{"id":"https://openalex.org/W4226469047","doi":"https://doi.org/10.1145/3505224","title":"An OpenMP Runtime for Transparent Work Sharing across Cache-Incoherent Heterogeneous Nodes","display_name":"An OpenMP Runtime for Transparent Work Sharing across Cache-Incoherent Heterogeneous Nodes","publication_year":2021,"publication_date":"2021-11-30","ids":{"openalex":"https://openalex.org/W4226469047","doi":"https://doi.org/10.1145/3505224"},"language":"en","primary_location":{"id":"doi:10.1145/3505224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3505224","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3505224","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3505224","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089319989","display_name":"Robert Lyerly","orcid":"https://orcid.org/0000-0001-9452-2958"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Lyerly","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031026926","display_name":"Carlos Bilbao","orcid":"https://orcid.org/0000-0002-4750-5124"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Bilbao","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":"https://orcid.org/0000-0002-4750-5124","affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001805471","display_name":"Changwoo Min","orcid":"https://orcid.org/0000-0001-6225-5357"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changwoo Min","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003307688","display_name":"Christopher J. Rossbach","orcid":"https://orcid.org/0000-0003-0329-3657"},"institutions":[{"id":"https://openalex.org/I74786994","display_name":"Kitware (United States)","ror":"https://ror.org/02s2acn37","country_code":"US","type":"company","lineage":["https://openalex.org/I74786994"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J. Rossbach","raw_affiliation_strings":["University of Texas at Austin and VMware Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin and VMware Research","institution_ids":["https://openalex.org/I74786994","https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067528153","display_name":"Binoy Ravindran","orcid":"https://orcid.org/0000-0002-8663-739X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binoy Ravindran","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4597,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66115214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"39","issue":"1-4","first_page":"1","last_page":"30"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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":0.9141576886177063},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8197816610336304},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8043386936187744},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5915123820304871},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5417711138725281},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5298813581466675},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5099993944168091},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.4764297902584076},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.44392481446266174},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.4244045317173004},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4033566117286682},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37752971053123474},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.375765323638916},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22608041763305664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13308808207511902},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.1055564284324646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9141576886177063},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8197816610336304},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8043386936187744},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5915123820304871},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5417711138725281},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5298813581466675},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5099993944168091},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.4764297902584076},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.44392481446266174},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.4244045317173004},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4033566117286682},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37752971053123474},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.375765323638916},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22608041763305664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13308808207511902},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.1055564284324646},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3505224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3505224","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3505224","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"}],"best_oa_location":{"id":"doi:10.1145/3505224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3505224","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3505224","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2295858120","display_name":null,"funder_award_id":"N00174-16-C-0018","funder_id":"https://openalex.org/F4320337644","funder_display_name":"Naval