{"id":"https://openalex.org/W4388662245","doi":"https://doi.org/10.1145/3581784.3607030","title":"5 ExaFlop/s HPL-MxP Benchmark with Linear Scalability on the 40-Million-Core Sunway Supercomputer","display_name":"5 ExaFlop/s HPL-MxP Benchmark with Linear Scalability on the 40-Million-Core Sunway Supercomputer","publication_year":2023,"publication_date":"2023-11-11","ids":{"openalex":"https://openalex.org/W4388662245","doi":"https://doi.org/10.1145/3581784.3607030"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607030","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607030","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607030","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/10.1145/3581784.3607030","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090666485","display_name":"Rongfen Lin","orcid":"https://orcid.org/0000-0003-0321-5405"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rongfen Lin","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021551205","display_name":"Xinhui Yuan","orcid":"https://orcid.org/0000-0002-1375-6435"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Yuan","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Qinghai University, Xining, Qinghai, China","Tsinghua University, Beijing, China","Tsinghua University, Beijing, China Qinghai University, Xining, Qinghai, China"],"affiliations":[{"raw_affiliation_string":"Qinghai University, Xining, Qinghai, China","institution_ids":["https://openalex.org/I116265982"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China Qinghai University, Xining, Qinghai, China","institution_ids":["https://openalex.org/I116265982","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093259863","display_name":"Wanwang Yin","orcid":"https://orcid.org/0000-0003-3680-2681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wanwang Yin","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041876687","display_name":"Jienan Yao","orcid":"https://orcid.org/0009-0006-6514-3119"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jienan Yao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113046378","display_name":"Junda Shi","orcid":"https://orcid.org/0009-0007-6122-8868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junda Shi","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102726786","display_name":"Qiang Sun","orcid":"https://orcid.org/0009-0006-7122-4986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Sun","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101887195","display_name":"Chaobo Song","orcid":"https://orcid.org/0009-0009-0988-2760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaobo Song","raw_affiliation_strings":["National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"National Research Center of Parallel Computer Engineering &amp; Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102774642","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0001-5131-2520"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5090666485"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7085,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90551661,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9988999962806702,"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":0.8089160919189453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7556646466255188},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7473074197769165},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7442798614501953},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6877477169036865},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6786720752716064},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5018649101257324},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2109748125076294},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10259866714477539},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09817361831665039}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8089160919189453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556646466255188},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7473074197769165},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7442798614501953},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6877477169036865},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6786720752716064},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5018649101257324},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2109748125076294},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10259866714477539},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09817361831665039},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581784.3607030","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607030","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607030","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581784.3607030","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607030","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607030","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G326708228","display_name":null,"funder_award_id":"2242210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6706443894","display_name":null,"funder_award_id":"U2242210","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388662245.pdf","grobid_xml":"https://content.openalex.org/works/W4388662245.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1777209000","https://openalex.org/W1946080187","https://openalex.org/W1981534910","https://openalex.org/W1984070826","https://openalex.org/W2033614580","https://openalex.org/W2044953540","https://openalex.org/W2073306876","https://openalex.org/W2081114193","https://openalex.org/W2106171663","https://openalex.org/W2136834900","https://openalex.org/W2161588460","https://openalex.org/W2170611190","https://openalex.org/W2170996201","https://openalex.org/W2475126267","https://openalex.org/W2599973081","https://openalex.org/W2895305554","https://openalex.org/W3137083963","https://openalex.org/W3141650078","https://openalex.org/W4205771935","https://openalex.org/W4252947628","https://openalex.org/W4282959339","https://openalex.org/W4321636633"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4255172949","https://openalex.org/W2011430815","https://openalex.org/W4321606653","https://openalex.org/W1599154403","https://openalex.org/W4401278057"],"abstract_inverted_index":{"HPL-MxP":[0,65,71],"is":[1,54],"an":[2,39],"emerging":[3],"high":[4],"performance":[5,42],"benchmark":[6,32],"used":[7],"to":[8,33,121],"measure":[9],"the":[10,25,31,55,64,74,101,128],"mixed-precision":[11,41],"computing":[12,116],"capability":[13],"of":[14,50,69,86,123],"leading":[15],"supercomputers.":[16,158],"In":[17],"this":[18],"work,":[19],"we":[20],"present":[21],"our":[22,70],"efforts":[23],"on":[24,63,150],"new":[26],"Sunway":[27,151],"that":[28,83,99,118],"linearly":[29],"scales":[30],"over":[34,48],"40":[35],"million":[36],"cores,":[37],"sustains":[38],"overall":[40],"exceeding":[43],"5":[44],"ExaFlop/s,":[45],"and":[46,80,95,112,126,136],"achieves":[47],"85%":[49],"peak":[51],"performance,":[52],"which":[53],"highest":[56],"efficiency":[57],"reached":[58],"among":[59],"all":[60,87],"heterogeneous":[61,157],"systems":[62],"list.":[66],"The":[67],"optimizations":[68],"implementation":[72],"include":[73],"following:":[75],"(1)":[76],"a":[77,92,114],"Two-Direction":[78],"Look-Ahead":[79],"Overlap":[81],"algorithm":[82],"enables":[84],"overlaps":[85],"communications":[88,125],"with":[89],"computation;":[90],"(2)":[91],"multi-level":[93],"process-mapping":[94],"communication":[96,137],"scheduling":[97],"method":[98],"uses":[100],"entire":[102],"network":[103],"as":[104,106,153,155],"best":[105],"possible":[107],"while":[108,132],"maintaining":[109],"conflict-free":[110],"algorithm-flow;":[111],"(3)":[113],"CG-Fusion":[115],"framework":[117],"eliminates":[119],"up":[120],"60%":[122],"inter-chip":[124],"removes":[127],"memory":[129],"access":[130],"bottleneck":[131],"serving":[133],"both":[134],"computation":[135],"simultaneously.":[138],"This":[139],"work":[140],"could":[141],"also":[142],"provide":[143],"useful":[144],"insights":[145],"for":[146],"tuning":[147],"cutting-edge":[148],"applications":[149],"supercomputers":[152],"well":[154],"other":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
