{"id":"https://openalex.org/W3006501671","doi":"https://doi.org/10.1177/1094342020905637","title":"Hybrid multi-projection method using sparse approximate inverses on GPU clusters","display_name":"Hybrid multi-projection method using sparse approximate inverses on GPU clusters","publication_year":2020,"publication_date":"2020-02-13","ids":{"openalex":"https://openalex.org/W3006501671","doi":"https://doi.org/10.1177/1094342020905637","mag":"3006501671"},"language":"en","primary_location":{"id":"doi:10.1177/1094342020905637","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020905637","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/A5073884496","display_name":"Byron E. Moutafis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byron E Moutafis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004595458","display_name":"George A. Gravvanis","orcid":"https://orcid.org/0000-0003-1562-3633"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"George A Gravvanis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077744079","display_name":"Christos K. Filelis\u2010Papadopoulos","orcid":"https://orcid.org/0000-0002-6591-970X"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Christos K Filelis-Papadopoulos","raw_affiliation_strings":["Department of Electrical and Computer Engineering, School of Engineering University Campus, Democritus University of Thrace, Kimmeria, Xanthi, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, School of Engineering University Campus, Democritus University of Thrace, Kimmeria, Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004595458"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4222,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66298779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"34","issue":"3","first_page":"282","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":1.0,"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"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/preconditioner","display_name":"Preconditioner","score":0.8584770560264587},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.8222016096115112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300290465354919},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6620863080024719},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.6084288954734802},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.48037466406822205},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.476445734500885},{"id":"https://openalex.org/keywords/biconjugate-gradient-method","display_name":"Biconjugate gradient method","score":0.47136440873146057},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.43589097261428833},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.431194931268692},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4281705915927887},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4225074350833893},{"id":"https://openalex.org/keywords/conjugate-residual-method","display_name":"Conjugate residual method","score":0.4199311137199402},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.356466144323349},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.2953430414199829},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19245144724845886},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.10879239439964294}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.8584770560264587},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.8222016096115112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300290465354919},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6620863080024719},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.6084288954734802},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.48037466406822205},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.476445734500885},{"id":"https://openalex.org/C89408827","wikidata":"https://www.wikidata.org/wiki/Q855169","display_name":"Biconjugate gradient method","level":5,"score":0.47136440873146057},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.43589097261428833},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.431194931268692},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4281705915927887},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4225074350833893},{"id":"https://openalex.org/C91394653","wikidata":"https://www.wikidata.org/wiki/Q5161159","display_name":"Conjugate residual