{"id":"https://openalex.org/W2162525251","doi":"https://doi.org/10.1177/1094342015580139","title":"Acceleration of GPU-based Krylov solvers via data transfer reduction","display_name":"Acceleration of GPU-based Krylov solvers via data transfer reduction","publication_year":2015,"publication_date":"2015-04-08","ids":{"openalex":"https://openalex.org/W2162525251","doi":"https://doi.org/10.1177/1094342015580139","mag":"2162525251"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015580139","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015580139","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":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1361293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012133869","display_name":"Hartwig Anzt","orcid":"https://orcid.org/0000-0003-2177-952X"},"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":"Hartwig Anzt","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Tennessee, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Tennessee, 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":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Tennessee, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Tennessee, USA","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":["Innovative Computing Laboratory, University of Tennessee, Tennessee, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064935880","display_name":"William Sawyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4391767926","display_name":"CSCS - Swiss National Supercomputing Centre","ror":"https://ror.org/04rzmms09","country_code":null,"type":"facility","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088","https://openalex.org/I4391767926"]},{"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":"William Sawyer","raw_affiliation_strings":["Swiss National Supercomputing Centre (CSCS), Lugano, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss National Supercomputing Centre (CSCS), Lugano, Switzerland","institution_ids":["https://openalex.org/I4391767926","https://openalex.org/I59105498"]}]},{"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/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"]},{"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/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Tennessee, USA","Oak Ridge National Laboratory, Tennessee, USA","University of Manchester, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Tennessee, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, Tennessee, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6802,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93524102,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"29","issue":"3","first_page":"366","last_page":"383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9761999845504761,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9707000255584717,"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/krylov-subspace","display_name":"Krylov subspace","score":0.790740430355072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868348360061646},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.7290908694267273},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6114282011985779},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5951175689697266},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5827085375785828},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5647624731063843},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5238730311393738},{"id":"https://openalex.org/keywords/biconjugate-gradient-stabilized-method","display_name":"Biconjugate gradient stabilized method","score":0.5148848295211792},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.5008730888366699},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4988827705383301},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4797476530075073},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4611530303955078},{"id":"https://openalex.org/keywords/biconjugate-gradient-method","display_name":"Biconjugate gradient method","score":0.4523979425430298},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4390038549900055},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.43112078309059143},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.41241899132728577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2803621292114258},{"id":"https://openalex.org/keywords/conjugate-residual-method","display_name":"Conjugate residual method","score":0.19000571966171265},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.13666990399360657},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.11990952491760254},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.0964709222316742},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09206458926200867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07956007122993469}],"concepts":[{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.790740430355072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868348360061646},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.7290908694267273},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6114282011985779},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5951175689697266},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5827085375785828},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5647624731063843},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5238730311393738},{"id":"https://openalex.org/C120553275","wikidata":"https://www.wikidata.org/wiki/Q4903720","display_name":"Biconjugate gradient stabilized method","level":3,"score":0.5148848295211792},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.5008730888366699},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4988827705383301},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4797476530075073},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4611530303955078},{"id":"https://openalex.org/C89408827","wikidata":"https://www.wikidata.org/wiki/Q855169","display_name":"Biconjugate gradient method","level":5,"score":0.4523979425430298},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4390038549900055},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.43112078309059143},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.41241899132728577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2803621292114258},{"id":"https://openalex.org/C91394653","wikidata":"https://www.wikidata.org/wiki/Q5161159","display_name":"Conjugate