{"id":"https://openalex.org/W2037628906","doi":"https://doi.org/10.1109/cluster.2012.9","title":"GPGPU Memory Estimation and Optimization Targeting OpenCL Architecture","display_name":"GPGPU Memory Estimation and Optimization Targeting OpenCL Architecture","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2037628906","doi":"https://doi.org/10.1109/cluster.2012.9","mag":"2037628906"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2012.9","doi":"https://doi.org/10.1109/cluster.2012.9","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2012.9","pdf_url":null,"source":{"id":"https://openalex.org/S4210207155","display_name":"IEEE International Conference on Cluster Computing (CLUSTER)","issn_l":"1552-5244","issn":["1552-5244","2168-9253"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"},"volume":null,"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/A5102111728","display_name":"Junfeng Zhu","orcid":"https://orcid.org/0009-0002-8745-1391","observed_orcids":["https://orcid.org/0009-0002-8745-1391"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Zhu","raw_affiliation_strings":["Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China","Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389256","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-2960-089X","observed_orcids":["https://orcid.org/0000-0002-2960-089X"]},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["No. 38 Res. Inst., China Electron. Technol. Group Corp., Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"No. 38 Res. Inst., China Electron. Technol. Group Corp., Hefei, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100932138","display_name":"Baifeng Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baifeng Wu","raw_affiliation_strings":["Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China","Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Inst. of Comput. Sci. & Technol., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4211,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52468582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"449","last_page":"458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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":0.0,"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/gpgpu","display_name":"GPGPU","score":0.843999981880188},{"id":"https://openalex.org/keywords/opencl","display_name":"OpenCL","score":0.9010000228881836},{"id":"https://openalex.org/keywords/polyhedral-representation","display_name":"polyhedral representation","score":0.8109999895095825},{"id":"https://openalex.org/keywords/graph-coloring","display_name":"graph coloring","score":0.8939999938011169},{"id":"https://openalex.org/keywords/memory-access-patterns","display_name":"memory access patterns","score":0.625},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"memory bandwidth","score":0.7450000047683716},{"id":"https://openalex.org/keywords/data-reuse","display_name":"data reuse","score":0.7870000004768372},{"id":"https://openalex.org/keywords/parallel-program-optimization","display_name":"parallel program optimization","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9023157358169556},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6514137983322144},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6489112377166748},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5940394401550293},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5349019765853882},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.49749138951301575},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.49727705121040344},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.4767359495162964},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.46993881464004517},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.446778267621994},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.4303615093231201},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4272604286670685},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.4245193898677826},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.42032259702682495},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.348499596118927},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.22579416632652283},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.19579535722732544},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13428524136543274},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2012.9","doi":"https://doi.org/10.1109/cluster.2012.9","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2012.9","pdf_url":null,"source":{"id":"https://openalex.org/S4210207155","display_name":"IEEE International Conference on Cluster Computing (CLUSTER)","issn_l":"1552-5244","issn":["1552-5244","2168-9253"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Cluster Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1992851788","https://openalex.org/W2000335122","https://openalex.org/W2016939324","https://openalex.org/W2031775479","https://openalex.org/W2076485607","https://openalex.org/W2083056254","https://openalex.org/W2095632265","https://openalex.org/W2108157916","https://openalex.org/W2108792719","https://openalex.org/W2117228145","https://openalex.org/W2124644009","https://openalex.org/W2128022558","https://openalex.org/W2128125098","https://openalex.org/W2139143992","https://openalex.org/W2139774022","https://openalex.org/W2147193503","https://openalex.org/W2153492376","https://openalex.org/W2160245390","https://openalex.org/W2170634604","https://openalex.org/W3138570118","https://openalex.org/W3150013291","https://openalex.org/W4250981202"],"related_works":["https://openalex.org/W2978129602","https://openalex.org/W2206143169","https://openalex.org/W2014967131","https://openalex.org/W2368435077","https://openalex.org/W3030752614","https://openalex.org/W2087375070","https://openalex.org/W6979995236","https://openalex.org/W2268210706","https://openalex.org/W1981004441","https://openalex.org/W121033536"],"abstract_inverted_index":{"The":[0],"enormous":[1],"computational":[2],"power":[3],"available":[4],"in":[5,72],"modern":[6],"graphics":[7],"processing":[8,49],"units":[9],"(GPUs)":[10],"has":[11],"enabled":[12],"the":[13,39,87,92,109,116,120,133,139,143,157,171,177,180,185,192,218,222,230],"widely":[14],"use":[15],"of":[16,24,41,68,83,91,112,118,141,150,173,179,187,191,206],"them":[17],"for":[18,28,43,138,203],"general-purpose":[19],"applications.":[20],"However,":[21],"manual":[22],"development":[23],"high-performance":[25],"parallel":[26],"codes":[27],"GPUs":[29],"is":[30,63],"still":[31],"very":[32],"challenging.":[33],"In":[34],"order":[35,73],"to":[36,64,74,131,160,169,217],"fully":[37],"exploit":[38],"capability":[40],"GPU":[42,202],"general":[44],"purpose":[45,117,186],"computing":[46],"under":[47],"heterogeneous":[48],"platforms,":[50],"we":[51,94,107,126,155,211],"propose":[52],"performance":[53,111,226,233],"estimation":[54],"and":[55,76,80,176,221],"optimization":[56],"methods":[57],"targeting":[58],"OpenCL":[59,181],"architecture.":[60],"Our":[61],"approach":[62],"utilize":[65,127],"polyhedral":[66],"representation":[67],"a":[69,204],"source":[70],"program":[71],"optimize":[75],"allocate":[77,161],"global":[78,122,224,231],"memory":[79,82,88,110,123,135,145,166,182,225,232],"fast":[81,165,193],"GPUs.":[84],"By":[85],"checking":[86],"access":[89,96,136],"patterns":[90,137],"program,":[93,114],"discover":[95],"instances":[97],"those":[98],"can":[99,228],"be":[100],"grouped":[101],"together":[102],"using":[103],"graph":[104],"coloring.":[105],"Subsequently,":[106],"estimate":[108,229],"this":[113],"with":[115,184,215],"eliminating":[119],"uncoalesced":[121],"accesses.":[124],"Then,":[125],"data":[128,152,162,174],"space":[129],"transformation":[130],"alter":[132],"irregular":[134],"sake":[140],"improving":[142],"off-chip":[144],"bandwidth":[146],"by":[147],"taking":[148],"advantage":[149],"vector":[151],"types.":[153],"Meanwhile,":[154],"detect":[156],"reuse":[158],"information":[159],"into":[163],"distinct":[164],"regions":[167],"according":[168],"both":[170],"properties":[172],"accesses":[175],"characteristics":[178],"model,":[183],"making":[188],"best":[189],"usage":[190],"on-chip":[194],"memory.":[195],"Experimental":[196],"results":[197],"on":[198],"an":[199],"AMD/ATI":[200],"HD5850":[201],"set":[205],"commonly-used":[207],"benchmarks":[208],"show":[209],"that":[210],"achieve":[212],"2.1X\u00a1\u00ab6.7X":[213],"speedup":[214],"respect":[216],"un-optimized":[219],"versions":[220],"present":[223],"model":[227],"relative":[234],"accurately.":[235]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2016-06-24T00:00:00"}