{"id":"https://openalex.org/W4368353224","doi":"https://doi.org/10.1145/3578356.3592589","title":"Profiling and Monitoring Deep Learning Training Tasks","display_name":"Profiling and Monitoring Deep Learning Training Tasks","publication_year":2023,"publication_date":"2023-05-04","ids":{"openalex":"https://openalex.org/W4368353224","doi":"https://doi.org/10.1145/3578356.3592589"},"language":"en","primary_location":{"id":"doi:10.1145/3578356.3592589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578356.3592589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.itu.dk/portal/da/publications/1bfc6ba0-f044-4ad1-9511-27c1e9925dcf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046504176","display_name":"Ehsan Yousefzadeh-Asl-Miandoab","orcid":"https://orcid.org/0000-0003-0156-1435"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ehsan Yousefzadeh-Asl-Miandoab","raw_affiliation_strings":["Computer Science, IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-0156-1435","affiliations":[{"raw_affiliation_string":"Computer Science, IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006238663","display_name":"Ties Robroek","orcid":"https://orcid.org/0009-0006-3451-5602"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ties Robroek","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0009-0006-3451-5602","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061990490","display_name":"P\u0131nar T\u00f6z\u00fcn","orcid":"https://orcid.org/0000-0001-6838-4854"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Pinar Tozun","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-6838-4854","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9071,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88001459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9968000054359436,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.9034441709518433},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8418700695037842},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5448616743087769},{"id":"https://openalex.org/keywords/embarrassingly-parallel","display_name":"Embarrassingly parallel","score":0.43041619658470154},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42299988865852356},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41635024547576904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40339723229408264},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35669368505477905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3208414614200592},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.27044975757598877},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2380352020263672},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.1262342929840088}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.9034441709518433},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8418700695037842},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5448616743087769},{"id":"https://openalex.org/C126909462","wikidata":"https://www.wikidata.org/wiki/Q5369501","display_name":"Embarrassingly parallel","level":3,"score":0.43041619658470154},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42299988865852356},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41635024547576904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40339723229408264},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35669368505477905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3208414614200592},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27044975757598877},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2380352020263672},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.1262342929840088}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3578356.3592589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3578356.3592589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd Workshop on Machine Learning and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/1bfc6ba0-f044-4ad1-9511-27c1e9925dcf","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/1bfc6ba0-f044-4ad1-9511-27c1e9925dcf","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yousefzadeh-Asl-Miandoab , E , Robroek , T T & T\u00f6z\u00fcn , P 2023 , ' Profiling and Monitoring Deep Learning Training Tasks ' , EuroMLSys '23 , pp. 18\u201325 . https://doi.org/10.1145/3578356.3592589","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/bfb83b46-73f5-494f-a042-a5f9b0e96c82","is_oa":false,"landing_page_url":"https://pure.itu.dk/portal/da/publications/bfb83b46-73f5-494f-a042-a5f9b0e96c82","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yousefzadeh-Asl-Miandoab, E, Robroek, T & T\u00f6z\u00fcn, P 2023, Profiling and Monitoring Deep Learning Training Tasks. in Proceedings of the 3rd Workshop on Machine Learning and Systems. Association for Computing Machinery, New York, pp. 18-25, Machine Learning and Systems, Rome, Italy, 08/05/2023. https://doi.org/10.1145/3578356.3592589","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/1bfc6ba0-f044-4ad1-9511-27c1e9925dcf","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/1bfc6ba0-f044-4ad1-9511-27c1e9925dcf","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yousefzadeh-Asl-Miandoab , E , Robroek , T T & T\u00f6z\u00fcn , P 2023 , ' Profiling and Monitoring Deep Learning Training Tasks ' , EuroMLSys '23 , pp. 18\u201325 . https://doi.org/10.1145/3578356.3592589","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G8774442388","display_name":null,"funder_award_id":"0171-00061B","funder_id":"https://openalex.org/F4320322928","funder_display_name":"Danmarks Frie Forskningsfond"}],"funders":[{"id":"https://openalex.org/F4320322928","display_name":"Danmarks Frie Forskningsfond","ror":"https://ror.org/02sptwz63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2007339694","https://openalex.org/W2050078636","https://openalex.org/W2117539524","https://openalex.org/W2136434791","https://openalex.org/W2170952599","https://openalex.org/W2610776462","https://openalex.org/W2970139027","https://openalex.org/W2999812057","https://openalex.org/W3008227512","https://openalex.org/W3128271665","https://openalex.org/W3137350414","https://openalex.org/W4282981531"],"related_works":["https://openalex.org/W1522943736","https://openalex.org/W4295122399","https://openalex.org/W2001581899","https://openalex.org/W1826438552","https://openalex.org/W2122454857","https://openalex.org/W2093790547","https://openalex.org/W4295125675","https://openalex.org/W4375867731","https://openalex.org/W2161444195","https://openalex.org/W4368353224"],"abstract_inverted_index":{"The":[0,18],"embarrassingly":[1],"parallel":[2],"nature":[3],"of":[4,23,47,57,74,95,105,154],"deep":[5,80],"learning":[6,81],"training":[7,48,82,115],"tasks":[8,49,83],"makes":[9],"CPU-GPU":[10],"co-processors":[11,51],"the":[12,33,45,55,72,92,96,100,143,152,160,184,201],"primary":[13],"commodity":[14],"hardware":[15],"for":[16,76,133],"them.":[17],"computing":[19],"and":[20,43,78,103,113,125,189],"memory":[21],"requirements":[22,56],"these":[24],"tasks,":[25],"however,":[26],"do":[27],"not":[28],"always":[29],"align":[30],"well":[31],"with":[32,130],"available":[34],"GPU":[35,161,179,193],"resources.":[36],"It":[37],"is,":[38],"therefore,":[39],"important":[40],"to":[41,52,67,90,138,148,156,166,173],"monitor":[42],"profile":[44],"behavior":[46],"on":[50,71,84,197],"understand":[53],"better":[54],"different":[58],"use":[59],"cases.":[60],"In":[61,88],"this":[62],"paper,":[63],"our":[64],"goal":[65],"is":[66],"shed":[68],"more":[69],"light":[70,112],"variety":[73],"tools":[75,122],"profiling":[77],"monitoring":[79,121],"server-grade":[85],"NVIDIA":[86],"GPUs.":[87],"addition":[89],"surveying":[91],"main":[93],"characteristics":[94],"tools,":[97],"we":[98],"analyze":[99],"functional":[101],"limitations":[102],"overheads":[104],"each":[106,168],"tool":[107,169],"by":[108],"using":[109],"a":[110,175,191],"both":[111],"heavy":[114],"scenario.":[116],"Our":[117],"results":[118],"show":[119],"that":[120],"like":[123],"nvidia-smi":[124],"dcgm":[126],"can":[127,181,195],"be":[128,149],"integrated":[129],"resource":[131],"managers":[132],"online":[134],"decision":[135],"making":[136],"thanks":[137],"their":[139],"low":[140],"overheads.":[141],"On":[142],"other":[144],"hand,":[145],"one":[146],"has":[147,170],"careful":[150],"about":[151,159],"set":[153],"metrics":[155],"correctly":[157],"reason":[158],"utilization.":[162],"When":[163],"it":[164],"comes":[165],"profiling,":[167],"its":[171],"time":[172],"shine;":[174],"framework-based":[176],"or":[177,187],"system-wide":[178],"profiler":[180,194],"first":[182],"detect":[183],"frequent":[185],"kernels":[186,199],"bottlenecks,":[188],"then,":[190],"lower-level":[192],"focus":[196],"particular":[198],"at":[200],"micro-architectural-level.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}