{"id":"https://openalex.org/W1987773847","doi":"https://doi.org/10.1145/2798725","title":"SKMD","display_name":"SKMD","publication_year":2015,"publication_date":"2015-08-31","ids":{"openalex":"https://openalex.org/W1987773847","doi":"https://doi.org/10.1145/2798725","mag":"1987773847"},"language":"en","primary_location":{"id":"doi:10.1145/2798725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2798725","pdf_url":null,"source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computer Systems","raw_type":"journal-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/A5065946847","display_name":"Janghaeng Lee","orcid":"https://orcid.org/0009-0005-1915-6077"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Janghaeng Lee","raw_affiliation_strings":["University of Michigan, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058642630","display_name":"Mehrzad Samadi","orcid":"https://orcid.org/0000-0002-3581-1255"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehrzad Samadi","raw_affiliation_strings":["University of Michigan, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I94588446","display_name":"Hongik University","ror":"https://ror.org/00egdv862","country_code":"KR","type":"education","lineage":["https://openalex.org/I94588446"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["Hongik University, Seoul, Korea","Hongik University , Seoul , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hongik University, Seoul, Korea","institution_ids":["https://openalex.org/I94588446"]},{"raw_affiliation_string":"Hongik University , Seoul , Korea","institution_ids":["https://openalex.org/I94588446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["University of Michigan, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1934,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.94000178,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"33","issue":"3","first_page":"1","last_page":"27"},"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":0.9994000196456909,"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":0.9988999962806702,"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":0.9085342884063721},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7134957313537598},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6750497221946716},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6369214057922363},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5446301698684692},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5365903377532959},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4815957248210907},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.47054606676101685},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3012092709541321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9085342884063721},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7134957313537598},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6750497221946716},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6369214057922363},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5446301698684692},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5365903377532959},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4815957248210907},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.47054606676101685},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3012092709541321},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2798725","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2798725","pdf_url":null,"source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computer Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.hanyang.ac.kr:20.500.11754/27542","is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=2798725","pdf_url":null,"source":{"id":"https://openalex.org/S4306401328","display_name":"The Royal Society of Chemistry\u2019s Journals, Books and Databases (The Royal Society of Chemistry)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2751430930","host_organization_name":"Royal Society of Chemistry","host_organization_lineage":["https://openalex.org/I2751430930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W45362603","https://openalex.org/W1502558230","https://openalex.org/W1651324627","https://openalex.org/W1843198456","https://openalex.org/W1966344015","https://openalex.org/W1987753170","https://openalex.org/W1996092188","https://openalex.org/W2011039300","https://openalex.org/W2024122052","https://openalex.org/W2028914809","https://openalex.org/W2040501492","https://openalex.org/W2056816375","https://openalex.org/W2098688018","https://openalex.org/W2102777365","https://openalex.org/W2108591264","https://openalex.org/W2109426995","https://openalex.org/W2109515201","https://openalex.org/W2112340065","https://openalex.org/W2128046183","https://openalex.org/W2130179171","https://openalex.org/W2140375692","https://openalex.org/W2146757372","https://openalex.org/W2147654959","https://openalex.org/W2149706766","https://openalex.org/W2150476673","https://openalex.org/W2152513418","https://openalex.org/W2153185479","https://openalex.org/W2153375074","https://openalex.org/W2159456929","https://openalex.org/W2159481344","https://openalex.org/W2167101788","https://openalex.org/W2167334577","https://openalex.org/W2169880332","https://openalex.org/W2751343396","https://openalex.org/W4250518453"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W3012895752","https://openalex.org/W3000570965","https://openalex.org/W2473478803","https://openalex.org/W2729363167","https://openalex.org/W2060611139"],"abstract_inverted_index":{"Heterogeneous":[0],"computing":[1],"on":[2,83,91,214],"CPUs":[3,77,126],"and":[4,66,127,161,193,221],"GPUs":[5,82,197,224],"has":[6,58],"traditionally":[7],"used":[8],"fixed":[9,93],"roles":[10,94],"for":[11,133,232],"each":[12],"device:":[13],"the":[14,30,38,56,62,92,105,142,146,158,164,181,185,194],"GPU":[15],"handles":[16,32,184],"data":[17,42,190],"parallel":[18],"work":[19,46,89],"by":[20,173],"taking":[21],"advantage":[22],"of":[23,27,72,118,152,188,212,235],"its":[24],"massive":[25],"number":[26],"cores":[28],"while":[29,141],"CPU":[31,220],"non":[33],"data-parallel":[34,121,137],"work,":[35],"such":[36],"as":[37,53],"sequential":[39],"code":[40],"or":[41],"transfer":[43,191],"management.":[44],"This":[45],"distribution":[47],"can":[48],"be":[49,96],"a":[50,69,97,111,119,135,215,227,233],"poor":[51,98],"solution":[52],"it":[54],"underutilizes":[55],"CPU,":[57],"difficulty":[59],"generalizing":[60],"beyond":[61],"single":[63,120,136],"CPU-GPU":[64],"combination,":[65],"may":[67,95],"waste":[68],"large":[70],"fraction":[71],"time":[73],"transferring":[74],"data.":[75],"Further,":[76],"are":[78],"performance":[79,171,195],"competitive":[80],"with":[81,199,217],"many":[84],"workloads,":[85,160],"thus":[86],"simply":[87],"partitioning":[88],"based":[90],"choice.":[99],"In":[100],"this":[101],"article,":[102],"we":[103],"present":[104],"single-kernel":[106],"multiple":[107,124],"devices":[108],"(SKMD)":[109],"system,":[110],"framework":[112],"that":[113],"transparently":[114],"orchestrates":[115],"collaborative":[116],"execution":[117,230],"kernel":[122,138],"across":[123,148],"asymmetric":[125,223],"GPUs.":[128],"The":[129,168],"programmer":[130],"is":[131,170],"responsible":[132],"developing":[134],"in":[139],"OpenCL,":[140],"system":[143,216],"automatically":[144],"partitions":[145],"workload":[147],"an":[149,209],"arbitrary":[150],"set":[151,234],"devices,":[153],"generates":[154],"kernels":[155],"to":[156,179,201,226],"execute":[157,180],"partial":[159,165],"efficiently":[162],"merges":[163],"outputs":[166],"together.":[167],"goal":[169],"improvement":[172],"maximally":[174],"utilizing":[175],"all":[176],"available":[177],"resources":[178],"kernel.":[182],"SKMD":[183,207],"difficult":[186],"challenges":[187],"exposed":[189],"costs":[192],"variations":[196],"have":[198],"respect":[200],"input":[202],"size.":[203],"On":[204],"real":[205],"hardware,":[206],"achieves":[208],"average":[210],"speedup":[211],"28%":[213],"one":[218],"multicore":[219],"two":[222],"compared":[225],"fastest":[228],"device":[229],"strategy":[231],"popular":[236],"OpenCL":[237],"kernels.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}
