{"id":"https://openalex.org/W4285387162","doi":"https://doi.org/10.1137/21m1395545","title":"Performance of the Low-Rank TT-SVD for Large Dense Tensors on Modern MultiCore CPUs","display_name":"Performance of the Low-Rank TT-SVD for Large Dense Tensors on Modern MultiCore CPUs","publication_year":2022,"publication_date":"2022-07-14","ids":{"openalex":"https://openalex.org/W4285387162","doi":"https://doi.org/10.1137/21m1395545"},"language":"en","primary_location":{"id":"doi:10.1137/21m1395545","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1395545","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific 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/A5048878210","display_name":"Melven R\u00f6hrig-Z\u00f6llner","orcid":"https://orcid.org/0000-0001-9851-5886"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Melven R\u00f6hrig-Z\u00f6llner","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9851-5886","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010377968","display_name":"Jonas Thies","orcid":"https://orcid.org/0000-0001-9231-9999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonas Thies","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070137241","display_name":"Achim Basermann","orcid":"https://orcid.org/0000-0003-3637-3231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Achim Basermann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048878210"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8201,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69904077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"44","issue":"4","first_page":"C287","last_page":"C309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9944000244140625,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/singular-value-decomposition","display_name":"Singular value decomposition","score":0.7361374497413635},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6161302328109741},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5694500803947449},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.523012101650238},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5147985816001892},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5141456723213196},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49731138348579407},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.48509347438812256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48485860228538513},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4689324200153351},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4596324861049652},{"id":"https://openalex.org/keywords/multilinear-algebra","display_name":"Multilinear algebra","score":0.4407294690608978},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4315345883369446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3938443660736084},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3184543251991272},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3118384778499603},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.16713860630989075},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.13343405723571777},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.1258479356765747},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10202792286872864},{"id":"https://openalex.org/keywords/division-algebra","display_name":"Division algebra","score":0.09509822726249695}],"concepts":[{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.7361374497413635},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6161302328109741},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5694500803947449},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.523012101650238},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5147985816001892},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5141456723213196},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49731138348579407},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.48509347438812256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48485860228538513},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4689324200153351},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4596324861049652},{"id":"https://openalex.org/C60321788","wikidata":"https://www.wikidata.org/wiki/Q1197190","display_name":"Multilinear algebra","level":5,"score":0.4407294690608978},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4315345883369446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3938443660736084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3184543251991272},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3118384778499603},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.16713860630989075},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.13343405723571777},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.1258479356765747},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10202792286872864},{"id":"https://openalex.org/C138354692","wikidata":"https://www.wikidata.org/wiki/Q1231309","display_name":"Division algebra","level":4,"score":0.09509822726249695},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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},{"id":"https://openalex.org/C169171071","wikidata":"https://www.wikidata.org/wiki/Q5449241","display_name":"Filtered