{"id":"https://openalex.org/W4366601518","doi":"https://doi.org/10.1145/3558481.3591072","title":"Parallel Memory-Independent Communication Bounds for SYRK","display_name":"Parallel Memory-Independent Communication Bounds for SYRK","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4366601518","doi":"https://doi.org/10.1145/3558481.3591072"},"language":"en","primary_location":{"id":"doi:10.1145/3558481.3591072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558481.3591072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-04076513v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028202081","display_name":"Hussam Al Daas","orcid":"https://orcid.org/0000-0001-9355-4042"},"institutions":[{"id":"https://openalex.org/I1286704778","display_name":"Rutherford Appleton Laboratory","ror":"https://ror.org/03gq8fr08","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1286704778","https://openalex.org/I162524378","https://openalex.org/I4210087105"]},{"id":"https://openalex.org/I4210092957","display_name":"Research Complex at Harwell","ror":"https://ror.org/00gqx0331","country_code":"GB","type":"facility","lineage":["https://openalex.org/I4210092957"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hussam Al Daas","raw_affiliation_strings":["Rutherford Appleton Laboratory, Didcot, United Kingdom","RAL - STFC Rutherford Appleton Laboratory (Harwell Campus, Didcot OX11 0FA - United Kingdom)"],"raw_orcid":"https://orcid.org/0000-0001-9355-4042","affiliations":[{"raw_affiliation_string":"Rutherford Appleton Laboratory, Didcot, United Kingdom","institution_ids":["https://openalex.org/I1286704778"]},{"raw_affiliation_string":"RAL - STFC Rutherford Appleton Laboratory (Harwell Campus, Didcot OX11 0FA - United Kingdom)","institution_ids":["https://openalex.org/I4210092957","https://openalex.org/I1286704778"]}]},{"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, Winston-Salem, NC, USA"],"raw_orcid":"https://orcid.org/0000-0003-1557-8027","affiliations":[{"raw_affiliation_string":"Wake Forest University, Winston-Salem, NC, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040521001","display_name":"Laura Grigori","orcid":"https://orcid.org/0000-0002-5880-1076"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laura Grigori","raw_affiliation_strings":["Inria Paris, Paris, France","ALPINES - Algorithms and parallel tools for integrated numerical simulations (France)"],"raw_orcid":"https://orcid.org/0000-0002-5880-1076","affiliations":[{"raw_affiliation_string":"Inria Paris, Paris, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"ALPINES - Algorithms and parallel tools for integrated numerical simulations (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669083","display_name":"Suraj Kumar","orcid":"https://orcid.org/0009-0001-1449-0165"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suraj Kumar","raw_affiliation_strings":["Inria Lyon, Lyon, France"],"raw_orcid":"https://orcid.org/0009-0001-1449-0165","affiliations":[{"raw_affiliation_string":"Inria Lyon, Lyon, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102860683","display_name":"Kathryn Rouse","orcid":"https://orcid.org/0009-0001-4045-0423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kathryn Rouse","raw_affiliation_strings":["Inmar Intelligence, Winston-Salem, NC, USA"],"raw_orcid":"https://orcid.org/0009-0001-4045-0423","affiliations":[{"raw_affiliation_string":"Inmar Intelligence, Winston-Salem, NC, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3767,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58531568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6632304787635803},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.603820264339447},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5925920009613037},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.5836414098739624},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5549775958061218},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4806289076805115},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4801746904850006},{"id":"https://openalex.org/keywords/symmetric-matrix","display_name":"Symmetric matrix","score":0.4761069715023041},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.47191479802131653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39258652925491333},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3882145881652832},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.3761087656021118},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3150167465209961},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31133317947387695},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.29811811447143555}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6632304787635803},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.603820264339447},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5925920009613037},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.5836414098739624},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5549775958061218},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4806289076805115},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4801746904850006},{"id":"https://openalex.org/C54848796","wikidata":"https://www.wikidata.org/wiki/Q339011","display_name":"Symmetric