{"id":"https://openalex.org/W1976033099","doi":"https://doi.org/10.4304/jsw.7.12.2695-2702","title":"An Improved Implementation of Preconditioned Conjugate Gradient Method on GPU","display_name":"An Improved Implementation of Preconditioned Conjugate Gradient Method on GPU","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1976033099","doi":"https://doi.org/10.4304/jsw.7.12.2695-2702","mag":"1976033099"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.7.12.2695-2702","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.7.12.2695-2702","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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/A5022811868","display_name":"Yechen Gui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yechen Gui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028538102","display_name":"Guijuan Zhang","orcid":"https://orcid.org/0000-0002-9545-8668"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guijuan Zhang","raw_affiliation_strings":["Shenzhen institutes of advanced technology, Chinese academy of sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen institutes of advanced technology, Chinese academy of sciences","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6999,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83430965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"7","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9995999932289124,"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":0.9995999932289124,"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/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9039307832717896},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.8740055561065674},{"id":"https://openalex.org/keywords/conjugate","display_name":"Conjugate","score":0.5429345369338989},{"id":"https://openalex.org/keywords/conjugate-residual-method","display_name":"Conjugate residual method","score":0.47314441204071045},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4484548270702362},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42984816431999207},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28802061080932617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15244150161743164},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.09510654211044312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07164609432220459},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.03871676325798035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9039307832717896},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.8740055561065674},{"id":"https://openalex.org/C197336794","wikidata":"https://www.wikidata.org/wiki/Q5161150","display_name":"Conjugate","level":2,"score":0.5429345369338989},{"id":"https://openalex.org/C91394653","wikidata":"https://www.wikidata.org/wiki/Q5161159","display_name":"Conjugate residual method","level":4,"score":0.47314441204071045},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4484548270702362},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42984816431999207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28802061080932617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15244150161743164},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.09510654211044312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07164609432220459},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.03871676325798035},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jsw.7.12.2695-2702","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.7.12.2695-2702","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W40887843","https://openalex.org/W1550780731","https://openalex.org/W1990832096","https://openalex.org/W2010069926","https://openalex.org/W2095292158","https://openalex.org/W2128853364","https://openalex.org/W2130128444","https://openalex.org/W2134778498","https://openalex.org/W2136834900","https://openalex.org/W2154118576","https://openalex.org/W2161992803","https://openalex.org/W2166092736","https://openalex.org/W2314485382","https://openalex.org/W6683997436"],"related_works":["https://openalex.org/W2129625121","https://openalex.org/W2375597358","https://openalex.org/W2356365850","https://openalex.org/W2383960336","https://openalex.org/W3159557833","https://openalex.org/W2353110519","https://openalex.org/W2352936229","https://openalex.org/W3159907817","https://openalex.org/W3123621400","https://openalex.org/W2388344948"],"abstract_inverted_index":{"An":[0],"improved":[1],"implementation":[2],"of":[3,37,71,132,148],"the":[4,23,35,38,43,69,72,88,158],"Preconditioned":[5],"Conjugate":[6],"Gradient":[7],"method":[8,50,83],"on":[9,121],"GPU":[10,116],"using":[11,87],"CUDA":[12,97],"(Compute":[13],"Unified":[14],"Device":[15],"Architecture)":[16],"is":[17,65,84,112,152],"proposed.":[18],"It":[19],"aims":[20],"to":[21,51,67,92,102],"solving":[22],"Poisson":[24,44],"equation":[25,45],"arising":[26],"in":[27],"liquid":[28],"animation":[29],"with":[30,139],"high":[31],"efficiency.":[32],"We":[33],"consider":[34],"features":[36],"linear":[39],"system":[40],"obtained":[41,153],"from":[42],"and":[46],"propose":[47],"an":[48,130],"optimization":[49,110],"solve":[52],"it.":[53],"First,":[54],"a":[55,79,146],"novel":[56],"storage":[57,63],"format":[58],"called":[59],"mDIA":[60],"(modified":[61],"diagonal":[62],"format)":[64],"presented":[66],"improve":[68],"efficiency":[70],"Sparse":[73],"Matrix-Vector":[74],"product":[75],"(SpMV)":[76],"operation.":[77],"Second,":[78],"parallel":[80],"Jacobi":[81],"iterative":[82],"proposed":[85,109],"when":[86],"Incomplete":[89],"Cholesky":[90],"preconditioner":[91],"explore":[93],"inherent":[94],"parallelism.":[95],"Third,":[96],"streams":[98],"are":[99],"also":[100],"introduced":[101],"overlap":[103],"computations":[104],"among":[105],"separate":[106],"streams.":[107],"The":[108],"technique":[111],"embedded":[113],"into":[114],"our":[115,126],"based":[117],"PCG":[118,155],"algorithm.":[119],"Results":[120],"Geforce":[122],"G100":[123],"show":[124],"that":[125],"SpMV":[127],"kernel":[128],"yields":[129],"improvement":[131],"nearly":[133],"100%":[134],"for":[135,154],"large":[136],"sparse":[137],"matrix":[138],"more":[140,149],"than":[141,150],"30,":[142],"0000":[143],"rows.":[144],"Also,":[145],"speedup":[147],"7":[151],"method,":[156],"making":[157],"real-time":[159],"physics":[160],"engine":[161],"possible.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}