{"id":"https://openalex.org/W4365450361","doi":"https://doi.org/10.1142/s0218126623502900","title":"Parallel Optimization of BLAS on a New-Generation Sunway Supercomputer","display_name":"Parallel Optimization of BLAS on a New-Generation Sunway Supercomputer","publication_year":2023,"publication_date":"2023-04-13","ids":{"openalex":"https://openalex.org/W4365450361","doi":"https://doi.org/10.1142/s0218126623502900"},"language":"en","primary_location":{"id":"doi:10.1142/s0218126623502900","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126623502900","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","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/A5077918834","display_name":"Yinqiao Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinqiao Ren","raw_affiliation_strings":["School of Software, Shandong University, Jinan, Shandong, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, Shandong, P. R. China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062702507","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0002-9026-2594"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Xu","raw_affiliation_strings":["School of Software, East China Normal University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-9026-2594","affiliations":[{"raw_affiliation_string":"School of Software, East China Normal University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062702507"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.423674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"32","issue":"17","first_page":null,"last_page":null},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9252891540527344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8045941591262817},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7992760539054871},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4542558193206787},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38824763894081116}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.9252891540527344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045941591262817},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7992760539054871},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4542558193206787},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38824763894081116},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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:10.1142/s0218126623502900","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126623502900","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2607504803","display_name":null,"funder_award_id":"2020YFA0607900","funder_id":"https://openalex.org/F4320335774","funder_display_name":"Key Technologies Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320335774","display_name":"Key Technologies Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2115585035","https://openalex.org/W2475126267","https://openalex.org/W2499702955","https://openalex.org/W2545915677","https://openalex.org/W2728256789","https://openalex.org/W2743163708","https://openalex.org/W2767373187","https://openalex.org/W2789228469","https://openalex.org/W2794940521","https://openalex.org/W2979138027","https://openalex.org/W3036005033","https://openalex.org/W3100903263","https://openalex.org/W3156772560","https://openalex.org/W3191277520","https://openalex.org/W3208078891","https://openalex.org/W4252301528","https://openalex.org/W4296339141"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384867379","https://openalex.org/W1599154403","https://openalex.org/W1582436825","https://openalex.org/W1925544630","https://openalex.org/W1996803181","https://openalex.org/W2979588510","https://openalex.org/W2004686618"],"abstract_inverted_index":{"The":[0],"new-generation":[1,68,86,145],"Sunway":[2,47,69,87,146],"supercomputer":[3,70],"has":[4],"ultra-high":[5],"computing":[6,92,99,151],"capacity.":[7],"But":[8],"due":[9,35],"to":[10,36,121,129],"the":[11,16,18,37,40,45,52,55,59,67,85,89,96,123,144,148,169,174,181,185],"unique":[12],"heterogeneous":[13],"architecture":[14],"of":[15,21,39,54,125,173,184],"supercomputer,":[17],"open-source":[19],"versions":[20],"basic":[22],"linear":[23],"algebra":[24],"subprograms":[25],"(BLAS)":[26],"are":[27],"insufficient":[28],"for":[29,75,88,112,147],"performance":[30,53],"or":[31],"compatibility.":[32],"In":[33],"addition,":[34],"update":[38],"architecture,":[41],"BLAS":[42,65,91,98,150,177],"based":[43,83,142],"on":[44,66,84,143],"previous":[46],"could":[48],"not":[49],"fully":[50],"exploit":[51],"successor.":[56],"To":[57],"address":[58],"challenges,":[60],"we":[61],"propose":[62],"an":[63,108],"optimized":[64,175,186],"in":[71],"this":[72],"paper.":[73],"Specially,":[74],"achieving":[76],"efficient":[77,132],"computation,":[78],"a":[79,138],"parallel":[80,139],"optimization":[81,140,159],"method":[82,141],"Level-1":[90],"between":[93,100,152],"vectors":[94,101],"and":[95,102,180],"Level-2":[97],"matrices":[103,153],"is":[104,116,119,154],"first":[105],"proposed.":[106],"Then,":[107],"adaptive":[109],"scheduling":[110],"algorithm":[111],"various":[113],"data":[114],"sizes":[115],"proposed,":[117,155],"which":[118,156],"used":[120],"balance":[122],"tasks":[124],"core":[126],"groups.":[127],"Finally,":[128],"achieve":[130],"highly":[131],"general":[133],"matrix":[134],"multiplication":[135],"(GEMM)":[136],"kernels,":[137],"Level-3":[149],"includes":[157],"source-level":[158],"as":[160,162],"well":[161],"assembly-level":[163],"optimization.":[164],"Experimental":[165],"results":[166],"show":[167],"that":[168],"memory":[170],"bandwidth":[171],"utilization":[172],"Level-1/2":[176],"exceeds":[178,189],"95%,":[179],"computational":[182],"efficiency":[183],"GEMM":[187],"kernel":[188],"94%.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
