{"id":"https://openalex.org/W4308090745","doi":"https://doi.org/10.1109/hpec55821.2022.9926362","title":"Sparse Deep Neural Network Inference Using Different Programming Models","display_name":"Sparse Deep Neural Network Inference Using Different Programming Models","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4308090745","doi":"https://doi.org/10.1109/hpec55821.2022.9926362"},"language":"en","primary_location":{"id":"doi:10.1109/hpec55821.2022.9926362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5010460625","display_name":"Hyungro Lee","orcid":"https://orcid.org/0000-0002-4221-7094"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyungro Lee","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA","Pacific Northwest National Laboratory, Richland, WA, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100901787","display_name":"Milan Jain","orcid":"https://orcid.org/0000-0002-1676-1117"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milan Jain","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA","Pacific Northwest National Laboratory, Richland, WA, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100670911","display_name":"Sayan Ghosh","orcid":"https://orcid.org/0000-0001-8758-7657"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayan Ghosh","raw_affiliation_strings":["Pacific Northwest National Laboratory,Richland,WA,USA","Pacific Northwest National Laboratory, Richland, WA, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory,Richland,WA,USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010460625"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":0.1007,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39111799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.995199978351593,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9916999936103821,"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":0.8272149562835693},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7263587117195129},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6821290850639343},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6656792759895325},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5859194993972778},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5817087888717651},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5332733392715454},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5202870965003967},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.49290013313293457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4782465994358063},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4691292941570282},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45045262575149536},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42808979749679565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.415910929441452},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34197384119033813},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.248200923204422},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18161830306053162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272149562835693},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7263587117195129},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6821290850639343},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6656792759895325},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5859194993972778},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5817087888717651},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5332733392715454},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5202870965003967},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.49290013313293457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4782465994358063},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4691292941570282},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45045262575149536},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42808979749679565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.415910929441452},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34197384119033813},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.248200923204422},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18161830306053162},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec55821.2022.9926362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec55821.2022.9926362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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":29,"referenced_works":["https://openalex.org/W143948075","https://openalex.org/W1541729506","https://openalex.org/W1988888548","https://openalex.org/W2007339694","https://openalex.org/W2014807599","https://openalex.org/W2059919683","https://openalex.org/W2612387305","https://openalex.org/W2626696598","https://openalex.org/W2791186466","https://openalex.org/W2898123186","https://openalex.org/W2956434358","https://openalex.org/W2973134322","https://openalex.org/W3014399784","https://openalex.org/W3082020764","https://openalex.org/W3100839241","https://openalex.org/W3113443077","https://openalex.org/W3115410382","https://openalex.org/W3117961507","https://openalex.org/W3121402054","https://openalex.org/W3134223578","https://openalex.org/W3175644086","https://openalex.org/W3208099998","https://openalex.org/W4200090124","https://openalex.org/W4230289604","https://openalex.org/W4287363917","https://openalex.org/W4290648346","https://openalex.org/W6765532259","https://openalex.org/W6775441114","https://openalex.org/W6790503700"],"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/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Sparse":[0,117],"deep":[1],"neural":[2],"networks":[3],"have":[4,21,58],"gained":[5],"increasing":[6],"attention":[7],"recently":[8],"in":[9,29,50,55,113],"achieving":[10],"speedups":[11,61],"on":[12,131],"inference":[13],"with":[14,24],"reduced":[15],"memory":[16],"footprints.":[17],"Real-world":[18],"applications":[19],"often":[20],"to":[22,84],"deal":[23],"sparse":[25],"data":[26],"and":[27,62,79,111,133],"irregularities":[28],"the":[30,46,74,89,114,125],"computations,":[31],"yet":[32],"a":[33],"wide":[34],"variety":[35],"of":[36,48,73,76,100,116],"Deep":[37,118],"Neural":[38,119],"Network":[39,120],"(DNN)":[40],"tasks":[41],"remain":[42],"dense":[43],"without":[44],"exploiting":[45],"advantages":[47],"sparsity":[49],"networks.":[51],"Recent":[52],"works":[53],"presented":[54],"MIT/IEEE/Amazon":[56],"GraphChallenge":[57],"demonstrated":[59],"significant":[60],"various":[63,77,101],"techniques.":[64],"Still,":[65],"we":[66,95],"find":[67],"that":[68],"there":[69],"is":[70],"limited":[71],"investigation":[72],"impact":[75],"Python":[78],"C/C++":[80],"based":[81],"programming":[82,104],"models":[83,105],"explore":[85],"new":[86],"opportunities":[87],"for":[88],"general":[90],"cases.":[91],"In":[92],"this":[93],"work,":[94],"provide":[96],"extensive":[97],"quantitative":[98],"evaluations":[99],"contemporary":[102],"GPGPU":[103],"such":[106],"as":[107],"Cupy,":[108],"Cuda":[109],"CUSPARSE,":[110],"Openmp":[112],"context":[115],"(SPDNN)":[121],"implementations":[122],"(derived":[123],"from":[124,136],"Graph":[126],"Challenge":[127],"reference":[128],"serial":[129],"code)":[130],"single":[132],"multiple":[134],"GPUs":[135],"NVIDIA":[137],"DGX-A100":[138],"40GB/80GB":[139],"platforms.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}