{"id":"https://openalex.org/W2092743535","doi":"https://doi.org/10.1145/2370816.2370877","title":"Acceleration of bulk memory operations in a heterogeneous multicore architecture","display_name":"Acceleration of bulk memory operations in a heterogeneous multicore architecture","publication_year":2012,"publication_date":"2012-09-19","ids":{"openalex":"https://openalex.org/W2092743535","doi":"https://doi.org/10.1145/2370816.2370877","mag":"2092743535"},"language":"en","primary_location":{"id":"doi:10.1145/2370816.2370877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2370816.2370877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on Parallel architectures and compilation techniques","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/A5100638004","display_name":"Jonghyuk Lee","orcid":"https://orcid.org/0000-0002-8163-9388"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"JongHyuk Lee","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383205","display_name":"Ziyi Liu","orcid":"https://orcid.org/0000-0002-2468-3104"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyi Liu","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051505683","display_name":"Xiaonan Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaonan Tian","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037812225","display_name":"Dong Hyuk Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Hyuk Woo","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109410921","display_name":"Weidong Shi","orcid":"https://orcid.org/0000-0002-9005-3071"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weidong Shi","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088219189","display_name":"Dainis Boumber","orcid":"https://orcid.org/0000-0001-9052-1202"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dainis Boumber","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102715061","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0002-5274-8526"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001790978","display_name":"Kyeong-An Kwon","orcid":"https://orcid.org/0000-0001-6406-6197"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyeong-An Kwon","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.1557324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"424"},"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":0.9990000128746033,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8507869243621826},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8019121885299683},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6571878790855408},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6492676734924316},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6237457990646362},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.5993573665618896},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5091044306755066},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.5005581378936768},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.4859951436519623},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4294186234474182},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.41069650650024414},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3339003920555115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507869243621826},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8019121885299683},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6571878790855408},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6492676734924316},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6237457990646362},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.5993573665618896},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5091044306755066},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.5005581378936768},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.4859951436519623},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4294186234474182},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.41069650650024414},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3339003920555115},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2370816.2370877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2370816.2370877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2120635877","https://openalex.org/W2164333604"],"related_works":["https://openalex.org/W3012895752","https://openalex.org/W2473478803","https://openalex.org/W2167303720","https://openalex.org/W2497617944","https://openalex.org/W1563139915","https://openalex.org/W2729363167","https://openalex.org/W2109715593","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W2268996566"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,161],"novel":[6],"approach":[7,117],"of":[8,181],"using":[9,109,152],"the":[10,22,24,34,39,45,50,53,65,68,70,78,86,106,119,168,182],"integrated":[11],"GPU":[12,40,48,60,66,71,121],"to":[13,38,144],"accelerate":[14],"conventional":[15],"operations":[16,37,140],"that":[17,136],"are":[18],"normally":[19],"performed":[20],"by":[21,77],"CPUs,":[23],"bulk":[25,35,54,138],"memory":[26,36,55,139],"operations,":[27],"such":[28],"as":[29,100,124,126],"memcpy":[30],"or":[31],"memset.":[32],"Offloading":[33],"has":[41],"many":[42],"advantages,":[43],"i)":[44],"throughput":[46],"driven":[47],"outperforms":[49],"CPU":[51,79,87,142],"on":[52,132],"operations;":[56],"ii)":[57],"for":[58,80,173,179],"on-die":[59],"with":[61,91],"unified":[62],"cache":[63,88],"between":[64],"and":[67,84,102,160],"CPU,":[69],"private":[72],"caches":[73],"can":[74,97],"be":[75,98],"leveraged":[76],"storing":[81],"moved":[82],"data":[83],"reducing":[85],"bottleneck;":[89],"iii)":[90],"additional":[92],"lightweight":[93],"hardware,":[94],"asynchronous":[95],"offload":[96],"supported":[99],"well;":[101],"iv)":[103],"different":[104],"from":[105],"prior":[107],"arts":[108],"dedicated":[110],"hardware":[111,122],"copy":[112],"engines":[113],"(e.g.,":[114],"DMA),":[115],"our":[116,133],"leverages":[118],"exiting":[120],"resources":[123],"much":[125],"possible.":[127],"The":[128],"performance":[129],"results":[130,169],"based":[131,163],"solution":[134],"showed":[135,170],"offloaded":[137],"outperform":[141],"up":[143],"4.3":[145],"times":[146],"in":[147],"micro":[148],"benchmarks":[149],"while":[150],"still":[151],"less":[153],"resources.":[154],"Using":[155],"eight":[156,183],"real":[157],"world":[158],"applications":[159],"cycle":[162],"full":[164],"system":[165],"simulation":[166],"environment,":[167],"30%":[171],"speedup":[172,178],"five,":[174],"more":[175],"than":[176],"20%":[177],"two":[180],"applications.":[184]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
