{"id":"https://openalex.org/W2037303555","doi":"https://doi.org/10.1145/1369396.1369399","title":"Compiler and hardware support for reducing the synchronization of speculative threads","display_name":"Compiler and hardware support for reducing the synchronization of speculative threads","publication_year":2008,"publication_date":"2008-05-01","ids":{"openalex":"https://openalex.org/W2037303555","doi":"https://doi.org/10.1145/1369396.1369399","mag":"2037303555"},"language":"en","primary_location":{"id":"doi:10.1145/1369396.1369399","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1369396.1369399","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1369396.1369399","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/1369396.1369399","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053597061","display_name":"Antonia Zhai","orcid":"https://orcid.org/0000-0002-8921-1415"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Antonia Zhai","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN","University of Minnesota , Minneapolis, Mn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":"University of Minnesota , Minneapolis, Mn","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110755517","display_name":"J. Gregory Steffan","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J. Gregory Steffan","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031294241","display_name":"Christopher B. Colohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher B. Colohan","raw_affiliation_strings":["Google, Ann Arbor, Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Ann Arbor, Michigan","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076667915","display_name":"Todd C. Mowry","orcid":"https://orcid.org/0000-0003-4076-5684"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd C. Mowry","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, Pennsylvania","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053597061"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":4.1423,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94188331,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":"1","first_page":"1","last_page":"33"},"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/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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9983999729156494,"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":0.90191650390625},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8536187410354614},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.6526395082473755},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6453196406364441},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6176437139511108},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6129325032234192},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.5726592540740967},{"id":"https://openalex.org/keywords/speculation","display_name":"Speculation","score":0.546096920967102},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5192182660102844},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.48599013686180115},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.42786264419555664},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3420245051383972},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32037490606307983},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.29375159740448},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09690266847610474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.90191650390625},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8536187410354614},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.6526395082473755},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6453196406364441},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6176437139511108},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6129325032234192},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.5726592540740967},{"id":"https://openalex.org/C47941915","wikidata":"https://www.wikidata.org/wiki/Q107885","display_name":"Speculation","level":2,"score":0.546096920967102},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5192182660102844},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.48599013686180115},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.42786264419555664},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3420245051383972},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32037490606307983},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.29375159740448},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09690266847610474},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1369396.1369399","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1369396.1369399","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1369396.1369399","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.190.618","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.190.618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecg.toronto.edu/%7Esteffan/papers/zhai_taco08.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/1369396.1369399","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1369396.1369399","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/1369396.1369399","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2037303555.pdf","grobid_xml":"https://content.openalex.org/works/W2037303555.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W23693130","https://openalex.org/W79448102","https://openalex.org/W121029738","https://openalex.org/W1517128672","https://openalex.org/W1525227808","https://openalex.org/W1971965803","https://openalex.org/W1980999196","https://openalex.org/W1990199656","https://openalex.org/W2002219828","https://openalex.org/W2002549773","https://openalex.org/W2024547254","https://openalex.org/W2025317174","https://openalex.org/W2036918610","https://openalex.org/W2037462607","https://openalex.org/W2038198320","https://openalex.org/W2052285774","https://openalex.org/W2095703459","https://openalex.org/W2097230158","https://openalex.org/W2100184706","https://openalex.org/W2103224933","https://openalex.org/W2105121389","https://openalex.org/W2106018697","https://openalex.org/W2107782879","https://openalex.org/W2109502721","https://openalex.org/W2112438883","https://openalex.org/W2112833506","https://openalex.org/W2115543521","https://openalex.org/W2119452361","https://openalex.org/W2119786518","https://openalex.org/W2120518487","https://openalex.org/W2122842533","https://openalex.org/W2122939826","https://openalex.org/W2127642645","https://openalex.org/W2129523505","https://openalex.org/W2129962996","https://openalex.org/W2135470015","https://openalex.org/W2136798749","https://openalex.org/W2148555526","https://openalex.org/W2150547581","https://openalex.org/W2154693467","https://openalex.org/W2161943885","https://openalex.org/W2164393230","https://openalex.org/W2165856991","https://openalex.org/W2170659171","https://openalex.org/W2186799393","https://openalex.org/W2241877410","https://openalex.org/W2294451725","https://openalex.org/W2296006986","https://openalex.org/W2537115708","https://openalex.org/W2597339580","https://openalex.org/W2747214356","https://openalex.org/W4236604678","https://openalex.org/W4251828973","https://openalex.org/W4252742548","https://openalex.org/W4253172818","https://openalex.org/W4253355920","https://openalex.org/W4255946289","https://openalex.org/W6679392711"],"related_works":["https://openalex.org/W4244698026","https://openalex.org/W2104477546","https://openalex.org/W1601330807","https://openalex.org/W2110897014","https://openalex.org/W2179235191","https://openalex.org/W1968409088","https://openalex.org/W2127642645","https://openalex.org/W2759759","https://openalex.org/W1749933618","https://openalex.org/W2187874404"],"abstract_inverted_index":{"Thread-level":[0],"speculation":[1],"(TLS)":[2],"allows":[3],"us":[4],"to":[5,72,138],"automatically":[6,67],"parallelize":[7],"general-purpose":[8],"programs":[9],"by":[10,69,118],"supporting":[11],"parallel":[12],"execution":[13],"of":[14,31,41,91,123],"threads":[15,49],"that":[16,50,64,96,129,142],"might":[17],"not":[18,152],"actually":[19],"be":[20,136],"independent.":[21],"In":[22],"this":[23],"article,":[24],"we":[25,75],"focus":[26],"on":[27],"one":[28],"important":[29],"limitation":[30],"program":[32],"performance":[33,145],"under":[34],"TLS,":[35,74],"which":[36],"stalls":[37],"as":[38],"a":[39],"result":[40],"synchronizing":[42],"and":[43,80,84,121,149],"forwarding":[44,115,122],"scalar":[45,92,124],"values":[46],"between":[47],"speculative":[48],"would":[51],"otherwise":[52],"cause":[53],"frequent":[54],"data":[55],"dependences":[56],"and,":[57],"hence,":[58],"failed":[59],"speculation.":[60],"Using":[61],"SPECint":[62],"benchmarks":[63],"have":[65],"been":[66],"transformed":[68],"our":[70,98],"compiler":[71,83,109,139],"exploit":[73],"present,":[76],"evaluate":[77],"in":[78],"detail,":[79],"compare":[81],"both":[82],"hardware":[85,130],"techniques":[86,131],"for":[87,101,132],"improving":[88],"the":[89,108,113,119,143,154],"communication":[90],"values.":[93,125],"We":[94,126],"find":[95],"through":[97],"dataflow":[99],"algorithms":[100],"three":[102],"increasingly":[103],"aggressive":[104],"instruction":[105],"scheduling":[106],"techniques,":[107],"can":[110,135],"drastically":[111],"reduce":[112],"critical":[114],"path":[116],"introduced":[117],"synchronization":[120,134],"also":[127],"show":[128],"reducing":[133],"complementary":[137],"scheduling,":[140],"but":[141],"additional":[144],"benefits":[146],"are":[147,150],"minimal":[148],"generally":[151],"worth":[153],"cost.":[155]},"counts_by_year":[{"year":2022,"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":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
