{"id":"https://openalex.org/W2921441046","doi":"https://doi.org/10.1109/tpds.2019.2905213","title":"A Performance Model for GPU Architectures that Considers On-Chip Resources: Application to Medical Image Registration","display_name":"A Performance Model for GPU Architectures that Considers On-Chip Resources: Application to Medical Image Registration","publication_year":2019,"publication_date":"2019-03-15","ids":{"openalex":"https://openalex.org/W2921441046","doi":"https://doi.org/10.1109/tpds.2019.2905213","mag":"2921441046"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2019.2905213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2905213","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/8790955/08667645.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/71/8790955/08667645.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031773859","display_name":"Junhao Wu","orcid":"https://orcid.org/0000-0001-8284-7421"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Wu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-8284-7421","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086985713","display_name":"Xuan Yang","orcid":"https://orcid.org/0000-0002-6680-6934"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Yang","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101733126","display_name":"Zhengrui Zhang","orcid":"https://orcid.org/0000-0001-7207-3258"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengrui Zhang","raw_affiliation_strings":["College of Information Engineering, Shenzhen University, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-7207-3258","affiliations":[{"raw_affiliation_string":"College of Information Engineering, Shenzhen University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668048","display_name":"Guoliang Chen","orcid":"https://orcid.org/0009-0002-7984-3184"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Chen","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101724957","display_name":"Rui Mao","orcid":"https://orcid.org/0000-0002-3645-5520"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Mao","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-3645-5520","affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.8748,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85113501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"30","issue":"9","first_page":"1947","last_page":"1961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8538423776626587},{"id":"https://openalex.org/keywords/image-registration","display_name":"Image registration","score":0.5855726599693298},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.4849274456501007},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.46172183752059937},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4467957019805908},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.4357045590877533},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4166336953639984},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41364067792892456},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3498973250389099},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.32648617029190063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3024786114692688},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12616440653800964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8538423776626587},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.5855726599693298},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.4849274456501007},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.46172183752059937},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4467957019805908},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.4357045590877533},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4166336953639984},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41364067792892456},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3498973250389099},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.32648617029190063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3024786114692688},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12616440653800964}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2019.2905213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2905213","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/8790955/08667645.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tpds.2019.2905213","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2905213","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/8790955/08667645.pdf","source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2856990048","display_name":"\u5fc3\u810f\u8fd0\u52a8\u6a21\u578b\u4f30\u8ba1\u4e2d\u7684\u6df1\u5ea6\u5b66\u4e60\u5f62\u72b6\u5339\u914d\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61871269","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325626","display_name":"Education Department of Jiangxi Province","ror":null},{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2921441046.pdf","grobid_xml":"https://content.openalex.org/works/W2921441046.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1904624772","https://openalex.org/W1966192292","https://openalex.org/W1967946179","https://openalex.org/W1976139981","https://openalex.org/W1979527452","https://openalex.org/W1981896890","https://openalex.org/W2002555321","https://openalex.org/W2006465004","https://openalex.org/W2016974693","https://openalex.org/W2018919812","https://openalex.org/W2021476856","https://openalex.org/W2033597569","https://openalex.org/W2041702240","https://openalex.org/W2045040977","https://openalex.org/W2047012348","https://openalex.org/W2065319605","https://openalex.org/W2075559423","https://openalex.org/W2082238959","https://openalex.org/W2083883508","https://openalex.org/W2090475106","https://openalex.org/W2092340922","https://openalex.org/W2093043622","https://openalex.org/W2093326633","https://openalex.org/W2097110160","https://openalex.org/W2099891946","https://openalex.org/W2100415730","https://openalex.org/W2103742924","https://openalex.org/W2105545110","https://openalex.org/W2110195531","https://openalex.org/W2113282196","https://openalex.org/W2117610793","https://openalex.org/W2122373806","https://openalex.org/W2125980577","https://openalex.org/W2126082093","https://openalex.org/W2132450860","https://openalex.org/W2142769604","https://openalex.org/W2146378653","https://openalex.org/W2151195685","https://openalex.org/W2170509487","https://openalex.org/W2263959547","https://openalex.org/W2465463737","https://openalex.org/W2466767104","https://openalex.org/W2468453073","https://openalex.org/W2527629189","https://openalex.org/W2751871758","https://openalex.org/W2997701623","https://openalex.org/W3005101099","https://openalex.org/W3006997840","https://openalex.org/W4234833047","https://openalex.org/W4250047567","https://openalex.org/W4256231890","https://openalex.org/W4298876635","https://openalex.org/W6674843673"],"related_works":["https://openalex.org/W2065289416","https://openalex.org/W2017236304","https://openalex.org/W3142211975","https://openalex.org/W2115579119","https://openalex.org/W2136854845","https://openalex.org/W1879443270","https://openalex.org/W2018912978","https://openalex.org/W2130914040","https://openalex.org/W2119122672","https://openalex.org/W4292904049"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"have":[4,18,102],"become":[5],"extremely":[6],"important":[7],"devices":[8],"for":[9,47],"accelerating":[10],"computing":[11],"performance":[12,26,40],"in":[13,97],"many":[14],"applications.":[15],"However,":[16],"there":[17],"been":[19],"few":[20],"accurate":[21,124],"models":[22],"to":[23,42,79,94,120,132,151,181],"estimate":[24,43],"the":[25,44,85,88,127,133,139,143,153,169,190],"of":[27,62,87,126,142,161,185],"such":[28],"applications":[29],"running":[30,51,129],"on":[31,52,157,168],"modern":[32],"GPUs.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37,117],"propose":[38],"a":[39,122],"model":[41,90],"execution":[45],"times":[46],"massively":[48],"parallel":[49],"programs":[50],"NVIDIA":[53],"GPUs,":[54],"one":[55],"that":[56,104],"takes":[57],"on-chip":[58,107],"resources":[59,109],"and":[60,67,110,166,173,187],"cost":[61],"data":[63,111],"transfer":[64,112],"between":[65],"CPU":[66],"GPU":[68,108,158],"into":[69],"consideration.":[70],"Four":[71],"different":[72,75],"GPUs":[73],"with":[74,114],"architectures":[76],"were":[77,118],"used":[78],"evaluate":[80],"our":[81,115,149],"model.":[82,135],"We":[83],"demonstrated":[84,103],"effectiveness":[86],"proposed":[89],"by":[91,105,137,148],"applying":[92],"it":[93,179],"various":[95],"tasks":[96],"medical":[98],"image":[99],"registration.":[100],"Experiments":[101],"capturing":[106],"time":[113],"model,":[116,150],"able":[119],"obtain":[121],"more":[123],"prediction":[125],"actual":[128],"time,":[130],"compared":[131],"traditional":[134],"Moreover,":[136],"using":[138],"optimal":[140],"value":[141],"block":[144],"size":[145],"parameter,":[146],"estimated":[147],"accelerate":[152],"landmark":[154],"tracking":[155],"task":[156],"devices,":[159],"speedups":[160],"approximately":[162],"80\u00d7,":[163],"100\u00d7,":[164],"200\u00d7":[165],"800\u00d7,":[167],"C2050,":[170],"K20c,":[171],"M5000":[172],"P100":[174],"can":[175],"be":[176],"achieved,":[177],"making":[178],"possible":[180],"track":[182],"massive":[183],"numbers":[184],"landmarks":[186],"thereby":[188],"improving":[189],"registration":[191],"accuracy.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}