{"id":"https://openalex.org/W4386542982","doi":"https://doi.org/10.1007/s11227-023-05587-4","title":"Distributed out-of-memory NMF on CPU/GPU architectures","display_name":"Distributed out-of-memory NMF on CPU/GPU architectures","publication_year":2023,"publication_date":"2023-09-08","ids":{"openalex":"https://openalex.org/W4386542982","doi":"https://doi.org/10.1007/s11227-023-05587-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-023-05587-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-023-05587-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05587-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05587-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057287658","display_name":"Ismael Boureima","orcid":"https://orcid.org/0000-0002-6450-4107"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ismael Boureima","raw_affiliation_strings":["Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA"],"affiliations":[{"raw_affiliation_string":"Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012614331","display_name":"Manish Bhattarai","orcid":"https://orcid.org/0000-0002-1421-3643"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manish Bhattarai","raw_affiliation_strings":["Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA"],"affiliations":[{"raw_affiliation_string":"Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066261993","display_name":"Maksim E. Eren","orcid":"https://orcid.org/0000-0002-4362-0256"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maksim Eren","raw_affiliation_strings":["Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA"],"affiliations":[{"raw_affiliation_string":"Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038345001","display_name":"Erik Skau","orcid":"https://orcid.org/0000-0002-7707-0838"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik Skau","raw_affiliation_strings":["Computer, Computational, and Statistical Science Division, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA"],"affiliations":[{"raw_affiliation_string":"Computer, Computational, and Statistical Science Division, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031290916","display_name":"Philip A. Romero","orcid":"https://orcid.org/0000-0002-2586-7263"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Romero","raw_affiliation_strings":["HPC Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA"],"affiliations":[{"raw_affiliation_string":"HPC Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073911119","display_name":"Stephan Eidenbenz","orcid":"https://orcid.org/0000-0002-2628-1854"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephan Eidenbenz","raw_affiliation_strings":["Computer, Computational, and Statistical Science Division, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA"],"affiliations":[{"raw_affiliation_string":"Computer, Computational, and Statistical Science Division, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079029372","display_name":"Boian S. Alexandrov","orcid":"https://orcid.org/0000-0001-8636-4603"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boian Alexandrov","raw_affiliation_strings":["Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA"],"affiliations":[{"raw_affiliation_string":"Theoritical Divison, Los Alamos National Laboratory, Los Alamos, 87545, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5057287658"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.1906,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80244173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"80","issue":"3","first_page":"3970","last_page":"3999"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9879000186920166,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9879000186920166,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9879000186920166,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9853000044822693,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.896039605140686},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7041317224502563},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5922516584396362},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5901097059249878},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5077827572822571},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5026218891143799},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.49870872497558594},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4573056995868683},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4512828290462494},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4452105760574341},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.43679213523864746},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4189453125},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3980494737625122},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3339177966117859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.896039605140686},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7041317224502563},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5922516584396362},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5901097059249878},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5077827572822571},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5026218891143799},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.49870872497558594},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4573056995868683},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4512828290462494},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4452105760574341},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.43679213523864746},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4189453125},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3980494737625122},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3339177966117859},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11227-023-05587-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-023-05587-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05587-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:2246858","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2246858","pdf_url":"https://www.osti.gov/servlets/purl/2246858","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}],"best_oa_location":{"id":"doi:10.1007/s11227-023-05587-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-023-05587-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-023-05587-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1127810244","display_name":null,"funder_award_id":"89233218CNA0000","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1406813184","display_name":null,"funder_award_id":"89233218CNA000","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G1426318481","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G1489425746","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1527848044","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1872210597","display_name":null,"funder_award_id":"DE-AC52-06NA2539","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2031045238","display_name":null,"funder_award_id":"DE-AC52-06NA253","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G216489703","display_name":null,"funder_award_id":"89233218CNA00000","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G2296932962","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2356915424","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320337547","funder_display_name":"Laboratory Directed Research and Development"},{"id":"https://openalex.org/G2613504715","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G2980544840","display_name":null,"funder_award_id":"Contract No. DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G3083956167","display_name":null,"funder_award_id":"20190020DR","funder_id":"https://openalex.org/F4320337547","funder_display_name":"Laboratory Directed Research and