{"id":"https://openalex.org/W2618168961","doi":"https://doi.org/10.1145/3079079.3079106","title":"On improving performance of sparse matrix-matrix multiplication on GPUs","display_name":"On improving performance of sparse matrix-matrix multiplication on GPUs","publication_year":2017,"publication_date":"2017-05-31","ids":{"openalex":"https://openalex.org/W2618168961","doi":"https://doi.org/10.1145/3079079.3079106","mag":"2618168961"},"language":"en","primary_location":{"id":"doi:10.1145/3079079.3079106","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3079079.3079106","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3079106&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3079106&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039567585","display_name":"Rakshith Kunchum","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rakshith Kunchum","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018849921","display_name":"Ankur Chaudhry","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Chaudhry","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063598519","display_name":"Qingpeng Niu","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingpeng Niu","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063948428","display_name":"Israt Nisa","orcid":"https://orcid.org/0000-0001-5022-5716"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Israt Nisa","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5039567585"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.0804,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88229874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.8113066554069519},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6491888761520386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6350526809692383},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.6203837990760803},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6128632426261902},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5530536770820618},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.4948350787162781},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4351988434791565},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35202404856681824},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22884225845336914},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.16796746850013733},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07012540102005005},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.0690663754940033}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.8113066554069519},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6491888761520386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6350526809692383},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.6203837990760803},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6128632426261902},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5530536770820618},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.4948350787162781},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4351988434791565},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35202404856681824},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22884225845336914},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.16796746850013733},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07012540102005005},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.0690663754940033},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3079079.3079106","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3079079.3079106","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3079106&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3079079.3079106","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3079079.3079106","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3079106&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1263021256","display_name":null,"funder_award_id":"D16PC00183","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G1838942446","display_name":null,"funder_award_id":"1440749","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4318646374","display_name":"XPS: FULL: Collaborative Research: PARAGRAPH: Parallel, Scalable Graph Analytics","funder_award_id":"1629548","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7986979720","display_name":"CDS&E: Compiler/Runtime Support for Developing Scalable Parallel Multi-Scale Multi-Physics","funder_award_id":"1404995","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","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/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2618168961.pdf","grobid_xml":"https://content.openalex.org/works/W2618168961.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1506547947","https://openalex.org/W1515144947","https://openalex.org/W1589103334","https://openalex.org/W1839329870","https://openalex.org/W1973918431","https://openalex.org/W1980282429","https://openalex.org/W1985263109","https://openalex.org/W2002555321","https://openalex.org/W2007259720","https://openalex.org/W2009654791","https://openalex.org/W2035080386","https://openalex.org/W2043670592","https://openalex.org/W2066367171","https://openalex.org/W2089437293","https://openalex.org/W2095249664","https://openalex.org/W2122948532","https://openalex.org/W2134237243","https://openalex.org/W2168931017","https://openalex.org/W2410461480","https://openalex.org/W2544965371","https://openalex.org/W3022326557","https://openalex.org/W4299975359"],"related_works":["https://openalex.org/W2225983048","https://openalex.org/W2596457687","https://openalex.org/W3099313426","https://openalex.org/W752783541","https://openalex.org/W4287593139","https://openalex.org/W1516189266","https://openalex.org/W2093666864","https://openalex.org/W4378602953","https://openalex.org/W4312443197","https://openalex.org/W2256267046"],"abstract_inverted_index":{"Sparse":[0],"matrix-matrix":[1,24],"multiplication":[2,25],"(SpGEMM)":[3],"is":[4,26,34,45,55,89],"an":[5],"important":[6],"primitive":[7],"for":[8,36],"many":[9,61],"data":[10],"analytics":[11],"algorithms,":[12],"such":[13],"as":[14],"Markov":[15],"clustering.":[16],"Unlike":[17],"the":[18,32,37,47,51,78],"dense":[19],"case,":[20],"where":[21],"performance":[22],"of":[23,50,80],"considerably":[27],"higher":[28],"than":[29],"matrix-vector":[30],"multiplication,":[31],"opposite":[33],"true":[35],"sparse":[38,53],"case":[39],"on":[40],"GPUs.":[41],"A":[42],"significant":[43],"challenge":[44],"that":[46,88],"sparsity":[48],"structure":[49],"output":[52],"matrix":[54],"not":[56],"known":[57],"a":[58,85],"priori,":[59],"and":[60,83],"additive":[62],"contributions":[63],"must":[64],"be":[65,92],"combined":[66],"to":[67,76,91,95],"generate":[68],"its":[69],"non-zero":[70],"elements.":[71],"We":[72],"use":[73],"synthetic":[74],"matrices":[75],"characterize":[77],"effectiveness":[79],"alternate":[81],"approaches":[82],"devise":[84],"hybrid":[86],"approach":[87],"demonstrated":[90],"consistently":[93],"superior":[94],"other":[96],"available":[97],"GPU":[98],"SpGEMM":[99],"implementations.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}