{"id":"https://openalex.org/W1986844835","doi":"https://doi.org/10.1137/13092589x","title":"Simultaneous Input and Output Matrix Partitioning for Outer-Product--Parallel Sparse Matrix-Matrix Multiplication","display_name":"Simultaneous Input and Output Matrix Partitioning for Outer-Product--Parallel Sparse Matrix-Matrix Multiplication","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1986844835","doi":"https://doi.org/10.1137/13092589x","mag":"1986844835"},"language":"en","primary_location":{"id":"doi:10.1137/13092589x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/13092589x","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","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/A5048117226","display_name":"Kadir Akbudak","orcid":"https://orcid.org/0000-0002-1057-1590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kadir Akbudak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087435011","display_name":"Cevdet Aykanat","orcid":"https://orcid.org/0000-0002-4559-1321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cevdet Aykanat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4662,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92225727,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"36","issue":"5","first_page":"C568","last_page":"C590"},"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":0.9991999864578247,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7795112133026123},{"id":"https://openalex.org/keywords/hypergraph","display_name":"Hypergraph","score":0.7112144827842712},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6031201481819153},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5698741674423218},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5664457678794861},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5253036618232727},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.5001399517059326},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4797029197216034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.468517541885376},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42060425877571106},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4175226390361786},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1889834702014923}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7795112133026123},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.7112144827842712},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6031201481819153},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5698741674423218},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5664457678794861},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5253036618232727},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.5001399517059326},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4797029197216034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.468517541885376},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42060425877571106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4175226390361786},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1889834702014923},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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/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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/13092589x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/13092589x","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/12688","is_oa":false,"landing_page_url":"http://hdl.handle.net/11693/12688","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":"SIAM Journal on Scientific Computing","raw_type":"Article"},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/26546","is_oa":false,"landing_page_url":"http://hdl.handle.net/11693/26546","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":"SIAM Journal on Scientific Computing","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1965798822","https://openalex.org/W1966406013","https://openalex.org/W1991470918","https://openalex.org/W2003458338","https://openalex.org/W2019104854","https://openalex.org/W2020428152","https://openalex.org/W2022916138","https://openalex.org/W2042088790","https://openalex.org/W2053705619","https://openalex.org/W2056999868","https://openalex.org/W2065607954","https://openalex.org/W2069277577","https://openalex.org/W2080053067","https://openalex.org/W2089437293","https://openalex.org/W2121253712","https://openalex.org/W2141380216","https://openalex.org/W2142184646","https://openalex.org/W2332437841","https://openalex.org/W3106161546","https://openalex.org/W4245503759"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2086123442"],"abstract_inverted_index":{"For":[0],"outer-product--parallel":[1],"sparse":[2],"matrix-matrix":[3],"multiplication":[4],"(SpGEMM)":[5],"of":[6,19,27,43,60,77,124,130,137,145,159,168,184,191,198],"the":[7,44,61,65,78,97,101,106,111,117,133,138,147,151,156,165,169,182,192,219],"form":[8],"$C\\!=\\!A\\!\\times\\!B$,":[9],"we":[10],"propose":[11],"three":[12,31],"hypergraph":[13,32,53,221],"models":[14,33,69,186,222],"that":[15,161,218],"achieve":[16],"simultaneous":[17],"partitioning":[18,42,59,76,83,119,143],"input":[20,28,45],"and":[21,39,48,67,73,100,212],"output":[22,62,79],"matrices":[23,46],"without":[24],"any":[25],"replication":[26],"data.":[29],"All":[30],"perform":[34,70],"conformable":[35],"one-dimensional":[36],"(1D)":[37],"columnwise":[38,75],"1D":[40,71,74],"rowwise":[41,72],"$A$":[47],"$B$,":[49],"respectively.":[50,81],"The":[51,142],"first":[52,98],"model":[54],"performs":[55],"two-dimensional":[56],"(2D)":[57],"nonzero-based":[58],"matrix,":[63,80],"whereas":[64],"second":[66,112,166],"third":[68],"This":[82],"scheme":[84],"induces":[85],"a":[86,195],"two-phase":[87],"parallel":[88,139,170,175,205],"SpGEMM":[89,94,108,140,171,176,200],"algorithm,":[90],"where":[91],"communication-free":[92],"local":[93,107],"computations":[95],"constitute":[96,110],"phase":[99,167],"multiple":[102],"single-node-accumulation":[103],"operations":[104],"on":[105,122,202],"results":[109],"phase.":[113],"In":[114],"these":[115],"models,":[116],"two":[118,134,203],"constraints":[120],"defined":[121,149],"weights":[123],"vertices":[125],"encode":[126],"balancing":[127],"computational":[128],"loads":[129],"processors":[131],"during":[132,164],"separate":[135],"phases":[136],"algorithm.":[141,172],"objective":[144],"minimizing":[146,155],"cutsize":[148],"over":[150],"cut":[152],"nets":[153],"encodes":[154],"total":[157],"volume":[158],"communication":[160],"will":[162],"occur":[163],"An":[173],"MPI-based":[174],"library":[177,193],"is":[178],"developed":[179],"to":[180],"verify":[181],"validity":[183],"our":[185],"in":[187],"practice.":[188],"Parallel":[189],"runs":[190],"for":[194],"wide":[196],"range":[197],"realistic":[199],"instances":[201],"large-scale":[204],"systems":[206],"JUQUEEN":[207],"(an":[208,214],"IBM":[209],"BlueGene/Q":[210],"system)":[211],"SuperMUC":[213],"Intel-based":[215],"cluster)":[216],"show":[217],"proposed":[220],"attain":[223],"high":[224],"speedup":[225],"values.":[226]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}