{"id":"https://openalex.org/W3043359183","doi":"https://doi.org/10.1109/hpec43674.2020.9286180","title":"Layer-Parallel Training with GPU Concurrency of Deep Residual Neural Networks via Nonlinear Multigrid","display_name":"Layer-Parallel Training with GPU Concurrency of Deep Residual Neural Networks via Nonlinear Multigrid","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3043359183","doi":"https://doi.org/10.1109/hpec43674.2020.9286180","mag":"3043359183"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.07336","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081266095","display_name":"Andrew C. Kirby","orcid":"https://orcid.org/0000-0001-8431-1807"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Kirby","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103227438","display_name":"Siddharth Samsi","orcid":"https://orcid.org/0009-0000-2884-9688"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Samsi","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064275902","display_name":"Michael Jones","orcid":"https://orcid.org/0000-0001-5215-2346"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Jones","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000293770","display_name":"Albert Reuther","orcid":"https://orcid.org/0000-0002-3168-3663"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Reuther","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072108599","display_name":"Jeremy Kepner","orcid":"https://orcid.org/0000-0001-9668-2613"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Kepner","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043450560","display_name":"Vijay Gadepally","orcid":"https://orcid.org/0000-0002-4598-2808"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Gadepally","raw_affiliation_strings":["Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Lincoln Laboratory Supercomputing Center, Lexington, MA, USA","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9843000173568726,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9793000221252441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8180292844772339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8144243955612183},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7737956047058105},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.7506139278411865},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.6870700716972351},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6363106966018677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6300522685050964},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5917785167694092},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5710058808326721},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4818342924118042},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.46059098839759827},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41881507635116577},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.41284382343292236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31639689207077026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3091634511947632},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.19788506627082825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07248586416244507}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8180292844772339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144243955612183},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7737956047058105},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.7506139278411865},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.6870700716972351},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6363106966018677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6300522685050964},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5917785167694092},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5710058808326721},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4818342924118042},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.46059098839759827},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41881507635116577},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.41284382343292236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31639689207077026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3091634511947632},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.19788506627082825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07248586416244507},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.07336","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07336","pdf_url":"https://arxiv.org/pdf/2007.07336","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":"mag:3043359183","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.07336.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.07336","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.07336","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.07336","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.07336","pdf_url":"https://arxiv.org/pdf/2007.07336","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043359183.pdf","grobid_xml":"https://content.openalex.org/works/W3043359183.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W80576238","https://openalex.org/W1510543252","https://openalex.org/W1593882739","https://openalex.org/W1667652561","https://openalex.org/W2012630580","https://openalex.org/W2028499920","https://openalex.org/W2046099891","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2524221349","https://openalex.org/W2609332365","https://openalex.org/W2765729611","https://openalex.org/W2883672905","https://openalex.org/W2943926935","https://openalex.org/W2963302407","https://openalex.org/W2963755523","https://openalex.org/W2964016678","https://openalex.org/W2970148471","https://openalex.org/W2970959587","https://openalex.org/W2972087877","https://openalex.org/W2973727699","https://openalex.org/W2990673743","https://openalex.org/W3004424267","https://openalex.org/W3016691807","https://openalex.org/W3033308515","https://openalex.org/W3099432326","https://openalex.org/W3138798301","https://openalex.org/W4246367117","https://openalex.org/W6752307458"],"related_works":["https://openalex.org/W2579119161","https://openalex.org/W2546392110","https://openalex.org/W2019660832","https://openalex.org/W2733142328","https://openalex.org/W2585947313","https://openalex.org/W3046901963","https://openalex.org/W2043201574","https://openalex.org/W123808431","https://openalex.org/W2939123531","https://openalex.org/W2075929547","https://openalex.org/W1489079604","https://openalex.org/W1585860052","https://openalex.org/W1570695572","https://openalex.org/W2091007698","https://openalex.org/W2609589754","https://openalex.org/W1514796698","https://openalex.org/W1593881607","https://openalex.org/W1480903242","https://openalex.org/W2132951989","https://openalex.org/W1501628336"],"abstract_inverted_index":{"A":[0],"Multigrid":[1],"Full":[2],"Approximation":[3],"Storage":[4],"algorithm":[5],"for":[6],"solving":[7],"Deep":[8],"Residual":[9],"Networks":[10],"is":[11],"developed":[12],"to":[13],"enable":[14],"neural":[15],"network":[16],"parallelized":[17],"layer-wise":[18,35],"training":[19],"and":[20],"concurrent":[21],"computational":[22],"kernel":[23],"execution":[24],"on":[25],"GPUs.":[26],"This":[27],"work":[28],"demonstrates":[29],"a":[30],"10.2x":[31],"speedup":[32],"over":[33],"traditional":[34],"model":[36],"parallelism":[37],"techniques":[38],"using":[39],"the":[40],"same":[41],"number":[42],"of":[43],"compute":[44],"units.":[45]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}