{"id":"https://openalex.org/W4293731110","doi":"https://doi.org/10.1109/tpds.2022.3202518","title":"Increasing the Efficiency of Massively Parallel Sparse Matrix-Matrix Multiplication in First-Principles Calculation on the New-Generation Sunway Supercomputer","display_name":"Increasing the Efficiency of Massively Parallel Sparse Matrix-Matrix Multiplication in First-Principles Calculation on the New-Generation Sunway Supercomputer","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4293731110","doi":"https://doi.org/10.1109/tpds.2022.3202518"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3202518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3202518","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/A5057045655","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-0562-0319"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xin Chen","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110933605","display_name":"Yingxiang Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165734","display_name":"National Supercomputing Center of Tianjin","ror":"https://ror.org/05tngxm14","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210165734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingxiang Gao","raw_affiliation_strings":["National Supercomputer Center in Tianjin, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"National Supercomputer Center in Tianjin, Tianjin, China","institution_ids":["https://openalex.org/I4210165734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007597716","display_name":"Honghui Shang","orcid":"https://orcid.org/0000-0003-4957-4251"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":"Honghui Shang","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394179","display_name":"Fang Li","orcid":"https://orcid.org/0000-0002-3555-2126"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang Li","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700874","display_name":"Zhiqian Xu","orcid":"https://orcid.org/0000-0003-4022-2380"},"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqian Xu","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352268","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-7870-6535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056860593","display_name":"Dexun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dexun Chen","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering and Technology, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5057045655"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6567,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84461361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"12","first_page":"4752","last_page":"4766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9556999802589417,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9556999802589417,"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":0.9138000011444092,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9088000059127808,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.8769775032997131},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7878801822662354},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.7391794323921204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7357419729232788},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6321756839752197},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5468248724937439},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5141223073005676},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4668387174606323},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4434422552585602},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13295266032218933},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11834302544593811},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07675150036811829},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.07366254925727844},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0734063982963562}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8769775032997131},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7878801822662354},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.7391794323921204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357419729232788},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6321756839752197},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5468248724937439},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5141223073005676},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4668387174606323},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4434422552585602},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13295266032218933},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11834302544593811},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07675150036811829},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.07366254925727844},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0734063982963562},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3202518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3202518","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":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1289081580","display_name":null,"funder_award_id":"22003073","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2073684863","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"],"abstract_inverted_index":{"The":[0,120],"first-principles":[1],"approach":[2],"based":[3],"on":[4,96],"density-functional":[5],"theory":[6,9],"(DFT)/density-functional":[7],"perturbation":[8],"(DFPT)":[10],"is":[11,29,65,89],"widely":[12],"used":[13],"in":[14,35,53],"calculations":[15,93],"of":[16,47,62,129],"the":[17,42,45,48,57,63,67,73,97,104,113],"systems\u2019":[18],"ground":[19],"state":[20],"energy,":[21],"response":[22,77],"properties":[23],"(e.g.,":[24],"polarizability,":[25],"phonon":[26],"dispersions)":[27],"and":[28,38,76,94],"playing":[30],"an":[31],"increasingly":[32],"important":[33],"role":[34],"chemistry,":[36],"physics":[37],"materials":[39],"science.":[40],"For":[41],"large-scale":[43],"calculations,":[44],"computation":[46],"density":[49,51,74,78],"matrix/response":[50],"matrix":[52,75],"DFT/DFPT":[54],"has":[55,107],"become":[56],"main":[58],"performance":[59,109],"bottleneck.":[60],"One":[61],"solutions":[64],"using":[66],"linear":[68],"scaling":[69],"method":[70,106],"to":[71,112,124],"get":[72],"matrix.":[79],"Here":[80],"a":[81],"massively":[82],"parallel":[83,115],"medium":[84],"sparse":[85],"matrix-matrix":[86],"multiplication":[87],"algorithm":[88],"designed":[90],"for":[91],"first-principle":[92],"implemented":[95],"new-generation":[98],"Sunway":[99],"supercomputer.":[100],"Experiments":[101],"show":[102],"that":[103],"proposed":[105],"obvious":[108],"advantages":[110],"compared":[111],"original":[114],"version":[116],"under":[117],"moderate":[118],"sparsity.":[119],"computing":[121],"cores":[122],"scale":[123],"3,900,000":[125],"with":[126],"strong":[127],"scalability":[128],"77.3":[130],"<inline-formula><tex-math":[131],"notation=\"LaTeX\">$\\%$</tex-math></inline-formula>":[132],".":[133]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
