded":[172],"(CMT)":[173],"processor.":[174],"show":[176],"that":[177,231],"best":[179,210],"obtained":[182],"restricting":[184],"sharing":[186,203],"banks":[191],"engines":[195],"On":[198],"other":[200],"hand,":[201],"front-end":[206],"resources":[207],"approach.":[211],"When":[212],"compared":[213],"against":[214],"CMT":[220,253,261],"provides":[222],"very":[223],"competitive":[224],"IPC":[225],"average,":[228],"90-96%":[229],"partitioned":[233],"while":[235],"being":[236],"scalable":[238],"much":[240],"efficient.":[243],"In":[244],"CMP":[246,259],"organization,":[247],"gap":[249],"between":[250],"shrinks":[255],"further,":[256],"making":[257],"highly":[264],"viable":[265],"alternative":[266],"future":[269]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}