{"id":"https://openalex.org/W2146081545","doi":"https://doi.org/10.1145/2259016.2259029","title":"Automatic speculative DOALL for clusters","display_name":"Automatic speculative DOALL for clusters","publication_year":2012,"publication_date":"2012-03-31","ids":{"openalex":"https://openalex.org/W2146081545","doi":"https://doi.org/10.1145/2259016.2259029","mag":"2146081545"},"language":"en","primary_location":{"id":"doi:10.1145/2259016.2259029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2259016.2259029","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 International Symposium on Code Generation and Optimization","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/A5100722345","display_name":"Hanjun Kim","orcid":"https://orcid.org/0000-0002-0762-7901"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hanjun Kim","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110187017","display_name":"Nick Johnson","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick P. Johnson","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415731","display_name":"Jae W. Lee","orcid":"https://orcid.org/0000-0002-4266-4919"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae W. Lee","raw_affiliation_strings":["SungKyunKwan University, Suwon, Korea","Sungkyunkwan University , Suwon, Korea"],"affiliations":[{"raw_affiliation_string":"SungKyunKwan University, Suwon, Korea","institution_ids":["https://openalex.org/I848706"]},{"raw_affiliation_string":"Sungkyunkwan University , Suwon, Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott A. Mahlke","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008319090","display_name":"David I. August","orcid":"https://orcid.org/0000-0003-3327-1803"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David I. August","raw_affiliation_strings":["Princeton University, Princeton, NJ"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100722345"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":7.3028,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97541354,"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":"94","last_page":"103"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998000264167786,"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":0.9997000098228455,"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":0.8750764727592468},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8323100209236145},{"id":"https://openalex.org/keywords/speculative-multithreading","display_name":"Speculative multithreading","score":0.8129690885543823},{"id":"https://openalex.org/keywords/automatic-parallelization","display_name":"Automatic parallelization","score":0.7439437508583069},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.7263802886009216},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7126932740211487},{"id":"https://openalex.org/keywords/speculative-execution","display_name":"Speculative execution","score":0.6411608457565308},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6105695962905884},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5852384567260742},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5708956122398376},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5665513873100281},{"id":"https://openalex.org/keywords/speculation","display_name":"Speculation","score":0.5554955005645752},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5120266079902649},{"id":"https://openalex.org/keywords/dependence-analysis","display_name":"Dependence analysis","score":0.45444947481155396},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.2806941866874695},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20952609181404114},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18510258197784424},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.06651535630226135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8750764727592468},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8323100209236145},{"id":"https://openalex.org/C15296174","wikidata":"https://www.wikidata.org/wiki/Q7575343","display_name":"Speculative multithreading","level":4,"score":0.8129690885543823},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.7439437508583069},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.7263802886009216},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7126932740211487},{"id":"https://openalex.org/C141331961","wikidata":"https://www.wikidata.org/wiki/Q2164465","display_name":"Speculative execution","level":2,"score":0.6411608457565308},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6105695962905884},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5852384567260742},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5708956122398376},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5665513873100281},{"id":"https://openalex.org/C47941915","wikidata":"https://www.wikidata.org/wiki/Q107885","display_name":"Speculation","level":2,"score":0.5554955005645752},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5120266079902649},{"id":"https://openalex.org/C27390822","wikidata":"https://www.wikidata.org/wiki/Q320724","display_name":"Dependence