{"id":"https://openalex.org/W4235388166","doi":"https://doi.org/10.1109/cgo.2004.1281662","title":"Compiler optimization of memory-resident value communication between speculative threads","display_name":"Compiler optimization of memory-resident value communication between speculative threads","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W4235388166","doi":"https://doi.org/10.1109/cgo.2004.1281662"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2004.1281662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2004.1281662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium on Code Generation and Optimization, 2004. CGO 2004.","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/A5053597061","display_name":"Antonia Zhai","orcid":"https://orcid.org/0000-0002-8921-1415"},"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":true,"raw_author_name":"Antonia Zhai","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063294382","display_name":"C.B. Colohan","orcid":null},"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":"C.B. Colohan","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011672979","display_name":"J.G. 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.G. Steffan","raw_affiliation_strings":["Department of Electrical & Computer Engineering, University of Toronto, Toronto, ONT, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of Toronto, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053597061"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.0597,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.78360215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"50"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9979000091552734,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973000288009644,"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":0.8666221499443054},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7672284245491028},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7460813522338867},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.698573887348175},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.689643144607544},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.48785924911499023},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.46741724014282227},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.46013373136520386},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29592055082321167},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.2353396713733673},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09537801146507263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8666221499443054},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7672284245491028},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7460813522338867},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.698573887348175},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.689643144607544},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.48785924911499023},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.46741724014282227},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.46013373136520386},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29592055082321167},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.2353396713733673},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09537801146507263},{"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/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"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":1,"locations":[{"id":"doi:10.1109/cgo.2004.1281662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2004.1281662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Symposium on Code Generation and Optimization, 2004. CGO 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1524877046","https://openalex.org/W1525227808","https://openalex.org/W1536051636","https://openalex.org/W1593436246","https://openalex.org/W1979582240","https://openalex.org/W1990008205","https://openalex.org/W2002219828","https://openalex.org/W2002549773","https://openalex.org/W2009264559","https://openalex.org/W2105121389","https://openalex.org/W2105768184","https://openalex.org/W2106018697","https://openalex.org/W2109502721","https://openalex.org/W2112833506","https://openalex.org/W2122425694","https://openalex.org/W2122751766","https://openalex.org/W2136798749","https://openalex.org/W2148255965","https://openalex.org/W2148390433","https://openalex.org/W2161943885","https://openalex.org/W2914074464","https://openalex.org/W3136337477","https://openalex.org/W4234966451","https://openalex.org/W4244227015","https://openalex.org/W4245971498","https://openalex.org/W4247496551","https://openalex.org/W4251852027","https://openalex.org/W6631413207","https://openalex.org/W6650841601","https://openalex.org/W6674371507","https://openalex.org/W6675852564","https://openalex.org/W6728779937"],"related_works":["https://openalex.org/W2023832055","https://openalex.org/W3089467468","https://openalex.org/W2082485924","https://openalex.org/W2105895556","https://openalex.org/W2213849224","https://openalex.org/W2002505081","https://openalex.org/W1985089255","https://openalex.org/W2115561485","https://openalex.org/W2083681681","https://openalex.org/W2577630842"],"abstract_inverted_index":{"Efficient":[0],"inter-thread":[1],"value":[2,18,47,107],"communication":[3,19,48,108],"is":[4,27],"essential":[5],"for":[6,16,56,109,132],"improving":[7,17],"performance":[8,91],"in":[9],"thread-level":[10],"speculation":[11],"(TLS).":[12],"Although":[13],"several":[14],"mechanisms":[15],"using":[20,119],"hardware":[21,74],"support":[22],"have":[23],"been":[24],"proposed,":[25],"there":[26],"relatively":[28],"little":[29],"work":[30],"on":[31,39,42],"exploiting":[32],"the":[33,57,72,120,151,166],"potential":[34],"of":[35,45,59,153],"compiler":[36,43,54,121],"optimization.":[37],"Building":[38],"recent":[40],"research":[41],"optimization":[44,58],"scalar":[46],"between":[49,158],"speculative":[50,80],"threads,":[51],"we":[52,147],"propose":[53,118],"techniques":[55,168],"memory-resident":[60,67,126],"values.":[61],"In":[62,105],"TLS,":[63],"data":[64,100,111,127,145],"dependences":[65,101,112,146],"through":[66],"values":[68,134],"are":[69,103,169],"tracked":[70],"by":[71,77,142],"underlying":[73],"and":[75,93,160],"preserved":[76],"re-executing":[78],"any":[79],"thread":[81],"that":[82,102,141,165],"violates":[83],"a":[84,89],"dependence;":[85],"however,":[86],"re-execution":[87],"incurs":[88],"large":[90],"penalty":[92],"should":[94],"be":[95,114],"used":[96],"only":[97],"to":[98,122,135],"resolve":[99],"infrequent.":[104],"contrast,":[106],"frequently-occurring":[110,125,144],"must":[113],"very":[115],"efficient.":[116],"We":[117,139],"first":[123],"identify":[124],"dependences,":[128],"then":[129],"insert":[130],"synchronization":[131,163],"communicating":[133],"preserve":[136],"these":[137],"dependences.":[138],"find":[140],"synchronizing":[143],"can":[148],"significantly":[149],"improve":[150],"efficiency":[152],"parallel":[154],"execution.":[155],"A":[156],"comparison":[157],"compiler-inserted":[159],"hardware-inserted":[161],"memory":[162],"reveals":[164],"two":[167],"complementary,":[170],"with":[171],"each":[172],"technique":[173],"benefitting":[174],"different":[175],"benchmarks.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}