Sea Systems Command"},{"id":"https://openalex.org/G5090099226","display_name":null,"funder_award_id":"N00014-16-1-2711","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6382424048","display_name":null,"funder_award_id":"N00014-16-1-2711, N00014-16-1-2104, and N00014-18-1-2022","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6991968366","display_name":null,"funder_award_id":"N00014-18-1-2022","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8833138034","display_name":null,"funder_award_id":"N00014-16-1-2104","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320337644","display_name":"Naval Sea Systems Command","ror":"https://ror.org/03dm1p143"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4226469047.pdf","grobid_xml":"https://content.openalex.org/works/W4226469047.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W8143453","https://openalex.org/W35708471","https://openalex.org/W55478891","https://openalex.org/W1805440014","https://openalex.org/W1971391208","https://openalex.org/W1972995899","https://openalex.org/W1974264097","https://openalex.org/W2006312753","https://openalex.org/W2008558305","https://openalex.org/W2016357834","https://openalex.org/W2024206369","https://openalex.org/W2028069406","https://openalex.org/W2063799188","https://openalex.org/W2080592089","https://openalex.org/W2103265820","https://openalex.org/W2104008467","https://openalex.org/W2104861744","https://openalex.org/W2109065830","https://openalex.org/W2109360947","https://openalex.org/W2110653637","https://openalex.org/W2112121929","https://openalex.org/W2138180780","https://openalex.org/W2150476673","https://openalex.org/W2289231618","https://openalex.org/W2418688212","https://openalex.org/W2499905000","https://openalex.org/W2542250562","https://openalex.org/W2604468014","https://openalex.org/W2751343396","https://openalex.org/W2770722083","https://openalex.org/W2786356702","https://openalex.org/W2890345807","https://openalex.org/W2917155694","https://openalex.org/W3111402464","https://openalex.org/W4230802661"],"related_works":["https://openalex.org/W2145592252","https://openalex.org/W2407815036","https://openalex.org/W4255008187","https://openalex.org/W4250205214","https://openalex.org/W2036306661","https://openalex.org/W2143087414","https://openalex.org/W1797968800","https://openalex.org/W2105141138","https://openalex.org/W3216777841","https://openalex.org/W316086898"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,166],"present":[4],"libHetMP":[5,20,74,135,168],",":[6],"an":[7],"OpenMP":[8,141],"runtime":[9],"for":[10,185],"automatically":[11],"and":[12,41,71,101,144],"transparently":[13],"distributing":[14],"parallel":[15],"computation":[16],"across":[17,52,154],"heterogeneous":[18],"nodes.":[19],"targets":[21],"platforms":[22],"comprising":[23],"CPUs":[24,70,111,124],"with":[25,169],"different":[26],"instruction":[27],"set":[28,121],"architectures":[29],"(ISA)":[30],"coupled":[31],"by":[32,82,195],"a":[33,146,170,193],"high-speed":[34],"memory":[35],"interconnect,":[36],"where":[37],"cross-ISA":[38],"binary":[39],"incompatibility":[40],"non-coherent":[42],"caches":[43],"require":[44],"application":[45],"data":[46],"be":[47,50],"marshaled":[48],"to":[49,106,192],"shared":[51],"CPUs.":[53,156],"Because":[54,157],"of":[55,68,110,122,177],"this,":[56],"work":[57,104,118],"distribution":[58,77,198],"decisions":[59,78],"must":[60],"take":[61],"into":[62],"account":[63],"both":[64],"relative":[65,108],"compute":[66,137],"performance":[67,84,109,128],"asymmetric":[69,155],"communication":[72],"overheads.":[73],"drives":[75],"workload":[76],"without":[79],"programmer":[80],"intervention":[81],"measuring":[83],"characteristics":[85],"during":[86],"cross-node":[87,97],"execution.":[88],"A":[89],"novel":[90],"HetProbe":[91],"loop":[92],"iteration":[93],"scheduler":[94,172],"decides":[95],"if":[96],"execution":[98,152],"is":[99,114,131],"beneficial":[100],"either":[102],"distributes":[103],"according":[105],"the":[107,120,126],"when":[112,129],"it":[113,130,180],"or":[115],"places":[116],"all":[117],"on":[119],"homogeneous":[123],"providing":[125],"best":[127],"not.":[132],"We":[133],"evaluate":[134],"using":[136],"kernels":[138],"from":[139],"several":[140],"benchmark":[142],"suites":[143],"show":[145],"geometric":[147],"mean":[148],"41%":[149],"speedup":[150,184],"in":[151,188],"time":[153],"some":[158,189],"workloads":[159],"may":[160],"showcase":[161],"irregular":[162,186],"behavior":[163],"among":[164],"iterations,":[165],"extend":[167],"second":[171],"called":[173],"HetProbe-I.":[174],"The":[175],"evaluation":[176],"HetProbe-I":[178],"shows":[179],"can":[181],"further":[182],"improve":[183],"computation,":[187],"cases":[190],"up":[191],"24%,":[194],"triggering":[196],"periodic":[197],"decisions.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}