{"id":"https://openalex.org/W4399304499","doi":"https://doi.org/10.1145/3650200.3656611","title":"Stencil Computation with Vector Outer Product","display_name":"Stencil Computation with Vector Outer Product","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399304499","doi":"https://doi.org/10.1145/3650200.3656611"},"language":"en","primary_location":{"id":"doi:10.1145/3650200.3656611","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656611","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656611","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 38th ACM International Conference on Supercomputing","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/10.1145/3650200.3656611","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072193782","display_name":"Wenxuan Zhao","orcid":"https://orcid.org/0009-0007-4464-7104"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenxuan Zhao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, China and University of Chinese Academy of Science, China"],"raw_orcid":"https://orcid.org/0009-0007-4464-7104","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, China and University of Chinese Academy of Science, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072946868","display_name":"Liang Yuan","orcid":"https://orcid.org/0000-0003-3406-2907"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yuan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-3406-2907","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103258327","display_name":"Baicheng Yan","orcid":"https://orcid.org/0000-0003-1277-8357"},"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":"Baicheng Yan","raw_affiliation_strings":["Huawei Technologies Co. Ltd, China"],"raw_orcid":"https://orcid.org/0000-0003-1277-8357","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026906674","display_name":"Penghao Ma","orcid":"https://orcid.org/0009-0001-9684-2960"},"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":"Penghao Ma","raw_affiliation_strings":["Huawei Technologies Co., Ltd, China"],"raw_orcid":"https://orcid.org/0009-0001-9684-2960","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016255357","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0001-7520-9640"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0001-7520-9640","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039807594","display_name":"Long Wang","orcid":"https://orcid.org/0009-0004-1638-5993"},"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":"Long Wang","raw_affiliation_strings":["Huawei Technologies Co., Ltd, China"],"raw_orcid":"https://orcid.org/0009-0004-1638-5993","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006140602","display_name":"Zhe Wang","orcid":"https://orcid.org/0009-0009-1888-4311"},"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":"Zhe Wang","raw_affiliation_strings":["Huawei Technologies Co., Ltd, China"],"raw_orcid":"https://orcid.org/0009-0009-1888-4311","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072193782"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.9487,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71686372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"258"},"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":0.9965999722480774,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9961000084877014,"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/stencil","display_name":"Stencil","score":0.828420102596283},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7901444435119629},{"id":"https://openalex.org/keywords/outer-product","display_name":"Outer product","score":0.7369801998138428},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7232682108879089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7016260027885437},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6811984777450562},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5812722444534302},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5645812749862671},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.5546061396598816},{"id":"https://openalex.org/keywords/matrix-algebra","display_name":"Matrix algebra","score":0.5076793432235718},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.5045722723007202},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4838091731071472},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4811609983444214},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.476754754781723},{"id":"https://openalex.org/keywords/cross-product","display_name":"Cross product","score":0.46036210656166077},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3412441313266754},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32140302658081055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19055449962615967},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.17358210682868958}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.828420102596283},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7901444435119629},{"id":"https://openalex.org/C180623205","wikidata":"https://www.wikidata.org/wiki/Q1268589","display_name":"Outer product","level":3,"score":0.7369801998138428},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7232682108879089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016260027885437},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6811984777450562},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5812722444534302},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5645812749862671},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.5546061396598816},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.5076793432235718},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.5045722723007202},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4838091731071472},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4811609983444214},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.476754754781723},{"id":"https://openalex.org/C82927061","wikidata":"https://www.wikidata.org/wiki/Q178192","display_name":"Cross product","level":2,"score":0.46036210656166077},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3412441313266754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32140302658081055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19055449962615967},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.17358210682868958},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3650200.3656611","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656611","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656611","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 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3650200.3656611","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656611","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656611","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 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399304499.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1492882524","https://openalex.org/W1494930385","https://openalex.org/W1506424797","https://openalex.org/W1559264847","https://openalex.org/W1561247983","https://openalex.org/W1751458545","https://openalex.org/W1968013322","https://openalex.org/W1973271197","https://openalex.org/W1979457157","https://openalex.org/W1987588924","https://openalex.org/W1997375049","https://openalex.org/W2001258868","https://openalex.org/W2004711550","https://openalex.org/W2016618963","https://openalex.org/W2027402472","https://openalex.org/W2034761517","https://openalex.org/W2035430533","https://openalex.org/W2039378765","https://openalex.org/W2049241685","https://openalex.org/W2063249715","https://openalex.org/W2063656563","https://openalex.org/W2076780324","https://openalex.org/W2081422781","https://openalex.org/W2096672917","https://openalex.org/W2097757554","https://openalex.org/W2108730477","https://openalex.org/W2118031182","https://openalex.org/W2124343275","https://openalex.org/W2135736783","https://openalex.org/W2147423491","https://openalex.org/W2151764765","https://openalex.org/W2154078685","https://openalex.org/W2162323496","https://openalex.org/W2166622045","https://openalex.org/W2167713801","https://openalex.org/W2198872802","https://openalex.org/W2288740281","https://openalex.org/W2296218291","https://openalex.org/W2913533776","https://openalex.org/W2984920043","https://openalex.org/W2999265844","https://openalex.org/W3016220765","https://openalex.org/W3099448935","https://openalex.org/W3147517636","https://openalex.org/W3149084271","https://openalex.org/W3152199537","https://openalex.org/W3205799311","https://openalex.org/W4234392772","https://openalex.org/W4235662649","https://openalex.org/W4241603478","https://openalex.org/W4249968602","https://openalex.org/W4251000960","https://openalex.org/W4255560897","https://openalex.org/W4318603197"],"related_works":["https://openalex.org/W2477603266","https://openalex.org/W4386773258","https://openalex.org/W3119149376","https://openalex.org/W2773116000","https://openalex.org/W2053694797","https://openalex.org/W82706782","https://openalex.org/W146094780","https://openalex.org/W2468737113","https://openalex.org/W623349242","https://openalex.org/W4236121505"],"abstract_inverted_index":{"Matrix":[0],"computation":[1],"units":[2],"have":[3],"been":[4],"equipped":[5],"in":[6],"current":[7],"architectures":[8],"to":[9,44,59],"accelerate":[10],"AI":[11],"and":[12,20,56],"high":[13],"performance":[14],"computing":[15,55],"applications.":[16],"The":[17,29],"matrix":[18],"multiplication":[19],"vector":[21],"outer":[22],"product":[23],"are":[24,37],"two":[25],"basic":[26],"instruction":[27],"types.":[28],"latter":[30],"one":[31],"is":[32],"lighter":[33],"since":[34],"the":[35,61],"inputs":[36],"vectors.":[38],"Thus":[39],"it":[40],"provides":[41],"more":[42,57],"opportunities":[43],"develop":[45],"flexible":[46],"algorithms":[47],"for":[48],"problems":[49],"other":[50],"than":[51],"dense":[52],"linear":[53],"algebra":[54],"possibilities":[58],"optimize":[60],"implementation.":[62]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
