{"id":"https://openalex.org/W2126354187","doi":"https://doi.org/10.1109/i-span.2009.154","title":"Improving Dense Linear Equation Solver on Hybrid CPU-GPU System","display_name":"Improving Dense Linear Equation Solver on Hybrid CPU-GPU System","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2126354187","doi":"https://doi.org/10.1109/i-span.2009.154","mag":"2126354187"},"language":"en","primary_location":{"id":"doi:10.1109/i-span.2009.154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/i-span.2009.154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 10th International Symposium on Pervasive Systems, Algorithms, and Networks","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072253749","display_name":"Zhichao Cao","orcid":"https://orcid.org/0000-0002-8159-9072"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Cao","raw_affiliation_strings":["Department Computer Science & Technology, Tsinghua University, Beijing, China","Dept. Comp. Sci. & Tech., Tsinghua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science & Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. Comp. Sci. & Tech., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064134842","display_name":"Shiming Xu","orcid":"https://orcid.org/0000-0003-4999-3499"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shiming Xu","raw_affiliation_strings":["Delft Institute Applied Math, Technical University Delft, Delft, Netherlands","Delft Inst. Appl. Math., Tech. Univ. Delft, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Institute Applied Math, Technical University Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Inst. Appl. Math., Tech. Univ. Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["Department Computer Science & Technology, Tsinghua University, Beijing, China","Dept. Comp. Sci. & Tech., Tsinghua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science & Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. Comp. Sci. & Tech., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguang Chen","raw_affiliation_strings":["Department Computer Science & Technology, Tsinghua University, Beijing, China","Dept. Comp. Sci. & Tech., Tsinghua Univ., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department Computer Science & Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. Comp. Sci. & Tech., Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6022,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64556355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"556","last_page":"562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9987999796867371,"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":0.9987999796867371,"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/T11697","display_name":"Numerical Methods 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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9884999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8413757085800171},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8130717873573303},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7078310251235962},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6599314212799072},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.6397881507873535},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.604044497013092},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5450667142868042},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.537377119064331},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.5125045776367188},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.43258416652679443},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25863122940063477},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17696434259414673},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12175926566123962},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.08711668848991394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413757085800171},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8130717873573303},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7078310251235962},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6599314212799072},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.6397881507873535},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.604044497013092},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5450667142868042},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.537377119064331},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.5125045776367188},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.43258416652679443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25863122940063477},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17696434259414673},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12175926566123962},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.08711668848991394},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/i-span.2009.154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/i-span.2009.154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 10th International Symposium on Pervasive Systems, Algorithms, and Networks","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1568272005","https://openalex.org/W2063186542","https://openalex.org/W2111593426","https://openalex.org/W2112286143","https://openalex.org/W2169631286","https://openalex.org/W6633966643"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2020279179","https://openalex.org/W1972148443"],"abstract_inverted_index":{"In":[0,58],"recent":[1],"years,":[2],"GPU":[3,36,100],"(Graphic":[4],"Processor":[5],"Unit)":[6],"has":[7,16,37,52],"become":[8],"an":[9],"import":[10],"accelerator":[11],"for":[12,31,103],"conventional":[13],"applications.":[14],"User":[15],"to":[17,80,113],"program":[18],"in":[19,55],"GPU-based":[20],"environments,":[21],"such":[22],"as":[23],"CUDA,":[24],"and":[25,101],"it":[26,51],"usually":[27],"requires":[28],"detailed":[29],"tuning":[30],"good":[32],"performances.":[33],"Also":[34],"since":[35],"high":[38,83],"Single":[39],"Precision":[40,46],"(SP)":[41],"performance":[42,48,110],"while":[43,88],"its":[44],"Double":[45],"(DP)":[47],"falls":[49],"short,":[50],"limited":[53],"application":[54],"scientific":[56],"computing.":[57],"this":[59],"paper,":[60],"our":[61],"algorithm":[62,96],"aims":[63],"at":[64],"accelerating":[65],"the":[66,82,122],"solving":[67],"of":[68,86],"dense":[69],"linear":[70],"equation":[71],"on":[72],"hybrid":[73],"CPU-GPU":[74],"system.":[75],"We":[76],"adopt":[77],"iterative":[78],"refinement":[79],"utilize":[81,98],"SP":[84],"capability":[85],"GPUs":[87],"achieving":[89],"DP":[90],"precision":[91],"requirements.":[92],"Specifically,":[93],"we":[94],"implement":[95],"with":[97],"both":[99],"CPU":[102],"computation-intensive":[104],"parts":[105],"by":[106,118,125],"overlapping":[107],"computations.":[108],"Its":[109],"reaches":[111],"up":[112],"236":[114],"GFLOP/s,":[115],"which":[116],"is":[117],"far":[119],"better":[120],"than":[121],"result":[123],"achieved":[124],"DP-only":[126],"algorithms.":[127]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}