{"id":"https://openalex.org/W4400798745","doi":"https://doi.org/10.1145/3626203.3670632","title":"Orchestrating a DNN training job using an iScheduler Framework: a use case","display_name":"Orchestrating a DNN training job using an iScheduler Framework: a use case","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4400798745","doi":"https://doi.org/10.1145/3626203.3670632"},"language":"en","primary_location":{"id":"doi:10.1145/3626203.3670632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670632","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670632","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","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/10.1145/3626203.3670632","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036221367","display_name":"Manikya Swathi Vallabhajosyula","orcid":"https://orcid.org/0000-0002-9094-1722"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manikya Swathi Vallabhajosyula","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-9094-1722","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104682234","display_name":"Sandeep Satish Budhya","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Satish Budhya","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":"https://orcid.org/0009-0009-6905-5847","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102370125","display_name":"Akanksha Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akanksha Jain","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":"https://orcid.org/0009-0001-1895-4705","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111262026","display_name":"Maaz Baig","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maaz Baig","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":"https://orcid.org/0009-0009-0771-9863","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073535794","display_name":"Rajiv Ramnath","orcid":"https://orcid.org/0000-0003-0093-8560"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajiv Ramnath","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":"https://orcid.org/0000-0003-0093-8560","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11532449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9090999960899353,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9090999960899353,"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/training","display_name":"Training (meteorology)","score":0.7286879420280457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6769747734069824},{"id":"https://openalex.org/keywords/on-the-job-training","display_name":"On-the-job training","score":0.4900602102279663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41583120822906494},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.33340147137641907},{"id":"https://openalex.org/keywords/medical-education","display_name":"Medical education","score":0.19587212800979614}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7286879420280457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769747734069824},{"id":"https://openalex.org/C2778583658","wikidata":"https://www.wikidata.org/wiki/Q849415","display_name":"On-the-job training","level":3,"score":0.4900602102279663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41583120822906494},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.33340147137641907},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.19587212800979614},{"id":"https://openalex.org/C540751848","wikidata":"https://www.wikidata.org/wiki/Q6500754","display_name":"Internship","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626203.3670632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670632","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670632","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626203.3670632","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626203.3670632","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3626203.3670632","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G3607349625","display_name":null,"funder_award_id":"OAC-2112606","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400798745.pdf","grobid_xml":"https://content.openalex.org/works/W4400798745.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4386585077"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W3200271835","https://openalex.org/W590367774","https://openalex.org/W1996163466","https://openalex.org/W250806075","https://openalex.org/W2034041692"],"abstract_inverted_index":{"Orchestrating":[0],"DNN":[1,86,119],"training":[2,87,120],"jobs":[3],"efficiently":[4],"on":[5],"HPC":[6],"centers":[7],"such":[8],"as":[9],"Ohio":[10],"Supercomputer":[11,22],"Center":[12,17,23],"(OSC),":[13],"Texas":[14],"Advanced":[15],"Computing":[16],"(TACC),":[18],"and":[19,48,62,97,129,139,146],"San":[20],"Diego":[21],"(SDSC)":[24],"is":[25],"crucial":[26],"due":[27],"to":[28,56,81],"the":[29,72,108,112,136,147],"prevalence":[30],"of":[31,43,74,111],"AI-driven":[32],"workloads.":[33],"However,":[34],"managing":[35],"these":[36,68],"workloads":[37],"effectively":[38],"requires":[39],"a":[40,117],"deep":[41],"understanding":[42],"available":[44],"resources,":[45],"allocation":[46,128],"policies,":[47],"suitable":[49],"execution":[50,101],"configurations.":[51],"Current":[52],"approaches":[53],"often":[54],"lead":[55],"job":[57],"interruptions,":[58],"prolonged":[59],"wait":[60],"times,":[61],"inefficient":[63],"resource":[64,90,127],"utilization.":[65],"To":[66],"address":[67],"challenges,":[69],"we":[70,106],"propose":[71],"deployment":[73],"an":[75,99],"iScheduler":[76,113,145],"framework.":[77],"This":[78,131],"framework":[79,114],"aims":[80],"automate":[82],"workflow":[83],"orchestration":[84],"for":[85],"by":[88],"estimating":[89],"needs":[91],"(using":[92],"existing":[93],"state-of-art":[94],"estimation":[95],"models)":[96],"generating":[98],"infrastructure-aware":[100],"plan.":[102],"In":[103],"this":[104],"study,":[105],"demonstrate":[107],"practical":[109],"application":[110],"in":[115,125],"orchestrating":[116],"user-specific":[118],"workflow,":[121],"showcasing":[122],"its":[123],"capabilities":[124],"optimizing":[126],"scheduling.":[130],"poster":[132],"dives":[133],"deeper":[134],"into":[135],"user":[137,142],"case":[138],"shows":[140],"all":[141],"interactions":[143],"with":[144],"responses.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
