{"id":"https://openalex.org/W4290927676","doi":"https://doi.org/10.1145/3534678.3539036","title":"Profiling Deep Learning Workloads at Scale using Amazon SageMaker","display_name":"Profiling Deep Learning Workloads at Scale using Amazon SageMaker","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290927676","doi":"https://doi.org/10.1145/3534678.3539036"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539036","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","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/A5103522507","display_name":"Nathalie Rauschmayr","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nathalie Rauschmayr","raw_affiliation_strings":["Amazon Web Services, Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Vancouver, BC, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109895814","display_name":"S. Kama","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sami Kama","raw_affiliation_strings":["Amazon Web Services, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062000059","display_name":"Muhyun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhyun Kim","raw_affiliation_strings":["Amazon Web Services, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002210245","display_name":"Miyoung Choi","orcid":"https://orcid.org/0000-0002-2424-9965"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miyoung Choi","raw_affiliation_strings":["Amazon Web Services, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002843568","display_name":"Krishnaram Kenthapadi","orcid":"https://orcid.org/0000-0003-1237-087X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishnaram Kenthapadi","raw_affiliation_strings":["Fiddler AI, Palo Alto, CA, USA"],"affiliations":[{"raw_affiliation_string":"Fiddler AI, Palo Alto, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103522507"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6295,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.6759063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3801","last_page":"3809"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9954000115394592,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9952999949455261,"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/profiling","display_name":"Profiling (computer programming)","score":0.8429301977157593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8118929862976074},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7144659757614136},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6944534182548523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5841560363769531},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5663247108459473},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49168258905410767},{"id":"https://openalex.org/keywords/debugger","display_name":"Debugger","score":0.450533390045166},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3562858998775482},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.19693192839622498},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18300068378448486},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.13683485984802246}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8429301977157593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118929862976074},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7144659757614136},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6944534182548523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5841560363769531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5663247108459473},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49168258905410767},{"id":"https://openalex.org/C2778485113","wikidata":"https://www.wikidata.org/wiki/Q193231","display_name":"Debugger","level":3,"score":0.450533390045166},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3562858998775482},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.19693192839622498},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18300068378448486},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.13683485984802246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539036","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539036","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2136434791","https://openalex.org/W2144429536","https://openalex.org/W2964330541","https://openalex.org/W2967558351","https://openalex.org/W2977730164","https://openalex.org/W3005940936","https://openalex.org/W3006889321","https://openalex.org/W3037032032","https://openalex.org/W3042448927","https://openalex.org/W3049119995","https://openalex.org/W3099748883","https://openalex.org/W3101330584","https://openalex.org/W3105067168","https://openalex.org/W3112048118"],"related_works":["https://openalex.org/W2097578226","https://openalex.org/W2107838126","https://openalex.org/W2153803916","https://openalex.org/W2534779484","https://openalex.org/W2560326218","https://openalex.org/W2101770730","https://openalex.org/W176693245","https://openalex.org/W1998807269","https://openalex.org/W2394149918","https://openalex.org/W1751798423"],"abstract_inverted_index":{"With":[0],"the":[1,28,44,113],"rise":[2],"of":[3,30,32,46,68],"deep":[4,47],"learning":[5,8,48],"(DL),":[6],"machine":[7],"(ML)":[9],"has":[10],"become":[11],"compute":[12],"and":[13,37,53,92,106,147,159,172],"data":[14],"intensive,":[15],"typically":[16],"requiring":[17],"multi-node":[18],"multi-GPU":[19],"clusters.":[20],"As":[21],"state-of-the-art":[22],"models":[23,100],"grow":[24],"in":[25,27,139],"size":[26],"order":[29],"trillions":[31],"parameters,":[33],"their":[34],"computational":[35],"complexity":[36],"cost":[38,45],"also":[39],"increase":[40],"rapidly.":[41],"Since":[42],"2012,":[43],"doubled":[49],"roughly":[50],"every":[51],"quarter,":[52],"this":[54,78],"trend":[55],"is":[56],"likely":[57],"to":[58,63,119,134,157],"continue.":[59],"ML":[60],"practitioners":[61],"have":[62],"cope":[64],"with":[65,109],"common":[66],"challenges":[67],"efficient":[69],"resource":[70,166],"utilization":[71,90],"when":[72],"training":[73,141,170],"such":[74],"large":[75],"models.":[76],"In":[77],"paper,":[79],"we":[80,151],"propose":[81],"a":[82,123],"new":[83],"profiling":[84,98,114],"tool":[85,96],"that":[86,126,153],"cross-correlates":[87],"relevant":[88],"system":[89,131],"metrics":[91],"framework":[93],"operations.":[94],"The":[95],"supports":[97],"DL":[99,140],"at":[101],"scale,":[102],"identifies":[103],"performance":[104],"bottlenecks,":[105],"provides":[107],"insights":[108],"recommendations.":[110],"We":[111],"deployed":[112],"functionality":[115],"as":[116],"an":[117,128],"add-on":[118],"Amazon":[120],"SageMaker":[121],"Debugger,":[122],"fully-managed":[124],"service":[125],"leverages":[127],"on-the-fly":[129],"analysis":[130],"(called":[132],"rules)":[133],"automatically":[135],"identify":[136,158],"complex":[137],"issues":[138,161],"jobs.":[142],"By":[143],"presenting":[144],"deployment":[145],"results":[146],"customer":[148],"case":[149],"studies,":[150],"show":[152],"it":[154],"enables":[155],"users":[156],"fix":[160],"caused":[162],"by":[163],"inefficient":[164],"hardware":[165],"usage,":[167],"thereby":[168],"reducing":[169],"time":[171],"cost.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}