{"id":"https://openalex.org/W4200090124","doi":"https://doi.org/10.1109/hpec49654.2021.9622791","title":"Fast Sparse Deep Neural Network Inference with Flexible SpMM Optimization Space Exploration","display_name":"Fast Sparse Deep Neural Network Inference with Flexible SpMM Optimization Space Exploration","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W4200090124","doi":"https://doi.org/10.1109/hpec49654.2021.9622791"},"language":"en","primary_location":{"id":"doi:10.1109/hpec49654.2021.9622791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5103572960","display_name":"Jie Xin","orcid":"https://orcid.org/0000-0002-9162-6871"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jie Xin","raw_affiliation_strings":["School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023478949","display_name":"Xianqi Ye","orcid":"https://orcid.org/0000-0002-1896-9114"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianqi Ye","raw_affiliation_strings":["School of Software, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Software, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112720835","display_name":"Long Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Zheng","raw_affiliation_strings":["School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115599465","display_name":"Qinggang Wang","orcid":"https://orcid.org/0000-0002-9951-3345"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinggang Wang","raw_affiliation_strings":["School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071742820","display_name":"Yu Huang","orcid":"https://orcid.org/0000-0003-4178-0739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Huang","raw_affiliation_strings":["School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010485648","display_name":"Pengcheng Yao","orcid":"https://orcid.org/0000-0003-4701-2239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengcheng Yao","raw_affiliation_strings":["School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052456682","display_name":"Linchen Yu","orcid":"https://orcid.org/0000-0002-0620-101X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linchen Yu","raw_affiliation_strings":["School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022398389","display_name":"Xiaofei Liao","orcid":"https://orcid.org/0000-0001-6302-813X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofei Liao","raw_affiliation_strings":["School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5103572960"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3598,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.83515755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.996999979019165,"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/T12676","display_name":"Machine Learning and ELM","score":0.9948999881744385,"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":0.8472098708152771},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7044624090194702},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5484193563461304},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5082482695579529},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5021953582763672},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4888131320476532},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4866707921028137},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.45864421129226685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3953090310096741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472098708152771},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7044624090194702},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5484193563461304},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5082482695579529},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5021953582763672},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4888131320476532},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4866707921028137},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.45864421129226685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953090310096741},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec49654.2021.9622791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec49654.2021.9622791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2049487370","https://openalex.org/W2097117768","https://openalex.org/W2114977680","https://openalex.org/W2119144962","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2461193710","https://openalex.org/W2475334473","https://openalex.org/W2896457183","https://openalex.org/W2914631005","https://openalex.org/W2963446712","https://openalex.org/W2963477586","https://openalex.org/W2964537638","https://openalex.org/W2973134322","https://openalex.org/W2990514424","https://openalex.org/W2999347085","https://openalex.org/W3014399784","https://openalex.org/W3098650335","https://openalex.org/W3100809954","https://openalex.org/W3100839241","https://openalex.org/W3113443077","https://openalex.org/W3115410382","https://openalex.org/W3117140649","https://openalex.org/W3130660608","https://openalex.org/W3175618977","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6677580257","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6797677657"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2002978035","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2610007503"],"abstract_inverted_index":{"Deep":[0],"neural":[1,22],"networks":[2,23],"(DNN)":[3],"have":[4],"been":[5],"widely":[6],"used":[7],"in":[8,99,202],"many":[9,203],"fields.":[10],"With":[11],"the":[12,16,32,101,147,166,195],"ever-increasing":[13],"model":[14],"size,":[15],"DNN":[17,151],"scalability":[18],"suffers.":[19],"Sparse":[20,150],"deep":[21],"(SpDNN)":[24],"are":[25,208],"promising":[26],"to":[27,38,44,60,85,146,158,170,194],"resolve":[28],"this":[29,92,114],"problem,":[30],"but":[31,66],"sparse":[33,62],"data":[34],"makes":[35],"it":[36],"difficult":[37],"execute":[39],"efficiently":[40],"on":[41,113,136,176],"GPUs":[42,190,201],"due":[43,84],"load":[45],"imbalance":[46],"and":[47,138,173],"irregular":[48],"memory":[49],"accesses.":[50],"The":[51,205],"recent":[52],"MIT/IEEE/Amazon":[53],"GraphChallenge":[54],"has":[55],"shown":[56],"several":[57],"big":[58],"advances":[59],"fit":[61],"DNNs":[63],"into":[64],"GPUs,":[65],"we":[67,94,121],"observe":[68],"that":[69,126,185],"none":[70],"of":[71,103,109,119,133,168],"these":[72],"earlier":[73],"efforts":[74],"can":[75,127,191],"be":[76,192],"an":[77],"absolute":[78],"winner":[79],"for":[80],"all":[81],"dataset":[82],"cases":[83],"their":[86],"limited":[87],"optimization":[88],"space":[89,118],"considerations.":[90],"In":[91],"paper,":[93],"identify":[95],"some":[96],"new":[97,115],"opportunities":[98],"optimizing":[100],"execution":[102,135],"SpDNN":[104,134],"via":[105],"a":[106,130,177],"comprehensive":[107],"analysis":[108],"previous":[110],"works.":[111],"Based":[112],"large":[116],"design":[117],"SpDNN,":[120],"present":[122],"sparsity-aware":[123],"SpMM":[124,142],"algorithms":[125],"systematically":[128],"explore":[129],"performance-optimal":[131],"solution":[132],"GPU":[137],"further":[139],"generate":[140],"optimized":[141],"kernel":[143],"implementations.":[144],"Compared":[145],"2020":[148,196],"HPEC":[149],"Challenge":[152,197],"champions,":[153],"our":[154,186],"approach":[155,187],"achieves":[156],"up":[157,169],"55.6":[159],"TeraEdges":[160],"per":[161],"second":[162],"inference":[163],"throughput":[164],"with":[165],"speedups":[167],"13.74_":[171],"[1]":[172],"22.29_":[174],"[2]":[175],"single":[178],"NVIDIA":[179],"V100":[180],"GPU.":[181],"We":[182],"also":[183],"show":[184],"under":[188],"4":[189],"superior":[193],"Champion":[198],"using":[199],"768":[200],"cases.":[204],"source":[206],"codes":[207],"available":[209],"at":[210],"https://github.com/CGCL-codes/Graphchallenge21.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}