{"id":"https://openalex.org/W3164669718","doi":"https://doi.org/10.1145/3447818.3461616","title":"Task-graph scheduling extensions for efficient synchronization and communication","display_name":"Task-graph scheduling extensions for efficient synchronization and communication","publication_year":2021,"publication_date":"2021-06-03","ids":{"openalex":"https://openalex.org/W3164669718","doi":"https://doi.org/10.1145/3447818.3461616","mag":"3164669718"},"language":"en","primary_location":{"id":"doi:10.1145/3447818.3461616","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447818.3461616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM 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/A5059199719","display_name":"Seonmyeong Bak","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seonmyeong Bak","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071822072","display_name":"\u00d3scar Hern\u00e1ndez","orcid":"https://orcid.org/0000-0002-5380-6951"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oscar Hernandez","raw_affiliation_strings":["Oak Ridge National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104910026","display_name":"Mark Gates","orcid":"https://orcid.org/0000-0003-2996-1641"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Gates","raw_affiliation_strings":["University of Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043513001","display_name":"Vivek Sarkar","orcid":"https://orcid.org/0000-0002-3433-8830"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Sarkar","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"88","last_page":"101"},"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":0.9997000098228455,"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":0.9990000128746033,"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":0.8712224960327148},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6172093749046326},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.6115697622299194},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6013599038124084},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4999566078186035},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.323181688785553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8712224960327148},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6172093749046326},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.6115697622299194},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6013599038124084},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4999566078186035},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.323181688785553},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447818.3461616","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447818.3461616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1582954727","https://openalex.org/W1966938284","https://openalex.org/W1968020161","https://openalex.org/W1984848758","https://openalex.org/W1986340747","https://openalex.org/W1986864222","https://openalex.org/W2002194229","https://openalex.org/W2011903918","https://openalex.org/W2016559894","https://openalex.org/W2029804882","https://openalex.org/W2036551003","https://openalex.org/W2043013658","https://openalex.org/W2051634982","https://openalex.org/W2087440962","https://openalex.org/W2090409324","https://openalex.org/W2106843513","https://openalex.org/W2109065830","https://openalex.org/W2117293168","https://openalex.org/W2131573942","https://openalex.org/W2133250609","https://openalex.org/W2156187359","https://openalex.org/W2157124218","https://openalex.org/W2484422940","https://openalex.org/W2491195752","https://openalex.org/W2547058949","https://openalex.org/W2765106570","https://openalex.org/W2878316331","https://openalex.org/W2983126917","https://openalex.org/W2985428643","https://openalex.org/W4231299715","https://openalex.org/W4236558082","https://openalex.org/W4250588632","https://openalex.org/W4299937427"],"related_works":["https://openalex.org/W2403987929","https://openalex.org/W2039814159","https://openalex.org/W2374847384","https://openalex.org/W2063512590","https://openalex.org/W2107649022","https://openalex.org/W2356488190","https://openalex.org/W2966537581","https://openalex.org/W2079508979","https://openalex.org/W604331851","https://openalex.org/W2784059180"],"abstract_inverted_index":{"Task":[0],"graphs":[1],"have":[2,35],"been":[3,114],"studied":[4],"for":[5,10,141],"decades":[6],"as":[7,40],"a":[8,108],"foundation":[9],"scheduling":[11,37,58],"irregular":[12],"parallel":[13,26],"applications":[14],"and":[15,48,63,75,80,105,139,144,158],"incorporated":[16],"in":[17,107],"many":[18,24],"programming":[19],"models":[20],"including":[21],"OpenMP.":[22],"While":[23],"high-performance":[25,119],"libraries":[27],"are":[28],"based":[29],"on":[30,116],"task":[31],"graphs,":[32],"they":[33],"also":[34],"additional":[36],"requirements,":[38],"such":[39],"synchronization":[41,62],"within":[42,65],"inner":[43],"levels":[44],"of":[45,77,88,94,134,156,160],"data":[46],"parallelism":[47],"internal":[49],"blocking":[50],"communications.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"extend":[56],"task-graph":[57],"to":[59,68,84,102,124,136,152],"support":[60],"efficient":[61],"communication":[64],"tasks.":[66,90],"Compared":[67],"past":[69],"work,":[70],"our":[71,95,97,129],"scheduler":[72],"avoids":[73],"deadlock":[74],"oversubscription":[76],"worker":[78],"threads,":[79],"refines":[81],"victim":[82],"selection":[83],"increase":[85],"the":[86,92,100,117,125],"overlap":[87],"sibling":[89],"To":[91],"best":[93],"knowledge,":[96],"approach":[98,112],"is":[99],"first":[101],"combine":[103],"gang-scheduling":[104],"work-stealing":[106],"single":[109],"runtime.":[110],"Our":[111],"has":[113],"evaluated":[115,147],"SLATE":[118],"linear":[120],"algebra":[121],"library.":[122],"Relative":[123],"LLVM":[126],"OMP":[127],"runtime,":[128],"runtime":[130],"demonstrates":[131],"performance":[132],"improvements":[133],"up":[135],"13.82%,":[137],"15.2%,":[138],"36.94%":[140],"LU,":[142],"QR,":[143],"Cholesky,":[145],"respectively,":[146],"across":[148],"different":[149],"configurations":[150],"related":[151],"matrix":[153],"size,":[154],"number":[155],"nodes,":[157],"use":[159],"CPUs":[161],"vs":[162],"GPUs.":[163]},"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":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}