{"id":"https://openalex.org/W3156819950","doi":"https://doi.org/10.1109/cgo53902.2022.9741284","title":"A Compiler Framework for Optimizing Dynamic Parallelism on GPUs","display_name":"A Compiler Framework for Optimizing Dynamic Parallelism on GPUs","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W3156819950","doi":"https://doi.org/10.1109/cgo53902.2022.9741284","mag":"3156819950"},"language":"en","primary_location":{"id":"doi:10.1109/cgo53902.2022.9741284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo53902.2022.9741284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.02789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051331196","display_name":"Mhd Ghaith Olabi","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":true,"raw_author_name":"Mhd Ghaith Olabi","raw_affiliation_strings":["American University of Beirut,Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut,Lebanon","institution_ids":["https://openalex.org/I98635879"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Juan Gomez Luna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Gomez Luna","raw_affiliation_strings":["ETH Zürich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Onur Mutlu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Onur Mutlu","raw_affiliation_strings":["ETH Zürich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zürich,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wen-Mei Hwu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Mei Hwu","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":null,"display_name":"Izzat El Hajj","orcid":null},"institutions":[{"id":"https://openalex.org/I98635879","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21","country_code":"LB","type":"education","lineage":["https://openalex.org/I98635879"]}],"countries":["LB"],"is_corresponding":false,"raw_author_name":"Izzat El Hajj","raw_affiliation_strings":["American University of Beirut,Lebanon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American University of Beirut,Lebanon","institution_ids":["https://openalex.org/I98635879"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051331196"],"corresponding_institution_ids":["https://openalex.org/I98635879"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.22030000388622284,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10320","display_name":"Neural Networks and Applications","score":0.22030000388622284,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/compiler","display_name":"Compiler","score":0.7446046471595764},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7444453835487366},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7062830328941345},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6795189380645752},{"id":"https://openalex.org/keywords/just-in-time-compilation","display_name":"Just-in-time compilation","score":0.4224802255630493},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.41846901178359985},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4111519753932953}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7446046471595764},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444453835487366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7062830328941345},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6795189380645752},{"id":"https://openalex.org/C76782552","wikidata":"https://www.wikidata.org/wiki/Q110546","display_name":"Just-in-time compilation","level":3,"score":0.4224802255630493},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41846901178359985},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4111519753932953}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/cgo53902.2022.9741284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo53902.2022.9741284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.02789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.02789","pdf_url":"https://arxiv.org/pdf/2201.02789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/17048447","is_oa":true,"landing_page_url":"https://figshare.com/articles/software/A_Compiler_Framework_for_Optimizing_Dynamic_Parallelism_on_GPUs/17048447","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Software"},{"id":"doi:10.48550/arxiv.2201.02789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2201.02789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3156819950","is_oa":false,"landing_page_url":"https://scholarworks.aub.edu.lb/handle/10938/22235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null},{"id":"doi:10.6084/m9.figshare.17048447","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.17048447","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.02789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.02789","pdf_url":"https://arxiv.org/pdf/2201.02789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309999","display_name":"American University of Beirut","ror":"https://ror.org/04pznsd21"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3156819950.