{"id":"https://openalex.org/W2808128431","doi":"https://doi.org/10.1145/3208040.3208062","title":"Efficient sparse-matrix multi-vector product on GPUs","display_name":"Efficient sparse-matrix multi-vector product on GPUs","publication_year":2018,"publication_date":"2018-06-11","ids":{"openalex":"https://openalex.org/W2808128431","doi":"https://doi.org/10.1145/3208040.3208062","mag":"2808128431"},"language":"en","primary_location":{"id":"doi:10.1145/3208040.3208062","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3208040.3208062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing","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/A5027442506","display_name":"Changwan Hong","orcid":"https://orcid.org/0000-0001-9069-8374"},"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":"Changwan Hong","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/A5023057939","display_name":"Bortik Bandyopadhyay","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":"Bortik Bandyopadhyay","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/A5100676208","display_name":"Jinsung Kim","orcid":"https://orcid.org/0000-0003-3751-8869"},"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":"Jinsung Kim","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/A5043138528","display_name":"S\u00fcreyya Emre Kurt","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":"S\u00fcreyya Emre Kurt","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":"middle","author":{"id":"https://openalex.org/A5015482033","display_name":"Shivani Sabhlok","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":"Shivani Sabhlok","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/A5026046737","display_name":"\u00dcmit V. \u00c7ataly\u00fcrek","orcid":"https://orcid.org/0000-0002-5625-3758"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"\u00dcmit V. \u00c7ataly\u00fcrek","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755351","display_name":"Srinivasan Parthasarathy","orcid":"https://orcid.org/0000-0002-6062-6449"},"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":"Srinivasan Parthasarathy","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":10,"corresponding_author_ids":["https://openalex.org/A5027442506"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":6.9841,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.97659701,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"79"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9921000003814697,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.991599977016449,"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":0.7715059518814087},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7285908460617065},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6468308568000793},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6079141497612},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4703562259674072},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.45842093229293823},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43952909111976624},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4319199323654175},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4311586916446686},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42634889483451843},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.224697083234787},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.19432643055915833},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.118135005235672},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.11536815762519836},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07878956198692322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715059518814087},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7285908460617065},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6468308568000793},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6079141497612},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4703562259674072},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45842093229293823},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43952909111976624},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4319199323654175},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4311586916446686},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42634889483451843},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.224697083234787},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.19432643055915833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.118135005235672},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.11536815762519836},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07878956198692322},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3208040.3208062","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3208040.3208062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1106410802","display_name":null,"funder_award_id":"D16PC00183","funder_id":"https://openalex.org/F4320337531","funder_display_name":"Defense Sciences Office, DARPA"},{"id":"https://openalex.org/G6889846196","display_name":null,"funder_award_id":"1404995,1513120,1629548,1645599,1747447","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/F4320310009","display_name":"University of Florida","ror":"https://ror.org/02y3ad647"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337531","display_name":"Defense Sciences Office, DARPA","ror":"https://ror.org/0447fe631"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522512418","https://openalex.org/W1957031661","https://openalex.org/W1973966410","https://openalex.org/W1985312666","https://openalex.org/W2002555321","https://openalex.org/W2009347695","https://openalex.org/W2010777083","https://openalex.org/W2021088067","https://openalex.org/W2035080386","https://openalex.org/W2037517972","https://openalex.org/W2038071684","https://openalex.org/W2040404421","https://openalex.org/W2044489142","https://openalex.org/W2051142108","https://openalex.org/W2058927151","https://openalex.org/W2063244516","https://openalex.org/W2066349733","https://openalex.org/W2087507944","https://openalex.org/W2092284239","https://openalex.org/W2133990480","https://openalex.org/W2134237243","https://openalex.org/W2136324023","https://openalex.org/W2162283062","https://openalex.org/W2168931017","https://openalex.org/W2255383145","https://openalex.org/W2259950804","https://openalex.org/W2263374743","https://openalex.org/W2284629249","https://openalex.org/W2311803642","https://openalex.org/W2521497392","https://openalex.org/W2617247391","https://openalex.org/W2617403939","https://openalex.org/W2796649226","https://openalex.org/W2950015285","https://openalex.org/W2964299589","https://openalex.org/W4238995617","https://openalex.org/W4247712932"],"related_works":["https://openalex.org/W2011159963","https://openalex.org/W1981557297","https://openalex.org/W3142663483","https://openalex.org/W2350638539","https://openalex.org/W2023954774","https://openalex.org/W84129006","https://openalex.org/W2095778784","https://openalex.org/W1981345850","https://openalex.org/W2002833390","https://openalex.org/W2791204867"],"abstract_inverted_index":{"Sparse":[0,4],"Matrix-Vector":[1],"(SpMV)":[2],"and":[3,14,24,78,80,86,95],"Matrix-Multivector":[5],"(SpMM)":[6],"products":[7],"are":[8],"key":[9],"kernels":[10],"for":[11],"computational":[12],"science":[13],"data":[15],"science.":[16],"While":[17],"GPUs":[18,37],"offer":[19],"significantly":[20],"higher":[21],"peak":[22],"performance":[23,32,111],"memory":[25],"bandwidth":[26],"than":[27],"multicore":[28],"CPUs,":[29],"achieving":[30,91],"high":[31,92],"on":[33,36,49],"sparse":[34],"computations":[35],"is":[38],"very":[39],"challenging.":[40],"A":[41],"tremendous":[42],"amount":[43],"of":[44,53,99],"recent":[45],"research":[46],"has":[47,62],"focused":[48],"various":[50],"GPU":[51,97],"implementations":[52,116],"the":[54,58,104],"SpMV":[55,77],"kernel.":[56],"But":[57],"multi-vector":[59],"SpMM":[60,115],"kernel":[61],"received":[63],"much":[64],"less":[65],"attention.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"present":[71],"an":[72],"in-depth":[73],"analysis":[74],"to":[75,90],"contrast":[76],"SpMM,":[79],"develop":[81],"a":[82],"new":[83],"sparse-matrix":[84],"representation":[85],"computation":[87],"approach":[88],"suited":[89],"data-movement":[93],"efficiency":[94],"effective":[96],"parallelization":[98],"SpMM.":[100],"Experimental":[101],"evaluation":[102],"using":[103],"entire":[105],"SuiteSparse":[106],"matrix":[107],"suite":[108],"demonstrates":[109],"significant":[110],"improvement":[112],"over":[113],"existing":[114],"from":[117],"vendor":[118],"libraries.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}