{"id":"https://openalex.org/W4395483140","doi":"https://doi.org/10.1145/3629526.3645035","title":"MalleTrain: Deep Neural Networks Training on Unfillable Supercomputer Nodes","display_name":"MalleTrain: Deep Neural Networks Training on Unfillable Supercomputer Nodes","publication_year":2024,"publication_date":"2024-05-06","ids":{"openalex":"https://openalex.org/W4395483140","doi":"https://doi.org/10.1145/3629526.3645035"},"language":"en","primary_location":{"id":"doi:10.1145/3629526.3645035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645035","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 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3629526.3645035","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030474448","display_name":"Xiaolong Ma","orcid":"https://orcid.org/0009-0009-1374-7086"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaolong Ma","raw_affiliation_strings":["University of Nevada, Reno, Reno, NV, USA","University of Houston Houston, Texas, USA","University of Nevada, Reno Reno, Nevada, USA","University of Chicago Chicago, Illinois, USA","University of Illinois Chicago Chicago, Illinois, USA","Argonne National Laboratory Lemont, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Nevada, Reno, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Houston Houston, Texas, USA","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Nevada, Reno Reno, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Illinois Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"Argonne National Laboratory Lemont, Illinois, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381152","display_name":"Feng Yan","orcid":"https://orcid.org/0000-0001-9840-7754"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Yan","raw_affiliation_strings":["University of Houston, Houston, TX, USA","University of Chicago Chicago, Illinois, USA","University of Illinois Chicago Chicago, Illinois, USA","University of Houston Houston, Texas, USA","University of Nevada, Reno Reno, Nevada, USA","Argonne National Laboratory Lemont, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Illinois Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Houston Houston, Texas, USA","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Nevada, Reno Reno, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"Argonne National Laboratory Lemont, Illinois, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072565301","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-5176-003X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["University of Nevada, Reno, Reno, NV, USA","University of Chicago Chicago, Illinois, USA","University of Nevada, Reno Reno, Nevada, USA","Argonne National Laboratory Lemont, Illinois, USA","University of Illinois Chicago Chicago, Illinois, USA","University of Houston Houston, Texas, USA"],"affiliations":[{"raw_affiliation_string":"University of Nevada, Reno, Reno, NV, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Nevada, Reno Reno, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"Argonne National Laboratory Lemont, Illinois, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"University of Illinois Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Houston Houston, Texas, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["Argonne National Laboratory &amp; University of Chicago, Lemont, IL, USA","University of Nevada, Reno Reno, Nevada, USA","University of Chicago Chicago, Illinois, USA","University of Illinois Chicago Chicago, Illinois, USA","University of Houston Houston, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory &amp; University of Chicago, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Nevada, Reno Reno, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Illinois Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Houston Houston, Texas, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010928934","display_name":"Michael E. Papka","orcid":"https://orcid.org/0000-0002-6418-5767"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael E. Papka","raw_affiliation_strings":["Argonne National Laboratory &amp; University of Illinois Chicago, Lemont, IL, USA","University of Houston Houston, Texas, USA","University of Illinois Chicago Chicago, Illinois, USA","University of Nevada, Reno Reno, Nevada, USA","University of Chicago Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory &amp; University of Illinois Chicago, Lemont, IL, USA","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I1282105669","https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Houston Houston, Texas, USA","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Illinois Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Nevada, Reno Reno, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101649257","display_name":"Zhengchun Liu","orcid":"https://orcid.org/0000-0002-6647-4423"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengchun Liu","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA","University of Nevada, Reno Reno, Nevada, USA","University of Chicago Chicago, Illinois, USA","University of Illinois Chicago Chicago, Illinois, USA","University of Houston Houston, Texas, USA","Argonne National Laboratory Lemont, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"University of Nevada, Reno Reno, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Illinois Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]},{"raw_affiliation_string":"University of Houston Houston, Texas, USA","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"Argonne National Laboratory Lemont, Illinois, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068373159","display_name":"Rajkumar Kettimuthu","orcid":"https://orcid.org/0000-0002-0046-9883"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajkumar Kettimuthu","raw_affiliation_strings":["Argonne National Laboratory &amp; University of Chicago, Lemont, IL, USA","University of Houston Houston, Texas, USA","University of Nevada, Reno Reno, Nevada, USA","University of Chicago Chicago, Illinois, USA","University of Illinois Chicago Chicago, Illinois, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory &amp; University of Chicago, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Houston Houston, Texas, USA","institution_ids":["https://openalex.org/I44461941"]},{"raw_affiliation_string":"University of Nevada, Reno Reno, Nevada, USA","institution_ids":["https://openalex.org/I134113660"]},{"raw_affiliation_string":"University of Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"University of Illinois Chicago Chicago, Illinois, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5030474448"],"corresponding_institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I134113660","https://openalex.org/I39422238","https://openalex.org/I40347166","https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":0.9657,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7497254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"200"},"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":0.9987000226974487,"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":0.9979000091552734,"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/supercomputer","display_name":"Supercomputer","score":0.8824061155319214},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8456425666809082},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7900058627128601},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.627444863319397},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6174353361129761},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5992481112480164},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5002608299255371},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.4772926867008209},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.45762383937835693},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.45395228266716003},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4321436583995819},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4174201488494873},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40533655881881714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