{"id":"https://openalex.org/W4401408518","doi":"https://doi.org/10.1145/3673038.3673054","title":"SaSpGEMM: Sorting-Avoiding Sparse General Matrix-Matrix Multiplication on Multi-Core Processors","display_name":"SaSpGEMM: Sorting-Avoiding Sparse General Matrix-Matrix Multiplication on Multi-Core Processors","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408518","doi":"https://doi.org/10.1145/3673038.3673054"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673054","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113325229","display_name":"Chuhe Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chuhe Hong","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913669","display_name":"Qinglin Wang","orcid":"https://orcid.org/0000-0002-8286-6566"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Wang","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013830599","display_name":"Runzhang Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runzhang Mao","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078642919","display_name":"Yuechao Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuechao Liang","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085500551","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0003-1444-6778"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454211","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, China and National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113325229"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.4894,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6038019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1166","last_page":"1175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9966999888420105,"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":0.6517761945724487},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6511310935020447},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6292172074317932},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6189243793487549},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.528633713722229},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5149412751197815},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4724460244178772},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4204515814781189},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34563764929771423},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22762471437454224},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12739071249961853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517761945724487},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6511310935020447},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6292172074317932},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6189243793487549},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.528633713722229},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5149412751197815},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4724460244178772},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4204515814781189},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34563764929771423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22762471437454224},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12739071249961853},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/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/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":1,"locations":[{"id":"doi:10.1145/3673038.3673054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3673038.3673054","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3673038.3673054","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3673038.3673054","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401408518.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1515144947","https://openalex.org/W1985263109","https://openalex.org/W2007259720","https://openalex.org/W2025890876","https://openalex.org/W2035080386","https://openalex.org/W2082238959","https://openalex.org/W2089437293","https://openalex.org/W2095249664","https://openalex.org/W2295258302","https://openalex.org/W2751658790","https://openalex.org/W2791012218","https://openalex.org/W2808128431","https://openalex.org/W2891832717","https://openalex.org/W2914086833","https://openalex.org/W2923126305","https://openalex.org/W2964337156","https://openalex.org/W2970435804","https://openalex.org/W2979747168","https://openalex.org/W2990514424","https://openalex.org/W2990689488","https://openalex.org/W3000305333","https://openalex.org/W3041191963","https://openalex.org/W3057502114","https://openalex.org/W3132695675","https://openalex.org/W4220912491","https://openalex.org/W4247712932","https://openalex.org/W4321636675","https://openalex.org/W4379644415","https://openalex.org/W4385623132","https://openalex.org/W4386709563","https://openalex.org/W4400064739"],"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":{"We":[0,119],"propose":[1],"the":[2,13,41,58,69,84,175,181],"SaSpGEMM:":[3],"a":[4,38,102,115,121,167,193],"parallel":[5],"sparse":[6,71],"general":[7],"matrix-matrix":[8],"multiplication":[9],"(SpGEMM)":[10],"to":[11,67,137],"avoid":[12],"overhead":[14],"of":[15,20,43,49,77,81,162,170,188,196],"sorting.":[16,30],"The":[17,61],"typical":[18],"workflow":[19],"SpGEMM":[21],"contains:":[22],"size":[23],"prediction,":[24],"memory":[25],"allocation,":[26],"numeric":[27],"calculation":[28,59],"and":[29,53,143,152],"However,":[31],"sorting":[32],"has":[33],"always":[34],"been":[35],"overlooked":[36],"as":[37],"bottleneck":[39],"in":[40,51,55,83],"performance":[42],"SpGEMM.":[44],"It":[45],"constitutes":[46],"an":[47,159,185],"average":[48,160,186],"30%":[50],"HASH":[52,144],"55%":[54],"ESC":[56],"during":[57,90],"stage.":[60],"key":[62],"idea":[63],"behind":[64],"SaSpGEMM":[65,127],"is":[66,88],"leverage":[68],"compressed":[70],"row":[72,86],"(CSR)":[73],"storage":[74],"format\u2019s":[75],"feature":[76],"increasing":[78],"index":[79],"order":[80,113],"elements":[82],"same":[85],"which":[87],"sorted":[89],"preprocessing,":[91],"preserving":[92],"intermediate":[93],"products":[94],"ordered":[95],"consistently.":[96],"To":[97],"achieve":[98],"this,":[99],"we":[100],"introduce":[101],"linked":[103],"list-based":[104],"accumulator":[105],"(LLA)":[106],"designed":[107],"for":[108],"batch":[109],"insertion":[110],"while":[111],"maintaining":[112],"with":[114],"low":[116],"time":[117,133],"complexity.":[118],"provide":[120],"comprehensive":[122],"empirical":[123],"evidence":[124],"showing":[125],"that":[126],"outperforms":[128],"other":[129],"methods":[130,140],"based":[131],"on":[132,145,174],"complexity":[134],"analysis.":[135],"Compared":[136],"three":[138],"state-of-the-art":[139],"ESC,":[141],"SPA,":[142],"both":[146],"x86":[147],"(Intel":[148],"Xeon":[149,177],"Gold":[150,178],"6348)":[151],"ARM":[153],"(Phytium2000+)":[154],"architectures,":[155],"our":[156],"method":[157],"achieves":[158,184],"speedup":[161,169,187,195],"2.82x,":[163],"5.24x,":[164],"1.16x":[165],"(with":[166,192],"maximum":[168,194],"34.4x,":[171],"195x,":[172],"23.3x)":[173],"Intel":[176],"6348.":[179],"On":[180],"Phytium2000+,":[182],"it":[183],"2.21x,":[189],"4,65x,":[190],"1.05x":[191],"40.93x,":[197],"146.7x,":[198],"9.03x).":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
