{"id":"https://openalex.org/W3009472344","doi":"https://doi.org/10.1145/3378176","title":"Enabling Highly Efficient Batched Matrix Multiplications on SW26010 Many-core Processor","display_name":"Enabling Highly Efficient Batched Matrix Multiplications on SW26010 Many-core Processor","publication_year":2020,"publication_date":"2020-03-04","ids":{"openalex":"https://openalex.org/W3009472344","doi":"https://doi.org/10.1145/3378176","mag":"3009472344"},"language":"en","primary_location":{"id":"doi:10.1145/3378176","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3378176","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3378176","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3378176","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101829273","display_name":"Lijuan Jiang","orcid":"https://orcid.org/0000-0003-0288-6784"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijuan Jiang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005718995","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7426-6248"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100695928","display_name":"Wenjing Ma","orcid":"https://orcid.org/0000-0002-1795-4498"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Ma","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101829273"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":2.0793,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86469222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983999729156494,"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":0.9976999759674072,"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":0.8568025827407837},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7455207109451294},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7309815287590027},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6813777685165405},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6323005557060242},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5827746391296387},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5213069319725037},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46686768531799316},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.43453487753868103},{"id":"https://openalex.org/keywords/out-of-core-algorithm","display_name":"Out-of-core algorithm","score":0.41269540786743164},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0974869430065155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568025827407837},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7455207109451294},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7309815287590027},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6813777685165405},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6323005557060242},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5827746391296387},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5213069319725037},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46686768531799316},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.43453487753868103},{"id":"https://openalex.org/C79470037","wikidata":"https://www.wikidata.org/wiki/Q279748","display_name":"Out-of-core algorithm","level":2,"score":0.41269540786743164},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0974869430065155},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3378176","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3378176","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3378176","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3378176","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3378176","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3378176","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3009472344.pdf","grobid_xml":"https://content.openalex.org/works/W3009472344.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1533840382","https://openalex.org/W1985258161","https://openalex.org/W1990875063","https://openalex.org/W2002257715","https://openalex.org/W2002555321","https://openalex.org/W2035476608","https://openalex.org/W2054658678","https://openalex.org/W2071148743","https://openalex.org/W2073061372","https://openalex.org/W2079066236","https://openalex.org/W2091087653","https://openalex.org/W2091371833","https://openalex.org/W2099021415","https://openalex.org/W2135653967","https://openalex.org/W2152517358","https://openalex.org/W2170996201","https://openalex.org/W2280571487","https://openalex.org/W2330820318","https://openalex.org/W2346977986","https://openalex.org/W2471966094","https://openalex.org/W2475126267","https://openalex.org/W2499931820","https://openalex.org/W2530848289","https://openalex.org/W2531348778","https://openalex.org/W2561247022","https://openalex.org/W2562913534","https://openalex.org/W2565436413","https://openalex.org/W2617819327","https://openalex.org/W2622428623","https://openalex.org/W2751353152","https://openalex.org/W2753495321","https://openalex.org/W2896652512","https://openalex.org/W2913790721","https://openalex.org/W3085162807","https://openalex.org/W3101321165","https://openalex.org/W4244254628","https://openalex.org/W4246373967","https://openalex.org/W4297957988"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W2119413962","https://openalex.org/W4301930836","https://openalex.org/W2142016460","https://openalex.org/W2090793918","https://openalex.org/W2110605091","https://openalex.org/W2375658374","https://openalex.org/W1972572889"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,23],"systematic":[3],"methodology":[4],"for":[5,64],"optimizing":[6],"batched":[7,46,81],"matrix":[8,47,66,82],"multiplications":[9,83],"on":[10],"SW26010":[11,37],"many-core":[12],"processor":[13],"of":[14,36,45,94],"the":[15,33,41,53,61,79,87,95],"Sunway":[16],"TaihuLight":[17],"supercomputer.":[18],"Five":[19],"surrogate":[20],"algorithms":[21],"and":[22,38,68,74,90],"machine":[24],"learning\u2013based":[25],"algorithm":[26,43,54,63],"selector":[27,55],"are":[28],"proposed":[29],"to":[30,58],"fully":[31],"exploit":[32],"computing":[34],"capability":[35],"cope":[39],"with":[40,71],"sophisticated":[42],"characteristics":[44],"multiplications.":[48],"Experiment":[49],"results":[50],"show":[51],"that":[52],"is":[56],"able":[57],"adaptively":[59],"choose":[60],"appropriate":[62],"various":[65],"shapes":[67],"batch":[69],"sizes":[70],"low":[72],"overhead":[73],"high":[75],"accuracy.":[76],"In":[77],"particular,":[78],"optimized":[80],"can":[84],"substantially":[85],"outperform":[86],"non-batched":[88],"version":[89],"reach":[91],"around":[92],"84.8%":[93],"performance":[96],"upper":[97],"bound.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}