method","level":4,"score":0.4199311137199402},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.356466144323349},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2953430414199829},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19245144724845886},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.10879239439964294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342020905637","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020905637","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W948471287","https://openalex.org/W1506342804","https://openalex.org/W1542243431","https://openalex.org/W1548589512","https://openalex.org/W1907157228","https://openalex.org/W1964184638","https://openalex.org/W1967501281","https://openalex.org/W1994805693","https://openalex.org/W2003105834","https://openalex.org/W2021157069","https://openalex.org/W2024179839","https://openalex.org/W2026502086","https://openalex.org/W2031441286","https://openalex.org/W2032576830","https://openalex.org/W2035080386","https://openalex.org/W2041876368","https://openalex.org/W2044724368","https://openalex.org/W2057980100","https://openalex.org/W2070232376","https://openalex.org/W2078675418","https://openalex.org/W2081861751","https://openalex.org/W2083640533","https://openalex.org/W2084073638","https://openalex.org/W2104126767","https://openalex.org/W2126271681","https://openalex.org/W2155216327","https://openalex.org/W2162525251","https://openalex.org/W2167512083","https://openalex.org/W2207850197","https://openalex.org/W2282293358","https://openalex.org/W2316564661","https://openalex.org/W2406344247","https://openalex.org/W2516625134","https://openalex.org/W2617808919","https://openalex.org/W2740353165","https://openalex.org/W2752482825","https://openalex.org/W2769328682","https://openalex.org/W2912232378","https://openalex.org/W3125163728"],"related_works":["https://openalex.org/W1848849174","https://openalex.org/W2129625121","https://openalex.org/W4205386174","https://openalex.org/W2047317216","https://openalex.org/W2953323282","https://openalex.org/W4288596192","https://openalex.org/W2920482256","https://openalex.org/W2896548519","https://openalex.org/W2092712974","https://openalex.org/W2159515580"],"abstract_inverted_index":{"The":[0,26,42,93,173],"state-of-the-art":[1],"supercomputing":[2],"infrastructures":[3],"are":[4,30,178,242],"equipped":[5],"with":[6,67,108,140,189,206],"accelerators,":[7],"such":[8],"as":[9,16,50],"graphics":[10],"processing":[11],"units":[12],"(GPUs),":[13],"that":[14,118],"operate":[15],"coprocessors":[17],"for":[18,216,239],"each":[19],"workstation":[20],"of":[21,33,53,61,74,82,95,105,122,167,235],"the":[22,51,58,62,72,85,90,96,103,120,123,162,168,181,190,199,207,217,227,230,233,236],"distributed":[23,169],"memory":[24,170],"system.":[25],"multi-projection":[27,43,141],"type":[28,44,142],"methods":[29,37,45,138,143],"a":[31],"class":[32],"algebraic":[34],"domain":[35],"decomposition":[36],"based":[38],"on":[39,125],"semi-aggregation":[40],"techniques.":[41],"have":[46,144,151],"improved":[47,113,152],"convergence":[48,228],"behavior,":[49,229],"number":[52,73,104],"subdomains":[54,106],"increases,":[55],"due":[56],"to":[57,112,150,155],"corresponding":[59],"augmentation":[60],"semi-aggregated":[63],"local":[64,175,221],"linear":[65,176],"systems":[66,177],"more":[68],"coarse":[69],"components,":[70],"while":[71],"fine":[75],"components":[76],"is":[77,87,130,214],"reduced.":[78],"Moreover,":[79],"limited":[80],"amount":[81],"communications":[83],"among":[84],"workstations":[86],"required":[88],"by":[89,160,180],"proposed":[91,237],"method.":[92],"utilization":[94],"available":[97,163],"GPUs":[98,129,166],"allows":[99],"an":[100],"increase":[101],"in":[102,148],"along":[107,205],"finer-grained":[109],"parallelism,":[110],"leading":[111],"performance.":[114],"A":[115],"load-balancing":[116],"algorithm":[117],"ensures":[119],"concurrency":[121],"computations":[124],"multicore":[126],"processors":[127],"and":[128,165,232],"proposed.":[131],"Flexible":[132],"parallel":[133],"preconditioned":[134,182,200],"Krylov":[135],"subspace":[136],"iterative":[137],"enhanced":[139,188],"been":[145],"designed":[146],"appropriately":[147],"order":[149],"performance,":[153,231],"compared":[154],"CPU-only":[156],"or":[157],"GPU-only":[158],"executions,":[159],"exploiting":[161],"CPUs":[164],"system":[171],"concurrently.":[172],"unsymmetric":[174],"solved":[179],"Bi-Conjugate":[183],"Gradient":[184],"STABilized":[185],"(BiCGSTAB)":[186],"method":[187,204,238],"modified":[191],"generic":[192],"factored":[193,209],"approximate":[194,210],"sparse":[195,211],"inverse":[196,212],"preconditioner,":[197],"whereas":[198],"conjugate":[201],"gradient":[202],"(CG)":[203],"symmetric":[208,218],"preconditioner":[213],"used":[215],"positive":[219],"definite":[220],"coefficient":[222],"matrices.":[223],"Numerical":[224],"results":[225],"regarding":[226],"scalability":[234],"several":[240],"problems":[241],"given.":[243]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}