{"id":"https://openalex.org/W3082444099","doi":"https://doi.org/10.1109/hpec43674.2020.9286206","title":"At-Scale Sparse Deep Neural Network Inference With Efficient GPU Implementation","display_name":"At-Scale Sparse Deep Neural Network Inference With Efficient GPU Implementation","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3082444099","doi":"https://doi.org/10.1109/hpec43674.2020.9286206","mag":"3082444099"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286206","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.14152","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024169920","display_name":"Mert Hidayeto\u011flu","orcid":"https://orcid.org/0000-0001-9276-5075"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mert Hidayetoglu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032990831","display_name":"Carl Pearson","orcid":"https://orcid.org/0000-0001-6481-970X"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carl Pearson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041724753","display_name":"Vikram Sharma Mailthody","orcid":"https://orcid.org/0000-0002-9611-8075"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikram Sharma Mailthody","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089789557","display_name":"Eiman Ebrahimi","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eiman Ebrahimi","raw_affiliation_strings":["NVIDIA","nVidia"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]},{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinjun Xiong","raw_affiliation_strings":["IBM Research","IBM research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]},{"raw_affiliation_string":"IBM research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084546619","display_name":"Rakesh Nagi","orcid":"https://orcid.org/0000-0003-4022-6277"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh Nagi","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-mei Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5024169920"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.1963,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50158304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9997000098228455,"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":0.9997000098228455,"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/T12676","display_name":"Machine Learning and ELM","score":0.9984999895095825,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","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":0.8473422527313232},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7303839325904846},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7170418500900269},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5769363641738892},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5380493998527527},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.526525616645813},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.47928327322006226},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4733821451663971},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4434281289577484},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43806856870651245},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4215913712978363},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.41532862186431885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32919061183929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473422527313232},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7303839325904846},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7170418500900269},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5769363641738892},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5380493998527527},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.526525616645813},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.47928327322006226},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4733821451663971},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4434281289577484},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43806856870651245},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4215913712978363},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.41532862186431885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32919061183929443},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286206","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:2007.14152","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.14152","pdf_url":"https://arxiv.org/pdf/2007.14152","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:3082444099","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.14152.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.2007.14152","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.14152","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.14152","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.14152","pdf_url":"https://arxiv.org/pdf/2007.14152","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":[{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1719536385","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4694431782","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6488227018","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7114708214","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7388224766","display_name":null,"funder_award_id":"1725729","funder_id":"https://openalex.org/F4320332222","funder_display_name":"University of Illinois at Urbana-Champaign"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"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/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320316786","display_name":"Center for Cognitive Computing Systems Research","ror":null},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3082444099.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2902741896","https://openalex.org/W2955425717","https://openalex.org/W2964299589","https://openalex.org/W2964537638","https://openalex.org/W2965658867","https://openalex.org/W2971709192","https://openalex.org/W2973134322","https://openalex.org/W2973727699","https://openalex.org/W2985814104","https://openalex.org/W2989899068","https://openalex.org/W2990007648","https://openalex.org/W2990514424","https://openalex.org/W2990615851","https://openalex.org/W2990689488","https://openalex.org/W2990999343","https://openalex.org/W2991040477","https://openalex.org/W3014399784","https://openalex.org/W3030163527","https://openalex.org/W3035003500","https://openalex.org/W3100809954","https://openalex.org/W3100839241","https://openalex.org/W3130398772","https://openalex.org/W6677580257","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W3115410382","https://openalex.org/W3045744481","https://openalex.org/W3202517391","https://openalex.org/W3113443077","https://openalex.org/W2934222362","https://openalex.org/W2773313889","https://openalex.org/W2971709192","https://openalex.org/W2152014477","https://openalex.org/W2789177660","https://openalex.org/W3176486103","https://openalex.org/W2953264125","https://openalex.org/W3101434632","https://openalex.org/W2063257142","https://openalex.org/W3157025177","https://openalex.org/W2690141065","https://openalex.org/W2741888411","https://openalex.org/W3204998121","https://openalex.org/W2980186997","https://openalex.org/W2950263839","https://openalex.org/W3101555929"],"abstract_inverted_index":{"This":[0,75],"paper":[1],"presents":[2,77],"GPU":[3,153],"performance":[4],"optimization":[5],"and":[6,30,99,112,131,154],"scaling":[7],"results":[8,144],"for":[9,21,53,67,121,150,177],"inference":[10,141],"models":[11],"of":[12,35,42,59,157,165,168,181],"the":[13,28,32,40,56,85,96,115,122,127,166,169,178,186],"Sparse":[14,45,171],"Deep":[15,172],"Neural":[16,173],"Network":[17,174],"Challenge":[18,176],"2020.":[19],"Demands":[20],"network":[22],"quality":[23],"have":[24,50],"increased":[25],"rapidly,":[26],"pushing":[27],"size":[29],"thus":[31],"memory":[33,57,98],"requirements":[34],"many":[36],"neural":[37,47,61],"networks":[38,48],"beyond":[39],"capacity":[41],"available":[43],"accelerators.":[44],"deep":[46],"(SpDNN)":[49],"shown":[51],"promise":[52],"reining":[54],"in":[55,69],"footprint":[58],"large":[60],"networks.":[62],"However,":[63],"there":[64],"is":[65,194,206],"room":[66],"improvement":[68],"implementing":[70],"SpDNN":[71,108],"operations":[72],"on":[73,203],"GPUs.":[74,119,184],"work":[76],"optimized":[78,89],"sparse":[79,100],"matrix":[80],"multiplication":[81],"kernels":[82,90],"fused":[83],"with":[84],"ReLU":[86],"function.":[87],"The":[88],"reuse":[91],"input":[92],"feature":[93,116],"maps":[94,117],"from":[95,102],"shared":[97],"weights":[101,111],"registers.":[103],"For":[104],"multi-GPU":[105,132],"parallelism,":[106],"our":[107],"implementation":[109,188],"duplicates":[110],"statically":[113],"partition":[114],"across":[118],"Results":[120],"challenge":[123],"benchmarks":[124],"show":[125,200],"that":[126],"proposed":[128],"kernel":[129],"design":[130],"parallelization":[133],"achieve":[134],"up":[135,146],"to":[136,147],"180":[137],"TeraEdges":[138],"per":[139],"second":[140],"throughput.":[142],"These":[143],"are":[145],"4.3x":[148],"faster":[149,159,208],"a":[151],"single":[152],"an":[155],"order":[156],"magnitude":[158],"at":[160,196],"full":[161],"scale":[162],"than":[163,209],"those":[164],"champion":[167],"2019":[170],"Graph":[175],"same":[179,187],"generation":[180],"NVIDIA":[182,204],"V100":[183],"Using":[185],"<sup":[189],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[190],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">11</sup>":[191],"Our":[192],"code":[193],"open-source":[195],"https://github.com/merthidayetoglu/SpDNN_Challenge2020,":[197],"we":[198],"also":[199],"single-GPU":[201],"throughput":[202],"A100":[205],"2.37x":[207],"V100.":[210]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}