analysis","level":2,"score":0.45444947481155396},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.2806941866874695},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20952609181404114},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18510258197784424},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.06651535630226135},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2259016.2259029","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2259016.2259029","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 International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.8341","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.8341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://liberty.princeton.edu/Publications/cgo12_cluster_specdoall.pdf","raw_type":"text"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/34842","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/34842","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5474417998","display_name":null,"funder_award_id":"CCS-0964328OCI-1047879","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G7955788297","display_name":null,"funder_award_id":"FA8750-10-2-0253","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8987995071","display_name":null,"funder_award_id":"CCS-0964328OCI-1047879","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G982469847","display_name":null,"funder_award_id":"FA8650-09-C-7918","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W16598917","https://openalex.org/W1977838359","https://openalex.org/W2003895614","https://openalex.org/W2008258200","https://openalex.org/W2008677874","https://openalex.org/W2037462607","https://openalex.org/W2045506295","https://openalex.org/W2097447543","https://openalex.org/W2101304735","https://openalex.org/W2105864407","https://openalex.org/W2106018697","https://openalex.org/W2107497336","https://openalex.org/W2116170858","https://openalex.org/W2125340270","https://openalex.org/W2133734540","https://openalex.org/W2149037641","https://openalex.org/W2152657019","https://openalex.org/W2153185479","https://openalex.org/W2155410188","https://openalex.org/W2164738518","https://openalex.org/W2169875292","https://openalex.org/W3083604022","https://openalex.org/W4232637339","https://openalex.org/W4253095404","https://openalex.org/W4254473445","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3196293061","https://openalex.org/W2034886984","https://openalex.org/W4387670486","https://openalex.org/W2969801138","https://openalex.org/W2269131302","https://openalex.org/W3012385591","https://openalex.org/W2004692581","https://openalex.org/W3000039653","https://openalex.org/W2897479034","https://openalex.org/W2146081545"],"abstract_inverted_index":{"Automatic":[0],"parallelization":[1,15,53,63,89,99,177],"for":[2,67,91,115,128,178],"clusters":[3,179],"is":[4,16,82,126],"a":[5,96,107,112,153,159],"promising":[6],"alternative":[7],"to":[8,27,36,72,77],"time-consuming,":[9],"error-prone":[10],"manual":[11],"parallelization.":[12],"However,":[13],"automatic":[14,52,61,85,98],"frequently":[17],"limited":[18],"by":[19],"the":[20,28,37,73,83,118,124,129,138,144],"imprecision":[21],"of":[22,31,106,143,156],"static":[23,32,46],"analysis.":[24],"Moreover,":[25],"due":[26,71],"inherent":[29],"fragility":[30],"analysis,":[33],"small":[34],"changes":[35],"source":[38],"code":[39],"can":[40],"significantly":[41],"undermine":[42],"performance.":[43],"By":[44],"replacing":[45],"analysis":[47],"with":[48],"speculation":[49,133,165,173],"and":[50,57,111,123,140],"profiling,":[51],"becomes":[54],"more":[55],"robust":[56],"applicable.":[58],"A":[59],"na\u00efve":[60],"speculative":[62,86,113,145],"does":[64],"not":[65],"scale":[66],"distributed":[68],"memory":[69],"clusters,":[70],"high":[74],"bandwidth":[75],"required":[76],"validate":[78],"speculation.":[79],"This":[80,170],"work":[81],"first":[84],"DOALL":[87,163],"(Spec-DOALL)":[88],"system":[90],"clusters.":[92,116],"We":[93],"have":[94],"implemented":[95],"prototype":[97],"system,":[100],"called":[101],"Cluster":[102,135,150],"Spec-DOALL,":[103],"which":[104,132],"consists":[105],"Spec-DOALL":[108,136,151],"parallelizing":[109],"compiler":[110,119],"runtime":[114,125],"Since":[117],"optimizes":[120],"communication":[121,139],"patterns,":[122],"optimized":[127],"cases":[130],"in":[131],"succeeds,":[134],"minimizes":[137],"validation":[141],"overheads":[142],"runtime.":[146],"Across":[147],"8":[148],"benchmarks,":[149],"achieves":[152,166],"geomean":[154],"speedup":[155],"43.8x":[157],"on":[158],"120-core":[160],"cluster,":[161],"whereas":[162],"without":[164],"only":[167],"4.5x":[168],"speedup.":[169],"demonstrates":[171],"that":[172],"makes":[174],"scalable":[175],"fully-automatic":[176],"possible.":[180]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