.366740345954895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36655718088150024},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3389469385147095},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20644918084144592},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.08765357732772827}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8824061155319214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456425666809082},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7900058627128601},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.627444863319397},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6174353361129761},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5992481112480164},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5002608299255371},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.4772926867008209},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.45762383937835693},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.45395228266716003},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4321436583995819},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4174201488494873},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40533655881881714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.366740345954895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36655718088150024},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3389469385147095},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20644918084144592},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.08765357732772827},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3629526.3645035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645035","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 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.15668","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.15668","pdf_url":"https://arxiv.org/pdf/2404.15668","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"},{"id":"pmh:oai:uchicago.tind.io:11726","is_oa":true,"landing_page_url":"http://knowledge.uchicago.edu/record/11726","pdf_url":null,"source":{"id":"https://openalex.org/S4306402460","display_name":"Knowledge@UChicago (University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40347166","host_organization_name":"University of Chicago","host_organization_lineage":["https://openalex.org/I40347166"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://knowledge.uchicago.edu/record/11726","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3629526.3645035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629526.3645035","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 15th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1015216249","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1116540683","display_name":null,"funder_award_id":"DE-AC02-06CH11","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1313983767","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G1844751952","display_name":null,"funder_award_id":"DE-AC02_06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G2777053550","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3000213308","display_name":null,"funder_award_id":"DE-AC02-06CH113","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G3075337988","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G3801222974","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4145457401","display_name":null,"funder_award_id":"DE-AC02-06CH113","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5085543421","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G6044687550","display_name":"CAREER: Automated and Efficient Machine Learning as a Service","funder_award_id":"2048044","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6085113958","display_name":null,"funder_award_id":"E-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G650626725","display_name":null,"funder_award_id":"E-AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6667550434","display_name":null,"funder_award_id":"CAREER-2048044","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7230044214","display_name":null,"funder_award_id":"DE-AC02-06CH1135","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G7351994996","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8143874970","display_name":null,"funder_award_id":"AC02-06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8314672274","display_name":null,"funder_award_id":"DE-AC02-06CH11","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1596936080","https://openalex.org/W1986340747","https://openalex.org/W2014594876","https://openalex.org/W2085222386","https://openalex.org/W2112168774","https://openalex.org/W2123100429","https://openalex.org/W2155187164","https://openalex.org/W2946894050","https://openalex.org/W2962747323","https://openalex.org/W2964081807","https://openalex.org/W2965658867","https://openalex.org/W2996822528","https://openalex.org/W3037833767","https://openalex.org/W3080451848","https://openalex.org/W3175707606","https://openalex.org/W4312809242","https://openalex.org/W4323834595","https://openalex.org/W4383749386","https://openalex.org/W6774926797"],"related_works":["https://openalex.org/W2525033434","https://openalex.org/W4280533024","https://openalex.org/W1966243865","https://openalex.org/W4300992253","https://openalex.org/W1942762218","https://openalex.org/W1985270856","https://openalex.org/W1582436825","https://openalex.org/W3101274117","https://openalex.org/W4298207756","https://openalex.org/W1966875563"],"abstract_inverted_index":{"First-come":[0],"first-serve":[1],"scheduling":[2],"can":[3],"result":[4],"in":[5,51,144],"substantial":[6],"(up":[7],"to":[8,30,48,95,112,127,139,206,211],"10%)":[9],"of":[10,34,69,84,119,156,187],"transiently":[11],"idle":[12,189],"nodes":[13,20,191],"on":[14,161,198],"supercomputers.":[15],"Recognizing":[16],"that":[17,42,78,88,135],"such":[18],"unfilled":[19],"are":[21],"well-suited":[22],"for":[23,99,103,132,192],"deep":[24],"neural":[25,173],"network":[26],"(DNN)":[27],"training,":[28],"due":[29],"the":[31,43,66,70,80,117,149,154,184],"flexible":[32],"nature":[33],"DNN":[35,45,100,133,169,193],"training":[36,46,101,170,194,202],"tasks,":[37],"Liu":[38],"et":[39],"al.":[40],"proposed":[41],"re-scaling":[44],"tasks":[47],"fit":[49],"gaps":[50],"schedules":[52],"be":[53,96],"formulated":[54],"as":[55],"a":[56,76,120,157,162],"mixed-integer":[57],"linear":[58],"programming":[59],"(MILP)":[60],"problem,":[61],"and":[62,87,152,166,176],"demonstrated":[63],"via":[64],"simulation":[65],"potential":[67],"benefits":[68],"approach.":[71],"Here,":[72],"we":[73],"introduce":[74],"MalleTrain,":[75],"system":[77],"provides":[79],"first":[81],"practical":[82,185],"implementation":[83],"this":[85,113],"approach":[86],"furthermore":[89],"generalizes":[90],"it":[91,94,136],"by":[92,204],"allowing":[93],"used":[97],"even":[98],"applications":[102],"which":[104],"model":[105],"information":[106,131],"is":[107,116],"unknown":[108],"before":[109],"runtime.":[110],"Key":[111],"latter":[114],"innovation":[115],"use":[118],"lightweight":[121],"online":[122],"job":[123,213],"profiling":[124],"advisor":[125],"(JPA)":[126],"collect":[128],"critical":[129],"scalability":[130,214],"jobs---information":[134],"then":[137],"employs":[138],"optimize":[140],"resource":[141],"allocations":[142],"dynamically,":[143],"real":[145],"time.":[146],"We":[147],"describe":[148],"MalleTrain":[150],"architecture":[151,174],"present":[153],"results":[155,180],"detailed":[158],"experimental":[159],"evaluation":[160],"supercomputer":[163,190],"GPU":[164],"cluster":[165],"several":[167],"representative":[168],"workloads,":[171],"including":[172],"search":[175],"hyperparameter":[177],"optimization.":[178],"Our":[179],"not":[181],"only":[182],"confirm":[183],"feasibility":[186],"leveraging":[188],"but":[195],"improve":[196],"significantly":[197],"prior":[199],"results,":[200],"improving":[201],"throughput":[203],"up":[205],"22.3%":[207],"without":[208],"requiring":[209],"users":[210],"provide":[212],"information.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2024-04-26T00:00:00"}