algebra","level":3,"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":3,"locations":[{"id":"doi:10.1137/21m1395545","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1395545","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:elib.dlr.de:190125","is_oa":false,"landing_page_url":"https://doi.org/10.1137/21m1395545>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:tudelft.nl:uuid:5f241017-19b7-42cf-87a2-aa7439bb9d2d","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:5f241017-19b7-42cf-87a2-aa7439bb9d2d","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522241184","https://openalex.org/W1733387414","https://openalex.org/W1858056047","https://openalex.org/W1961751213","https://openalex.org/W1967077133","https://openalex.org/W1967859589","https://openalex.org/W1982811641","https://openalex.org/W1990044052","https://openalex.org/W1993482030","https://openalex.org/W1995406764","https://openalex.org/W1997870068","https://openalex.org/W2002555321","https://openalex.org/W2004742816","https://openalex.org/W2037768897","https://openalex.org/W2040059039","https://openalex.org/W2041408102","https://openalex.org/W2056704685","https://openalex.org/W2066972040","https://openalex.org/W2078636996","https://openalex.org/W2092590148","https://openalex.org/W2096699795","https://openalex.org/W2099611016","https://openalex.org/W2157237396","https://openalex.org/W2175670603","https://openalex.org/W2282989799","https://openalex.org/W2948703217","https://openalex.org/W2978272478","https://openalex.org/W2978683479","https://openalex.org/W3035965352","https://openalex.org/W3096024647","https://openalex.org/W3099398162","https://openalex.org/W3099878876","https://openalex.org/W3100193990","https://openalex.org/W3199663023","https://openalex.org/W4210523970","https://openalex.org/W4229666556"],"related_works":["https://openalex.org/W2525655506","https://openalex.org/W2094467911","https://openalex.org/W4360857812","https://openalex.org/W1982615145","https://openalex.org/W3006227194","https://openalex.org/W3147497457","https://openalex.org/W3121314575","https://openalex.org/W2142724386","https://openalex.org/W4206336957","https://openalex.org/W3004823601"],"abstract_inverted_index":{"There":[0],"are":[1,51,89],"several":[2],"factorizations":[3],"of":[4,78,142,237],"multidimensional":[5],"tensors":[6],"into":[7],"lower-dimensional":[8],"components,":[9],"known":[10],"as":[11,56,164,166,201,203],"\u201ctensor":[12],"networks.\u201d":[13],"We":[14,110,138,181],"consider":[15],"the":[16,68,76,93,140,143,148,193,205,222,238],"popular":[17],"\u201ctensor-train\u201d":[18],"(TT)":[19],"format":[20],"and":[21,42,53,64,129,135],"ask,":[22],"How":[23],"efficiently":[24],"can":[25,199],"we":[26,154],"compute":[27],"a":[28,32,112,124,130,184,196,212],"low-rank":[29,101,197],"approximation":[30,198],"from":[31,208],"full":[33],"tensor":[34,102,188],"on":[35,120],"current":[36],"multicore":[37],"CPUs?":[38],"Compared":[39],"to":[40,105,228,230],"sparse":[41],"dense":[43],"linear":[44],"algebra,":[45],"kernel":[46],"libraries":[47,61,88],"for":[48,82,92,158,162,187],"multilinear":[49],"algebra":[50,60],"rare":[52],"typically":[54,90],"not":[55],"well":[57,165],"optimized.":[58],"Linear":[59],"like":[62],"BLAS":[63],"LAPACK":[65],"may":[66],"provide":[67],"required":[69],"operations":[70],"in":[71],"principle":[72],"but":[73],"often":[74],"at":[75,224],"cost":[77],"additional":[79],"data":[80,206],"movements":[81],"rearranging":[83],"memory":[84,106],"layouts.":[85],"Furthermore,":[86],"these":[87],"optimized":[91],"compute-bound":[94],"case":[95],"(e.g.,":[96],"square":[97],"matrix":[98],"operations),":[99],"whereas":[100],"decompositions":[103],"lead":[104],"bandwidth":[107],"limited":[108],"operations.":[109],"propose":[111],"\u201cTT":[113],"singular":[114],"value":[115],"decomposition\u201d":[116],"(TT-SVD)":[117],"algorithm":[118,146],"based":[119],"two":[121],"building":[122],"blocks:":[123],"\u201cQ-less":[125],"tall-skinny":[126,132],"QR\u201d":[127],"factorization":[128,189],"fused":[131],"matrix-matrix":[133],"multiplication":[134],"reshape":[136],"operation.":[137],"analyze":[139],"performance":[141,150,156,179,219],"resulting":[144],"TT-SVD":[145,175],"using":[147],"roofline":[149],"model.":[151],"In":[152],"addition,":[153],"present":[155],"results":[157],"different":[159],"algorithmic":[160],"variants":[161],"shared-memory":[163],"distributed-memory":[167],"architectures.":[168],"Our":[169],"experiments":[170],"show":[171],"that":[172,183,216,233],"commonly":[173],"used":[174],"implementations":[176],"suffer":[177],"severe":[178],"penalties.":[180],"conclude":[182],"dedicated":[185],"library":[186],"kernels":[190],"would":[191],"benefit":[192],"community:":[194],"Computing":[195],"be":[200],"cheap":[202],"reading":[204],"twice":[207],"main":[209],"memory.":[210],"As":[211],"consequence,":[213],"an":[214],"implementation":[215],"achieves":[217],"realistic":[218],"will":[220],"move":[221],"limit":[223],"which":[225],"one":[226],"has":[227],"resort":[229],"randomized":[231],"methods":[232],"only":[234],"process":[235],"part":[236],"data.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-07-14T00:00:00"}