{"id":"https://openalex.org/W4399097577","doi":"https://doi.org/10.1142/s012962642450004x","title":"SPMSD: An Partitioning-Strategy for Parallel General Sparse Matrix-Matrix Multiplication on GPU","display_name":"SPMSD: An Partitioning-Strategy for Parallel General Sparse Matrix-Matrix Multiplication on GPU","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4399097577","doi":"https://doi.org/10.1142/s012962642450004x"},"language":"en","primary_location":{"id":"doi:10.1142/s012962642450004x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s012962642450004x","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","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/A5015599323","display_name":"Huanyu Cui","orcid":"https://orcid.org/0000-0001-7996-7545"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanyu Cui","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China"],"raw_orcid":"https://orcid.org/0000-0001-7996-7545","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031640535","display_name":"Nianbin Wang","orcid":"https://orcid.org/0000-0003-1738-7937"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nianbin Wang","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China"],"raw_orcid":"https://orcid.org/0000-0003-1738-7937","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012682887","display_name":"Qilong Han","orcid":"https://orcid.org/0000-0002-5185-8387"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qilong Han","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China"],"raw_orcid":"https://orcid.org/0000-0002-5185-8387","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423436","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0223-8181"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China"],"raw_orcid":"https://orcid.org/0000-0002-0223-8181","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":0.2142,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45901959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"34","issue":"02","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9994999766349792,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9957000017166138,"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":0.7139042019844055},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6650711894035339},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.578995943069458},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5646131038665771},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5595711469650269},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5330805778503418},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4781421422958374},{"id":"https://openalex.org/keywords/graph-partition","display_name":"Graph partition","score":0.473849356174469},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4719772934913635},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.469228595495224},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.43642687797546387},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.41392868757247925},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3179987072944641},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2451690137386322},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19427913427352905},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07785415649414062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139042019844055},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6650711894035339},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.578995943069458},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5646131038665771},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5595711469650269},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5330805778503418},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4781421422958374},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.473849356174469},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4719772934913635},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.469228595495224},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.43642687797546387},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.41392868757247925},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3179987072944641},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2451690137386322},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19427913427352905},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07785415649414062},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s012962642450004x","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s012962642450004x","pdf_url":null,"source":{"id":"https://openalex.org/S18360026","display_name":"Parallel Processing Letters","issn_l":"0129-6264","issn":["0129-6264","1793-642X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Parallel Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1564285798","https://openalex.org/W1973918431","https://openalex.org/W2007259720","https://openalex.org/W2065607954","https://openalex.org/W2556107930","https://openalex.org/W2620106252","https://openalex.org/W2886179562","https://openalex.org/W2912263513","https://openalex.org/W2914084747","https://openalex.org/W2964336816","https://openalex.org/W3035592585","https://openalex.org/W3041191963","https://openalex.org/W3091170309","https://openalex.org/W3096209535","https://openalex.org/W3106161546","https://openalex.org/W3126499951","https://openalex.org/W3126655641","https://openalex.org/W4230791431","https://openalex.org/W4240862739","https://openalex.org/W4243126102","https://openalex.org/W4254092058","https://openalex.org/W4256701974","https://openalex.org/W4285506300","https://openalex.org/W4400910398","https://openalex.org/W4401017734"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"SpGEMM":[0,32,119],"(General":[1],"Sparse":[2],"Matrix-Matrix":[3],"Multiplication)":[4],"is":[5,60,79,102,166,192],"one":[6],"of":[7,10,25,73,108,118,124,132,145,156,164,179],"the":[8,23,29,71,77,92,99,106,109,115,122,133,137,141,150,154,162,169,177,184],"kernels":[9],"an":[11],"algebraic":[12],"multi-grid":[13],"method,":[14,181],"graph":[15],"algorithm,":[16,50],"and":[17,67,127,136,143],"solving":[18],"linear":[19],"equations.":[20],"Due":[21],"to":[22,39,90,105,149,152],"non-uniformity":[24],"some":[26],"sparse":[27],"matrices,":[28],"existing":[30,170],"parallel":[31,116],"algorithms":[33],"suffer":[34],"from":[35],"load":[36],"imbalance,":[37],"lead":[38],"a":[40,48,64,86],"decrease":[41],"in":[42,76],"computational":[43,185],"efficiency.":[44],"This":[45],"paper":[46],"proposes":[47],"new":[49,87],"SPMSD":[51,113,165,182,189],"(SpGEMM":[52],"Based":[53],"on":[54,63,85,121],"Minimum":[55],"Standard":[56],"Deviation).":[57],"The":[58],"algorithm":[59],"developed":[61],"based":[62,84,120],"hash":[65,134],"table":[66,135],"partition":[68,88,110],"strategy.":[69,111],"First,":[70],"number":[72],"intermediate":[74,146],"results":[75,147],"matrix":[78,101],"divided":[80],"into":[81],"multiple":[82],"blocks":[83],"strategy":[89],"ensure":[91],"minimum":[93],"standard":[94],"deviation":[95],"among":[96],"blocks.":[97],"Second,":[98],"input":[100],"transformed":[103],"according":[104,148],"result":[107],"Finally,":[112],"performs":[114],"computing":[117],"advantages":[123],"fast":[125,129],"insertion":[126,142],"also":[128],"access":[130],"storage":[131],"calculation":[138],"process":[139],"controls":[140],"merging":[144],"offset":[151],"avoid":[153],"shortage":[155],"atomic":[157],"operations.":[158],"These":[159],"experiments":[160],"indicate":[161],"execution":[163],"faster":[167],"than":[168],"cuSPARSE":[171],"libraries":[172],"by":[173,187,194],"7.4x.":[174],"Compared":[175],"with":[176],"Out":[178],"Core":[180],"improves":[183],"performance":[186],"1.2x,":[188],"memory":[190],"utilization":[191],"decreased":[193],"0.19x.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}