{"id":"https://openalex.org/W2952868979","doi":"https://doi.org/10.18653/v1/p19-1626","title":"Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units","display_name":"Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2952868979","doi":"https://doi.org/10.18653/v1/p19-1626","mag":"2952868979"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1626","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1626","pdf_url":"https://www.aclweb.org/anthology/P19-1626.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1626.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013339281","display_name":"Arturo Argueta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arturo Argueta","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036026526","display_name":"David Chiang","orcid":"https://orcid.org/0000-0002-0435-4864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Chiang","raw_affiliation_strings":["Department of Computer Science and Engineering University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of Notre Dame","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013339281"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7446359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6215","last_page":"6224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7742339968681335},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.7514515519142151},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6555772423744202},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6042007207870483},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5696511268615723},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5683156847953796},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5557587742805481},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5528049468994141},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5432984828948975},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4378885328769684},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4144194722175598},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4047105312347412},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3940729796886444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34480682015419006},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2461172640323639},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0845983624458313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742339968681335},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7514515519142151},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6555772423744202},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6042007207870483},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5696511268615723},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5683156847953796},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5557587742805481},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5528049468994141},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5432984828948975},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4378885328769684},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4144194722175598},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4047105312347412},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3940729796886444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34480682015419006},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2461172640323639},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0845983624458313},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p19-1626","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1626","pdf_url":"https://www.aclweb.org/anthology/P19-1626.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1626","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1626","pdf_url":"https://www.aclweb.org/anthology/P19-1626.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952868979.pdf","grobid_xml":"https://content.openalex.org/works/W2952868979.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W1828163288","https://openalex.org/W1841592590","https://openalex.org/W1995596660","https://openalex.org/W2076039939","https://openalex.org/W2095650036","https://openalex.org/W2118558147","https://openalex.org/W2120432001","https://openalex.org/W2124592110","https://openalex.org/W2127766448","https://openalex.org/W2130942839","https://openalex.org/W2154590891","https://openalex.org/W2155893237","https://openalex.org/W2158899491","https://openalex.org/W2164215197","https://openalex.org/W2250262609","https://openalex.org/W2251682575","https://openalex.org/W2402144811","https://openalex.org/W2514741789","https://openalex.org/W2519314406","https://openalex.org/W2565851976","https://openalex.org/W2574685768","https://openalex.org/W2577255746","https://openalex.org/W2750846973","https://openalex.org/W2801655600","https://openalex.org/W2806113772","https://openalex.org/W2888555799","https://openalex.org/W2912601938","https://openalex.org/W2952230511","https://openalex.org/W2953384591","https://openalex.org/W2963034893","https://openalex.org/W2963247605","https://openalex.org/W2963374099","https://openalex.org/W2963506925","https://openalex.org/W2963625095","https://openalex.org/W2964199361","https://openalex.org/W4240168186","https://openalex.org/W4302296459"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4,43],"commonly":[5],"used":[6,108],"to":[7,123],"train":[8],"and":[9,52,94,104,125],"evaluate":[10],"neural":[11],"networks":[12],"efficiently.":[13],"While":[14],"previous":[15],"work":[16],"in":[17,45,109],"deep":[18],"learning":[19],"has":[20],"focused":[21],"on":[22,25,28,33,59,135],"accelerating":[23],"operations":[24,34],"dense":[26],"matrices/tensors":[27],"GPUs,":[29],"efforts":[30],"have":[31],"concentrated":[32],"involving":[35],"sparse":[36,41],"data":[37],"structures.":[38],"Operations":[39],"using":[40],"structures":[42],"common":[44,86],"natural":[46],"language":[47],"models":[48,57],"at":[49,71,96],"the":[50,72,84,97],"input":[51,73],"output":[53,98],"layers,":[54],"because":[55],"these":[56],"operate":[58],"sequences":[60],"over":[61,116],"discrete":[62],"alphabets.":[63],"We":[64,128],"present":[65],"two":[66],"new":[67],"GPU":[68,119,137],"algorithms:":[69],"one":[70,95],"layer,":[74,99],"for":[75,100],"multiplying":[76],"a":[77,80,91,101],"matrix":[78],"by":[79,90],"few-hot":[81],"vector":[82],"(generalizing":[83],"more":[85],"operation":[87],"of":[88,121],"multiplication":[89],"one-hot":[92],"vector)":[93],"fused":[102],"softmax":[103],"top-N":[105],"selection":[106],"(commonly":[107],"beam":[110],"search).":[111],"Our":[112],"methods":[113,133],"achieve":[114],"speedups":[115],"state-of-theart":[117],"parallel":[118],"baselines":[120],"up":[122],"7":[124],"50,":[126],"respectively.":[127],"also":[129],"illustrate":[130],"how":[131],"our":[132],"scale":[134],"different":[136],"architectures.":[138]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}