{"id":"https://openalex.org/W2143236775","doi":"https://doi.org/10.1109/icpp.2003.1240629","title":"Aggressive compiler optimization and parallelization with thread-level speculation","display_name":"Aggressive compiler optimization and parallelization with thread-level speculation","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2143236775","doi":"https://doi.org/10.1109/icpp.2003.1240629","mag":"2143236775"},"language":"en","primary_location":{"id":"doi:10.1109/icpp.2003.1240629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2003.1240629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Parallel Processing, 2003. Proceedings.","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":"https://openalex.org/A5101706560","display_name":"Liling Chen","orcid":"https://orcid.org/0000-0002-3062-5568"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Ling Chen","raw_affiliation_strings":["Intel Laboratories, Intel Corporation, Santa Clara, CA, USA","Intel Labs., Intel Corp., Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Labs., Intel Corp., Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101174906","display_name":"Youfeng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youfeng Wu","raw_affiliation_strings":["Intel Laboratories, Intel Corporation, Santa Clara, CA, USA","Intel Labs., Intel Corp., Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Laboratories, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Labs., Intel Corp., Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"607","last_page":"614"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8921182155609131},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7867244482040405},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.7397958040237427},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7372459173202515},{"id":"https://openalex.org/keywords/speculative-execution","display_name":"Speculative execution","score":0.6257325410842896},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5610856413841248},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.5053547024726868},{"id":"https://openalex.org/keywords/automatic-parallelization","display_name":"Automatic parallelization","score":0.5038170218467712},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.47403645515441895},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4703298509120941},{"id":"https://openalex.org/keywords/branch-predictor","display_name":"Branch predictor","score":0.4477092921733856},{"id":"https://openalex.org/keywords/just-in-time-compilation","display_name":"Just-in-time compilation","score":0.42581599950790405},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2619791030883789},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.25320154428482056},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.15203148126602173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8921182155609131},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7867244482040405},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.7397958040237427},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7372459173202515},{"id":"https://openalex.org/C141331961","wikidata":"https://www.wikidata.org/wiki/Q2164465","display_name":"Speculative execution","level":2,"score":0.6257325410842896},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5610856413841248},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.5053547024726868},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.5038170218467712},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.47403645515441895},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4703298509120941},{"id":"https://openalex.org/C168522837","wikidata":"https://www.wikidata.org/wiki/Q679552","display_name":"Branch predictor","level":2,"score":0.4477092921733856},{"id":"https://openalex.org/C76782552","wikidata":"https://www.wikidata.org/wiki/Q110546","display_name":"Just-in-time compilation","level":3,"score":0.42581599950790405},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2619791030883789},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.25320154428482056},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.15203148126602173}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpp.2003.1240629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2003.1240629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Parallel Processing, 2003. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1525227808","https://openalex.org/W1557792566","https://openalex.org/W1969834826","https://openalex.org/W1990349513","https://openalex.org/W2029479717","https://openalex.org/W2031487553","https://openalex.org/W2063255488","https://openalex.org/W2099018580","https://openalex.org/W2103224933","https://openalex.org/W2113617109","https://openalex.org/W2122545654","https://openalex.org/W2129962996","https://openalex.org/W2135470015","https://openalex.org/W2164795104","https://openalex.org/W3151299008","https://openalex.org/W4237994905","https://openalex.org/W4241739990","https://openalex.org/W4245971498","https://openalex.org/W4247496551","https://openalex.org/W4249725883","https://openalex.org/W4251862023","https://openalex.org/W6633400640"],"related_works":["https://openalex.org/W2897302968","https://openalex.org/W44766235","https://openalex.org/W2034886984","https://openalex.org/W2139338109","https://openalex.org/W2006417047","https://openalex.org/W3103215994","https://openalex.org/W2005952754","https://openalex.org/W2039947876","https://openalex.org/W33516859","https://openalex.org/W4249960043"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,158],"technique":[3],"that":[4,116],"exploits":[5],"close":[6],"collaboration":[7,94],"between":[8],"the":[9,12,29,42,49,54,72,88,93,101,117,135,139,145,153,163,167],"compiler":[10,26,55,122],"and":[11,20,62,66,83,97,131,178,183,187,201],"speculative":[13,98],"multithreaded":[14,99],"hardware":[15],"to":[16,150],"explore":[17],"aggressive":[18,69],"optimizations":[19,70],"parallelization":[21],"for":[22,128,137,181],"scalar":[23],"programs.":[24],"The":[25,108,190],"aggressively":[27],"optimizes":[28],"frequently":[30],"executed":[31],"code":[32],"in":[33],"user":[34],"programs":[35],"by":[36,171],"predicting":[37],"an":[38],"execution":[39,52,155,165],"path":[40],"or":[41],"values":[43],"of":[44,58,95],"long-latency":[45],"instructions.":[46],"Based":[47],"on":[48,71,120,134],"predicted":[50],"hot":[51],"path,":[53],"forms":[56],"regions":[57,114],"greatly":[59],"simplified":[60],"data":[61],"control":[63],"flow":[64],"graphs":[65],"then":[67],"performs":[68],"formed":[73],"regions.":[74],"Thread":[75],"level":[76],"speculation":[77],"(TLS)":[78],"helps":[79],"expose":[80],"program":[81,85,102],"parallelism":[82],"guarantees":[84],"correctness":[86],"when":[87],"prediction":[89],"is":[90,148,185],"incorrect.":[91],"With":[92,157],"compilers":[96],"support,":[100],"performance":[103,118,146,169,191],"can":[104,125,193],"be":[105,126,194],"significantly":[106],"improved.":[107],"preliminary":[109],"results":[110],"with":[111,152,162,196],"simple":[112],"trace":[113],"demonstrate":[115],"gain":[119,147,170,192],"dynamic":[121],"schedule":[123],"cycles":[124],"33%":[127],"some":[129],"benchmark":[130],"about":[132],"10%,":[133],"average,":[136],"all":[138],"eight":[140],"SpecInt95":[141],"benchmarks.":[142],"For":[143],"SpecInt2k,":[144],"up":[149],"23%":[151],"conservative":[154,164],"model.":[156],"cycle":[159],"accurate":[160],"simulator":[161],"model,":[166],"overall":[168],"considering":[172],"runtime":[173],"factors":[174],"(e.g.,":[175],"cache":[176],"misses":[177],"branch":[179],"misprediction)":[180],"vortex":[182],"m88ksim":[184],"12%":[186],"14.7%,":[188],"respectively.":[189],"higher":[195],"more":[197],"sophisticated":[198],"region":[199],"formation":[200],"region-based":[202],"optimizations.":[203]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}