{"id":"https://openalex.org/W3148434857","doi":"https://doi.org/10.1109/ipdps.2006.1639323","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/W3148434857","doi":"https://doi.org/10.1109/ipdps.2006.1639323","mag":"3148434857"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2006.1639323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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/A5050775522","display_name":"Takatoshi Ikeda","orcid":null},"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":"T. Ikeda","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Toyonaka, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, 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"},"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":"F. Ino","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Toyonaka, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, Toyonaka, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111729293","display_name":"Kenichi Hagihara","orcid":null},"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":"K. Hagihara","raw_affiliation_strings":["Graduate School of Information Science and Technology, Osaka University, Toyonaka, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Osaka University, 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":0.4464,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.59626064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"19","issue":null,"first_page":"10 pp.","last_page":"10 pp."},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9937000274658203,"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":0.8647189736366272},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.8555821180343628},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7334820032119751},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6827187538146973},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5340819358825684},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5183568596839905},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4983398914337158},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45043328404426575},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4215850830078125},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4164276421070099},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3017937242984772},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17969048023223877},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12655410170555115},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07789149880409241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8647189736366272},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.8555821180343628},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7334820032119751},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6827187538146973},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5340819358825684},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5183568596839905},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4983398914337158},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45043328404426575},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4215850830078125},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4164276421070099},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3017937242984772},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17969048023223877},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12655410170555115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07789149880409241}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2006.1639323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W40887843","https://openalex.org/W170769950","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/W2025516544","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/W2127091535","https://openalex.org/W2132973123","https://openalex.org/W2136834900","https://openalex.org/W2139774022","https://openalex.org/W2232710831","https://openalex.org/W2258313519","https://openalex.org/W2763437374","https://openalex.org/W2988817687","https://openalex.org/W2997945685","https://openalex.org/W4241667468","https://openalex.org/W6601653709","https://openalex.org/W6606978099","https://openalex.org/W6650325945","https://openalex.org/W6678771712"],"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/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"are":[4,41],"providing":[5],"increasingly":[6],"higher":[7],"performance":[8,66,78,93,163],"with":[9,169],"programmable":[10],"internal":[11],"processors,":[12],"namely":[13],"vertex":[14],"processors":[15,19],"(VPs)":[16],"and":[17,39,150,176],"fragment":[18],"(FPs).":[20],"Such":[21],"newly":[22],"added":[23],"capabilities":[24],"motivate":[25],"us":[26],"to":[27,68,74,90,127],"perform":[28],"general-purpose":[29],"computation":[30],"on":[31],"GPUs":[32],"(GPGPU)":[33],"beyond":[34],"graphics":[35],"applications.":[36],"Although":[37],"VPs":[38],"FPs":[40,51,71],"connected":[42],"in":[43,56,64,80,184],"a":[44,53,77,106,165],"pipeline,":[45],"many":[46],"GPGPU":[47,95,189],"implementations":[48,61],"utilize":[49],"only":[50],"as":[52],"computational":[54],"engine":[55],"the":[57,81,92,115,124,128,134,144,148,151,162,181],"GPU.":[58,152],"Therefore,":[59],"such":[60,137],"may":[62],"result":[63],"lower":[65],"due":[67],"highly":[69],"loaded":[70],"(as":[72],"compared":[73],"VPs)":[75],"being":[76],"bottleneck":[79],"pipeline":[82],"execution.":[83],"The":[84,153],"objective":[85],"of":[86,94,113,136,164,187],"our":[87,159],"work":[88],"is":[89,111],"improve":[91],"programs":[96],"by":[97,118,173],"eliminating":[98],"this":[99],"bottleneck.":[100],"To":[101],"achieve":[102],"this,":[103],"we":[104],"present":[105,133],"code":[107],"motion":[108],"technique":[109,160],"that":[110,140,157],"capable":[112],"reducing":[114,170],"FP":[116,125,182],"workload":[117,183],"moving":[119],"assembly":[120],"instructions":[121,139],"appropriately":[122],"from":[123],"program":[126,168],"VP":[129],"program.":[130],"We":[131],"also":[132],"definition":[135],"movable":[138],"do":[141],"not":[142],"change":[143],"I/O":[145],"specification":[146],"between":[147],"CPU":[149],"experimental":[154],"results":[155],"show":[156],"(1)":[158],"improves":[161],"Gaussian":[166],"filter":[167],"execution":[171],"time":[172],"approximately":[174],"40%":[175],"(2)":[177],"it":[178],"successfully":[179],"reduces":[180],"10":[185],"out":[186],"18":[188],"programs.":[190]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}