{"id":"https://openalex.org/W2891325938","doi":"https://doi.org/10.1109/tpds.2018.2871189","title":"Performance-Aware Model for Sparse Matrix-Matrix Multiplication on the Sunway TaihuLight Supercomputer","display_name":"Performance-Aware Model for Sparse Matrix-Matrix Multiplication on the Sunway TaihuLight Supercomputer","publication_year":2018,"publication_date":"2018-09-20","ids":{"openalex":"https://openalex.org/W2891325938","doi":"https://doi.org/10.1109/tpds.2018.2871189","mag":"2891325938"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2871189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2871189","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/A5035942362","display_name":"Yuedan Chen","orcid":"https://orcid.org/0000-0001-5665-268X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuedan Chen","raw_affiliation_strings":["National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-5665-268X","affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-2635-7716","affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016247312","display_name":"Wangdong Yang","orcid":"https://orcid.org/0000-0003-2681-7898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wangdong Yang","raw_affiliation_strings":["National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107094004","display_name":"Guoqing Xiao","orcid":"https://orcid.org/0000-0001-5008-4829"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Xiao","raw_affiliation_strings":["National Supercomputing Center in Changsha, College of Information Science and Engineering, Hunan University, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-5008-4829","affiliations":[{"raw_affiliation_string":"National Supercomputing Center in Changsha, College of Information Science and Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111752284","display_name":"Xianghui Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianghui Xie","raw_affiliation_strings":["State Key Laboratory of Mathematic Engineering and Advance Computing, Jiangnan Institute of Computing Technology, Wuxi, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematic Engineering and Advance Computing, Jiangnan Institute of Computing Technology, Wuxi, Jiangsu, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455376","display_name":"Tao Li","orcid":"https://orcid.org/0000-0003-1697-8022"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.0633,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.99685192,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"30","issue":"4","first_page":"923","last_page":"938"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.996399998664856,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9962000250816345,"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/supercomputer","display_name":"Supercomputer","score":0.9337025880813599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8021985292434692},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6935359835624695},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6170510053634644},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5018501281738281},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4831371009349823},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.46945255994796753},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4530486762523651},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41539716720581055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08548811078071594}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.9337025880813599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021985292434692},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6935359835624695},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6170510053634644},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5018501281738281},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4831371009349823},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.46945255994796753},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4530486762523651},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41539716720581055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08548811078071594},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2018.2871189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2871189","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1328409166","display_name":null,"funder_award_id":"61625202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2068411654","display_name":null,"funder_award_id":"61751204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5157801058","display_name":null,"funder_award_id":"61860206011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G796710601","display_name":null,"funder_award_id":"61806077","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G882002931","display_name":null,"funder_award_id":"61661146006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1964844604","https://openalex.org/W1967821347","https://openalex.org/W1973918431","https://openalex.org/W1980282429","https://openalex.org/W1981557297","https://openalex.org/W1985263109","https://openalex.org/W1986844835","https://openalex.org/W2003117296","https://openalex.org/W2010370862","https://openalex.org/W2022219663","https://openalex.org/W2025890876","https://openalex.org/W2035080386","https://openalex.org/W2039875226","https://openalex.org/W2066367171","https://openalex.org/W2082238959","https://openalex.org/W2091883426","https://openalex.org/W2095249664","https://openalex.org/W2128539477","https://openalex.org/W2235832317","https://openalex.org/W2321358174","https://openalex.org/W2410461480","https://openalex.org/W2521497392","https://openalex.org/W2539342202","https://openalex.org/W2542072367","https://openalex.org/W2582955817","https://openalex.org/W2618168961","https://openalex.org/W2751658790","https://openalex.org/W2753495321","https://openalex.org/W2767319308","https://openalex.org/W2788264912","https://openalex.org/W3022326557","https://openalex.org/W3105937213","https://openalex.org/W3111546386"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W1582436825","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"General":[0],"sparse":[1,131],"matrix-sparse":[2],"matrix":[3],"multiplication":[4],"(SpGEMM)":[5],"is":[6,56,119,213],"one":[7,195],"of":[8,17,62,100,109,139,158,162,180,184,229],"the":[9,45,60,73,107,110,123,130,136,142,148,156,159,167,171,190,205,216,227,231,237],"fundamental":[10],"linear":[11],"operations":[12],"in":[13,194,209],"a":[14,50,114],"wide":[15],"variety":[16],"scientific":[18],"applications.":[19],"To":[20],"implement":[21],"efficient":[22],"SpGEMM":[23,34,55,101,118,140,149,175,235],"for":[24,54,117,129,174,234],"many":[25],"large-scale":[26,163],"applications,":[27],"this":[28],"paper":[29],"proposes":[30],"scalable":[31],"and":[32,41,67,90,154,198,225],"optimized":[33],"kernels":[35,150,191,206],"based":[36,71],"on":[37,44,72,141,166,187,202,236],"COO,":[38],"CSR,":[39],"ELL,":[40],"CSC":[42],"formats":[43,128,233],"Sunway":[46,75,238],"TaihuLight":[47,239],"supercomputer.":[48,240],"First,":[49],"multi-level":[51],"parallelism":[52,61],"design":[53],"proposed":[57,111,120,217],"to":[58,96,121],"exploit":[59],"over":[63],"10":[64],"millions":[65],"cores":[66],"better":[68],"control":[69],"memory":[70],"special":[74],"architecture.":[76],"Optimization":[77],"strategies,":[78],"such":[79],"as":[80],"load":[81],"balance,":[82],"coalesced":[83],"DMA":[84],"transmission,":[85],"data":[86,164],"reuse,":[87],"vectorized":[88],"computation,":[89],"parallel":[91],"pipeline":[92],"processing,":[93],"are":[94,192,207],"applied":[95],"further":[97],"optimize":[98],"performance":[99,108,138],"kernels.":[102,112],"Second,":[103],"we":[104],"thoroughly":[105],"analyze":[106],"Third,":[113],"performance-aware":[115,172,218],"model":[116,173,219],"select":[122],"most":[124],"appropriate":[125],"compressed":[126],"storage":[127],"matrices":[132],"that":[133,215],"can":[134,220],"achieve":[135],"optimal":[137],"Sunway.":[143,168],"The":[144],"experimental":[145],"results":[146],"show":[147],"have":[151],"good":[152],"scalability":[153],"meet":[155],"challenge":[157],"high-speed":[160],"computing":[161],"sets":[165],"In":[169],"addition,":[170],"achieves":[176,199],"an":[177],"absolute":[178],"value":[179],"relative":[181],"error":[182],"rate":[183],"8.31":[185],"percent":[186,201],"average":[188,203],"when":[189,204],"executed":[193,208],"single":[196],"process":[197],"8.59":[200],"multiple":[210],"processes.":[211],"It":[212],"proved":[214],"perform":[221],"at":[222],"high":[223],"accuracy":[224],"satisfies":[226],"precision":[228],"selecting":[230],"best":[232]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":32}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
