{"id":"https://openalex.org/W2165689746","doi":null,"title":"A code motion technique for accelerating general-purpose computation on the GPU","display_name":"A code motion technique for accelerating general-purpose computation on the GPU","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2165689746","mag":"2165689746"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.113.8597","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.8597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-hagi.ist.osaka-u.ac.jp/research/papers/200604_ikeda_ipdps.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5050775522","display_name":"Takatoshi Ikeda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takatoshi Ikeda","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka Univ., Toyonaka, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka Univ., Toyonaka, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090008684","display_name":"Fumihiko Ino","orcid":"https://orcid.org/0000-0002-5757-7631","observed_orcids":["https://orcid.org/0000-0002-5757-7631"]},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumihiko Ino","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka Univ., Toyonaka, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka Univ., Toyonaka, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111729293","display_name":"Kenichi Hagihara","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenichi Hagihara","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka Univ., Toyonaka, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka Univ., Toyonaka, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":null,"apc_paid":null,"fwci":1.64,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86440467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":9.999999747378752e-05,"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/code-motion","display_name":"code motion","score":0.9240000247955322},{"id":"https://openalex.org/keywords/gpu-computing","display_name":"GPU computing","score":0.8220000267028809},{"id":"https://openalex.org/keywords/gpu-optimization","display_name":"GPU optimization","score":0.4819999933242798},{"id":"https://openalex.org/keywords/gaussian-filter","display_name":"Gaussian filtering","score":0.9110000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8690814971923828},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.8505996465682983},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7127869725227356},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6638191938400269},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5200937986373901},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.507438600063324},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4753308594226837},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.44205427169799805},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41128358244895935},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41041678190231323},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3059064745903015},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.17911329865455627},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16245749592781067},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1308826506137848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.113.8597","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.8597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-hagi.ist.osaka-u.ac.jp/research/papers/200604_ikeda_ipdps.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.1571","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.1571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hagi-www.ics.es.osaka-u.ac.jp/research/papers/200604_ikeda_ipdps.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W40887843","https://openalex.org/W170769950","https://openalex.org/W616583869","https://openalex.org/W1491178396","https://openalex.org/W1519234139","https://openalex.org/W1561264323","https://openalex.org/W1603142303","https://openalex.org/W1813030236","https://openalex.org/W1964031104","https://openalex.org/W1980855257","https://openalex.org/W2032309817","https://openalex.org/W2034147186","https://openalex.org/W2049890071","https://openalex.org/W2092047029","https://openalex.org/W2101111919","https://openalex.org/W2108157916","https://openalex.org/W2125313965","https://openalex.org/W2127091535","https://openalex.org/W2132973123","https://openalex.org/W2136834900","https://openalex.org/W2139774022","https://openalex.org/W2154118576","https://openalex.org/W2166063798","https://openalex.org/W2169706611","https://openalex.org/W2232710831","https://openalex.org/W2493581502","https://openalex.org/W2763437374","https://openalex.org/W2997945685"],"related_works":["https://openalex.org/W2186775643","https://openalex.org/W7096808425","https://openalex.org/W7100406846","https://openalex.org/W1995144992","https://openalex.org/W2556798365","https://openalex.org/W2342086348","https://openalex.org/W3207409367","https://openalex.org/W7095119620","https://openalex.org/W43173206","https://openalex.org/W4231159132"],"abstract_inverted_index":{"Recently,":[0],"graphics":[1,36],"processing":[2],"units":[3],"(GPUs)":[4],"are":[5,42],"providing":[6],"increasingly":[7],"higher":[8],"performance":[9,67,79,94,164],"with":[10,170],"programmable":[11],"internal":[12],"processors,":[13],"namely":[14],"vertex":[15],"processors":[16,20],"(VPs)":[17],"and":[18,40,151,178],"fragment":[19],"(FPs).":[21],"Such":[22],"newly":[23],"added":[24],"capabilities":[25],"motivate":[26],"us":[27],"to":[28,69,75,91,128],"perform":[29],"general-purpose":[30],"computation":[31],"on":[32],"GPUs":[33],"(GPGPU)":[34],"beyond":[35],"applications.":[37],"Although":[38],"VPs":[39],"FPs":[41,52,72],"connected":[43],"in":[44,57,65,81,186],"a":[45,54,78,107,166],"pipeline,":[46],"many":[47],"GPGPU":[48,96,191],"implementations":[49,62],"utilize":[50],"only":[51],"as":[53],"computational":[55],"engine":[56],"the":[58,82,93,116,125,129,135,145,149,152,163,183],"GPU.":[59,153],"Therefore,":[60],"such":[61,138],"may":[63],"result":[64],"lower":[66],"due":[68],"highly":[70],"loaded":[71],"(as":[73],"compared":[74],"VPs)":[76],"being":[77],"bottleneck":[80],"pipeline":[83],"execution.":[84],"The":[85,154],"objective":[86],"of":[87,95,114,137,165,189],"our":[88,160],"work":[89],"is":[90,112],"improve":[92],"programs":[97],"by":[98,119,174],"eliminating":[99],"this":[100],"bottleneck.":[101],"To":[102],"achieve":[103],"this,":[104],"we":[105],"present":[106,134],"code":[108],"motion":[109],"technique":[110,161],"that":[111,141,158],"capable":[113],"reducing":[115,171],"FP":[117,126,184],"workload":[118,185],"moving":[120],"assembly":[121],"instructions":[122,140],"appropriately":[123],"from":[124],"program":[127,169],"VP":[130],"program.":[131],"We":[132],"also":[133],"definition":[136],"movable":[139],"do":[142],"not":[143],"change":[144],"I/O":[146],"specification":[147],"between":[148],"CPU":[150],"experimental":[155],"results":[156],"show":[157],"(1)":[159],"improves":[162],"Gaussian":[167],"filter":[168],"execution":[172],"time":[173],"approximately":[175],"40":[176],"%":[177],"(2)":[179],"it":[180],"successfully":[181],"reduces":[182],"10":[187],"out":[188],"18":[190],"programs.":[192],"1.":[193]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2016-06-24T00:00:00"}