{"id":"https://openalex.org/W4310007239","doi":"https://doi.org/10.1109/ictc55196.2022.9952814","title":"Analysis of Several Sparse Formats for Matrices used in Sparse-Matrix Dense-Matrix Multiplication for Machine Learning on GPUs","display_name":"Analysis of Several Sparse Formats for Matrices used in Sparse-Matrix Dense-Matrix Multiplication for Machine Learning on GPUs","publication_year":2022,"publication_date":"2022-10-19","ids":{"openalex":"https://openalex.org/W4310007239","doi":"https://doi.org/10.1109/ictc55196.2022.9952814"},"language":"en","primary_location":{"id":"doi:10.1109/ictc55196.2022.9952814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc55196.2022.9952814","pdf_url":null,"source":{"id":"https://openalex.org/S4363607740","display_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100334088","display_name":"Donghyeon Kim","orcid":"https://orcid.org/0000-0001-5019-8199"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghyeon Kim","raw_affiliation_strings":["Chung-Ang University,Department of Food Engineering,Anseong,Republic of Korea","Department of Food Engineering, Chung-Ang University, Anseong, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Food Engineering,Anseong,Republic of Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Food Engineering, Chung-Ang University, Anseong, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676208","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0003-3751-8869"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinsung Kim","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University,Seoul,Republic of Korea","School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9961000084877014,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9961000084877014,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9613999724388123,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/sparse-matrix","display_name":"Sparse matrix","score":0.7717386484146118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6703819632530212},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5779536962509155},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5579283237457275},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5284115076065063},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.46470940113067627},{"id":"https://openalex.org/keywords/matrix-free-methods","display_name":"Matrix-free methods","score":0.4598977863788605},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43944287300109863},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4249271750450134},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3634756803512573}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7717386484146118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6703819632530212},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5779536962509155},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5579283237457275},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5284115076065063},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.46470940113067627},{"id":"https://openalex.org/C54219892","wikidata":"https://www.wikidata.org/wiki/Q4080929","display_name":"Matrix-free methods","level":4,"score":0.4598977863788605},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43944287300109863},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4249271750450134},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3634756803512573},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc55196.2022.9952814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc55196.2022.9952814","pdf_url":null,"source":{"id":"https://openalex.org/S4363607740","display_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G172742440","display_name":null,"funder_award_id":"NRF-2022R1G1A1013586","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2964337156","https://openalex.org/W3158112431","https://openalex.org/W4287208846","https://openalex.org/W6794457956"],"related_works":["https://openalex.org/W2375913285","https://openalex.org/W2155596814","https://openalex.org/W2091883426","https://openalex.org/W4285409149","https://openalex.org/W810196809","https://openalex.org/W2174948646","https://openalex.org/W2293771254","https://openalex.org/W2032786851","https://openalex.org/W4285148873","https://openalex.org/W2059710425"],"abstract_inverted_index":{"Sparse-matrix":[0],"dense-matrix":[1],"multiplication":[2],"(SpMM)":[3],"receives":[4],"one":[5,9,17],"sparse":[6,57,63,85,92,128,165],"matrix":[7,11,19,129],"and":[8,15,39,104,155,199],"dense":[10,18],"as":[12,20,32,60,97,194],"two":[13],"inputs,":[14],"outputs":[16],"a":[21,25,131,168],"result.":[22],"It":[23],"plays":[24],"vital":[26],"role":[27],"in":[28,84,143,161,184,188],"various":[29],"fields":[30],"such":[31,59,96,193],"deep":[33],"neural":[34,37],"networks":[35,38],"graph":[36],"analysis.":[40],"CUDA,":[41],"NVIDIA's":[42],"parallel":[43],"computing":[44],"platform,":[45],"provides":[46,122],"cuSPARSE":[47,88,153,186],"library":[48,89,124,154,158],"to":[49,74,79,181],"support":[50],"Basic":[51],"Linear":[52],"Algebra":[53],"Subroutines":[54],"(BLAS)":[55],"with":[56,117,167],"matrices":[58,95,166],"SpMM.":[61],"In":[62,77,109,147],"matrices,":[64,86],"zero":[65],"values":[66,83],"can":[67,141],"be":[68],"discarded":[69],"from":[70],"storage":[71],"or":[72],"computations":[73],"accelerate":[75],"execution.":[76],"order":[78],"represent":[80],"only":[81],"non-zero":[82],"the":[87,112,152,156,162,176,185],"supports":[90],"several":[91],"formats":[93,180],"for":[94,125,159],"COO":[98],"(COOrdinate),":[99],"CSR":[100],"(Compressed":[101,106],"Sparse":[102,107],"Row),":[103],"CSC":[105],"Column).":[108],"addition,":[110],"since":[111],"3rd":[113],"Gen.":[114],"Tensor":[115],"Cores":[116],"Ampere":[118],"was":[119],"introduced,":[120],"CUDA":[121],"cuSPARSELt":[123,157],"SpMM":[126,183],"whose":[127],"satisfies":[130],"2:4":[132,169],"sparsity":[133,139,170,192,198],"pattern,":[134],"which":[135],"is":[136],"approximately":[137],"50%":[138],"that":[140],"occur":[142],"machine":[144],"learning,":[145],"etc.":[146],"this":[148],"paper,":[149],"we":[150,174],"compare":[151,175],"SpMM,":[160],"case":[163],"of":[164,178,190],"pattern(50%":[171],"sparsity).":[172],"Furthermore,":[173],"performances":[177],"three":[179],"perform":[182],"library,":[187],"terms":[189],"different":[191],"75%":[195],"sparsity,":[196],"87.5%":[197],"99%":[200],"sparsity.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}