{"id":"https://openalex.org/W4416401445","doi":"https://doi.org/10.1145/3767295.3769366","title":"Maya: Optimizing Deep Learning Training Workloads using GPU Runtime Emulation","display_name":"Maya: Optimizing Deep Learning Training Workloads using GPU Runtime Emulation","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W4416401445","doi":"https://doi.org/10.1145/3767295.3769366"},"language":"en","primary_location":{"id":"doi:10.1145/3767295.3769366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769366","pdf_url":null,"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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3767295.3769366","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Srihas Yarlagadda","orcid":"https://orcid.org/0009-0005-4020-3931"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Srihas Yarlagadda","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0009-0005-4020-3931","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103066009","display_name":"Amey Agrawal","orcid":"https://orcid.org/0000-0003-2286-577X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amey Agrawal","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0003-2286-577X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043541606","display_name":"Elton M\u00e1rtires Pinto","orcid":"https://orcid.org/0000-0002-1348-4185"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elton Pinto","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0000-0002-4570-5333","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120508126","display_name":"Hakesh Darapaneni","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakesh Darapaneni","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0009-0003-2878-0571","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071926716","display_name":"Mitali Meratwal","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitali Meratwal","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0009-0007-9381-479X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034433732","display_name":"Shivam Kumar Mittal","orcid":"https://orcid.org/0009-0002-6438-5491"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivam Mittal","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0009-0003-9173-026X","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120556466","display_name":"Pranavi Bajjuri","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pranavi Bajjuri","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0009-0001-0065-2522","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102919742","display_name":"Srinivas Sridharan","orcid":"https://orcid.org/0009-0001-0651-370X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Sridharan","raw_affiliation_strings":["Nvidia Inc., Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0009-0001-0651-370X","affiliations":[{"raw_affiliation_string":"Nvidia Inc., Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048451114","display_name":"Alexey Tumanov","orcid":"https://orcid.org/0009-0005-7862-1477"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexey Tumanov","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":"https://orcid.org/0009-0005-7862-1477","affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00863309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1738","last_page":"1758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.390500009059906,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.390500009059906,"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/T12127","display_name":"Software System Performance and Reliability","score":0.17309999465942383,"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":0.09749999642372131,"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/workload","display_name":"Workload","score":0.6478999853134155},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.6419000029563904},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5719000101089478},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5565999746322632},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.521399974822998},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.45730000734329224},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.44769999384880066},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4083000123500824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116999864578247},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6478999853134155},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.6419000029563904},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5565999746322632},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.521399974822998},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.45730000734329224},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40220001339912415},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3968000113964081},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3682999908924103},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3767295.3769366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769366","pdf_url":null,"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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.20191","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.20191","pdf_url":"https://arxiv.org/pdf/2503.20191","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3767295.3769366","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767295.3769366","pdf_url":null,"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 21st European Conference on Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4867877946","display_name":null,"funder_award_id":"CNS-2420977","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"large":[1],"foundation":[2],"models":[3],"costs":[4],"hundreds":[5],"of":[6,8,36,83],"millions":[7],"dollars,":[9],"making":[10],"deployment":[11],"optimization":[12],"critical.":[13],"Current":[14],"approaches":[15],"require":[16,88],"machine":[17],"learning":[18],"engineers":[19],"to":[20,50,85],"manually":[21],"craft":[22],"training":[23,37],"recipes":[24],"through":[25],"error-prone":[26],"trial-and-error":[27],"on":[28],"expensive":[29],"compute":[30],"clusters.":[31],"To":[32],"enable":[33],"efficient":[34],"exploration":[35],"configurations,":[38],"researchers":[39],"have":[40],"developed":[41],"performance":[42,101],"modeling":[43],"systems.":[44],"However,":[45],"these":[46],"systems":[47,76],"force":[48],"users":[49],"translate":[51],"their":[52],"workloads":[53,84],"into":[54],"custom":[55],"specification":[56],"languages,":[57],"introducing":[58],"a":[59,80],"fundamental":[60],"semantic":[61],"gap":[62,71],"between":[63],"the":[64],"actual":[65],"workload":[66],"and":[67],"its":[68],"representation.":[69],"This":[70],"creates":[72],"an":[73],"inherent":[74],"tradeoff:":[75],"must":[77],"either":[78],"support":[79],"narrow":[81],"set":[82],"maintain":[86],"usability,":[87],"complex":[89],"specifications":[90],"that":[91],"limit":[92],"practical":[93],"adoption,":[94],"or":[95],"compromise":[96],"prediction":[97],"accuracy":[98],"with":[99],"simplified":[100],"models.":[102]},"counts_by_year":[],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}