matrix","level":3,"score":0.4761069715023041},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47191479802131653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39258652925491333},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3882145881652832},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3761087656021118},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3150167465209961},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31133317947387695},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29811811447143555},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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/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":4,"locations":[{"id":"doi:10.1145/3558481.3591072","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558481.3591072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04076513v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04076513","pdf_url":"https://inria.hal.science/hal-04076513v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SPAA '23 - ACM Symposium on Parallelism in Algorithms and Architectures, Jun 2023, Orlando, United States. &#x27E8;10.1145/3558481.3591072&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:osti.gov:1987853","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1987853","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:purl.org/net/epubs:work/56530728","is_oa":false,"landing_page_url":"https://epubs.stfc.ac.uk/work/56530728","pdf_url":null,"source":{"id":"https://openalex.org/S4306400600","display_name":"ePubs (Science and Technology Facilities Council, Research Councils UK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162524378","host_organization_name":"Science and Technology Facilities Council","host_organization_lineage":["https://openalex.org/I162524378"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04076513v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04076513","pdf_url":"https://inria.hal.science/hal-04076513v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SPAA '23 - ACM Symposium on Parallelism in Algorithms and Architectures, Jun 2023, Orlando, United States. &#x27E8;10.1145/3558481.3591072&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G155429490","display_name":null,"funder_award_id":"CCF-1942892, OAC-2106920","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1620472780","display_name":null,"funder_award_id":"810367","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"},{"id":"https://openalex.org/G3903888952","display_name":null,"funder_award_id":"2106920","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G422536779","display_name":null,"funder_award_id":"CCF-1942892","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4332098366","display_name":null,"funder_award_id":"1942892","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7683707404","display_name":null,"funder_award_id":"810367","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8928785057","display_name":null,"funder_award_id":"DE-SC-0023296","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366601518.pdf","grobid_xml":"https://content.openalex.org/works/W4366601518.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1972501001","https://openalex.org/W2010747199","https://openalex.org/W2023122441","https://openalex.org/W2065231486","https://openalex.org/W2090322880","https://openalex.org/W2093529653","https://openalex.org/W2099611016","https://openalex.org/W2104373803","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2168748809","https://openalex.org/W2170796499","https://openalex.org/W2623569379","https://openalex.org/W3033869768","https://openalex.org/W3100417409","https://openalex.org/W4231150350","https://openalex.org/W4238637948","https://openalex.org/W4250589301","https://openalex.org/W4280640669","https://openalex.org/W4285006655","https://openalex.org/W4288072583","https://openalex.org/W4302336677","https://openalex.org/W6606093611"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W1749782192","https://openalex.org/W4232554674","https://openalex.org/W2353146130","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W2094139070","https://openalex.org/W1933089384"],"abstract_inverted_index":{"In":[0],"this":[1,71],"paper,":[2],"we":[3,73,90],"focus":[4],"on":[5,109],"the":[6,27,35,38,51,104,138],"parallel":[7,76,135],"communication":[8,77],"cost":[9],"of":[10,29,34,37,55,65,103,137],"multiplying":[11],"a":[12,19,59,111,121,130],"matrix":[13,31,67,87,141],"with":[14,82],"its":[15],"transpose,":[16],"known":[17],"as":[18],"symmetric":[20,116,139],"rank-k":[21],"update":[22],"(SYRK).":[23],"SYRK":[24,56,81],"requires":[25],"half":[26],"computation":[28],"general":[30,66,86],"multiplication":[32],"because":[33],"symmetry":[36],"output":[39,140],"matrix.":[40],"Recent":[41],"work":[42],"(Beaumont":[43],"et":[44],"al.,":[45],"SPAA":[46],"'22)":[47],"has":[48],"demonstrated":[49],"that":[50,64,92],"sequential":[52],"I/O":[53],"complexity":[54],"is":[57],"also":[58],"constant":[60],"factor":[61],"smaller":[62,83],"than":[63,85],"multiplication.":[68],"Inspired":[69],"by":[70,97],"progress,":[72],"establish":[74],"memory-independent":[75],"lower":[78,105],"bounds":[79],"for":[80,134],"constants":[84,94],"multiplication,":[88],"and":[89,118,142],"show":[91],"these":[93],"are":[95],"tight":[96],"presenting":[98],"communication-optimal":[99],"algorithms.":[100],"The":[101,126],"crux":[102],"bound":[106],"proof":[107],"relies":[108],"extending":[110],"key":[112],"geometric":[113],"inequality":[114],"to":[115],"computations":[117],"analytically":[119],"solving":[120],"constrained":[122],"nonlinear":[123],"optimization":[124],"problem.":[125],"optimal":[127],"algorithms":[128],"use":[129],"triangular":[131],"blocking":[132],"scheme":[133],"distribution":[136],"corresponding":[143],"computation.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}
