{"id":"https://openalex.org/W2023128081","doi":"https://doi.org/10.1145/1229428.1229474","title":"Speculative thread decomposition through empirical optimization","display_name":"Speculative thread decomposition through empirical optimization","publication_year":2007,"publication_date":"2007-03-14","ids":{"openalex":"https://openalex.org/W2023128081","doi":"https://doi.org/10.1145/1229428.1229474","mag":"2023128081"},"language":"en","primary_location":{"id":"doi:10.1145/1229428.1229474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1229428.1229474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGPLAN symposium on Principles and practice of parallel programming","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/A5112225524","display_name":"Troy A. Johnson","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Troy A. Johnson","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045622261","display_name":"Rudolf Eigenmann","orcid":"https://orcid.org/0000-0003-1651-827X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudolf Eigenmann","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103145581","display_name":"T. N. Vijaykumar","orcid":"https://orcid.org/0000-0001-6624-4372"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. N. Vijaykumar","raw_affiliation_strings":["Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1398,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.93659749,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"205","last_page":"214"},"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":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9944000244140625,"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":0.8400760889053345},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.8128960132598877},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.690243124961853},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5988848209381104},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.48012399673461914},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.44938933849334717},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.44681432843208313},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.441069632768631},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3703363537788391},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24010232090950012},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16338741779327393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400760889053345},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.8128960132598877},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.690243124961853},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5988848209381104},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.48012399673461914},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.44938933849334717},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.44681432843208313},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.441069632768631},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3703363537788391},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24010232090950012},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16338741779327393},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1229428.1229474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1229428.1229474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1355","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/364","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7900000214576721,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W143088316","https://openalex.org/W188832472","https://openalex.org/W277936934","https://openalex.org/W1525227808","https://openalex.org/W1548567038","https://openalex.org/W1579674405","https://openalex.org/W1920053666","https://openalex.org/W1920457490","https://openalex.org/W1974831646","https://openalex.org/W1986926028","https://openalex.org/W2000490573","https://openalex.org/W2010220656","https://openalex.org/W2011060258","https://openalex.org/W2024547254","https://openalex.org/W2040466547","https://openalex.org/W2044280736","https://openalex.org/W2047301304","https://openalex.org/W2078429521","https://openalex.org/W2081656192","https://openalex.org/W2083868341","https://openalex.org/W2103224933","https://openalex.org/W2105897359","https://openalex.org/W2106018697","https://openalex.org/W2110652915","https://openalex.org/W2111678563","https://openalex.org/W2115351238","https://openalex.org/W2116210226","https://openalex.org/W2119786518","https://openalex.org/W2120518487","https://openalex.org/W2122059338","