{"id":"https://openalex.org/W2989621752","doi":"https://doi.org/10.1109/hpec.2019.8916473","title":"Exploration of Fine-Grained Parallelism for Load Balancing Eager K-truss on GPU and CPU","display_name":"Exploration of Fine-Grained Parallelism for Load Balancing Eager K-truss on GPU and CPU","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2989621752","doi":"https://doi.org/10.1109/hpec.2019.8916473","mag":"2989621752"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2019.8916473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.07929","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Maia P. Blanco","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maia P. Blanco","raw_affiliation_strings":["Carnegie Mellon University,Dept. of Electrical and Computer Engineering,Pittsburgh,United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Dept. of Electrical and Computer Engineering,Pittsburgh,United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tze Meng Low","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tze Meng Low","raw_affiliation_strings":["Carnegie Mellon University,Dept. of Electrical and Computer Engineering,Pittsburgh,United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Dept. of Electrical and Computer Engineering,Pittsburgh,United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kyungjoo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyungjoo Kim","raw_affiliation_strings":["Center for Computing Research Sandia National Laboratories,Albuquerque,United States"],"affiliations":[{"raw_affiliation_string":"Center for Computing Research Sandia National Laboratories,Albuquerque,United States","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.0389,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8843988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9991000294685364,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.6985999941825867},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5213000178337097},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5011000037193298},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45890000462532043},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4584999978542328},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.3986000120639801},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.3594000041484833},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.34880000352859497},{"id":"https://openalex.org/keywords/bulk-synchronous-parallel","display_name":"Bulk synchronous parallel","score":0.3273000121116638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8794000148773193},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7767999768257141},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6985999941825867},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5213000178337097},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.3986000120639801},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C156891508","wikidata":"https://www.wikidata.org/wiki/Q1004114","display_name":"Bulk synchronous parallel","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2779370713","wikidata":"https://www.wikidata.org/wiki/Q357554","display_name":"Load management","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hpec.2019.8916473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.07929","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.07929","pdf_url":"https://arxiv.org/pdf/2009.07929","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:osti.gov:1641202","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1641202","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1641896","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1641896","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.07929","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.07929","pdf_url":"https://arxiv.org/pdf/2009.07929","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2078794610","https://openalex.org/W2145764405","https://openalex.org/W2518858713","https://openalex.org/W2747404479","https://openalex.org/W2765752351","https://openalex.org/W2902685757","https://openalex.org/W2902887439","https://openalex.org/W2952707032","https://openalex.org/W2963467900"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,82],"present":[4],"a":[5,11,36,85,93],"performance":[6,21],"exploration":[7],"on":[8,70,89,96],"Eager":[9],"K-truss,":[10],"linear-algebraic":[12],"formulation":[13],"of":[14,27],"the":[15,42,90,97],"K-truss":[16],"graph":[17],"algorithm.":[18],"We":[19,57],"address":[20],"issues":[22],"related":[23],"to":[24,40,54,100],"load":[25],"imbalance":[26],"parallel":[28,38,61,103],"tasks":[29],"in":[30,65],"symmetric,":[31],"triangular":[32],"graphs":[33],"by":[34],"presenting":[35],"fine-grained":[37,60,102],"approach":[39,46,62],"executing":[41],"support":[43],"computation.":[44],"This":[45],"also":[47],"increases":[48],"available":[49],"parallelism,":[50],"making":[51],"it":[52],"amenable":[53],"GPU":[55,98],"execution.":[56],"demonstrate":[58],"our":[59,101],"using":[63],"implementations":[64],"Kokkos":[66],"and":[67,75,92],"evaluate":[68],"them":[69],"an":[71,76],"Intel":[72],"Skylake":[73],"CPU":[74,91],"Nvidia":[77],"Tesla":[78],"V100":[79],"GPU.":[80],"Overall,":[81],"observe":[83],"between":[84],"1.261.":[86],"48x":[87],"improvement":[88,95],"9.97-16.92x":[94],"due":[99],"formulation.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-12-05T00:00:00"}