{"id":"https://openalex.org/W4318328338","doi":"https://doi.org/10.1145/3559009.3569667","title":"High-Performance Architecture Aware Sparse Convolutional Neural Networks for GPUs","display_name":"High-Performance Architecture Aware Sparse Convolutional Neural Networks for GPUs","publication_year":2022,"publication_date":"2022-10-08","ids":{"openalex":"https://openalex.org/W4318328338","doi":"https://doi.org/10.1145/3559009.3569667"},"language":"en","primary_location":{"id":"doi:10.1145/3559009.3569667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3559009.3569667","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569667","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569667","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030682860","display_name":"Lizhi Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lizhi Xiang","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["Meta Platforms"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Platforms","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1015,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42205697,"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":"265","last_page":"278"},"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/T10812","display_name":"Human Pose and Action Recognition","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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":0.8373536467552185},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7232315540313721},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6484926342964172},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6086503863334656},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5802333354949951},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5469238758087158},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5110567808151245},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4199942946434021},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41160228848457336},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38285011053085327},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3554547429084778},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.340023398399353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33281147480010986},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10326126217842102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373536467552185},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7232315540313721},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6484926342964172},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6086503863334656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5802333354949951},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5469238758087158},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5110567808151245},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4199942946434021},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41160228848457336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38285011053085327},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3554547429084778},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.340023398399353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33281147480010986},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10326126217842102},{"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3559009.3569667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3559009.3569667","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569667","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3559009.3569667","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3559009.3569667","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569667","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G447955464","display_name":null,"funder_award_id":"2018016","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"},{"id":"https://openalex.org/F4320310050","display_name":"University of Utah","ror":"https://ror.org/03r0ha626"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318328338.pdf","grobid_xml":"https://content.openalex.org/works/W4318328338.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1585377561","https://openalex.org/W1996901117","https://openalex.org/W2108598243","https://openalex.org/W2119144962","https://openalex.org/W2143612262","https://openalex.org/W2194775991","https://openalex.org/W2311857205","https://openalex.org/W2312404985","https://openalex.org/W2400429454","https://openalex.org/W2482315298","https://openalex.org/W2526421605","https://openalex.org/W2559655401","https://openalex.org/W2737202447","https://openalex.org/W2757184610","https://openalex.org/W2767274246","https://openalex.org/W2785856116","https://openalex.org/W2884001105","https://openalex.org/W2884159461","https://openalex.org/W2949967139","https://openalex.org/W2963363373","https://openalex.org/W2963446712","https://openalex.org/W2964233199","https://openalex.org/W3013377280","https://openalex.org/W3019166713","https://openalex.org/W4301045096","https://openalex.org/W6640289440","https://openalex.org/W6726275242","https://openalex.org/W6739663239","https://openalex.org/W6747230043"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2373300491","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W4391382578"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNN)":[3],"are":[4],"used":[5],"to":[6,28,53,79,83,151],"analyze":[7],"data":[8,76],"with":[9,141],"spatial/temporal":[10],"structure.":[11],"In":[12,56,111],"recent":[13],"years,":[14],"CNN's":[15],"popularity":[16],"has":[17],"increased":[18],"exponentially":[19],"by":[20,134],"virtue":[21],"of":[22,65,73,122,129,138],"its":[23,29],"accuracy":[24],"and":[25,40,48,68,75,160],"applicability.":[26],"Due":[27],"massive":[30],"deployment":[31],"scale,":[32],"especially":[33,108],"in":[34,46],"the":[35,63,70,87,93,136,142],"automotive":[36],"industry,":[37],"image":[38],"analytics,":[39],"portable":[41],"devices,":[42],"even":[43],"fractional":[44],"improvement":[45],"performance":[47,137],"power":[49],"consumption":[50],"can":[51,147],"lead":[52],"enormous":[54],"savings.":[55],"this":[57,103,112],"work,":[58],"we":[59,114],"focus":[60],"on":[61],"exploiting":[62],"sparsity":[64,88,96],"feature":[66,94,124,157],"maps":[67],"reducing":[69],"required":[71],"number":[72],"computations":[74],"movement,":[77],"leading":[78],"improved":[80],"performance.":[81],"Compared":[82],"kernel":[84],"sparsity,":[85],"where":[86],"structure":[89],"is":[90,97,132],"known":[91,99],"apriori,":[92],"map":[95,125,158],"only":[98],"during":[100],"runtime,":[101],"making":[102],"a":[104,116],"challenging":[105],"optimization":[106],"problem,":[107],"for":[109],"GPUs.":[110],"paper,":[113],"develop":[115],"GPU-friendly":[117],"Sparse":[118],"CNN":[119],"framework":[120],"capable":[121],"handling":[123],"sparsity.":[126],"The":[127],"efficacy":[128],"our":[130,139],"approach":[131,146],"demonstrated":[133],"comparing":[135],"implementation":[140],"state-of-the-art":[143],"implementations.":[144],"Our":[145],"also":[148],"be":[149],"extended":[150],"support":[152],"upcoming":[153],"techniques":[154],"such":[155],"as":[156],"pruning":[159],"submanifold":[161],"sparse":[162],"convolutional":[163],"Networks.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}