{"id":"https://openalex.org/W1971421905","doi":"https://doi.org/10.1145/2751205.2751234","title":"A Stall-Aware Warp Scheduling for Dynamically Optimizing Thread-level Parallelism in GPGPUs","display_name":"A Stall-Aware Warp Scheduling for Dynamically Optimizing Thread-level Parallelism in GPGPUs","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W1971421905","doi":"https://doi.org/10.1145/2751205.2751234","mag":"1971421905"},"language":"en","primary_location":{"id":"doi:10.1145/2751205.2751234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","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/A5088901322","display_name":"Yulong Yu","orcid":"https://orcid.org/0000-0003-0170-087X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Yu","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108999688","display_name":"Weijun Xiao","orcid":"https://orcid.org/0000-0002-2147-7575"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijun Xiao","raw_affiliation_strings":["Virginia Commonwealth University, Richmond, VA, USA","Virginia Commonwealth University, Richmond (VA), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Commonwealth University, Richmond, VA, USA","institution_ids":["https://openalex.org/I184840846"]},{"raw_affiliation_string":"Virginia Commonwealth University, Richmond (VA), USA","institution_ids":["https://openalex.org/I184840846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087956045","display_name":"Xubin He","orcid":"https://orcid.org/0000-0002-5071-2861"},"institutions":[{"id":"https://openalex.org/I184840846","display_name":"Virginia Commonwealth University","ror":"https://ror.org/02nkdxk79","country_code":"US","type":"education","lineage":["https://openalex.org/I184840846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xubin He","raw_affiliation_strings":["Virginia Commonwealth University, Richmond, VA, USA","Virginia Commonwealth University, Richmond (VA), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Commonwealth University, Richmond, VA, USA","institution_ids":["https://openalex.org/I184840846"]},{"raw_affiliation_string":"Virginia Commonwealth University, Richmond (VA), USA","institution_ids":["https://openalex.org/I184840846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059541676","display_name":"He Guo","orcid":"https://orcid.org/0000-0003-0955-7692"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Guo","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427475","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-5133-3978"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100638657","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-0747-1361"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"24"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994000196456909,"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":0.9987999796867371,"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":0.8841091394424438},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.803650975227356},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7338172793388367},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6927140355110168},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6046884655952454},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.559748113155365},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5440685749053955},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4186428487300873},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27834683656692505},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.2024972140789032},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18889373540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8841091394424438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.803650975227356},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7338172793388367},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6927140355110168},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6046884655952454},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.559748113155365},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5440685749053955},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4186428487300873},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27834683656692505},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2024972140789032},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18889373540878296},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2751205.2751234","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2751205.2751234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1251571214","display_name":null,"funder_award_id":"11372067","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W2006197381","https://openalex.org/W2018150881","https://openalex.org/W2018767489","https://openalex.org/W2025358418","https://openalex.org/W2038086570","https://openalex.org/W2043420024","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2050019858","https://openalex.org/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2079248286","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2096661534","https://openalex.org/W2100011668","https://openalex.org/W2103838950","https://openalex.org/W2111669132","https://openalex.org/W2129817042","https://openalex.org/W2132598270","https://openalex.org/W2136944230","https://openalex.org/W2138761132","https://openalex.org/W2142444503","https://openalex.org/W2150851481","https://openalex.org/W2152956697","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2166338303","https://openalex.org/W2168921806","https://openalex.org/W2169880332","https://openalex.org/W2170601541","https://openalex.org/W2273440736","https://openalex.org/W4244454515","https://openalex.org/W4252178669","https://openalex.org/W4256537352"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"General-Purpose":[0],"Graphic":[1],"Processing":[2],"Units":[3],"(GPGPU)":[4],"have":[5],"been":[6],"widely":[7],"used":[8],"in":[9,85],"high":[10,22],"performance":[11],"computing":[12],"as":[13],"application":[14],"accelerators":[15],"due":[16],"to":[17,74,92],"their":[18],"massive":[19],"parallelism":[20,45],"and":[21,36],"throughput.":[23],"A":[24],"GPGPU":[25,95],"generally":[26],"contains":[27],"two":[28],"layers":[29],"of":[30],"schedulers,":[31],"a":[32,37,90],"cooperative-thread-array":[33],"(CTA)":[34],"scheduler":[35,88],"warp":[38,62,87],"scheduler,":[39],"which":[40,71],"administer":[41],"the":[42,50,57,86,94],"thread":[43],"level":[44],"(TLP).":[46],"Previous":[47],"research":[48],"shows":[49],"maximized":[51],"TLP":[52,68,83],"does":[53],"not":[54,66],"always":[55],"deliver":[56],"optimal":[58],"performance.":[59],"Unfortunately,":[60],"existing":[61],"scheduling":[63],"schemes":[64],"do":[65],"optimize":[67],"at":[69],"runtime,":[70],"is":[72],"impossible":[73],"fit":[75],"various":[76],"access":[77],"patterns":[78],"for":[79],"diverse":[80],"applications.":[81],"Dynamic":[82],"optimization":[84],"remains":[89],"challenge":[91],"exploit":[93],"highly-parallel":[96],"compute":[97],"power.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}