{"id":"https://openalex.org/W2024547254","doi":"https://doi.org/10.1145/1065944.1065964","title":"Exposing speculative thread parallelism in SPEC2000","display_name":"Exposing speculative thread parallelism in SPEC2000","publication_year":2005,"publication_date":"2005-06-15","ids":{"openalex":"https://openalex.org/W2024547254","doi":"https://doi.org/10.1145/1065944.1065964","mag":"2024547254"},"language":"en","primary_location":{"id":"doi:10.1145/1065944.1065964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065944.1065964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth 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/A5043131465","display_name":"Manohar K. Prabhu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Manohar K. Prabhu","raw_affiliation_strings":["Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023857198","display_name":"Kunle Olukotun","orcid":"https://orcid.org/0000-0002-8779-0636"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunle Olukotun","raw_affiliation_strings":["Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043131465"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":9.2331,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.98198105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"152"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991999864578247,"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":0.9990000128746033,"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":0.888534426689148},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.7757680416107178},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.741582989692688},{"id":"https://openalex.org/keywords/uniprocessor-system","display_name":"Uniprocessor system","score":0.732096791267395},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7188965082168579},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6564169526100159},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.6474241018295288},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.5916342735290527},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5613150596618652},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5606971383094788},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.5502016544342041},{"id":"https://openalex.org/keywords/implicit-parallelism","display_name":"Implicit parallelism","score":0.5452521443367004},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5232688188552856},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4474848210811615},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4434354305267334},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.44207754731178284},{"id":"https://openalex.org/keywords/automatic-parallelization","display_name":"Automatic parallelization","score":0.43569517135620117},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4278082549571991},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4252842366695404},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.374406635761261},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3046947121620178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.888534426689148},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.7757680416107178},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.741582989692688},{"id":"https://openalex.org/C79189994","wikidata":"https://www.wikidata.org/wiki/Q3488021","display_name":"Uniprocessor system","level":3,"score":0.732096791267395},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7188965082168579},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6564169526100159},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.6474241018295288},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.5916342735290527},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5613150596618652},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5606971383094788},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.5502016544342041},{"id":"https://openalex.org/C3543717","wikidata":"https://www.wikidata.org/wiki/Q6007302","display_name":"Implicit parallelism","level":4,"score":0.5452521443367004},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5232688188552856},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4474848210811615},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4434354305267334},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.44207754731178284},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.43569517135620117},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4278082549571991},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4252842366695404},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.374406635761261},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3046947121620178}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1065944.1065964","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1065944.1065964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.5903","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.5903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-hydra.stanford.edu/publications/PPoPP05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W49459401","https://openalex.org/W1977838359","https://openalex.org/W2000490573","https://openalex.org/W2029171059","https://openalex.org/W2053687647","https://openalex.org/W2064909421","https://openalex.org/W2088377490","https://openalex.org/W2095703459","https://openalex.org/W2100932767","https://openalex.org/W2105121389","https://openalex.org/W2106018697","https://openalex.org/W2119786518","https://openalex.org/W2120518487","https://openalex.org/W2127642645","https://openalex.org/W2131974229","https://openalex.org/W2143535196","https://openalex.org/W2146173591","https://openalex.org/W2146826599","https://openalex.org/W2151290553","https://openalex.org/W2161943885","https://openalex.org/W2163629952","https://openalex.org/W2168277865","https://openalex.org/W4229591902"],"related_works":["https://openalex.org/W2105992728","https://openalex.org/W2164738518","https://openalex.org/W4247496551","https://openalex.org/W2137185887","https://openalex.org/W4236721623","https://openalex.org/W1999531921","https://openalex.org/W1989479421","https://openalex.org/W1491993965","https://openalex.org/W2126220043","https://openalex.org/W2274823567"],"abstract_inverted_index":{"As":[0,39],"increasing":[1],"the":[2,22,33,48,74,81,122,124,133],"performance":[3,23,222],"of":[4,24,35,47,60,77,151,160,175],"single-threaded":[5],"processors":[6,12],"becomes":[7],"increasingly":[8],"difficult,":[9],"consumer":[10],"desktop":[11],"are":[13,72],"moving":[14],"toward":[15],"multi-core":[16],"designs.":[17],"One":[18],"way":[19],"to":[20,65,91,95,126,139,148,154,167,178,185,216],"enhance":[21],"chip":[25,231],"multiprocessors":[26],"that":[27,71,136,162,181],"has":[28],"received":[29],"considerable":[30],"attention":[31],"is":[32],"use":[34,59],"thread-level":[36,203],"speculation":[37],"(TLS).":[38],"a":[40,149,230],"case":[41],"study,":[42],"we":[43,86,113,198],"manually":[44],"parallelized":[45],"several":[46],"SPEC":[49],"CPU2000":[50],"floating":[51],"point":[52],"and":[53,68,116,132,157,188,220],"integer":[54],"applications":[55,97,180,228],"using":[56,130,193],"TLS.":[57,235],"The":[58],"manual":[61,194],"parallelization":[62,195],"enabled":[63],"us":[64],"apply":[66,93],"techniques":[67],"programmer":[69],"expertise":[70],"beyond":[73],"current":[75],"capabilities":[76],"automated":[78],"parallelizers.":[79],"With":[80],"experience":[82],"gained":[83],"from":[84,229],"this,":[85],"provide":[87,199],"insight":[88],"into":[89],"ways":[90],"aggressively":[92],"TLS":[94,108,155,168,186],"parallelize":[96],"for":[98],"high":[99],"performance.":[100,191],"This":[101],"information":[102],"can":[103,172,182,223],"help":[104,163],"guide":[105],"future":[106],"advanced":[107],"compiler":[109],"design.For":[110],"each":[111],"application,":[112,123],"discuss":[114],"how":[115,215],"where":[117,202],"parallelism":[118,129,166,204],"was":[119],"located":[120],"within":[121],"impediments":[125],"extracting":[127],"this":[128],"TLS,":[131],"code":[134],"transformations":[135],"were":[137],"required":[138],"overcome":[140],"these":[141,146,207,218,227],"impediments.":[142],"We":[143],"also":[144],"generalize":[145],"experiences":[147],"discussion":[150],"common":[152],"hindrances":[153],"parallelization,":[156],"describe":[158],"methods":[159],"programming":[161],"expose":[164],"application":[165],"systems.":[169],"These":[170],"guidelines":[171],"assist":[173],"developers":[174],"uniprocessor":[176],"programs":[177],"create":[179],"easily":[183],"port":[184],"systems":[187],"yield":[189],"good":[190],"By":[192],"on":[196,201,226],"SPEC2000,":[197],"guidance":[200],"exists":[205],"in":[206],"well":[208],"known":[209],"benchmarks,":[210],"what":[211,221],"limits":[212],"its":[213],"extraction,":[214],"reduce":[217],"limitations":[219],"be":[224],"expected":[225],"multiprocessor":[232],"system":[233],"with":[234]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}