{"id":"https://openalex.org/W2167334577","doi":"https://doi.org/10.1145/1555754.1555775","title":"An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness","display_name":"An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness","publication_year":2009,"publication_date":"2009-06-20","ids":{"openalex":"https://openalex.org/W2167334577","doi":"https://doi.org/10.1145/1555754.1555775","mag":"2167334577"},"language":"en","primary_location":{"id":"doi:10.1145/1555754.1555775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1555754.1555775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th annual international symposium on Computer architecture","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/A5084791414","display_name":"Sunpyo Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sunpyo Hong","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084791414"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":42.0384,"has_fulltext":false,"cited_by_count":637,"citation_normalized_percentile":{"value":0.99905402,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"163"},"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/T10715","display_name":"Distributed and Parallel Computing 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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9958999752998352,"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":0.872493326663971},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.700421929359436},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6983117461204529},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6983013153076172},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6245884895324707},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.47293949127197266},{"id":"https://openalex.org/keywords/parallel-programming-model","display_name":"Parallel programming model","score":0.46661630272865295},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.45990654826164246},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4543548822402954},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4543333649635315},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4428647458553314},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4385184347629547},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.42021432518959045},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41838011145591736},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.41613125801086426},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16369828581809998},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09646889567375183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.872493326663971},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.700421929359436},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6983117461204529},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6983013153076172},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6245884895324707},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.47293949127197266},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.46661630272865295},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.45990654826164246},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4543548822402954},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4543333649635315},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4428647458553314},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4385184347629547},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.42021432518959045},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41838011145591736},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.41613125801086426},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16369828581809998},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09646889567375183},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1555754.1555775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1555754.1555775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th annual international symposium on Computer architecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.8219","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.8219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/%7Ehyesoon/hong_isca09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1867214769","https://openalex.org/W1979527452","https://openalex.org/W1991222965","https://openalex.org/W2028499920","https://openalex.org/W2073617099","https://openalex.org/W2109426995","https://openalex.org/W2115676933","https://openalex.org/W2121539621","https://openalex.org/W2137044408","https://openalex.org/W2143749395","https://openalex.org/W2153492376","https://openalex.org/W2155503253","https://openalex.org/W2163290010","https://openalex.org/W2169150396","https://openalex.org/W2527328949","https://openalex.org/W3048716914","https://openalex.org/W3138798301"],"related_works":["https://openalex.org/W2109126387","https://openalex.org/W2142344422","https://openalex.org/W1483753031","https://openalex.org/W2334687145","https://openalex.org/W2085780778","https://openalex.org/W2103813409","https://openalex.org/W2378666660","https://openalex.org/W4253043195","https://openalex.org/W1784161403","https://openalex.org/W2139618719"],"abstract_inverted_index":{"GPU":[0,40],"architectures":[1,41],"are":[2],"increasingly":[3],"important":[4],"in":[5],"the":[6,32,61,68],"multi-core":[7],"era":[8],"due":[9],"to":[10,42,55],"their":[11,57,72],"high":[12],"number":[13],"of":[14,19,35,71],"parallel":[15,21,37],"processors.":[16],"Programming":[17],"thousands":[18],"massively":[20],"threads":[22],"is":[23,46],"a":[24],"big":[25],"challenge":[26],"for":[27],"software":[28],"engineers,":[29],"but":[30],"understanding":[31,67],"performance":[33,45,69],"bottlenecks":[34],"those":[36],"programs":[38],"on":[39,53],"improve":[43],"application":[44],"even":[47],"more":[48],"difficult.":[49],"Current":[50],"approaches":[51],"rely":[52],"programmers":[54],"tune":[56],"applications":[58],"by":[59],"exploiting":[60],"design":[62],"space":[63],"exhaustively":[64],"without":[65],"fully":[66],"characteristics":[70],"applications.":[73]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":41},{"year":2017,"cited_by_count":57},{"year":2016,"cited_by_count":50},{"year":2015,"cited_by_count":56},{"year":2014,"cited_by_count":75},{"year":2013,"cited_by_count":72},{"year":2012,"cited_by_count":65}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}