{"id":"https://openalex.org/W2021450636","doi":"https://doi.org/10.1145/2807591.2807613","title":"Performance of random sampling for computing low-rank approximations of a dense matrix on GPUs","display_name":"Performance of random sampling for computing low-rank approximations of a dense matrix on GPUs","publication_year":2015,"publication_date":"2015-10-27","ids":{"openalex":"https://openalex.org/W2021450636","doi":"https://doi.org/10.1145/2807591.2807613","mag":"2021450636"},"language":"en","primary_location":{"id":"doi:10.1145/2807591.2807613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2807591.2807613","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2807613&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2807613&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065253192","display_name":"Th\u00e9o Mary","orcid":"https://orcid.org/0000-0001-9949-4634"},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I17866349","display_name":"Universit\u00e9 F\u00e9d\u00e9rale de Toulouse Midi-Pyr\u00e9n\u00e9es","ror":"https://ror.org/004raaa70","country_code":"FR","type":"education","lineage":["https://openalex.org/I17866349"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Th\u00e9o Mary","raw_affiliation_strings":["Universit\u00e9 de Toulouse, UPS-IRIT, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Toulouse, UPS-IRIT, France","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I17866349","https://openalex.org/I4210119061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052397462","display_name":"Ichitaro Yamazaki","orcid":"https://orcid.org/0000-0002-6196-2508"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ichitaro Yamazaki","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee","UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakub Kurzak","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee","UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee","UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee","UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, Knoxville, Tennessee","UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tennessee, Knoxville, Tennessee","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"UNIVERSITY OF TENNESSEE, KNOXVILLE, TENNESSEE","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7842379212379456},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6671419143676758},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6341254711151123},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5688265562057495},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5309241414070129},{"id":"https://openalex.org/keywords/kepler","display_name":"Kepler","score":0.5120206475257874},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4396291673183441},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.42568475008010864},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41803762316703796},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4125562906265259},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3970300853252411},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15404200553894043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842379212379456},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6671419143676758},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6341254711151123},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5688265562057495},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5309241414070129},{"id":"https://openalex.org/C207963374","wikidata":"https://www.wikidata.org/wiki/Q47592","display_name":"Kepler","level":3,"score":0.5120206475257874},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4396291673183441},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.42568475008010864},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41803762316703796},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4125562906265259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3970300853252411},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15404200553894043},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","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},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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:10.1145/2807591.2807613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2807591.2807613","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2807613&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02311280v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02311280","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sc15.supercomputing.org/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/2807591.2807613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2807591.2807613","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2807613&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1351316705","display_name":null,"funder_award_id":"DE-SC0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1687433189","display_name":"SI2-SSI: Collaborative Research: Sustained Innovation for Linear Algebra Software (SILAS)","funder_award_id":"1339822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3653277020","display_name":null,"funder_award_id":"DE-FG02-13ER26137,DE-SC0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7186324567","display_name":null,"funder_award_id":"DE-FG02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8684078510","display_name":null,"funder_award_id":"DE-FG02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8753669605","display_name":null,"funder_award_id":"N14-11-00190","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/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2021450636.pdf","grobid_xml":"https://content.openalex.org/works/W2021450636.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1558296484","https://openalex.org/W1559275088","https://openalex.org/W1964681401","https://openalex.org/W1967501281","https://openalex.org/W1968691112","https://openalex.org/W1972501001","https://openalex.org/W1982811641","https://openalex.org/W1998269045","https://openalex.org/W1999352252","https://openalex.org/W2001135345","https://openalex.org/W2010747199","https://openalex.org/W2032487920","https://openalex.org/W2057261601","https://openalex.org/W2058401000","https://openalex.org/W2111221242","https://openalex.org/W2117756735","https://openalex.org/W2141696759","https://openalex.org/W2152356156","https://openalex.org/W2156722294","https://openalex.org/W2157237396","https://openalex.org/W2618281564","https://openalex.org/W2798909945","https://openalex.org/W2951184550","https://openalex.org/W4213311204","https://openalex.org/W4231477146","https://openalex.org/W4244670803","https://openalex.org/W6750968397"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W1973739845","https://openalex.org/W119752240","https://openalex.org/W4391266752","https://openalex.org/W2898722594","https://openalex.org/W2125326641"],"abstract_inverted_index":{"A":[0],"low-rank":[1],"approximation":[2,122],"of":[3,35,49,90,95,123,133,148,159],"a":[4,19,141,146],"dense":[5],"matrix":[6],"plays":[7],"an":[8,17,62,98,164],"important":[9],"role":[10],"in":[11,83],"many":[12,169],"applications.":[13],"To":[14,79],"compute":[15,143],"such":[16,53],"approximation,":[18],"common":[20],"approach":[21,42,64,118],"uses":[22],"the":[23,31,50,88,116,121,124,130,134,157,160,179,183],"QR":[24],"factorization":[25],"with":[26,93,182],"column":[27],"pivoting":[28],"(QRCP).":[29],"Though":[30],"reliability":[32],"and":[33,171],"efficiency":[34],"QRCP":[36,96],"have":[37],"been":[38],"demonstrated,":[39],"this":[40,84],"deterministic":[41,117],"requires":[43],"costly":[44],"communication":[45,54,185],"at":[46],"each":[47],"step":[48],"factorization.":[51],"Since":[52],"is":[55,76,174],"becoming":[56,77],"increasingly":[57],"expensive":[58],"on":[59,66,97,140,178],"modern":[60],"computers,":[61],"alternative":[63],"based":[65],"random":[67,91,107,135,161],"sampling,":[68],"which":[69],"can":[70,109],"be":[71,110],"implemented":[72],"using":[73],"communication-optimal":[74],"kernels,":[75],"attractive.":[78],"study":[80],"its":[81,172],"potential,":[82],"paper,":[85],"we":[86],"compare":[87],"performance":[89,103],"sampling":[92,108,136,162],"that":[94,106],"NVIDIA":[99],"Kepler":[100,152],"GPU.":[101],"Our":[102],"results":[104,155],"demonstrate":[105,156],"up":[111],"to":[112,176],"12.8x":[113],"faster":[114],"than":[115],"for":[119,168],"computing":[120],"same":[125],"accuracy.":[126],"We":[127],"also":[128],"present":[129],"parallel":[131],"scaling":[132],"over":[137,150],"multiple":[138],"GPUs":[139],"single":[142],"node,":[144],"showing":[145],"speedup":[147],"3.8x":[149],"three":[151],"GPUs.":[153],"These":[154],"potential":[158,173],"as":[163],"excellent":[165],"computational":[166],"tool":[167],"applications,":[170],"likely":[175],"grow":[177],"emerging":[180],"computers":[181],"increasing":[184],"costs.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}