{"id":"https://openalex.org/W2057317268","doi":"https://doi.org/10.1109/cluster.2013.6702633","title":"A parallel optimization method for stencil computation on the domain that is bigger than memory capacity of GPUs","display_name":"A parallel optimization method for stencil computation on the domain that is bigger than memory capacity of GPUs","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2057317268","doi":"https://doi.org/10.1109/cluster.2013.6702633","mag":"2057317268"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2013.6702633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5015867638","display_name":"Guanghao Jin","orcid":"https://orcid.org/0000-0003-2116-4410"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Guanghao Jin","raw_affiliation_strings":["JST-CREST, Tokyo Institute of Technology, Tokyo, Japan","Tokyo Institute of Technology, JST CREST, Tokyo, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JST-CREST, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of Technology, JST CREST, Tokyo, Japan#TAB#","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011254074","display_name":"Toshio Endo","orcid":"https://orcid.org/0000-0001-7297-6211"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshio Endo","raw_affiliation_strings":["JST-CREST, Tokyo Institute of Technology, Tokyo, Japan","Tokyo Institute of Technology, JST CREST, Tokyo, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JST-CREST, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Institute of Technology, JST CREST, Tokyo, Japan#TAB#","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["NII, Tokyo Institute of Technology, Tokyo, Japan","Tokyo Inst. of Technol., NII, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NII, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Tokyo Inst. of Technol., NII, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9927999973297119,"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/stencil","display_name":"Stencil","score":0.981658399105072},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8301006555557251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8290526866912842},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.778527021408081},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6195733547210693},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.5129830241203308},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4516708552837372},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.430163711309433},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.42895907163619995},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4230685532093048},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24928158521652222},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07298681139945984},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.06484004855155945}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.981658399105072},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8301006555557251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8290526866912842},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.778527021408081},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6195733547210693},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.5129830241203308},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4516708552837372},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.430163711309433},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.42895907163619995},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4230685532093048},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24928158521652222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07298681139945984},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.06484004855155945},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2013.6702633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6700000166893005,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2026173834","https://openalex.org/W2028725669","https://openalex.org/W2039378765","https://openalex.org/W2056295840","https://openalex.org/W2083051666","https://openalex.org/W2100705537","https://openalex.org/W2129050115","https://openalex.org/W2150319905","https://openalex.org/W2154786353","https://openalex.org/W3152199537","https://openalex.org/W6664917920","https://openalex.org/W6674979789","https://openalex.org/W6681908283"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2010557350","https://openalex.org/W2177020196","https://openalex.org/W1582436825","https://openalex.org/W1429949169","https://openalex.org/W1996803181","https://openalex.org/W2979588510","https://openalex.org/W3139770841","https://openalex.org/W2044758662","https://openalex.org/W85427715"],"abstract_inverted_index":{"The":[0],"problem":[1,41,72,94],"size":[2,42],"of":[3,23,47,84,100],"the":[4,13,44],"stencil":[5,35,85,101],"computation":[6,36,86],"on":[7,66,103,115,131],"GPU":[8,68],"cluster":[9],"is":[10,18,121],"limited":[11],"by":[12],"memory":[14,45,81],"capacity":[15,46],"GPUs,":[16],"which":[17,120],"typically":[19],"smaller":[20],"than":[21,43,128],"that":[22,107],"host":[24],"memories.":[25],"This":[26],"paper":[27],"proposes":[28],"and":[29,49,87,113,124],"evaluates":[30],"parallel":[31],"optimization":[32],"method":[33,78,110],"for":[34,111],"to":[37,56,69,79,91,95],"achieve":[38,57,70],"scalability,":[39],"larger":[40],"GPUs":[48,116],"high":[50],"performance.":[51,98],"It":[52,74],"uses":[53],"2D":[54],"decomposition":[55],"scalability":[58,119],"over":[59],"GPUs.":[60],"Then":[61],"it":[62],"enables":[63],"bigger":[64,71],"sub-domain":[65],"each":[67],"size.":[73],"applies":[75],"temporal":[76],"blocking":[77],"improve":[80],"access":[82],"locality":[83],"reuses":[88],"former":[89],"result":[90],"solve":[92],"redundant":[93],"get":[96],"higher":[97],"Evaluation":[99],"simulation":[102],"3D":[104],"domain":[105],"shows":[106],"our":[108],"new":[109],"7-point":[112],"19-point":[114],"achieves":[117],"good":[118],"1.45":[122],"times":[123,126],"1.72":[125],"better":[127],"other":[129],"methods":[130],"average.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}