{"id":"https://openalex.org/W4400798820","doi":"https://doi.org/10.1145/3626203.3670555","title":"Reference Implementation of Smart Scheduler: A CI-Aware, AI-Driven Scheduling Framework for HPC Workloads","display_name":"Reference Implementation of Smart Scheduler: A CI-Aware, AI-Driven Scheduling Framework for HPC Workloads","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4400798820","doi":"https://doi.org/10.1145/3626203.3670555"},"language":"en","primary_location":{"id":"doi:10.1145/3626203.3670555","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626203.3670555","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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":"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":2.234,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.87361206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980999827384949,"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":0.9980999827384949,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9907000064849854,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9829999804496765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8503221869468689},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6485947966575623},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5014450550079346},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.43865087628364563},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43281590938568115},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4087791442871094},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32658514380455017},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05464157462120056},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.05252695083618164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503221869468689},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6485947966575623},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5014450550079346},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.43865087628364563},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43281590938568115},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4087791442871094},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32658514380455017},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05464157462120056},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.05252695083618164},{"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:10.1145/3626203.3670555","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626203.3670555","pdf_url":null,"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":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W3035078899","https://openalex.org/W3156001951","https://openalex.org/W4284958556","https://openalex.org/W4386585077","https://openalex.org/W4388662073"],"related_works":["https://openalex.org/W1809394610","https://openalex.org/W2128410848","https://openalex.org/W2101285930","https://openalex.org/W2102390841","https://openalex.org/W2118368532","https://openalex.org/W2126232624","https://openalex.org/W2434525066","https://openalex.org/W3140149227","https://openalex.org/W2130555437","https://openalex.org/W3023290810"],"abstract_inverted_index":{"Many":[0],"modern":[1],"scientific":[2],"workloads":[3,24,116],"in":[4],"HPC":[5],"centers":[6],"rely":[7],"heavily":[8],"on":[9],"AI-driven":[10],"tasks,":[11],"particularly":[12],"deep":[13],"neural":[14],"network":[15],"(DNN)":[16],"training":[17,213],"workloads.":[18],"Efficiently":[19],"managing":[20],"and":[21,37,48,87,117,119,138,196],"scheduling":[22,51],"these":[23],"via":[25],"SLURM":[26,172],"interfaces":[27],"requires":[28],"users":[29],"to":[30,66,75,79,131,145,155,186],"comprehensively":[31],"understand":[32],"available":[33,64],"resources,":[34],"allocation":[35],"policies,":[36],"suitable":[38],"execution":[39,193],"configurations":[40],"aligned":[41],"with":[42],"their":[43],"models\u2019":[44],"estimated":[45],"resource":[46,85,125,173],"requirements":[47],"constraints.":[49],"Typically,":[50],"jobs":[52,198],"involves":[53],"using":[54],"default":[55],"configurations,":[56],"adjusting":[57],"them":[58],"as":[59],"needed,":[60],"or":[61],"requesting":[62],"maximum":[63],"limits":[65],"ensure":[67],"uninterrupted":[68],"execution.":[69,149],"However,":[70],"this":[71],"approach":[72],"can":[73,112],"lead":[74],"job":[76,148],"interruptions":[77],"due":[78],"underprovisioning,":[80],"prolonged":[81],"wait":[82],"times,":[83],"inefficient":[84],"utilization,":[86],"increased":[88],"costs":[89],"from":[90],"overprovisioning.":[91],"These":[92],"issues":[93],"ultimately":[94],"degrade":[95],"cluster":[96],"performance,":[97],"emphasizing":[98],"the":[99,114,161,170,203],"need":[100],"for":[101],"a":[102,147,157,191,210],"more":[103],"efficient":[104],"solution":[105],"like":[106],"an":[107,165,177],"AI-enabled":[108,178],"Scheduler":[109],"framework":[110,158,207],"that":[111,159,180],"profile":[113],"DNN":[115,212],"estimate":[118],"provision":[120],"resources":[121],"dynamically.":[122],"The":[123],"existing":[124],"estimation":[126],"models":[127],"are":[128],"trained":[129],"independently":[130],"predict":[132],"various":[133],"aspects":[134],"of":[135,163,205],"batch":[136],"processing":[137],"scheduling,":[139],"which":[140,168],"do":[141],"not":[142],"work":[143],"cohesively":[144],"orchestrate":[146,187],"In":[150],"our":[151,206],"work,":[152],"we":[153],"propose":[154],"introduce":[156],"investigates":[160],"feasibility":[162,204],"implementing":[164],"iScheduler":[166],"framework,":[167],"transforms":[169],"traditional":[171],"provisioning":[174],"workflow":[175,188],"into":[176],"scheduler":[179],"plugs":[181],"different":[182],"estimators":[183],"where":[184],"needed":[185],"by":[189,208],"generating":[190],"cyberinfrastructure-aware":[192],"plan,":[194],"schedules":[195],"monitors":[197],"till":[199],"completion.":[200],"We":[201],"demonstrate":[202],"orchestrating":[209],"user-specific":[211],"workload.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}