{"id":"https://openalex.org/W2990514424","doi":"https://doi.org/10.1109/hpec.2019.8916223","title":"A GPU Implementation of the Sparse Deep Neural Network Graph Challenge","display_name":"A GPU Implementation of the Sparse Deep Neural Network Graph Challenge","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2990514424","doi":"https://doi.org/10.1109/hpec.2019.8916223","mag":"2990514424"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2019.8916223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5031617537","display_name":"Mauro Bisson","orcid":"https://orcid.org/0000-0002-3025-8227"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mauro Bisson","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079530787","display_name":"Massimiliano Fatica","orcid":"https://orcid.org/0000-0002-5839-1644"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Massimiliano Fatica","raw_affiliation_strings":["NVIDIA Corporation, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031617537"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":1.1135,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8250619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9983999729156494,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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/cuda","display_name":"CUDA","score":0.9010632038116455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8301422595977783},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6192731857299805},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5980716943740845},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5945829749107361},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5287118554115295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4443497955799103},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.41010528802871704},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3816126585006714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32543450593948364},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2083401083946228},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1365930736064911},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10427659749984741}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9010632038116455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301422595977783},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6192731857299805},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5980716943740845},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5945829749107361},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5287118554115295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4443497955799103},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41010528802871704},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3816126585006714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32543450593948364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2083401083946228},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1365930736064911},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10427659749984741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2019.8916223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2296412986","https://openalex.org/W2559678521","https://openalex.org/W2742989511","https://openalex.org/W2747404479","https://openalex.org/W2765752351","https://openalex.org/W2902685757","https://openalex.org/W2973134322","https://openalex.org/W3100734586","https://openalex.org/W3100809954","https://openalex.org/W3100839241","https://openalex.org/W3105090504","https://openalex.org/W6910447991"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W3213381848","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,18,55],"CUDA":[4,44],"implementation":[5],"of":[6,20,51],"the":[7,11,14,32,38],"latest":[8],"addition":[9],"to":[10],"Graph":[12],"Challenge,":[13],"inference":[15,33],"computation":[16],"on":[17],"collection":[19],"large":[21],"sparse":[22],"deep":[23],"neural":[24],"networks.":[25],"A":[26],"single":[27],"Tesla":[28],"V100":[29],"can":[30],"compute":[31],"at":[34],"3.7":[35],"TeraEdges/s.":[36],"Using":[37],"managed":[39],"memory":[40],"API":[41],"available":[42],"in":[43],"allows":[45],"for":[46],"simple":[47],"and":[48],"efficient":[49],"distribution":[50],"these":[52],"computations":[53],"across":[54],"multiGPU":[56],"NVIDIA":[57],"DGX-2":[58],"server.":[59]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}