residual method","level":4,"score":0.19000571966171265},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.13666990399360657},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.11990952491760254},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.0964709222316742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09206458926200867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07956007122993469},{"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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"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},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1177/1094342015580139","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015580139","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/82369bb9-0b0f-43fd-9524-0be8273176de","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/82369bb9-0b0f-43fd-9524-0be8273176de","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Anzt, H, Tomov, S, Luszczek, P, Sawyer, W & Dongarra, J 2015, 'Acceleration of GPU-based Krylov solvers via data transfer reduction', International Journal of High Performance Computing Applications, vol. 29, no. 3, pp. 366-383. https://doi.org/10.1177/1094342015580139","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:osti.gov:1361293","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1361293","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:pure.atira.dk:publications/82369bb9-0b0f-43fd-9524-0be8273176de","is_oa":false,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/acceleration-of-gpubased-krylov-solvers-via-data-transfer-reduction(82369bb9-0b0f-43fd-9524-0be8273176de).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":"Anzt, H, Tomov, S, Luszczek, P, Sawyer, W & Dongarra, J 2015, 'Acceleration of GPU-based Krylov solvers via data transfer reduction', International Journal of High Performance Computing Applications, vol. 29, no. 3, pp. 366-383. https://doi.org/10.1177/1094342015580139","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:osti.gov:1361293","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1361293","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},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W592368443","https://openalex.org/W1506342804","https://openalex.org/W1512055056","https://openalex.org/W1524015806","https://openalex.org/W1544702288","https://openalex.org/W1575701986","https://openalex.org/W1588915715","https://openalex.org/W1856844978","https://openalex.org/W1907157228","https://openalex.org/W1965034778","https://openalex.org/W1967501281","https://openalex.org/W1975818677","https://openalex.org/W1977146902","https://openalex.org/W2045920776","https://openalex.org/W2065166766","https://openalex.org/W2111667319","https://openalex.org/W2122978030","https://openalex.org/W2124007994","https://openalex.org/W2128539477","https://openalex.org/W2144215687","https://openalex.org/W2151819818","https://openalex.org/W2155216327","https://openalex.org/W2168276615","https://openalex.org/W2259574154","https://openalex.org/W2262570173","https://openalex.org/W2316564661","https://openalex.org/W2470876823","https://openalex.org/W2518567779","https://openalex.org/W3123057955","https://openalex.org/W4256207042"],"related_works":["https://openalex.org/W4286903191","https://openalex.org/W2069713958","https://openalex.org/W2566317144","https://openalex.org/W1848849174","https://openalex.org/W2067153720","https://openalex.org/W2896577559","https://openalex.org/W2047317216","https://openalex.org/W2070483007","https://openalex.org/W2169039980","https://openalex.org/W2129625121"],"abstract_inverted_index":{"Krylov":[0,94,218],"subspace":[1,95,219],"iterative":[2,96,220],"solvers":[3],"are":[4,50,206],"often":[5,68],"the":[6,17,80,84,91,105,118,129,159,171,180,186,209],"method":[7,119],"of":[8,43,53,60,83,93,127,212],"choice":[9],"when":[10],"solving":[11],"large":[12],"sparse":[13,148,204],"linear":[14,61],"systems.":[15],"At":[16],"same":[18],"time,":[19],"hardware":[20],"accelerators":[21],"such":[22],"as":[23,47,134,201,203],"graphics":[24,99,144,160,214],"processing":[25,100,145,161,215],"units":[26,216],"continue":[27],"to":[28,70,78,120,155,178],"offer":[29],"significant":[30,111],"floating":[31],"point":[32],"performance":[33,172],"gains":[34],"for":[35,98,208],"matrix":[36],"and":[37,75,102,140,174],"vector":[38],"computations":[39],"through":[40,123],"easy-to-use":[41],"libraries":[42,49],"computational":[44],"kernels.":[45],"However,":[46],"these":[48],"usually":[51],"composed":[52],"a":[54,143,168],"well":[55,202],"optimized":[56],"but":[57],"limited":[58],"set":[59],"algebra":[62],"operations,":[63],"applications":[64],"that":[65,110,152,185,195],"use":[66,158,175],"them":[67],"fail":[69,77],"reduce":[71,121],"certain":[72],"data":[73,177],"communications,":[74],"hence":[76],"leverage":[79],"full":[81],"potential":[82],"accelerator.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89,166,193],"target":[90],"acceleration":[92],"methods":[97],"units,":[101],"in":[103],"particular":[104],"Biconjugate":[106],"Gradient":[107],"Stabilized":[108],"solver":[109],"improvement":[112],"can":[113],"be":[114],"achieved":[115],"by":[116,136,141],"reformulating":[117],"data-communications":[122],"application-specific":[124],"kernels":[125],"instead":[126],"using":[128],"generic":[130],"BLAS":[131],"kernels,":[132],"e.g.":[133],"provided":[135],"NVIDIA\u2019s":[137],"cuBLAS":[138],"library,":[139],"designing":[142],"unit":[146],"specific":[147],"matrix-vector":[149],"product":[150],"kernel":[151],"is":[153],"able":[154],"more":[156],"efficiently":[157],"unit\u2019s":[162],"computing":[163],"power.":[164],"Furthermore,":[165],"derive":[167],"model":[169],"estimating":[170],"improvement,":[173],"experimental":[176],"validate":[179],"expected":[181],"runtime":[182],"savings.":[183],"Considering":[184],"derived":[187],"implementation":[188],"achieves":[189],"significantly":[190],"higher":[191],"performance,":[192],"assert":[194],"similar":[196],"optimizations":[197],"addressing":[198],"algorithm":[199],"structure,":[200],"matrix-vector,":[205],"crucial":[207],"subsequent":[210],"development":[211],"high-performance":[213],"accelerated":[217],"methods.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}