{"id":"https://openalex.org/W2057962110","doi":"https://doi.org/10.1145/2145816.2145860","title":"Speculative parallelization on GPGPUs","display_name":"Speculative parallelization on GPGPUs","publication_year":2012,"publication_date":"2012-02-25","ids":{"openalex":"https://openalex.org/W2057962110","doi":"https://doi.org/10.1145/2145816.2145860","mag":"2057962110"},"language":"en","primary_location":{"id":"doi:10.1145/2145816.2145860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","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/A5081240542","display_name":"Min Feng","orcid":"https://orcid.org/0000-0002-0107-0196"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Min Feng","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA","University of California, RIverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"University of California, RIverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699251","display_name":"Rajiv Gupta","orcid":"https://orcid.org/0000-0002-9348-3974"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajiv Gupta","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA","University of California, RIverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"University of California, RIverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048949780","display_name":"Laxmi N. Bhuyan","orcid":"https://orcid.org/0000-0002-8759-0458"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmi N. Bhuyan","raw_affiliation_strings":["University of California, Riverside, Riverside, CA, USA","University of California, RIverside, Riverside, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"University of California, RIverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081240542"],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":1.1602,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78274311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"294"},"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":0.9987000226974487,"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":0.9983999729156494,"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":0.904028594493866},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8678334951400757},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6222909688949585},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5786572098731995},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.576416015625},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5541799664497375},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.4975424110889435},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.43459463119506836},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27469533681869507},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23237308859825134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.904028594493866},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8678334951400757},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6222909688949585},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5786572098731995},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.576416015625},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5541799664497375},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.4975424110889435},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.43459463119506836},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27469533681869507},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23237308859825134},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2145816.2145860","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332550","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2128329055","https://openalex.org/W2129232868","https://openalex.org/W2153185479","https://openalex.org/W2156455047","https://openalex.org/W2170634604","https://openalex.org/W4242965270"],"related_works":["https://openalex.org/W4308771405","https://openalex.org/W2355873265","https://openalex.org/W17155033","https://openalex.org/W2963669501","https://openalex.org/W3112369086","https://openalex.org/W3080197661","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4318471783","https://openalex.org/W2149245348"],"abstract_inverted_index":{"This":[0],"paper":[1],"overviews":[2],"the":[3,18,55,63,73,80,87,94],"first":[4],"speculative":[5],"parallelization":[6],"technique":[7],"for":[8,143],"GPUs":[9],"that":[10,23,131],"can":[11,132],"exploit":[12],"parallelism":[13],"in":[14,17,108,145],"loops":[15,144],"even":[16],"presence":[19],"of":[20,32,38,65,89,118],"dynamic":[21],"irregularities":[22],"may":[24],"give":[25,133],"rise":[26,134],"to":[27,57,71,86,92,135],"cross-iteration":[28,90,136],"dependences.":[29,137],"The":[30],"execution":[31],"a":[33],"speculatively":[34],"parallelized":[35],"loop":[36],"consists":[37],"five":[39],"phases:":[40],"scheduling,":[41],"computation,":[42],"misspeculation":[43,48,52,69,95],"check,":[44],"result":[45,66,74],"committing,":[46],"and":[47,68,76,125],"recovery.":[49],"We":[50,61,114],"perform":[51],"check":[53],"on":[54,102],"GPU":[56],"minimize":[58],"its":[59],"cost.":[60],"optimize":[62],"procedures":[64],"committing":[67],"recovery":[70,77],"reduce":[72,93],"copying":[75],"overhead.":[78],"Finally,":[79],"scheduling":[81],"policies":[82],"are":[83],"designed":[84],"according":[85],"types":[88],"dependences":[91],"rate.":[96],"Our":[97,138],"preliminary":[98],"evaluation":[99],"was":[100],"conducted":[101],"an":[103,109],"nVidia":[104],"Tesla":[105],"C1060":[106],"hosted":[107],"Intel(R)":[110],"Xeon(R)":[111],"E5540":[112],"machine.":[113],"use":[115],"three":[116],"benchmarks":[117],"which":[119],"two":[120],"contain":[121,127],"irregular":[122,128],"memory":[123],"accesses":[124],"one":[126],"control":[129],"flows":[130],"implementation":[139],"achieves":[140],"3.6x-13.8x":[141],"speedups":[142],"these":[146],"benchmarks.":[147]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
