{"id":"https://openalex.org/W2399225167","doi":"https://doi.org/10.1109/tpds.2015.2453970","title":"Locality-Aware Parallel Sparse Matrix-Vector and Matrix-Transpose-Vector Multiplication on Many-Core Processors","display_name":"Locality-Aware Parallel Sparse Matrix-Vector and Matrix-Transpose-Vector Multiplication on Many-Core Processors","publication_year":2015,"publication_date":"2015-07-08","ids":{"openalex":"https://openalex.org/W2399225167","doi":"https://doi.org/10.1109/tpds.2015.2453970","mag":"2399225167"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2015.2453970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2453970","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5002536001","display_name":"M. Ozan Karsavuran","orcid":"https://orcid.org/0000-0002-0298-3034"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"M. Ozan Karsavuran","raw_affiliation_strings":["Department of Computer Engineering, Bilkent University, Ankara, Turkey","Department of Computer Engineering, Bilkent University, 6800, Ankara, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bilkent University, Ankara, Turkey","institution_ids":["https://openalex.org/I168864056"]},{"raw_affiliation_string":"Department of Computer Engineering, Bilkent University, 6800, Ankara, Turkey","institution_ids":["https://openalex.org/I168864056"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048117226","display_name":"Kadir Akbudak","orcid":"https://orcid.org/0000-0002-1057-1590"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Kadir Akbudak","raw_affiliation_strings":["Department of Computer Engineering, Bilkent University, Ankara, Turkey","Department of Computer Engineering, Bilkent University, 6800, Ankara, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bilkent University, Ankara, Turkey","institution_ids":["https://openalex.org/I168864056"]},{"raw_affiliation_string":"Department of Computer Engineering, Bilkent University, 6800, Ankara, Turkey","institution_ids":["https://openalex.org/I168864056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087435011","display_name":"Cevdet Aykanat","orcid":"https://orcid.org/0000-0002-4559-1321"},"institutions":[{"id":"https://openalex.org/I168864056","display_name":"Bilkent University","ror":"https://ror.org/02vh8a032","country_code":"TR","type":"education","lineage":["https://openalex.org/I168864056"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cevdet Aykanat","raw_affiliation_strings":["Department of Computer Engineering, Bilkent University, Ankara, Turkey","Department of Computer Engineering, Bilkent University, 6800, Ankara, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bilkent University, Ankara, Turkey","institution_ids":["https://openalex.org/I168864056"]},{"raw_affiliation_string":"Department of Computer Engineering, Bilkent University, 6800, Ankara, Turkey","institution_ids":["https://openalex.org/I168864056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6355,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90362694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":"6","first_page":"1713","last_page":"1726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9944999814033508,"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/transpose","display_name":"Transpose","score":0.7654650211334229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743375837802887},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6658187508583069},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.579054057598114},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5240723490715027},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4468998908996582},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.42781782150268555},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4073886573314667},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11565378308296204},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09747904539108276},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.09300079941749573},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.08659738302230835}],"concepts":[{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.7654650211334229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743375837802887},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6658187508583069},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.579054057598114},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5240723490715027},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4468998908996582},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.42781782150268555},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4073886573314667},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11565378308296204},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09747904539108276},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.09300079941749573},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.08659738302230835},{"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":2,"locations":[{"id":"doi:10.1109/tpds.2015.2453970","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2453970","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/36500","is_oa":false,"landing_page_url":"http://hdl.handle.net/11693/36500","pdf_url":null,"source":{"id":"https://openalex.org/S4306400079","display_name":"Bilkent University Institutional Repository (Bilkent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I168864056","host_organization_name":"Bilkent University","host_organization_lineage":["https://openalex.org/I168864056"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3257769024","display_name":null,"funder_award_id":"2014-2020","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"},{"id":"https://openalex.org/G3583131366","display_name":null,"funder_award_id":"653838","funder_id":"https://openalex.org/F4320321047","funder_display_name":"Partnership for Advanced Computing in Europe AISBL"},{"id":"https://openalex.org/G5842544232","display_name":null,"funder_award_id":"653838","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"}],"funders":[{"id":"https://openalex.org/F4320321047","display_name":"Partnership for Advanced Computing in Europe AISBL","ror":"https://ror.org/038j4hz26"},{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1252105715","https://openalex.org/W1506342804","https://openalex.org/W1518947877","https://openalex.org/W1552509329","https://openalex.org/W1776498962","https://openalex.org/W1966259407","https://openalex.org/W1968795497","https://openalex.org/W1987840949","https://openalex.org/W1996309908","https://openalex.org/W2002555321","https://openalex.org/W2009196736","https://openalex.org/W2023871968","https://openalex.org/W2025003325","https://openalex.org/W2035080386","https://openalex.org/W2044756790","https://openalex.org/W2076680677","https://openalex.org/W2078174680","https://openalex.org/W2086867325","https://openalex.org/W2092013581","https://openalex.org/W2095836023","https://openalex.org/W2097897435","https://openalex.org/W2099625934","https://openalex.org/W2101511474","https://openalex.org/W2103660617","https://openalex.org/W2126004407","https://openalex.org/W2138621811","https://openalex.org/W2142184646","https://openalex.org/W2146003804","https://openalex.org/W2161845544","https://openalex.org/W2269751313","https://openalex.org/W3103552514","https://openalex.org/W6633152989","https://openalex.org/W6693569684"],"related_works":["https://openalex.org/W3014652911","https://openalex.org/W1749782192","https://openalex.org/W4232554674","https://openalex.org/W1515810787","https://openalex.org/W2293771254","https://openalex.org/W2153754850","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W1956063732","https://openalex.org/W2094139070"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"and":[2,20,121,135,164,174,177,194,234],"matrix-transpose-vector":[3],"multiplication":[4],"(SpMM":[5],"<sup":[6,14,50,69,141],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[7,15,18,51,70,142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">T</sup>":[8,16,52,71,143],"V)":[9],"repeatedly":[10],"performed":[11],"as":[12],"z\u2190A":[13],"<sub":[17],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">x</sub>":[19],"y\u2190":[21],"A":[22,26,33],"z":[23],"(or":[24],"y":[25],"w)":[27],"for":[28,47,133,256],"the":[29,60,81,179,185,205,219,227,230,235,238,248,257,263],"same":[30,82,186],"sparse":[31,215],"matrix":[32,149],"is":[34,54],"a":[35,105,211],"kernel":[36],"operation":[37],"widely":[38],"used":[39],"in":[40,91,170,241],"various":[41],"iterative":[42],"solvers.":[43],"One":[44],"important":[45],"optimization":[46],"serial":[48],"SpMM":[49,68,140],"V":[53,72,144],"reusing":[55,161,252],"A-matrix":[56,75,162,253],"nonzeros,":[57],"which":[58,110,159],"halves":[59],"memory":[61],"bandwidth":[62],"requirement.":[63],"However,":[64],"thread-level":[65,137],"parallelization":[66,138],"of":[67,109,139,181,201,207,214,229,237,259],"that":[73,102,145,247],"reuses":[74],"nonzeros":[76,163,254],"necessitates":[77],"concurrent":[78,86,182,260],"writes":[79,87,183,261],"to":[80,184],"output-vector":[83,187],"entries.":[84,188],"These":[85,189],"can":[88],"be":[89],"handled":[90],"two":[92,154,190],"ways:":[93],"via":[94],"atomic":[95],"updates":[96],"or":[97,114],"thread-local":[98],"temporary":[99],"output":[100],"vectors":[101],"will":[103],"undergo":[104],"reduction":[106],"operation,":[107],"both":[108],"are":[111],"not":[112],"efficient":[113,134],"scalable":[115,136],"on":[116,210,218],"processors":[117],"with":[118],"many":[119],"cores":[120],"complicated":[122],"cache-coherency":[123],"protocols.":[124],"In":[125],"this":[126],"work,":[127],"we":[128],"identify":[129],"five":[130],"quality":[131,232],"criteria":[132,233],"utilizes":[146],"one-dimensional":[147],"(1D)":[148],"partitioning.":[150],"We":[151,203],"also":[152,245],"propose":[153],"locality-aware":[155],"1D":[156],"partitioning":[157],"methods,":[158],"achieve":[160],"intermediate":[165],"z-vector":[166,175],"entries;":[167,176],"exploiting":[168],"locality":[169],"accessing":[171],"x-,":[172],"y-,":[173],"reducing":[178],"number":[180],"methods":[191,209,240],"utilize":[192],"rowwise":[193],"columnwise":[195],"singly":[196],"bordered":[197],"block-diagonal":[198],"(SB)":[199],"forms":[200],"A.":[202],"evaluate":[204],"validity":[206,228,236],"our":[208],"wide":[212],"range":[213],"matrices.":[216],"Experiments":[217],"60-core":[220],"cache-coherent":[221],"Intel":[222],"Xeon":[223],"Phi":[224],"processor":[225],"show":[226,246],"identified":[231],"proposed":[239,264],"practice.":[242],"The":[243],"results":[244],"performance":[249],"improvement":[250],"from":[251],"compensates":[255],"overhead":[258],"through":[262],"SB-based":[265],"methods.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}