{"id":"https://openalex.org/W2914989766","doi":"https://doi.org/10.1145/3293883.3302260","title":"High performance distributed deep learning","display_name":"High performance distributed deep learning","publication_year":2019,"publication_date":"2019-02-05","ids":{"openalex":"https://openalex.org/W2914989766","doi":"https://doi.org/10.1145/3293883.3302260","mag":"2914989766"},"language":"en","primary_location":{"id":"doi:10.1145/3293883.3302260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293883.3302260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","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/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"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":true,"raw_author_name":"Dhabaleswar K. (DK) Panda","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004330728","display_name":"Ammar Ahmad Awan","orcid":"https://orcid.org/0000-0002-6272-3760"},"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":"Ammar Ahmad Awan","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"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":"Hari Subramoni","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024879682"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.8098,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.76249501,"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":"452","last_page":"454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7100720405578613},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48693549633026123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40121734142303467},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3336293697357178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7100720405578613},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48693549633026123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40121734142303467},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3336293697357178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293883.3302260","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293883.3302260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2155893237","https://openalex.org/W2271840356","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"The":[0,123],"current":[1],"wave":[2],"of":[3,43,54,67,94,115,165,197],"advances":[4],"in":[5,70,83,186],"Deep":[6,55],"Learning":[7],"(DL)":[8],"has":[9,126],"led":[10],"to":[11,47,111,155,169,189,193],"many":[12],"exciting":[13],"challenges":[14,149],"and":[15,20,35,45,50,73,98,140,150],"opportunities":[16,151],"for":[17,152,173],"Computer":[18],"Science":[19],"Artificial":[21],"Intelligence":[22],"researchers":[23],"alike.":[24],"Modern":[25],"DL":[26,99,102,124],"frameworks":[27,103],"like":[28,137],"Caffe2,":[29],"TensorFlow,":[30],"Cognitive":[31],"Toolkit":[32],"(CNTK),":[33],"PyTorch,":[34],"several":[36],"others":[37],"have":[38],"emerged":[39],"that":[40,133],"offer":[41],"ease":[42],"use":[44],"flexibility":[46],"describe,":[48],"train,":[49],"deploy":[51],"various":[52],"types":[53],"Neural":[56],"Networks":[57],"(DNNs).":[58],"In":[59,142],"this":[60,143,187],"tutorial,":[61],"we":[62,145,182],"will":[63,89,146],"provide":[64],"an":[65,92],"overview":[66,93],"interesting":[68],"trends":[69],"DNN":[71,96,116,159,175,200],"design":[72],"how":[74],"cutting-edge":[75],"hardware":[76],"architectures":[77,97],"are":[78,118],"playing":[79],"a":[80,106,204],"key":[81],"role":[82],"moving":[84],"the":[85,113,191],"field":[86],"forward.":[87],"We":[88,161],"also":[90,119,162],"present":[91],"different":[95,129],"frameworks.":[100],"Most":[101],"started":[104],"with":[105],"single-node/single-GPU":[107],"design.":[108],"However,":[109],"approaches":[110],"parallelize":[112],"process":[114],"training":[117,131,176,201],"being":[120],"actively":[121],"explored.":[122],"community":[125],"moved":[127],"along":[128],"distributed":[130,158,199],"designs":[132],"exploit":[134],"communication":[135,153],"runtimes":[136,154],"gRPC,":[138],"MPI,":[139],"NCCL.":[141],"context,":[144],"highlight":[147,163],"new":[148],"efficiently":[156],"support":[157],"training.":[160],"some":[164],"our":[166],"co-design":[167],"efforts":[168],"utilize":[170],"CUDA-Aware":[171],"MPI":[172],"large-scale":[174],"on":[177,203],"modern":[178,205],"GPU":[179,206],"clusters.":[180],"Finally,":[181],"include":[183],"hands-on":[184],"exercises":[185],"tutorial":[188],"enable":[190],"attendees":[192],"gain":[194],"first-hand":[195],"experience":[196],"running":[198],"experiments":[202],"cluster.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}