{"id":"https://openalex.org/W2963343843","doi":"https://doi.org/10.1145/3339186.3339194","title":"Accelerate DNN Performance with Sparse Matrix Compression in Halide","display_name":"Accelerate DNN Performance with Sparse Matrix Compression in Halide","publication_year":2019,"publication_date":"2019-07-22","ids":{"openalex":"https://openalex.org/W2963343843","doi":"https://doi.org/10.1145/3339186.3339194","mag":"2963343843"},"language":"en","primary_location":{"id":"doi:10.1145/3339186.3339194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3339186.3339194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 48th International Conference on Parallel Processing","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/A5034885231","display_name":"Chao-Lin Lee","orcid":"https://orcid.org/0000-0002-4619-3843"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chao-Lin Lee","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110945055","display_name":"Chen-Ting Chao","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen-Ting Chao","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038803698","display_name":"Jenq\u2010Kuen Lee","orcid":"https://orcid.org/0000-0001-9919-6258"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072319470","display_name":"Ming-Yu Hung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148979","display_name":"MediaTek (Taiwan)","ror":"https://ror.org/05g9jck81","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210148979"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Yu Hung","raw_affiliation_strings":["MediaTek Inc., Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Inc., Hsinchu, Taiwan","institution_ids":["https://openalex.org/I4210148979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009835723","display_name":"Chung-Wen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148979","display_name":"MediaTek (Taiwan)","ror":"https://ror.org/05g9jck81","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210148979"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Wen Huang","raw_affiliation_strings":["MediaTek Inc., Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MediaTek Inc., Hsinchu, Taiwan","institution_ids":["https://openalex.org/I4210148979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4068,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65112507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"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":0.9973000288009644,"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":0.9973000288009644,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9900000095367432,"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/computer-science","display_name":"Computer science","score":0.8359848260879517},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6528822779655457},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6329960227012634},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5679747462272644},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5621753334999084},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5218393206596375},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49673181772232056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4934007227420807},{"id":"https://openalex.org/keywords/transformation-matrix","display_name":"Transformation matrix","score":0.4913605749607086},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4839042127132416},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43655261397361755},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4334668815135956},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3886067271232605},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32192468643188477},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07693979144096375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359848260879517},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6528822779655457},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6329960227012634},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5679747462272644},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5621753334999084},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5218393206596375},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49673181772232056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934007227420807},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.4913605749607086},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4839042127132416},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43655261397361755},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4334668815135956},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3886067271232605},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32192468643188477},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07693979144096375},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3339186.3339194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3339186.3339194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322410","display_name":"MediaTek","ror":"https://ror.org/05g9jck81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1989988531","https://openalex.org/W2006295906","https://openalex.org/W2044921083","https://openalex.org/W2134038353","https://openalex.org/W2189481802","https://openalex.org/W2886662478","https://openalex.org/W4251637954"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W3157543420","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W4390971171","https://openalex.org/W4385338604","https://openalex.org/W3081626085"],"abstract_inverted_index":{"Machine":[0],"learning":[1,33,55],"nowadays":[2],"is":[3,34,75,92,134],"profoundly":[4],"impacting":[5],"every":[6],"aspect":[7],"of":[8,14,29,37,43,47,53,67,73,104,114,154],"our":[9,162,174],"lives.":[10],"With":[11,146],"the":[12,15,25,68,79,102,112,152],"evolution":[13],"machine":[16,30],"learning,":[17,23],"many":[18],"techniques,":[19],"such":[20],"as":[21,86],"deep":[22,54],"improve":[24,101,127],"accuracy":[26],"and":[27,45,82,122],"performance":[28,103,159],"learning.":[31],"Deep":[32],"a":[35,57,124],"set":[36],"ML":[38],"techniques":[39],"that":[40,140,166],"use":[41],"layers":[42],"transformation":[44],"consist":[46],"neural":[48],"networks.":[49],"The":[50],"power":[51],"consumption":[52],"becomes":[56],"serious":[58],"problem":[59],"when":[60],"it":[61],"comes":[62],"to":[63,93,100,126,157],"edge":[64],"computing.":[65],"One":[66],"most":[69],"computationally":[70],"demanding":[71],"operation":[72,129,168],"DNN":[74],"convolution":[76,105,128,167],"which":[77],"preserve":[78],"image":[80,85,136],"arrangement":[81],"obtain":[83],"partial":[84],"an":[87,95,135],"input":[88],"feature.":[89],"Our":[90],"goal":[91],"find":[94,123],"effective":[96],"way":[97,125],"for":[98],"programmers":[99],"operation.":[106],"In":[107,161],"this":[108,147],"paper,":[109],"we":[110,149],"proposed":[111],"design":[113],"sparse":[115],"matrix":[116,156],"compression":[117],"schedule":[118],"primitives":[119],"in":[120],"Halide":[121,133],"with":[130,173],"im2col":[131,155],"method.":[132],"processing":[137],"programming":[138],"language":[139],"separates":[141],"algorithm":[142],"from":[143],"its":[144],"schedule.":[145],"design,":[148],"can":[150,169],"compress":[151],"result":[153],"achieve":[158,170],"improvements.":[160],"experiments,":[163],"results":[164],"show":[165],"20X":[171],"speedup":[172],"implementation.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}