Development"},{"id":"https://openalex.org/G3178611384","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G3299391273","display_name":null,"funder_award_id":"E-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3359278407","display_name":null,"funder_award_id":"9233218CNA000001","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3495016435","display_name":null,"funder_award_id":"20190020DR","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G359075050","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3700687868","display_name":null,"funder_award_id":"AC52-06NA25396","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G3793674015","display_name":null,"funder_award_id":"9233218CNA000001","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G4169061630","display_name":null,"funder_award_id":"Contract No. DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4327825534","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G4694431782","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4844714250","display_name":null,"funder_award_id":"No. DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G4950733632","display_name":null,"funder_award_id":"000001","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5657628048","display_name":null,"funder_award_id":"AC52-06NA25396","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G574648691","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320337547","funder_display_name":"Laboratory Directed Research and Development"},{"id":"https://openalex.org/G5840121450","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G6083127429","display_name":null,"funder_award_id":"00001","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6387710405","display_name":null,"funder_award_id":"9233218CNA00000","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G6488227018","display_name":null,"funder_award_id":"DE-AC05-00OR227","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6563880843","display_name":null,"funder_award_id":"No.  89233218CNA000001","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G691578896","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6932788750","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320337547","funder_display_name":"Laboratory Directed Research and Development"},{"id":"https://openalex.org/G69704028","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6995210142","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G7038891139","display_name":null,"funder_award_id":"89233218","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G7083220807","display_name":null,"funder_award_id":"00000","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G7114708214","display_name":null,"funder_award_id":"DE-AC05-00OR2272","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7381447481","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7500863821","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G75892134","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G7851296133","display_name":null,"funder_award_id":"9233218CNA000001","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8269158468","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8527529014","display_name":null,"funder_award_id":"DE-AC52-06NA2539","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G8659807574","display_name":null,"funder_award_id":"89233218CNA000001","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8799952057","display_name":null,"funder_award_id":"DE-AC05-00OR22","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8803809456","display_name":null,"funder_award_id":"89233218CNA00000","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G996238640","display_name":null,"funder_award_id":"89233218CNA00000","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320337547","display_name":"Laboratory Directed Research and Development","ror":"https://ror.org/01e41cf67"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386542982.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W888179491","https://openalex.org/W1561391377","https://openalex.org/W1606870026","https://openalex.org/W1902027874","https://openalex.org/W2004143838","https://openalex.org/W2008255210","https://openalex.org/W2055783427","https://openalex.org/W2072191009","https://openalex.org/W2119477002","https://openalex.org/W2119644916","https://openalex.org/W2124680066","https://openalex.org/W2144351558","https://openalex.org/W2152061559","https://openalex.org/W2404400936","https://openalex.org/W2535374105","https://openalex.org/W2563832136","https://openalex.org/W2744546448","https://openalex.org/W2759315951","https://openalex.org/W2893530532","https://openalex.org/W2916485956","https://openalex.org/W2922446902","https://openalex.org/W2951338975","https://openalex.org/W3003257820","https://openalex.org/W3004480399","https://openalex.org/W3004896252","https://openalex.org/W3035965352","https://openalex.org/W3081111652","https://openalex.org/W3099276598","https://openalex.org/W3099878876","https://openalex.org/W3099947442","https://openalex.org/W3117843218","https://openalex.org/W3120226788","https://openalex.org/W3130402426","https://openalex.org/W3164436820","https://openalex.org/W3173185726","https://openalex.org/W3193658714","https://openalex.org/W3200202160","https://openalex.org/W4200302909","https://openalex.org/W4223476925","https://openalex.org/W4225743392","https://openalex.org/W4226405319","https://openalex.org/W4308090781","https://openalex.org/W4312802177","https://openalex.org/W6827284736","https://openalex.org/W6894045420","https://openalex.org/W6950071284"],"related_works":["https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W2293771254","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W2914631005","https://openalex.org/W2032786851","https://openalex.org/W2039875226","https://openalex.org/W2952630098","https://openalex.org/W4386764095"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"propose":[2],"an":[3,197],"efficient":[4],"distributed":[5],"out-of-memory":[6,68],"implementation":[7,21,166],"of":[8,202],"the":[9,71,82,164,170],"non-negative":[10],"matrix":[11,56,78,97,195,201],"factorization":[12],"(NMF)":[13],"algorithm":[14,64],"for":[15,52,67],"heterogeneous":[16],"high-performance-computing":[17],"systems.":[18,61],"The":[19,62],"proposed":[20],"is":[22,65,79,88,120,142],"based":[23,151],"on":[24,27,58,178],"prior":[25],"work":[26],"NMFk,":[28],"which":[29],"can":[30],"perform":[31],"automatic":[32],"model":[33],"selection":[34],"and":[35,39,54,93,95,118,129,132,140,196],"extract":[36],"latent":[37],"variables":[38],"patterns":[40],"from":[41,158],"data.":[42],"In":[43],"this":[44],"work,":[45],"we":[46],"extend":[47],"NMFk":[48],"by":[49,90],"adding":[50],"support":[51],"dense":[53,96,192],"sparse":[55,94,200],"operation":[57],"multi-node,":[59],"multi-GPU":[60,182],"resulting":[63],"optimized":[66,145],"problems":[69],"where":[70],"memory":[72],"required":[73],"to":[74,125,160,180],"factorize":[75],"a":[76,191],"given":[77],"greater":[80],"than":[81],"available":[83],"GPU":[84,103],"memory.":[85],"Memory":[86],"complexity":[87],"reduced":[89,143],"batching/tiling":[91],"strategies,":[92],"operations":[98],"are":[99],"significantly":[100],"accelerated":[101],"with":[102,113,135,163,185],"cores":[104,107],"(or":[105],"tensor":[106],"when":[108,189],"available).":[109],"Input/output":[110],"latency":[111,133],"associated":[112,134],"batch":[114],"copies":[115],"between":[116],"host":[117],"device":[119],"hidden":[121],"using":[122,144,167],"CUDA":[123],"streams":[124],"overlap":[126],"data":[127],"transfers":[128],"compute":[130],"asynchronously,":[131],"collective":[136],"communications":[137],"(both":[138],"intra-node":[139],"inter-node)":[141],"NVIDIA":[146],"Collective":[147],"Communication":[148],"Library":[149],"(NCCL)":[150],"communicators.":[152],"Benchmark":[153],"results":[154],"show":[155],"significant":[156],"improvement,":[157],"32X":[159],"76x":[161],"speedup,":[162],"new":[165],"GPUs":[168,188],"over":[169],"CPU-based":[171],"NMFk.":[172],"Good":[173],"weak":[174],"scaling":[175],"was":[176],"demonstrated":[177],"up":[179],"4096":[181],"cluster":[183],"nodes":[184],"approximately":[186],"25,000":[187],"decomposing":[190],"340":[193],"Terabyte-size":[194],"11":[198],"Exabyte-size":[199],"density":[203],"$$10^{-6}$$":[204],"<mml:math":[205],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[206],"<mml:msup>":[207],"<mml:mn>10</mml:mn>":[208],"<mml:mrow>":[209],"<mml:mo>-</mml:mo>":[210],"<mml:mn>6</mml:mn>":[211],"</mml:mrow>":[212],"</mml:msup>":[213],"</mml:math>":[214],".":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
