{"id":"https://openalex.org/W2605702315","doi":"https://doi.org/10.1137/17m1135578","title":"Strassen's Algorithm for Tensor Contraction","display_name":"Strassen's Algorithm for Tensor Contraction","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2605702315","doi":"https://doi.org/10.1137/17m1135578","mag":"2605702315"},"language":"en","primary_location":{"id":"doi:10.1137/17m1135578","is_oa":false,"landing_page_url":"https://doi.org/10.1137/17m1135578","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/A5101717259","display_name":"Jianyu Huang","orcid":"https://orcid.org/0000-0001-7595-5539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianyu Huang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7595-5539","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019062687","display_name":"Devin A. Matthews","orcid":"https://orcid.org/0000-0003-2795-5483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Devin A. Matthews","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2795-5483","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061722569","display_name":"Robert A. Geijn","orcid":"https://orcid.org/0009-0004-6434-8492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert A. van de Geijn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8447,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85857852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"40","issue":"3","first_page":"C305","last_page":"C326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9991000294685364,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9836000204086304,"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/strassen-algorithm","display_name":"Strassen algorithm","score":0.9498381614685059},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7680329084396362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6094204187393188},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.592728316783905},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5564059019088745},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5254965424537659},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4178749918937683},{"id":"https://openalex.org/keywords/contraction","display_name":"Contraction (grammar)","score":0.41780540347099304},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36917757987976074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3395998179912567}],"concepts":[{"id":"https://openalex.org/C39096654","wikidata":"https://www.wikidata.org/wiki/Q728507","display_name":"Strassen algorithm","level":4,"score":0.9498381614685059},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7680329084396362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6094204187393188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.592728316783905},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5564059019088745},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5254965424537659},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4178749918937683},{"id":"https://openalex.org/C163415756","wikidata":"https://www.wikidata.org/wiki/Q126473","display_name":"Contraction (grammar)","level":2,"score":0.41780540347099304},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36917757987976074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3395998179912567},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/17m1135578","is_oa":false,"landing_page_url":"https://doi.org/10.1137/17m1135578","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3833732184","display_name":null,"funder_award_id":"CCF-1714091","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G641497076","display_name":null,"funder_award_id":"ACI-1550493","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320308258","display_name":"Qualcomm","ror":"https://ror.org/002zrf773"},{"id":"https://openalex.org/F4320332414","display_name":"Department of Mechanical Engineering, University of Texas at Austin","ror":"https://ror.org/00hj54h04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1584675441","https://openalex.org/W1967329527","https://openalex.org/W1971275758","https://openalex.org/W1985122440","https://openalex.org/W1993079359","https://openalex.org/W1994298443","https://openalex.org/W2002257715","https://openalex.org/W2004182761","https://openalex.org/W2006973305","https://openalex.org/W2024165284","https://openalex.org/W2035476608","https://openalex.org/W2039748980","https://openalex.org/W2040832766","https://openalex.org/W2045822279","https://openalex.org/W2051325990","https://openalex.org/W2056999868","https://openalex.org/W2069006374","https://openalex.org/W2072800519","https://openalex.org/W2073061372","https://openalex.org/W2090432916","https://openalex.org/W2092930273","https://openalex.org/W2104281151","https://openalex.org/W2108138101","https://openalex.org/W2147348850","https://openalex.org/W2252007067","https://openalex.org/W2412152731","https://openalex.org/W2493665548","https://openalex.org/W2516525699","https://openalex.org/W2588061952","https://openalex.org/W2963137752"],"related_works":["https://openalex.org/W1974407206","https://openalex.org/W2004916460","https://openalex.org/W2962985479","https://openalex.org/W2020777648","https://openalex.org/W1523285705","https://openalex.org/W2772956802","https://openalex.org/W2056120647","https://openalex.org/W1829171354","https://openalex.org/W2069906535","https://openalex.org/W4387712010"],"abstract_inverted_index":{"Tensor":[0],"contraction":[1],"(TC)":[2],"is":[3,14,27,126],"an":[4,89],"important":[5],"computational":[6],"kernel":[7],"widely":[8],"used":[9],"in":[10,30,58,139],"numerous":[11],"applications.":[12],"It":[13],"a":[15,68,71,84,99,107,133,163],"multidimensional":[16],"generalization":[17],"of":[18,103,122],"matrix":[19],"multiplication":[20],"(GEMM).":[21],"While":[22],"Strassen's":[23,64,104],"algorithm":[24,105],"for":[25,83,166],"GEMM":[26,82],"well":[28,137],"studied":[29],"theory":[31],"and":[32,115,118,146],"practice,":[33],"extending":[34],"it":[35],"to":[36,48,53,97,106,153],"accelerate":[37],"TC":[38,62,80],"has":[39],"not":[40],"been":[41],"previously":[42],"pursued.":[43],"Thus,":[44],"we":[45,76],"believe":[46],"this":[47],"be":[49],"the":[50,120],"first":[51],"paper":[52],"demonstrate":[54],"how":[55],"one":[56],"can":[57,77,160],"practice":[59,140],"speed":[60],"up":[61,152],"with":[63,88,132,169],"algorithm.":[65],"By":[66],"adopting":[67],"block-scatter-matrix":[69],"format,":[70],"novel":[72],"matrix-centric":[73],"tensor":[74],"layout,":[75],"conceptually":[78],"view":[79],"as":[81,136,138,162],"general":[85],"stride":[86],"storage,":[87],"implicit":[90],"tensor-to-matrix":[91],"transformation.":[92],"This":[93],"insight":[94],"enables":[95],"us":[96],"tailor":[98],"recent":[100,108],"state-of-the-art":[101,109],"implementation":[102],"TC,":[110],"avoiding":[111],"explicit":[112],"transpositions":[113],"(permutations)":[114],"extra":[116],"workspace,":[117],"reducing":[119],"overhead":[121],"memory":[123,148],"movement":[124],"that":[125],"incurred.":[127],"Performance":[128],"benefits":[129],"are":[130],"demonstrated":[131],"performance":[134],"model":[135],"on":[141],"modern":[142],"single":[143],"core,":[144],"multicore,":[145],"distributed":[147],"parallel":[149],"architectures,":[150],"achieving":[151],"$1.3":[154],"\\times$":[155],"speedup.":[156,171],"The":[157],"resulting":[158],"implementations":[159],"serve":[161],"drop-in":[164],"replacement":[165],"various":[167],"applications":[168],"significant":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}