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1502558230","https://openalex.org/W1989562524","https://openalex.org/W1997162567","https://openalex.org/W2029940394","https://openalex.org/W2090278477","https://openalex.org/W2100218206","https://openalex.org/W2119222363","https://openalex.org/W2123440268","https://openalex.org/W2149234156","https://openalex.org/W2155794378","https://openalex.org/W2238700765","https://openalex.org/W2260499435","https://openalex.org/W2294347342","https://openalex.org/W2474844316","https://openalex.org/W2505199798","https://openalex.org/W2511683765","https://openalex.org/W2559781775","https://openalex.org/W2611998574","https://openalex.org/W2617756197","https://openalex.org/W2765329037","https://openalex.org/W2766166018","https://openalex.org/W2788517652","https://openalex.org/W2808709390","https://openalex.org/W2883965613","https://openalex.org/W2902741896","https://openalex.org/W2922104589","https://openalex.org/W2984946966","https://openalex.org/W3173612853","https://openalex.org/W3190445506","https://openalex.org/W4231595696","https://openalex.org/W4236446046","https://openalex.org/W4246166885","https://openalex.org/W6601566974","https://openalex.org/W6680839877","https://openalex.org/W6733757634","https://openalex.org/W6748322718","https://openalex.org/W6760029516"],"related_works":["https://openalex.org/W2922104589","https://openalex.org/W2517408153","https://openalex.org/W2058692170","https://openalex.org/W2125550683","https://openalex.org/W2098644672","https://openalex.org/W3096250264","https://openalex.org/W2055384566","https://openalex.org/W2580282987","https://openalex.org/W2199705654","https://openalex.org/W2759780398","https://openalex.org/W2163743729","https://openalex.org/W1500357398","https://openalex.org/W2140379632","https://openalex.org/W3030752614","https://openalex.org/W2770697997","https://openalex.org/W2133803493","https://openalex.org/W2019143817","https://openalex.org/W1982851095","https://openalex.org/W2296596226","https://openalex.org/W3028670792"],"abstract_inverted_index":{"Dynamic":[0],"parallelism":[1,27,42,94,214,264,279,308],"on":[2],"GPUs":[3],"allows":[4],"GPU":[5,11],"threads":[6,122,130],"to":[7,69,150,206,257],"dynamically":[8,115],"launch":[9,66],"other":[10,202],"threads.":[12],"It":[13],"is":[14,28,168,195],"useful":[15],"in":[16,64,77,95,131,174,183,201,209,218,227,314],"applications":[17,96,276,287,294,304],"with":[18,97,191,277,309],"nested":[19,26,98,278],"parallelism,":[20,291,300],"particularly":[21],"where":[22],"the":[23,72,90,118,128,132,139,152,175,184,188,210,219,228,259,273],"amount":[24],"of":[25,53,61,92,120,141,177,212,261,275,284],"irregular":[29],"and":[30,71,108,126,186,215,301],"cannot":[31],"be":[32],"predicted":[33],"beforehand.":[34],"However,":[35],"prior":[36,231,315],"works":[37],"have":[38],"shown":[39],"that":[40,242,268,288,295,305],"dynamic":[41,93,178,213,263,290,299,307],"may":[43],"impose":[44],"a":[45,50,85,113,146,164,238,281],"high":[46,65],"performance":[47,274],"penalty":[48],"when":[49],"large":[51,59],"number":[52,60,119],"small":[54,73],"grids":[55,162],"are":[56],"launched.":[57],"The":[58,100],"launches":[62],"results":[63],"latency":[67],"due":[68],"congestion,":[70],"grid":[74,114],"sizes":[75],"result":[76],"hardware":[78],"underutilization.To":[79],"address":[80],"this":[81],"issue,":[82],"we":[83],"propose":[84,205],"compiler":[86,185,220,229,255,270],"framework":[87,101,256,271],"for":[88],"optimizing":[89,262],"use":[91,289,298,306],"parallelism.":[99,179],"features":[102],"three":[103,250],"key":[104],"optimizations:":[105],"thresholding,":[106],"coarsening,":[107],"aggregation.":[109],"Thresholding":[110],"involves":[111,137,158],"launching":[112],"only":[116],"if":[117],"child":[121,129,161],"exceeds":[123],"some":[124],"threshold,":[125],"serializing":[127],"parent":[133],"thread":[134,143],"otherwise.":[135],"Coarsening":[136,194],"executing":[138],"work":[140,154],"multiple":[142,160],"blocks":[144],"by":[145,172,230,236,280],"single":[147,165],"coarsened":[148],"block":[149],"amortize":[151],"common":[153],"across":[155],"them.":[156],"Aggregation":[157,223],"combining":[159],"into":[163,252],"aggregated":[166],"grid.Thresholding":[167],"sometimes":[169,196],"applied":[170,197],"manually":[171],"programmers":[173],"context":[176,211],"We":[180,204,233,246],"automate":[181,216],"it":[182,217],"discuss":[187],"challenges":[189],"associated":[190],"doing":[192],"so.":[193],"as":[198,221,312],"an":[199,253],"optimization":[200],"contexts.":[203],"apply":[207],"coarsening":[208],"well.":[222],"has":[224],"been":[225],"automated":[226],"work.":[232,316],"enhance":[234],"aggregation":[235,240,310],"proposing":[237],"new":[239],"technique":[241],"uses":[243],"multi-block":[244],"granularity.":[245],"also":[247],"integrate":[248],"these":[249],"optimizations":[251],"open-source":[254],"simplify":[258],"process":[260],"code.Our":[265],"evaluation":[266],"shows":[267],"our":[269],"improves":[272],"geometric":[282],"mean":[283],"43.0\u00d7":[285],"over":[286,293,303],"8.7\u00d7":[292],"do":[296],"not":[297],"3.6\u00d7":[302],"alone":[311],"proposed":[313]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}