{"id":"https://openalex.org/W4316252370","doi":"https://doi.org/10.1145/3545008.3545031","title":"Automatically Generating High-performance Matrix Multiplication Kernels on the Latest Sunway Processor","display_name":"Automatically Generating High-performance Matrix Multiplication Kernels on the Latest Sunway Processor","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4316252370","doi":"https://doi.org/10.1145/3545008.3545031"},"language":"en","primary_location":{"id":"doi:10.1145/3545008.3545031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009323865","display_name":"Xiaohan Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohan Tao","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028753892","display_name":"Yu Zhu","orcid":"https://orcid.org/0000-0001-8836-7939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhu","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725035","display_name":"Boyang Wang","orcid":"https://orcid.org/0000-0001-8973-2328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyang Wang","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101431784","display_name":"Jinlong Xu","orcid":"https://orcid.org/0000-0002-6261-8186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinlong Xu","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033392056","display_name":"Jianmin Pang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianmin Pang","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000546902","display_name":"Jie Zhao","orcid":"https://orcid.org/0000-0003-2303-9736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991000294685364,"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":0.9842000007629395,"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":0.8037519454956055},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7434325814247131},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7265793085098267},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6036774516105652},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.587106466293335},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4742031395435333},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4566168189048767},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34386807680130005},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1416078507900238},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07810026407241821},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.0779309868812561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037519454956055},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7434325814247131},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7265793085098267},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6036774516105652},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.587106466293335},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4742031395435333},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4566168189048767},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34386807680130005},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1416078507900238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07810026407241821},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0779309868812561},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","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:10.1145/3545008.3545031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.550000011920929}],"awards":[{"id":"https://openalex.org/G7619151073","display_name":null,"funder_award_id":"U20A20226","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1191262899","https://openalex.org/W1558370006","https://openalex.org/W1991009705","https://openalex.org/W2034761517","https://openalex.org/W2064872546","https://openalex.org/W2067575922","https://openalex.org/W2073061372","https://openalex.org/W2076517649","https://openalex.org/W2077143534","https://openalex.org/W2168412050","https://openalex.org/W2252007067","https://openalex.org/W2475126267","https://openalex.org/W2516525699","https://openalex.org/W2592969254","https://openalex.org/W2753495321","https://openalex.org/W2767373187","https://openalex.org/W2885356209","https://openalex.org/W2912456980","https://openalex.org/W2962871385","https://openalex.org/W2979365412","https://openalex.org/W3009472344","https://openalex.org/W3104745751","https://openalex.org/W3119880013","https://openalex.org/W3177452048","https://openalex.org/W3210190478","https://openalex.org/W4220850685","https://openalex.org/W4231010555","https://openalex.org/W4243796884"],"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/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"We":[0,120],"present":[1],"an":[2],"approach":[3,104],"to":[4,40,56,83,111,118],"the":[5,14,23,31,77,86,106,137],"automatic":[6],"generation":[7],"of":[8,26,30,85],"efficient":[9,113],"matrix":[10,49,114,126],"multiplication":[11,50,127],"code":[12,44,115],"on":[13,34],"latest":[15],"Sunway":[16,27],"processor,":[17],"which":[18],"will":[19],"be":[20],"employed":[21],"by":[22,97,140],"next-generation":[24],"machine":[25],"TaihuLight,":[28],"one":[29],"fastest":[32],"supercomputers":[33],"earth.":[35],"The":[36],"method":[37,91],"allows":[38],"users":[39],"write":[41],"simple":[42],"C":[43],"and":[45,66,128,143],"automatically":[46],"generates":[47],"high-performance":[48],"kernels.":[51,79],"It":[52],"uses":[53],"polyhedral":[54],"transformations":[55],"implement":[57],"rapid":[58],"compute":[59],"decomposition,":[60],"data":[61],"exchanges":[62],"across":[63],"memory":[64,67],"hierarchy":[65],"latency":[68],"hiding.":[69],"An":[70],"assembly":[71],"routine":[72],"is":[73],"finally":[74],"integrated":[75],"into":[76,123],"generated":[78],"While":[80],"achieving":[81],"up":[82],"90.14%":[84],"theoretical":[87],"peak":[88],"performance,":[89],"our":[90,103],"surpasses":[92],"a":[93],"highly":[94],"tuned":[95],"library":[96],"9.44%.":[98],"Compared":[99],"with":[100],"existing":[101],"techniques,":[102],"reduces":[105],"software":[107],"development":[108],"life":[109],"cycle":[110],"generate":[112],"from":[116],"months":[117],"seconds.":[119],"also":[121],"take":[122],"account":[124],"batched":[125],"some":[129],"fusion":[130],"patterns":[131],"for":[132],"deep":[133],"learning":[134],"(DL),":[135],"outperforming":[136],"library-based":[138],"implementations":[139],"1.30":[141],"\u00d7":[142],"1.67":[144],"\u00d7.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
