{"id":"https://openalex.org/W4318541676","doi":"https://doi.org/10.1145/3575693.3575705","title":"Lucid: A Non-intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs","display_name":"Lucid: A Non-intrusive, Scalable and Interpretable Scheduler for Deep Learning Training Jobs","publication_year":2023,"publication_date":"2023-01-27","ids":{"openalex":"https://openalex.org/W4318541676","doi":"https://doi.org/10.1145/3575693.3575705"},"language":"en","primary_location":{"id":"doi:10.1145/3575693.3575705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575705","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575705","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575705","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035921543","display_name":"Qinghao Hu","orcid":"https://orcid.org/0000-0003-1034-7502"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qinghao Hu","raw_affiliation_strings":["Nanyang Technological University, Singapore / Shanghai AI Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore / Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691587","display_name":"Meng Zhang","orcid":"https://orcid.org/0000-0002-0922-1358"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Meng Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614087","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0001-8456-0491"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["SenseTime, China / Shanghai AI Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime, China / Shanghai AI Laboratory, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041572550","display_name":"Yonggang Wen","orcid":"https://orcid.org/0000-0002-2751-5114"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yonggang Wen","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101591101","display_name":"Tianwei Zhang","orcid":"https://orcid.org/0000-0001-6595-6650"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianwei Zhang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9940000176429749,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9930999875068665,"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/scalability","display_name":"Scalability","score":0.83638995885849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7932600975036621},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7661769390106201},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6720370650291443},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5916004180908203},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5690965056419373},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5470957159996033},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4976027309894562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44662293791770935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3613176941871643},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20943588018417358},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.08814901113510132}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.83638995885849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932600975036621},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7661769390106201},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6720370650291443},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5916004180908203},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5690965056419373},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5470957159996033},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4976027309894562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44662293791770935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3613176941871643},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20943588018417358},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.08814901113510132},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3575693.3575705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575705","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575705","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3575693.3575705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575705","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575705","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318541676.pdf","grobid_xml":"https://content.openalex.org/works/W4318541676.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2001496424","https://openalex.org/W2025549137","https://openalex.org/W2046945713","https://openalex.org/W2074988668","https://openalex.org/W2100830825","https://openalex.org/W2105947650","https://openalex.org/W2108598243","https://openalex.org/W2137726616","https://openalex.org/W2194775991","https://openalex.org/W2219888463","https://openalex.org/W2282821441","https://openalex.org/W2295598076","https://openalex.org/W2560674852","https://openalex.org/W2605350416","https://openalex.org/W2764100055","https://openalex.org/W2798515322","https://openalex.org/W2890991187","https://openalex.org/W2900228909","https://openalex.org/W2911964244","https://openalex.org/W2919115771","https://openalex.org/W2945976633","https://openalex.org/W2963163009","https://openalex.org/W2963909453","https://openalex.org/W2982083293","https://openalex.org/W3010528756","https://openalex.org/W3011751313","https://openalex.org/W3012514909","https://openalex.org/W3022298203","https://openalex.org/W3038898937","https://openalex.org/W3098136764","https://openalex.org/W3108033633","https://openalex.org/W3121689374","https://openalex.org/W3130571442","https://openalex.org/W3131071874","https://openalex.org/W3136172274","https://openalex.org/W3155243801","https://openalex.org/W3155949183","https://openalex.org/W3156127671","https://openalex.org/W3157306683","https://openalex.org/W3197816522","https://openalex.org/W3200583622","https://openalex.org/W3203600045","https://openalex.org/W3206418100","https://openalex.org/W3209503812","https://openalex.org/W4205916020","https://openalex.org/W4206790491","https://openalex.org/W4220691208","https://openalex.org/W4290991121","https://openalex.org/W6968987339"],"related_works":["https://openalex.org/W4321442002","https://openalex.org/W2015265939","https://openalex.org/W2284072287","https://openalex.org/W2611067230","https://openalex.org/W2387706296","https://openalex.org/W2155788121","https://openalex.org/W4235469518","https://openalex.org/W2480201319","https://openalex.org/W2294325978","https://openalex.org/W96612179"],"abstract_inverted_index":{"While":[0],"recent":[1],"deep":[2,50],"learning":[3,51],"workload":[4,52],"schedulers":[5],"exhibit":[6],"excellent":[7,151],"performance,":[8],"it":[9,145],"is":[10,69],"arduous":[11],"to":[12,18,88,104,136],"deploy":[13],"them":[14],"in":[15],"practice":[16],"due":[17],"some":[19],"substantial":[20],"defects,":[21],"including":[22],"inflexible":[23],"intrusive":[24],"manner,":[25],"exorbitant":[26],"integration":[27],"and":[28,45,76,101,114,150],"maintenance":[29,113],"cost,":[30],"limited":[31],"scalability,":[32],"as":[33,35],"well":[34],"opaque":[36],"decision":[37],"processes.":[38],"Motivated":[39],"by":[40,134],"these":[41],"issues,":[42],"we":[43],"design":[44],"implement":[46],"Lucid,":[47],"a":[48,65,119],"non-intrusive":[49],"scheduler":[53,142],"based":[54,95],"on":[55,96],"interpretable":[56],"models.":[57],"It":[58],"consists":[59],"of":[60],"three":[61],"innovative":[62],"modules.":[63],"First,":[64],"two-dimensional":[66],"optimized":[67],"profiler":[68],"introduced":[70],"for":[71,153],"efficient":[72,106],"job":[73,79,98,131],"metric":[74],"collection":[75],"timely":[77],"debugging":[78],"feedback.":[80],"Second,":[81],"Lucid":[82,92,109,127],"utilizes":[83],"an":[84],"indolent":[85],"packing":[86],"strategy":[87],"circumvent":[89],"interference.":[90],"Third,":[91],"orchestrates":[93],"resources":[94],"estimated":[97],"priority":[99],"values":[100],"sharing":[102],"scores":[103],"achieve":[105],"scheduling.":[107],"Additionally,":[108],"promotes":[110],"model":[111],"performance":[112],"system":[115,121,148],"transparent":[116],"adjustment":[117],"via":[118],"well-designed":[120],"optimizer.":[122],"Our":[123],"evaluation":[124],"shows":[125],"that":[126],"reduces":[128],"the":[129],"average":[130],"completion":[132],"time":[133],"up":[135],"1.3\u00d7":[137],"compared":[138],"with":[139],"state-of-the-art":[140],"preemptive":[141],"Tiresias.":[143],"Furthermore,":[144],"provides":[146],"explicit":[147],"interpretations":[149],"scalability":[152],"practical":[154],"deployment.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}