{"id":"https://openalex.org/W2128329055","doi":"https://doi.org/10.1145/1950365.1950408","title":"On-the-fly elimination of dynamic irregularities for GPU computing","display_name":"On-the-fly elimination of dynamic irregularities for GPU computing","publication_year":2011,"publication_date":"2011-03-05","ids":{"openalex":"https://openalex.org/W2128329055","doi":"https://doi.org/10.1145/1950365.1950408","mag":"2128329055"},"language":"en","primary_location":{"id":"doi:10.1145/1950365.1950408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1950365.1950408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth international conference on Architectural support for programming languages and operating systems","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/A5049890668","display_name":"Eddy Z. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eddy Z. Zhang","raw_affiliation_strings":["The College of William and Mary, Williamsburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071089468","display_name":"Yunlian Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunlian Jiang","raw_affiliation_strings":["The College of William and Mary, Williamsburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053834265","display_name":"Ziyu Guo","orcid":"https://orcid.org/0000-0002-4792-1398"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyu Guo","raw_affiliation_strings":["The College of William and Mary, Williamsburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072871314","display_name":"Kai Tian","orcid":"https://orcid.org/0009-0008-9578-8406"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Tian","raw_affiliation_strings":["The College of William and Mary, Williamsburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["The College of William and Mary, Williamsburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":174,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"380"},"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":0.9986000061035156,"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":0.9966999888420105,"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":0.8754127025604248},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5948992371559143},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5853557586669922},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5655860304832458},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5396931171417236},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.49921131134033203},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.4987952709197998},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4905034899711609},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48401662707328796},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.46109285950660706},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3724287748336792},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.12351614236831665},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12262573838233948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8754127025604248},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5948992371559143},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5853557586669922},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5655860304832458},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5396931171417236},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.49921131134033203},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.4987952709197998},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4905034899711609},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48401662707328796},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.46109285950660706},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3724287748336792},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.12351614236831665},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12262573838233948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1950365.1950408","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1950365.1950408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth international conference on Architectural support for programming languages and operating systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1491178396","https://openalex.org/W1537323515","https://openalex.org/W1547909858","https://openalex.org/W1989945523","https://openalex.org/W1990313671","https://openalex.org/W1992851788","https://openalex.org/W2013247896","https://openalex.org/W2028499920","https://openalex.org/W2080422774","https://openalex.org/W2080592089","https://openalex.org/W2083056254","https://openalex.org/W2089482246","https://openalex.org/W2112121929","https://openalex.org/W2118936983","https://openalex.org/W2129232868","https://openalex.org/W2145866640","https://openalex.org/W2156831150","https://openalex.org/W2160786443","https://openalex.org/W2164417656","https://openalex.org/W2169880332","https://openalex.org/W2170634604","https://openalex.org/W3138798301","https://openalex.org/W4255314729","https://openalex.org/W7026635939"],"related_works":["https://openalex.org/W4399354997","https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W4225414539"],"abstract_inverted_index":{"The":[0],"power-efficient":[1],"massively":[2],"parallel":[3],"Graphics":[4],"Processing":[5],"Units":[6],"(GPUs)":[7],"have":[8,37],"become":[9],"increasingly":[10],"influential":[11],"for":[12,113,236],"general-purpose":[13],"computing":[14],"over":[15],"the":[16,154,170,178,201,209],"past":[17],"few":[18],"years.":[19],"However,":[20],"their":[21,94,97],"efficiency":[22,199],"is":[23,146,189,206,221],"sensitive":[24],"to":[25,54,69,134,192,208],"dynamic":[26,71,85,116,135,225],"irregular":[27],"memory":[28,78,92],"references":[29],"and":[30,77,91,96,102,109,121,151,234],"control":[31,75,89],"flows":[32,76,90],"in":[33,73,87,137,173,214,223,227],"an":[34,50],"application.":[35,203],"Experiments":[36,217],"shown":[38],"great":[39],"performance":[40,180],"gains":[41,57],"when":[42],"these":[43],"irregularities":[44,72,86,117,136,168,226],"are":[45],"removed.":[46],"But":[47],"it":[48,205],"remains":[49],"open":[51],"question":[52],"how":[53],"achieve":[55],"those":[56],"through":[58,118],"software":[59,132,149],"approaches":[60],"on":[61,153],"modern":[62],"GPUs.This":[63],"paper":[64],"presents":[65,125],"a":[66,126,130,147,174,237],"systematic":[67],"exploration":[68],"tackle":[70],"both":[74,88,165],"references.":[79],"It":[80,104,124,145,163],"reveals":[81],"some":[82],"properties":[83],"of":[84,167,200,211,239],"references,":[93],"interactions,":[95],"relations":[98],"with":[99],"program":[100],"data":[101,119],"threads.":[103],"describes":[105],"several":[106,142],"heuristics-based":[107],"algorithms":[108],"runtime":[110],"adaptation":[111],"techniques":[112],"effectively":[114],"removing":[115],"reordering":[120],"job":[122],"swapping.":[123],"framework,":[127],"G-Streamline,":[128],"as":[129],"unified":[131],"solution":[133,150],"GPU":[138,193,202,215,228],"computing.":[139],"G-Streamline":[140,220],"has":[141],"distinctive":[143],"properties.":[144],"pure":[148],"works":[152],"fly,":[155],"requiring":[156],"no":[157,197],"hardware":[158],"extensions":[159],"or":[160],"offline":[161],"profiling.":[162],"treats":[164],"types":[166],"at":[169],"same":[171],"time":[172],"holistic":[175],"fashion,":[176],"maximizing":[177],"whole-program":[179],"by":[181],"resolving":[182],"conflicts":[183],"among":[184],"optimizations.":[185],"Its":[186],"optimization":[187],"overhead":[188],"largely":[190],"transparent":[191],"kernel":[194],"executions,":[195],"jeopardizing":[196],"basic":[198],"Finally,":[204],"robust":[207],"presence":[210],"various":[212],"complexities":[213],"applications.":[216,240],"show":[218],"that":[219],"effective":[222],"reducing":[224],"computing,":[229],"producing":[230],"speedups":[231],"between":[232],"1.07":[233],"2.5":[235],"variety":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":35},{"year":2013,"cited_by_count":28},{"year":2012,"cited_by_count":22}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}