{"id":"https://openalex.org/W1980282429","doi":"https://doi.org/10.1145/2699470","title":"Optimizing Sparse Matrix\u2014Matrix Multiplication for the GPU","display_name":"Optimizing Sparse Matrix\u2014Matrix Multiplication for the GPU","publication_year":2015,"publication_date":"2015-10-26","ids":{"openalex":"https://openalex.org/W1980282429","doi":"https://doi.org/10.1145/2699470","mag":"1980282429"},"language":"en","primary_location":{"id":"doi:10.1145/2699470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2699470","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-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/A5112582638","display_name":"Steven Dalton","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven Dalton","raw_affiliation_strings":["University of Illinois at Urbana--Champaign, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana--Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027808971","display_name":"Luke N. Olson","orcid":"https://orcid.org/0000-0002-5283-6104"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke Olson","raw_affiliation_strings":["University of Illinois at Urbana--Champaign, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana--Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108095852","display_name":"Nathan Bell","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Bell","raw_affiliation_strings":["Google, Mountain View, CA","Google, Mountain View, CA;"],"affiliations":[{"raw_affiliation_string":"Google, Mountain View, CA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Mountain View, CA;","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112582638"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":15.5033,"has_fulltext":false,"cited_by_count":126,"citation_normalized_percentile":{"value":0.99376353,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"41","issue":"4","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8558565378189087},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7827022075653076},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7552717924118042},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6653069257736206},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6242002248764038},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5695528984069824},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5243057012557983},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5185925960540771},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4520721733570099},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4441654086112976},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4229307770729065},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40224742889404297},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.17036586999893188},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15827736258506775},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10410037636756897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558565378189087},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7827022075653076},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7552717924118042},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6653069257736206},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6242002248764038},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5695528984069824},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5243057012557983},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5185925960540771},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4520721733570099},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4441654086112976},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4229307770729065},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40224742889404297},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.17036586999893188},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15827736258506775},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10410037636756897},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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},{"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2699470","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2699470","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Mathematical Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W92933111","https://openalex.org/W126446084","https://openalex.org/W1506547947","https://openalex.org/W1569090332","https://openalex.org/W1855227287","https://openalex.org/W1975359839","https://openalex.org/W1985263109","https://openalex.org/W1985291160","https://openalex.org/W2002555321","https://openalex.org/W2003168947","https://openalex.org/W2017086619","https://openalex.org/W2035080386","https://openalex.org/W2065607954","https://openalex.org/W2083221501","https://openalex.org/W2089437293","https://openalex.org/W2089939118","https://openalex.org/W2103877122","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2134237243","https://openalex.org/W2141380216","https://openalex.org/W2162707967","https://openalex.org/W2182472769","https://openalex.org/W3106161546","https://openalex.org/W6629619268"],"related_works":["https://openalex.org/W2293771254","https://openalex.org/W2122511197","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W2914631005","https://openalex.org/W2032786851","https://openalex.org/W2952630098","https://openalex.org/W3132517792","https://openalex.org/W2029856617"],"abstract_inverted_index":{"Sparse":[0],"matrix--matrix":[1],"multiplication":[2],"(SpGEMM)":[3],"is":[4,73],"a":[5,64],"key":[6],"operation":[7,52],"in":[8],"numerous":[9],"areas":[10],"from":[11],"information":[12],"to":[13,33,86],"the":[14,25,31,40,50,82,92,97],"physical":[15],"sciences.":[16],"Implementing":[17],"SpGEMM":[18,51,83],"efficiently":[19],"on":[20],"throughput-oriented":[21],"processors,":[22],"such":[23],"as":[24],"graphics":[26],"processing":[27],"unit":[28],"(GPU),":[29],"requires":[30],"programmer":[32],"expose":[34],"substantial":[35],"fine-grained":[36],"parallelism":[37],"while":[38],"conserving":[39],"limited":[41],"off-chip":[42],"memory":[43,98],"bandwidth.":[44],"Balancing":[45],"these":[46],"concerns,":[47],"we":[48],"decompose":[49],"into":[53],"three":[54],"highly":[55],"parallel":[56],"phases:":[57],"expansion,":[58],"sorting,":[59],"and":[60,62,76,95],"contraction,":[61],"introduce":[63],"set":[65],"of":[66],"complementary":[67],"bandwidth-saving":[68],"performance":[69,89],"optimizations.":[70],"Our":[71],"implementation":[72],"fully":[74],"general":[75],"our":[77],"optimization":[78],"strategy":[79],"adaptively":[80],"processes":[81],"workload":[84],"row-wise":[85],"substantially":[87],"improve":[88],"by":[90],"decreasing":[91],"work":[93],"complexity":[94],"utilizing":[96],"hierarchy":[99],"more":[100],"effectively.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
