{"id":"https://openalex.org/W4399282536","doi":"https://doi.org/10.1145/3650200.3656598","title":"AutoSched: An Adaptive Self-configured Framework for Scheduling Deep Learning Training Workloads","display_name":"AutoSched: An Adaptive Self-configured Framework for Scheduling Deep Learning Training Workloads","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399282536","doi":"https://doi.org/10.1145/3650200.3656598"},"language":"en","primary_location":{"id":"doi:10.1145/3650200.3656598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656598","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656598","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","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/10.1145/3650200.3656598","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100732619","display_name":"Wei Gao","orcid":"https://orcid.org/0000-0002-7048-1722"},"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":"Wei Gao","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7048-1722","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437329","display_name":"Xu Zhang","orcid":"https://orcid.org/0009-0004-5608-6955"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Chongqing University, China"],"raw_orcid":"https://orcid.org/0009-0004-5608-6955","affiliations":[{"raw_affiliation_string":"Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061145765","display_name":"Shan Huang","orcid":"https://orcid.org/0009-0009-8491-4873"},"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":"Shan Huang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0009-0009-8491-4873","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073264981","display_name":"Shangwei Guo","orcid":"https://orcid.org/0000-0002-6443-5308"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangwei Guo","raw_affiliation_strings":["Chongqing University, China"],"raw_orcid":"https://orcid.org/0000-0002-6443-5308","affiliations":[{"raw_affiliation_string":"Chongqing University, China","institution_ids":["https://openalex.org/I158842170"]}]},{"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 and Shanghai AI Lab, China"],"raw_orcid":"https://orcid.org/0000-0001-8456-0491","affiliations":[{"raw_affiliation_string":"SenseTime, China and Shanghai AI Lab, 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":"https://orcid.org/0000-0002-2751-5114","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":"https://orcid.org/0000-0001-6595-6650","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"473","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.8375274538993835},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.8151408433914185},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.7303003668785095},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6153941750526428},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.467180073261261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4273764193058014},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.37662604451179504},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30362534523010254},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0679735541343689}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375274538993835},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.8151408433914185},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7303003668785095},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6153941750526428},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.467180073261261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4273764193058014},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37662604451179504},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30362534523010254},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0679735541343689},{"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:10.1145/3650200.3656598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656598","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656598","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650200.3656598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656598","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656598","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399282536.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2032430826","https://openalex.org/W2066787289","https://openalex.org/W2093701909","https://openalex.org/W2613206411","https://openalex.org/W2783614532","https://openalex.org/W2798515322","https://openalex.org/W2922457781","https://openalex.org/W3022298203","https://openalex.org/W3022630129","https://openalex.org/W3092126302","https://openalex.org/W3122749996","https://openalex.org/W3163661296","https://openalex.org/W3205395194","https://openalex.org/W3206418100","https://openalex.org/W3209503812","https://openalex.org/W4205916020","https://openalex.org/W4220691208","https://openalex.org/W4366504025","https://openalex.org/W4388076418"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2414054180"],"abstract_inverted_index":{"Modern":[0],"Deep":[1],"Learning":[2],"Training":[3],"(DLT)":[4],"schedulers":[5,34],"in":[6,57],"GPU":[7],"datacenters":[8],"are":[9,47],"designed":[10],"to":[11,21,39],"be":[12,22],"very":[13],"sophisticated":[14],"with":[15],"many":[16],"configurations.":[17],"These":[18],"configurations":[19,42,77],"need":[20],"adjusted":[23],"delicately":[24],"as":[25],"they":[26,46],"can":[27],"significantly":[28],"affect":[29],"the":[30,36,41,51,69,75],"scheduling":[31],"performance.":[32],"Existing":[33],"require":[35],"datacenter":[37,59],"operator":[38],"tune":[40],"only":[43],"once":[44],"before":[45],"deployed,":[48],"based":[49],"on":[50],"historical":[52,70],"workload":[53],"traces.":[54],"Unfortunately,":[55],"workloads":[56],"a":[58,66],"would":[60],"experience":[61],"dynamic":[62],"changes":[63],"and":[64],"deviate":[65],"lot":[67],"from":[68],"ones":[71],"over":[72],"time,":[73],"making":[74],"pre-determined":[76],"less":[78],"effective.":[79]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}