{"id":"https://openalex.org/W4238492389","doi":"https://doi.org/10.1109/aspdac.2009.4796483","title":"Aspects of GPU for general purpose high performance computing","display_name":"Aspects of GPU for general purpose high performance computing","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W4238492389","doi":"https://doi.org/10.1109/aspdac.2009.4796483"},"language":"en","primary_location":{"id":"doi:10.1109/aspdac.2009.4796483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2009.4796483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Asia and South Pacific Design Automation Conference","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/A5009108314","display_name":"Reiji Suda","orcid":"https://orcid.org/0000-0001-8797-6011"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Reiji Suda","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081984471","display_name":"Takayuki Aoki","orcid":"https://orcid.org/0000-0001-6436-3255"},"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":"Takayuki Aoki","raw_affiliation_strings":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090496070","display_name":"Shoichi Hirasawa","orcid":"https://orcid.org/0000-0002-3313-4158"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichi Hirasawa","raw_affiliation_strings":["Graduate School of Information Systems, University of Electro-Communications, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006972521","display_name":"Akira Nukada","orcid":"https://orcid.org/0000-0001-7959-6975"},"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":"Akira Nukada","raw_affiliation_strings":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019287870","display_name":"Hiroki Honda","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Honda","raw_affiliation_strings":["Graduate School of Information Systems, University of Electro-Communications, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Systems, University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252086","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-2126-2926"},"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":["Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Global Scientific Information and Computing Center, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009108314"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.6382,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91080414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"216","last_page":"223"},"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.89442378282547},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.831637442111969},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.737739622592926},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6509315371513367},{"id":"https://openalex.org/keywords/spmd","display_name":"SPMD","score":0.6312698125839233},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5952260494232178},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5023643970489502},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.48580455780029297},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.36236125230789185},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3369303345680237},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.19563117623329163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.89442378282547},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.831637442111969},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.737739622592926},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6509315371513367},{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.6312698125839233},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5952260494232178},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5023643970489502},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.48580455780029297},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36236125230789185},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3369303345680237},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.19563117623329163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aspdac.2009.4796483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2009.4796483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W185895490","https://openalex.org/W1501013319","https://openalex.org/W2326452577","https://openalex.org/W3141650078","https://openalex.org/W3145767355","https://openalex.org/W6607488862"],"related_works":["https://openalex.org/W2306680564","https://openalex.org/W1594028627","https://openalex.org/W1672168401","https://openalex.org/W1963859303","https://openalex.org/W1979287416","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538"],"abstract_inverted_index":{"We":[0],"discuss":[1,72],"hardware":[2],"and":[3,13,34,51,71],"software":[4,57],"aspects":[5],"of":[6,18,25,47,67],"GPGPU,":[7],"specifically":[8],"focusing":[9],"on":[10,75],"NVIDIA":[11],"cards":[12],"CUDA,":[14],"from":[15],"the":[16],"viewpoints":[17],"parallel":[19],"computing.":[20],"The":[21],"major":[22],"weak":[23],"points":[24],"GPU":[26],"against":[27],"newest":[28],"supercomputers":[29],"are":[30],"identified":[31],"to":[32],"be":[33],"summarized":[35],"as":[36],"only":[37],"four":[38],"points:":[39],"large":[40],"SIMD":[41],"vector":[42],"length,":[43],"small":[44],"memory,":[45],"absence":[46],"fast":[48],"L2":[49],"cache,":[50],"high":[52],"register":[53],"spill":[54],"penalty.":[55],"As":[56],"concerns,":[58],"we":[59],"derive":[60],"optimal":[61],"scheduling":[62],"algorithm":[63],"for":[64],"latency":[65],"hiding":[66],"host-device":[68],"data":[69],"transfer,":[70],"SPMD":[73],"parallelism":[74],"GPUs.":[76]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}