{"id":"https://openalex.org/W2942941461","doi":"https://doi.org/10.1145/3297280.3297426","title":"Multithreaded double queuing for balanced CPU-GPU memory copying","display_name":"Multithreaded double queuing for balanced CPU-GPU memory copying","publication_year":2019,"publication_date":"2019-04-08","ids":{"openalex":"https://openalex.org/W2942941461","doi":"https://doi.org/10.1145/3297280.3297426","mag":"2942941461"},"language":"en","primary_location":{"id":"doi:10.1145/3297280.3297426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297280.3297426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing","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/A5025447658","display_name":"Sang-Hun Cho","orcid":"https://orcid.org/0009-0002-9511-5347"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghun Cho","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049661151","display_name":"Jaewan Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewan Hong","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074392155","display_name":"Jungsik Choi","orcid":"https://orcid.org/0000-0001-9177-2484"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungsik Choi","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035561846","display_name":"Hwansoo Han","orcid":"https://orcid.org/0000-0001-7182-8452"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwansoo Han","raw_affiliation_strings":["Sungkyunkwan University, Suwon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University, Suwon, Republic of Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.6471,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.58636479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1444","last_page":"1450"},"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":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9987999796867371,"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":0.8700319528579712},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6326778531074524},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.6297290325164795},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5176116228103638},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.5173494219779968},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4761902391910553},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4682900309562683},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.45599502325057983},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3001326322555542},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2995474338531494},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.26087281107902527},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.08240655064582825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8700319528579712},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6326778531074524},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.6297290325164795},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5176116228103638},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.5173494219779968},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4761902391910553},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4682900309562683},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.45599502325057983},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3001326322555542},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2995474338531494},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.26087281107902527},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.08240655064582825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297280.3297426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3297280.3297426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W579519726","https://openalex.org/W1983096721","https://openalex.org/W2070630412","https://openalex.org/W2157802978","https://openalex.org/W2235673048","https://openalex.org/W2412976325","https://openalex.org/W3125984961","https://openalex.org/W3198160809","https://openalex.org/W4292169167"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2088078730","https://openalex.org/W2400763249","https://openalex.org/W1482063109","https://openalex.org/W2043940072","https://openalex.org/W2984905932","https://openalex.org/W2368611950","https://openalex.org/W2115229350"],"abstract_inverted_index":{"Memory":[0,54],"transfers":[1,25,96],"between":[2,57,97],"CPU":[3,58,99],"host":[4,98],"and":[5,59,100],"GPU":[6,15,18,60,91,101],"devices":[7,120],"are":[8,61],"known":[9],"to":[10,47,84,124],"impose":[11],"heavy":[12],"overhead":[13],"on":[14],"applications.":[16],"For":[17,34],"applications":[19],"with":[20,121],"large":[21],"data":[22,95],"inputs,":[23],"memory":[24,35,51,77,92,107,113],"frequently":[26],"take":[27],"much":[28],"longer":[29],"than":[30],"kernel":[31],"execution":[32],"time.":[33],"transfer":[36,52,108,114],"mechanism":[37,42],"for":[38],"unpinned":[39],"pages,":[40],"current":[41,67,111],"in":[43,65,90,115,126],"CUDA":[44,68,112],"library":[45],"fails":[46],"achieve":[48],"the":[49,66,87,94,106],"maximum":[50],"potential.":[53],"bandwidth":[55,89],"discrepancy":[56],"not":[62],"properly":[63],"considered":[64],"library.":[69],"In":[70],"our":[71],"work,":[72],"we":[73],"propose":[74],"a":[75,127],"multithreaded":[76],"copy":[78],"technique":[79,104],"that":[80],"uses":[81],"double":[82],"queuing":[83],"fully":[85],"utilize":[86],"PCIe":[88],"during":[93],"device.":[102],"Our":[103],"doubles":[105],"rate":[109],"of":[110],"cudaMemcpy()":[116],"by":[117],"allowing":[118],"multiple":[119],"different":[122],"bandwidths":[123],"operate":[125],"balanced":[128],"manner.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}