{"id":"https://openalex.org/W3130678148","doi":"https://doi.org/10.1145/3437801.3441605","title":"A fast work-efficient SSSP algorithm for GPUs","display_name":"A fast work-efficient SSSP algorithm for GPUs","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3130678148","doi":"https://doi.org/10.1145/3437801.3441605","mag":"3130678148"},"language":"en","primary_location":{"id":"doi:10.1145/3437801.3441605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441605","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441605","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441605","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100719993","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-3040-0422"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Wang","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111677561","display_name":"Don Fussell","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Don Fussell","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103038181","display_name":"Calvin Lin","orcid":"https://orcid.org/0000-0001-6284-4629"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin Lin","raw_affiliation_strings":["The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100719993"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.3581,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88074801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"146"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9990000128746033,"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":0.843539834022522},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7455037236213684},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5099469423294067},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.49454042315483093},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.47049781680107117},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4508313238620758},{"id":"https://openalex.org/keywords/priority-queue","display_name":"Priority queue","score":0.4448523223400116},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43725037574768066},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39168834686279297},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.13456842303276062},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07789883017539978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06978204846382141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843539834022522},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7455037236213684},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5099469423294067},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.49454042315483093},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.47049781680107117},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4508313238620758},{"id":"https://openalex.org/C26951474","wikidata":"https://www.wikidata.org/wiki/Q629283","display_name":"Priority queue","level":3,"score":0.4448523223400116},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43725037574768066},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39168834686279297},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13456842303276062},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07789883017539978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06978204846382141},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437801.3441605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441605","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441605","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3437801.3441605","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441605","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441605","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2958680242","display_name":null,"funder_award_id":"CCF-1823546","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6902435264","display_name":"FoMR: Using Machine Learning to Design Next Generation Caches and Data Prefetchers","funder_award_id":"1823546","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130678148.pdf","grobid_xml":"https://content.openalex.org/works/W3130678148.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1487977379","https://openalex.org/W1997162567","https://openalex.org/W2016490257","https://openalex.org/W2035080386","https://openalex.org/W2044346360","https://openalex.org/W2057112598","https://openalex.org/W2097717378","https://openalex.org/W2098903349","https://openalex.org/W2107173440","https://openalex.org/W2124861237","https://openalex.org/W2169528473","https://openalex.org/W2227557434","https://openalex.org/W2336892223","https://openalex.org/W2502734103","https://openalex.org/W2581090187","https://openalex.org/W2772468880","https://openalex.org/W2912007486","https://openalex.org/W2951135776"],"related_works":["https://openalex.org/W2505380084","https://openalex.org/W2045183646","https://openalex.org/W2086739451","https://openalex.org/W3183233360","https://openalex.org/W2162409446","https://openalex.org/W189328514","https://openalex.org/W3151684823","https://openalex.org/W3049636605","https://openalex.org/W1974858599","https://openalex.org/W2158032519"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,65,72,78],"new":[4],"Single":[5],"Source":[6],"Shortest":[7],"Path":[8],"(SSSP)":[9],"algorithm":[10],"for":[11,33],"GPUs.":[12,94],"Our":[13,69],"key":[14],"advancement":[15],"is":[16,22],"an":[17],"improved":[18],"work":[19,37,56,75],"scheduler,":[20],"which":[21],"central":[23],"to":[24,64],"the":[25,61],"performance":[26],"of":[27,67],"SSSP":[28,34],"algorithms.":[29],"Previous":[30],"GPU":[31],"solutions":[32,53],"use":[35],"simple":[36],"schedulers":[38],"that":[39,47],"can":[40,59],"be":[41],"implemented":[42],"efficiently":[43,91],"on":[44,77,93],"GPUs":[45],"but":[46],"produce":[48],"low":[49],"quality":[50,87],"schedules.":[51],"Such":[52],"yield":[54],"poor":[55],"efficiency":[57],"and":[58],"underutilize":[60],"hardware":[62],"due":[63],"lack":[66],"parallelism.":[68],"solution":[70],"introduces":[71],"more":[73],"sophisticated":[74],"scheduler---based":[76],"novel":[79],"highly":[80],"parallel":[81],"approximate":[82],"priority":[83],"queue---that":[84],"produces":[85],"high":[86],"schedules":[88],"while":[89],"being":[90],"implementable":[92]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}