{"id":"https://openalex.org/W7155093050","doi":"https://doi.org/10.1007/s42514-026-00275-0","title":"Exploiting intra-core heterogeneity for high-performance dense linear algebra on Huawei Ascend 910 NPUs","display_name":"Exploiting intra-core heterogeneity for high-performance dense linear algebra on Huawei Ascend 910 NPUs","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155093050","doi":"https://doi.org/10.1007/s42514-026-00275-0"},"language":"en","primary_location":{"id":"doi:10.1007/s42514-026-00275-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42514-026-00275-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","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/A5022896605","display_name":"\u90ed\u58eb\u7eb3","orcid":null},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shina Guo","raw_affiliation_strings":["School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Management and Engineering, Shanghai University of Finance and Economics, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134165521","display_name":"Weiguo Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguo Gao","raw_affiliation_strings":["School of Mathematical Sciences, School of Data Science, Fudan University, Shanghai, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, School of Data Science, Fudan University, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113990871","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-9192-4684"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Huawei Corporation, Shanghai, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Corporation, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113452525","display_name":"Xinghui Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinghui Tian","raw_affiliation_strings":["Huawei Corporation, Shanghai, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Corporation, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134144187","display_name":"Yuan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Yuan Tang","raw_affiliation_strings":["School of Computer Science, School of Software, Fudan University, Shanghai, People\u2019s Republic of China","Shanghai Key Laboratory of Intelligent Information Processing, Shanghai, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, School of Software, Fudan University, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Shanghai, People\u2019s Republic of China","institution_ids":["https://openalex.org/I4210153682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5134144187"],"corresponding_institution_ids":["https://openalex.org/I24943067","https://openalex.org/I4210153682"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50525465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"3","first_page":"294","last_page":"313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8264999985694885,"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":0.8264999985694885,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.02459999918937683,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.02019999921321869,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/scheduling","display_name":"Scheduling (production processes)","score":0.6028000116348267},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5562999844551086},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.47450000047683716},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4456000030040741},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4327000081539154},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4077000021934509},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184999823570251},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5893999934196472},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5562999844551086},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38269999623298645},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.3206000030040741},{"id":"https://openalex.org/C128099668","wikidata":"https://www.wikidata.org/wiki/Q573952","display_name":"Lazy evaluation","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C176032523","wikidata":"https://www.wikidata.org/wiki/Q753127","display_name":"Topological sorting","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C184596265","wikidata":"https://www.wikidata.org/wiki/Q2651576","display_name":"Model of computation","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42514-026-00275-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42514-026-00275-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6115949167","display_name":null,"funder_award_id":"TC20240528049","funder_id":"https://openalex.org/F4320322183","funder_display_name":"Huawei Technologies"}],"funders":[{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1972501001","https://openalex.org/W1981534910","https://openalex.org/W2002257715","https://openalex.org/W2007768252","https://openalex.org/W2010747199","https://openalex.org/W2026237859","https://openalex.org/W2028637981","https://openalex.org/W2052196304","https://openalex.org/W2073061372","https://openalex.org/W2102291960","https://openalex.org/W2104373803","https://openalex.org/W2124480634","https://openalex.org/W2126982080","https://openalex.org/W2163688235","https://openalex.org/W2252007067","https://openalex.org/W2606722458","https://openalex.org/W2895305554","https://openalex.org/W2964106805","https://openalex.org/W3157657667","https://openalex.org/W3187688612","https://openalex.org/W4229666556","https://openalex.org/W4231150350","https://openalex.org/W4390479470","https://openalex.org/W4399845821","https://openalex.org/W6940976035"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2026-04-22T00:00:00"}
