{"id":"https://openalex.org/W4213440247","doi":"https://doi.org/10.1109/tpds.2022.3153113","title":"A Native Tensor\u2013Vector Multiplication Algorithm for High Performance Computing","display_name":"A Native Tensor\u2013Vector Multiplication Algorithm for High Performance Computing","publication_year":2022,"publication_date":"2022-02-23","ids":{"openalex":"https://openalex.org/W4213440247","doi":"https://doi.org/10.1109/tpds.2022.3153113"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3153113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3153113","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/363347","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054189914","display_name":"Pedro J. Mart\u00ednez-Ferrer","orcid":"https://orcid.org/0000-0002-6097-6676"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pedro J. Martinez-Ferrer","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC), Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-6097-6676","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073922794","display_name":"A. N. Yzelman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. N. Yzelman","raw_affiliation_strings":["Computing Systems Laboratory, Huawei Technologies Switzerland, Z&#x00FC;rich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Systems Laboratory, Huawei Technologies Switzerland, Z&#x00FC;rich, Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041767872","display_name":"Vicen\u00e7 Beltr\u00e1n","orcid":"https://orcid.org/0000-0002-3580-9630"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Vicen\u00e7 Beltran","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC), Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3580-9630","affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2723,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43817527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"33","issue":"12","first_page":"3363","last_page":"3374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976999759674072,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9325000047683716,"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/computer-science","display_name":"Computer science","score":0.8707795143127441},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6522682309150696},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5814829468727112},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5345444083213806},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.47544384002685547},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46646153926849365},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45298606157302856},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4524948298931122},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4458223879337311},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3502030372619629}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707795143127441},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6522682309150696},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5814829468727112},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5345444083213806},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.47544384002685547},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46646153926849365},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45298606157302856},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4524948298931122},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4458223879337311},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3502030372619629},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":2,"locations":[{"id":"doi:10.1109/tpds.2022.3153113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3153113","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/363347","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/363347","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/363347","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/363347","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323868","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2018282388","https://openalex.org/W2024165284","https://openalex.org/W2064872546","https://openalex.org/W2072800519","https://openalex.org/W2175048909","https://openalex.org/W2252007067","https://openalex.org/W2471966094","https://openalex.org/W2528907418","https://openalex.org/W2588061952","https://openalex.org/W2590246587","https://openalex.org/W2924444427","https://openalex.org/W2956014075","https://openalex.org/W2963137752","https://openalex.org/W2982047938","https://openalex.org/W3101321165","https://openalex.org/W4244254628","https://openalex.org/W4255801121"],"related_works":["https://openalex.org/W3093936885","https://openalex.org/W2994146737","https://openalex.org/W295308437","https://openalex.org/W2992046671","https://openalex.org/W2106539092","https://openalex.org/W4205300683","https://openalex.org/W56570565","https://openalex.org/W334259611","https://openalex.org/W2152099439","https://openalex.org/W1907136119"],"abstract_inverted_index":{"Tensor":[0],"computations":[1],"are":[2,89],"important":[3],"mathematical":[4],"operations":[5],"for":[6,47,82,131,189],"applications":[7],"that":[8],"rely":[9],"on":[10,92,179],"multidimensional":[11],"data.":[12],"The":[13],"tensor\u2013vector":[14],"multiplication":[15],"(TVM)":[16],"is":[17,36,170],"the":[18,50,116,120,128,141,149,166,173,186],"most":[19,51],"memory-bound":[20],"tensor":[21],"contraction":[22,142],"in":[23,49],"this":[24],"class":[25],"of":[26,119,127,140,185],"operations.":[27],"This":[28],"article":[29],"proposes":[30],"an":[31],"open-source":[32],"TVM":[33,121,150,175],"algorithm":[34,58],"which":[35],"much":[37],"simpler":[38],"and":[39,64,75,98,101,108,125,137,177,183],"efficient":[40],"than":[41],"previous":[42],"approaches,":[43],"making":[44],"it":[45],"suitable":[46],"integration":[48],"popular":[52],"BLAS":[53],"libraries":[54],"available":[55],"today.":[56],"Our":[57],"has":[59],"been":[60],"written":[61],"from":[62],"scratch":[63],"features":[65],"unit-stride":[66],"memory":[67,111,136],"accesses,":[68],"cache":[69],"awareness,":[70],"mode":[71,153],"obliviousness,":[72],"full":[73],"vectorization":[74],"multi-threading":[76],"as":[77,79],"well":[78],"NUMA":[80,132,145],"awareness":[81],"non-hierarchically":[83],"stored":[84],"dense":[85],"tensors.":[86,191],"Numerical":[87],"experiments":[88],"carried":[90],"out":[91],"tensors":[93,115],"up":[94],"to":[95,157,162],"order":[96],"10":[97],"various":[99],"compilers":[100],"hardware":[102],"architectures":[103],"equipped":[104],"with":[105,134,147,172],"traditional":[106],"DDR":[107,135],"high":[109],"bandwidth":[110,130,188],"(HBM).":[112],"For":[113],"large":[114,190],"average":[117,180],"performance":[118,159],"ranges":[122],"between":[123,181],"62%":[124],"76%":[126],"theoretical":[129,187],"systems":[133,146],"remains":[138],"independent":[139],"mode.":[143],"On":[144],"HBM":[148],"exhibits":[151],"some":[152],"dependency":[154],"but":[155],"manages":[156],"reach":[158],"figures":[160],"close":[161],"peak":[163],"values.":[164],"Finally,":[165],"higher-order":[167],"power":[168],"method":[169],"benchmarked":[171],"proposed":[174],"kernel":[176],"delivers":[178],"58%":[182],"69%":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