https://openalex.org/W2122545654","https://openalex.org/W2125340270","https://openalex.org/W2131867938","https://openalex.org/W2135992106","https://openalex.org/W2136798749","https://openalex.org/W2148339733","https://openalex.org/W2150547581","https://openalex.org/W2168618049","https://openalex.org/W2294451725","https://openalex.org/W2296006986","https://openalex.org/W2912452116","https://openalex.org/W4229591902","https://openalex.org/W4292003697","https://openalex.org/W6670936421"],"related_works":["https://openalex.org/W4252501555","https://openalex.org/W2003848320","https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W4246454774","https://openalex.org/W2162051035"],"abstract_inverted_index":{"Chip":[0],"multiprocessors":[1],"(CMPs),":[2],"or":[3],"multi-core":[4],"processors,":[5],"have":[6],"become":[7],"a":[8,30,45,108,155,159,162,193,281,299,302,320,325,335],"common":[9],"way":[10],"of":[11,75,90,122,165,196,246,257,280,331,343,350],"reducing":[12,100],"chip":[13],"complexity":[14,149],"and":[15,80,150,173,202,224,251,312],"power":[16],"consumption":[17],"while":[18,103],"maintaining":[19],"high":[20],"performance.":[21],"Speculative":[22],"CMPs":[23],"use":[24],"hardware":[25,137],"to":[26,33,39,52,70,168,221,242,284,358],"enforce":[27],"dependence,":[28,77],"allowing":[29,329],"parallelizing":[31],"compiler":[32,160],"generate":[34],"multithreaded":[35],"code":[36],"without":[37],"needing":[38],"prove":[40],"independence.":[41],"In":[42],"these":[43,84],"systems,":[44],"sequential":[46],"program":[47],"is":[48,107,127,143,186,261],"decomposed":[49],"into":[50,188],"threads":[51,58,92,106,172,177,241,290],"be":[53],"executed":[54],"in":[55,136,264,298],"parallel;":[56],"dependent":[57],"cause":[59],"performance":[60],"degradation,":[61],"but":[62,126,142],"do":[63],"not":[64,204],"affect":[65],"correctness.":[66],"Thread":[67],"decomposition":[68,113,135,147,185,206,233,259],"attempts":[69],"reduce":[71],"the":[72,88,91,98,101,105,119,123,130,146,166,175,179,189,197,232,247,258,273,277,285,294,332,351],"run-time":[73,140,151,278],"overheads":[74,85,102],"data":[76],"thread":[78,282,295,304,322],"misprediction,":[79],"load":[81],"imbalance.":[82],"Because":[83,237],"depend":[86],"on":[87,289,345],"runtimes":[89],"that":[93,192,276,291,319],"are":[94],"being":[95],"created":[96],"by":[97,117,129,145,215,230],"decomposition,":[99],"creating":[104],"circular":[109],"problem.":[110],"Static":[111],"compile-time":[112],"handles":[114],"this":[115,269],"problem":[116,214],"estimating":[118],"run":[120,164,181,195],"times":[121,220],"candidate":[124,171,240],"threads,":[125,223,328],"limited":[128,144],"estimates'":[131],"inaccuracy.":[132],"Dynamic":[133],"execution-time":[134],"has":[138,199],"better":[139],"information,":[141],"hardware's":[148],"overhead.":[152,207],"We":[153,208,362],"propose":[154],"third":[156],"approach":[157],"where":[158],"instruments":[161],"profile":[163,180,235,265],"application":[167,190,198],"search":[169,256],"through":[170],"pick":[174,222],"best":[176],"as":[178],"executes.":[182],"The":[183],"resultant":[184],"compiled":[187],"so":[191],"production":[194],"no":[200],"instrumentation":[201],"does":[203],"incurany":[205],"avoid":[209,226],"static":[210,360],"decomposition's":[211,228],"estimation":[212],"accuracy":[213],"using":[216],"actual":[217],"profile-run":[218],"execution":[219],"we":[225,238,271,338],"dynamic":[227],"overhead":[229,279],"performing":[231],"at":[234,308],"time.":[236],"allow":[239],"span":[243],"arbitrary":[244],"sections":[245],"application's":[248],"call":[249],"graph":[250],"loop":[252],"nests,":[253],"an":[254,340],"exhaustive":[255],"space":[260],"prohibitive,":[262],"even":[263],"runs.":[266],"To":[267],"address":[268],"issue,":[270],"make":[272],"key":[274],"observation":[275,317],"depends,":[283],"first":[286],"order,":[287],"only":[288,324],"overlap":[292,306],"with":[293,307,366],"inexecution":[296],"(e.g.,":[297],"four-core":[300],"CMP,":[301],"given":[303,321],"can":[305],"most":[309],"three":[310,313],"preceding":[311],"following":[314],"threads).":[315],"This":[316],"implies":[318],"affects":[323],"few":[326],"other":[327],"pruning":[330],"space.":[333],"Using":[334],"CMP":[336],"simulator,":[337],"achieve":[339],"average":[341],"speedup":[342],"3.51":[344],"four":[346],"cores":[347],"for":[348],"five":[349],"SPEC":[352],"CFP2000":[353],"benchmarks,":[354],"which":[355],"compares":[356],"favorably":[357],"recent":[359],"techniques.":[361],"also":[363],"discuss":[364],"experiments":[365],"CINT2000.":[367]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
