{"id":"https://openalex.org/W2962779982","doi":"https://doi.org/10.1145/3178487.3178522","title":"Shared-memory parallelization of MTTKRP for dense tensors","display_name":"Shared-memory parallelization of MTTKRP for dense tensors","publication_year":2018,"publication_date":"2018-02-06","ids":{"openalex":"https://openalex.org/W2962779982","doi":"https://doi.org/10.1145/3178487.3178522","mag":"2962779982"},"language":"en","primary_location":{"id":"doi:10.1145/3178487.3178522","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178487.3178522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","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/A5015111861","display_name":"Koby Hayashi","orcid":"https://orcid.org/0000-0003-0781-0543"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koby Hayashi","raw_affiliation_strings":["Wake Forest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064243391","display_name":"Grey Ballard","orcid":"https://orcid.org/0000-0003-1557-8027"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grey Ballard","raw_affiliation_strings":["Wake Forest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101476540","display_name":"Yujie Jiang","orcid":"https://orcid.org/0000-0002-9320-2888"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujie Jiang","raw_affiliation_strings":["Wake Forest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061109417","display_name":"Michael J. Tobia","orcid":"https://orcid.org/0000-0002-5013-0597"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Tobia","raw_affiliation_strings":["Wake Forest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University","institution_ids":["https://openalex.org/I47251452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47251452"],"apc_list":null,"apc_paid":null,"fwci":1.5845,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83482143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"394"},"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":0.992900013923645,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8348716497421265},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7859987020492554},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7481520175933838},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7159192562103271},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.660580039024353},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5873415470123291},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5588979125022888},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5497546195983887},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5084099173545837},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.46491342782974243},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.45945602655410767},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.44749659299850464},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.43065914511680603},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35243508219718933},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3411898910999298},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18581455945968628},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11805981397628784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348716497421265},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7859987020492554},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7481520175933838},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7159192562103271},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.660580039024353},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5873415470123291},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5588979125022888},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5497546195983887},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5084099173545837},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.46491342782974243},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.45945602655410767},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.44749659299850464},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.43065914511680603},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35243508219718933},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3411898910999298},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18581455945968628},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11805981397628784},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178487.3178522","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178487.3178522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8352826283","display_name":null,"funder_award_id":"ACI-1642385","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1823244711","https://openalex.org/W2004642969","https://openalex.org/W2008972618","https://openalex.org/W2750586907","https://openalex.org/W2758189514"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2185094550","https://openalex.org/W2088823210","https://openalex.org/W2135766592"],"abstract_inverted_index":{"The":[0,30],"matricized-tensor":[1],"times":[2],"Khatri-Rao":[3],"product":[4],"(MTTKRP)":[5],"is":[6],"the":[7,36],"computational":[8],"bottleneck":[9],"for":[10,25],"algorithms":[11,24,31],"computing":[12],"CP":[13,64],"decompositions":[14],"of":[15,35,66,75],"tensors.":[16,29],"In":[17],"this":[18],"work,":[19],"we":[20],"develop":[21],"shared-memory":[22],"parallel":[23,59,81],"MTTKRP":[26],"involving":[27],"dense":[28],"cast":[32],"nearly":[33],"all":[34],"computation":[37],"as":[38],"matrix":[39],"operations":[40],"in":[41,54],"order":[42],"to":[43,61,77],"use":[44,57],"optimized":[45],"BLAS":[46],"subroutines,":[47],"and":[48,71],"they":[49],"avoid":[50],"reordering":[51],"tensor":[52],"entries":[53],"memory.":[55],"We":[56],"our":[58],"implementation":[60],"compute":[62],"a":[63,67,73],"decomposition":[65],"neuroimaging":[68],"data":[69],"set":[70],"achieve":[72],"speedup":[74],"up":[76],"7.4X":[78],"over":[79],"existing":[80],"software.":[82]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}