{"id":"https://openalex.org/W2100705537","doi":"https://doi.org/10.1109/ipdps.2008.4536251","title":"Massive supercomputing coping with heterogeneity of modern accelerators","display_name":"Massive supercomputing coping with heterogeneity of modern accelerators","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2100705537","doi":"https://doi.org/10.1109/ipdps.2008.4536251","mag":"2100705537"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2008.4536251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536251","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},"type":"article","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/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":true,"raw_author_name":"Toshio Endo","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","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":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011254074"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":5.5112,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96021481,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/supercomputer","display_name":"Supercomputer","score":0.9065419435501099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8367496728897095},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.8240950107574463},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7149231433868408},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7140300273895264},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49746206402778625},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4945177733898163},{"id":"https://openalex.org/keywords/metacomputing","display_name":"Metacomputing","score":0.472404420375824},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46933120489120483},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4570385217666626},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.43894466757774353},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.410094678401947},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40724846720695496},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3648604154586792},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1075894832611084},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08367016911506653}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.9065419435501099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8367496728897095},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.8240950107574463},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7149231433868408},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7140300273895264},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49746206402778625},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4945177733898163},{"id":"https://openalex.org/C2779120266","wikidata":"https://www.wikidata.org/wiki/Q6822443","display_name":"Metacomputing","level":2,"score":0.472404420375824},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46933120489120483},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4570385217666626},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.43894466757774353},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.410094678401947},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40724846720695496},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3648604154586792},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1075894832611084},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08367016911506653},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdps.2008.4536251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2008.4536251","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"Proceedings - IEEE International Parallel and Distributed Processing Symposium","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.329.3836","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.329.3836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://matsu-www.is.titech.ac.jp/~endo/papers/endo-ipdps08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.723.8221","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.723.8221","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://matsu-www.is.titech.ac.jp/sites/default/files/docs/publication/CTT100575651.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W57243869","https://openalex.org/W1575732703","https://openalex.org/W1816932979","https://openalex.org/W1900026725","https://openalex.org/W1971952282","https://openalex.org/W2046309377","https://openalex.org/W2085118703","https://openalex.org/W2108792719","https://openalex.org/W2120781145","https://openalex.org/W2136834900","https://openalex.org/W2139613964","https://openalex.org/W2149835018","https://openalex.org/W2157779169","https://openalex.org/W2163229756","https://openalex.org/W3145506805","https://openalex.org/W6638416746","https://openalex.org/W6662129016"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2966127030","https://openalex.org/W2956082141","https://openalex.org/W1507415763","https://openalex.org/W2068145882","https://openalex.org/W2146148574"],"abstract_inverted_index":{"Heterogeneous":[0],"supercomputers":[1],"with":[2,65,97],"combined":[3,46,137],"general-purpose":[4],"and":[5,20,37,101,131,146],"accelerated":[6],"CPUs":[7],"promise":[8],"to":[9,16,99,112],"be":[10,69],"the":[11,60,85,92,103,113,118,143,152,160,168],"future":[12],"major":[13],"architecture":[14],"due":[15],"their":[17],"wide-ranging":[18],"generality":[19],"superior":[21],"performance":[22,83,163],"/":[23],"power":[24],"ratio.":[25],"However,":[26],"developing":[27],"applications":[28,63,78],"that":[29,50,59,90],"achieve":[30],"effective":[31,52],"scalability":[32],"is":[33,159],"still":[34],"very":[35],"difficult,":[36],"in":[38,44,135,167],"fact":[39],"unproven":[40],"on":[41,117,151,164],"large-scale":[42],"machines":[43],"such":[45,55],"setting.":[47],"We":[48,108,122],"show":[49],"an":[51],"method":[53,111],"for":[54],"heterogeneous":[56,106,120,165],"systems":[57,166],"so":[58],"porting":[61,76],"from":[62],"written":[64],"homogeneous":[66],"assumptions":[67],"could":[68],"achieved.":[70],"For":[71],"this":[72],"goal,":[73],"we":[74],"divide":[75],"of":[77,84],"into":[79],"several":[80],"steps,":[81],"analyze":[82],"kernel":[86],"computation,":[87],"create":[88],"processes":[89],"virtualize":[91],"underlying":[93],"processors,":[94],"tune":[95],"parameters":[96],"preferences":[98],"accelerators,":[100],"balance":[102],"load":[104],"between":[105],"nodes.":[107],"apply":[109],"our":[110],"parallel":[114],"Linpack":[115,162],"benchmark":[116],"TSUBAME":[119],"supercomputer.":[121],"efficiently":[123],"utilize":[124],"both":[125],"10,000":[126],"general":[127],"purpose":[128],"CPU":[129],"cores":[130],"648":[132],"SIMD":[133],"accelerators":[134],"a":[136],"fashion\u2014the":[138],"resulting":[139],"56.43":[140],"TFlops":[141],"utilized":[142],"entire":[144],"machine,":[145],"not":[147],"only":[148],"ranked":[149],"significantly":[150],"Top500":[153],"supercomputer":[154],"list,":[155],"but":[156],"also":[157],"it":[158],"highest":[161],"world.":[169]},"counts_by_year":[{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}