{"id":"https://openalex.org/W1982123268","doi":"https://doi.org/10.1007/s10766-010-0155-0","title":"Value Prediction and Speculative Execution on GPU","display_name":"Value Prediction and Speculative Execution on GPU","publication_year":2010,"publication_date":"2010-11-30","ids":{"openalex":"https://openalex.org/W1982123268","doi":"https://doi.org/10.1007/s10766-010-0155-0","mag":"1982123268"},"language":"en","primary_location":{"id":"doi:10.1007/s10766-010-0155-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10766-010-0155-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10766-010-0155-0.pdf","source":{"id":"https://openalex.org/S148521650","display_name":"International Journal of Parallel Programming","issn_l":"0885-7458","issn":["0885-7458","1573-7640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10766-010-0155-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050739558","display_name":"Shaoshan Liu","orcid":"https://orcid.org/0000-0002-5132-8351"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Shaoshan Liu","raw_affiliation_strings":["Microsoft, Redmond, WA, USA","Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105937751","display_name":"Christine Eisenbeis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144804","display_name":"Laboratoire de Recherche en Informatique","ror":"https://ror.org/04e3ktk27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210144804","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210126360","display_name":"Inria Saclay - \u00cele de France","ror":"https://ror.org/0315e5x55","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christine Eisenbeis","raw_affiliation_strings":["Alchemy team, INRIA Saclay - \u00cele-de-France & Univ Paris-Sud 11 (LRI, UMR CNRS 8623), Orsay, 91405, France","Alchemy team, INRIA Saclay - \u00cele-de-France & Univ Paris-Sud 11 (LRI, UMR CNRS 8623)"],"affiliations":[{"raw_affiliation_string":"Alchemy team, INRIA Saclay - \u00cele-de-France & Univ Paris-Sud 11 (LRI, UMR CNRS 8623), Orsay, 91405, France","institution_ids":["https://openalex.org/I4210126360","https://openalex.org/I4210144804","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Alchemy team, INRIA Saclay - \u00cele-de-France & Univ Paris-Sud 11 (LRI, UMR CNRS 8623)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210144804","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019948826","display_name":"Jean\u2010Luc Gaudiot","orcid":"https://orcid.org/0000-0001-9164-8731"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]},{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gaudiot","raw_affiliation_strings":["University of California, Irvine, CA, USA","University of California"],"affiliations":[{"raw_affiliation_string":"University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050739558"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":3.0323,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91535671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"5","first_page":"533","last_page":"552"},"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":0.9973999857902527,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9950000047683716,"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":0.8989371061325073},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7381588220596313},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6696389317512512},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.5983057618141174},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5932696461677551},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5836362838745117},{"id":"https://openalex.org/keywords/speculative-execution","display_name":"Speculative execution","score":0.561522901058197},{"id":"https://openalex.org/keywords/speculation","display_name":"Speculation","score":0.5122498869895935},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4739368259906769},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18056663870811462}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8989371061325073},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7381588220596313},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6696389317512512},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.5983057618141174},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5932696461677551},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5836362838745117},{"id":"https://openalex.org/C141331961","wikidata":"https://www.wikidata.org/wiki/Q2164465","display_name":"Speculative execution","level":2,"score":0.561522901058197},{"id":"https://openalex.org/C47941915","wikidata":"https://www.wikidata.org/wiki/Q107885","display_name":"Speculation","level":2,"score":0.5122498869895935},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4739368259906769},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18056663870811462},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10766-010-0155-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10766-010-0155-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10766-010-0155-0.pdf","source":{"id":"https://openalex.org/S148521650","display_name":"International Journal of Parallel Programming","issn_l":"0885-7458","issn":["0885-7458","1573-7640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel Programming","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10766-010-0155-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10766-010-0155-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10766-010-0155-0.pdf","source":{"id":"https://openalex.org/S148521650","display_name":"International Journal of Parallel Programming","issn_l":"0885-7458","issn":["0885-7458","1573-7640"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel Programming","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G150059068","display_name":"Collaborative Research:    A Programmable, Efficient, and Dynamic Architecture and Compilation Framework for Networking Applications","funder_award_id":"0541403","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6851345361","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1982123268.pdf","grobid_xml":"https://content.openalex.org/works/W1982123268.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1975908320","https://openalex.org/W2002219828","https://openalex.org/W2019344885","https://openalex.org/W2029171059","https://openalex.org/W2052285774","https://openalex.org/W2078429521","https://openalex.org/W2099059122","https://openalex.org/W2129523505","https://openalex.org/W2131867938","https://openalex.org/W2135470015","https://openalex.org/W2154693467","https://openalex.org/W2167258273","https://openalex.org/W2169875292","https://openalex.org/W2296006986","https://openalex.org/W2996943613","https://openalex.org/W4252351367"],"related_works":["https://openalex.org/W2003935582","https://openalex.org/W2950520577","https://openalex.org/W1991844655","https://openalex.org/W1229628","https://openalex.org/W2105992728","https://openalex.org/W74409296","https://openalex.org/W2009213655","https://openalex.org/W2593878938","https://openalex.org/W2468095077","https://openalex.org/W1554644772"],"abstract_inverted_index":{"GPUs":[0,12,39,93,119],"and":[1,43,58,173],"CPUs":[2],"have":[3],"fundamentally":[4],"different":[5],"architectures.":[6],"It":[7],"is":[8],"conventional":[9],"wisdom":[10],"that":[11,18,65,79,153],"can":[13,120],"accelerate":[14,53,63],"only":[15,169],"those":[16],"applications":[17],"exhibit":[19],"very":[20],"high":[21,84],"parallelism,":[22,57,68],"especially":[23],"vector":[24],"parallelism":[25],"such":[26],"as":[27,112],"image":[28],"processing.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,46,132],"explore":[34,133],"the":[35,82,102,134,146,154,163],"possibility":[36],"of":[37,137,162],"using":[38],"for":[40],"value":[41,49,88],"prediction":[42,50,89],"speculative":[44,138],"execution:":[45],"implement":[47],"software":[48,59,87,106,147],"techniques":[51,61,90,108,116],"to":[52,62,72,81,117,144],"programs":[54,64],"with":[55,168],"limited":[56],"speculation":[60,107],"contain":[66],"runtime":[67],"which":[69],"are":[70],"hard":[71],"parallelize":[73],"statically.":[74],"Our":[75],"experiment":[76],"results":[77,151],"show":[78],"due":[80],"relatively":[83],"overhead,":[85],"mapping":[86,114],"on":[91,129,141],"existing":[92,118],"may":[94],"not":[95],"bring":[96,122],"any":[97],"immediate":[98],"performance":[99,124,148],"gain.":[100],"On":[101],"other":[103],"hand,":[104],"although":[105],"introduce":[109],"some":[110,123],"overhead":[111],"well,":[113],"these":[115,130],"already":[121],"gain":[125],"over":[126],"CPU.":[127],"Based":[128],"observations,":[131],"hardware":[135,155,171],"implementation":[136],"execution":[139],"operations":[140,167],"GPU":[142],"architectures":[143],"reduce":[145],"overheads.":[149,177],"The":[150],"indicate":[152],"extensions":[156],"result":[157],"in":[158],"almost":[159],"tenfold":[160],"reduction":[161],"control":[164],"divergent":[165],"sequential":[166],"moderate":[170],"(5\u20138%)":[172],"power":[174],"consumption":[175],"(1\u20135%)":[176]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}