{"id":"https://openalex.org/W3154152825","doi":"https://doi.org/10.1177/1094342013502097","title":"A novel hybrid CPU\u2013GPU generalized eigensolver for electronic structure calculations based on fine-grained memory aware tasks","display_name":"A novel hybrid CPU\u2013GPU generalized eigensolver for electronic structure calculations based on fine-grained memory aware tasks","publication_year":2013,"publication_date":"2013-08-30","ids":{"openalex":"https://openalex.org/W3154152825","doi":"https://doi.org/10.1177/1094342013502097","mag":"3154152825"},"language":"en","primary_location":{"id":"doi:10.1177/1094342013502097","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013502097","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","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/A5101964224","display_name":"Azzam Haidar","orcid":"https://orcid.org/0000-0002-3177-2084"},"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":"Azzam Haidar","raw_affiliation_strings":["Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","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":true,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","School of Mathematics and School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Electrical Engineering and Computer Science, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"School of Mathematics and School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083650104","display_name":"Raffaele Solc\u00e0","orcid":"https://orcid.org/0009-0009-9346-4376"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Raffaele Solc\u00e0","raw_affiliation_strings":["Institut for Theoretical Physics, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Institut for Theoretical Physics, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061452348","display_name":"T. C. Schulthess","orcid":"https://orcid.org/0000-0002-1086-5812"},"institutions":[{"id":"https://openalex.org/I59105498","display_name":"Swisscom (Switzerland)","ror":"https://ror.org/04t1f4f50","country_code":"CH","type":"company","lineage":["https://openalex.org/I59105498"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas Schulthess","raw_affiliation_strings":["Swiss National Supercomputer Center, Lugano, Switzerland"],"affiliations":[{"raw_affiliation_string":"Swiss National Supercomputer Center, Lugano, Switzerland","institution_ids":["https://openalex.org/I59105498"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083604741"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":5.3915,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.95806063,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":"2","first_page":"196","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8559308052062988},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6718371510505676},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6487908363342285},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5292966365814209},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5045062303543091},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46308451890945435},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.41052526235580444},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1973169445991516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559308052062988},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6718371510505676},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6487908363342285},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5292966365814209},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5045062303543091},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46308451890945435},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.41052526235580444},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1973169445991516}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1094342013502097","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342013502097","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/6de4f985-c0b8-45c8-a47c-50c3b79da3c9","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/6de4f985-c0b8-45c8-a47c-50c3b79da3c9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Haidar, A, Tomov, S, Dongarra, J, Solc\u00e0, R & Schulthess, T 2014, 'A Novel Hybrid CPU-GPU Generalized Eigensolver for Electronic Structure Calculations Based on Fine Grained Memory Aware Tasks', International Journal of High Performance Computing Applications, vol. 28, no. 2, pp. 196-209. https://doi.org/10.1177/1094342013502097","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/6de4f985-c0b8-45c8-a47c-50c3b79da3c9","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/a-novel-hybrid-cpugpu-generalized-eigensolver-for-electronic-structure-calculations-based-on-fine-grained-memory-aware-tasks(6de4f985-c0b8-45c8-a47c-50c3b79da3c9).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Haidar, A, Tomov, S, Dongarra, J, Solc\u00e0, R & Schulthess, T 2014, 'A Novel Hybrid CPU-GPU Generalized Eigensolver for Electronic Structure Calculations Based on Fine Grained Memory Aware Tasks', International Journal of High Performance Computing Applications, vol. 28, no. 2, pp. 196-209. https://doi.org/10.1177/1094342013502097","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1481082265","https://openalex.org/W1522512418","https://openalex.org/W1802445103","https://openalex.org/W1991973947","https://openalex.org/W2014515149","https://openalex.org/W2025400771","https://openalex.org/W2045271686","https://openalex.org/W2048968534","https://openalex.org/W2065402594","https://openalex.org/W2073260424","https://openalex.org/W2079120751","https://openalex.org/W2102181290","https://openalex.org/W2104110430","https://openalex.org/W2107410315","https://openalex.org/W2107864772","https://openalex.org/W2111533539","https://openalex.org/W2119522963","https://openalex.org/W2125960020","https://openalex.org/W2164895445","https://openalex.org/W2568342123","https://openalex.org/W4229666556","https://openalex.org/W4229724516","https://openalex.org/W4231150350","https://openalex.org/W4301491118"],"related_works":["https://openalex.org/W2011840458","https://openalex.org/W3213381848","https://openalex.org/W1588481459","https://openalex.org/W2017587301","https://openalex.org/W2005148983","https://openalex.org/W2030707850","https://openalex.org/W3038415719","https://openalex.org/W2244094767","https://openalex.org/W4386975487","https://openalex.org/W2096672917"],"abstract_inverted_index":{"The":[0,124],"adoption":[1],"of":[2,71,81,86,102,112,147,152],"hybrid":[3,61,65,122],"CPU\u2013GPU":[4,62],"nodes":[5],"in":[6,21,129],"traditional":[7],"supercomputing":[8],"platforms":[9],"such":[10],"as":[11,89],"the":[12,53,69,108,113,138,157],"Cray-XK6":[13],"opens":[14],"acceleration":[15],"opportunities":[16],"for":[17,68],"electronic":[18,159],"structure":[19,160],"calculations":[20],"materials":[22],"science":[23],"and":[24,78,120,140],"chemistry":[25],"applications,":[26],"where":[27],"medium-sized":[28],"generalized":[29,97],"eigenvalue":[30,38],"problems":[31,39],"must":[32],"be":[33],"solved":[34],"many":[35],"times.":[36],"These":[37],"are":[40,127,154],"too":[41],"small":[42],"to":[43],"effectively":[44],"solve":[45],"on":[46,58,145],"distributed":[47],"systems,":[48],"but":[49,85],"can":[50],"benefit":[51],"from":[52],"massive":[54,79],"computing":[55],"power":[56],"concentrated":[57],"a":[59,96],"single-node,":[60],"system.":[63],"However,":[64],"systems":[66],"call":[67],"development":[70],"new":[72],"algorithms":[73,101],"that":[74],"efficiently":[75],"exploit":[76],"heterogeneity":[77],"parallelism":[80],"not":[82],"just":[83],"GPUs,":[84],"multicore/manycore":[87],"CPUs":[88],"well.":[90],"Addressing":[91],"these":[92],"demands,":[93],"we":[94],"developed":[95],"eigensolver":[98],"featuring":[99],"novel":[100],"increased":[103],"computational":[104],"intensity":[105],"(compared":[106],"with":[107],"standard":[109],"algorithms),":[110],"decomposition":[111],"computation":[114],"into":[115],"fine-grained":[116],"memory":[117],"aware":[118],"tasks,":[119],"their":[121],"execution.":[123],"resulting":[125],"eigensolvers":[126],"state-of-the-art":[128],"high-performance":[130],"computing,":[131],"significantly":[132],"outperforming":[133],"existing":[134],"libraries.":[135],"We":[136],"describe":[137],"algorithm":[139],"analyze":[141],"its":[142],"performance":[143],"impact":[144],"applications":[146],"interest":[148],"when":[149],"different":[150],"fractions":[151],"eigenvectors":[153],"needed":[155],"by":[156],"host":[158],"code.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2025-10-10T00:00:00"}