{"id":"https://openalex.org/W2343940989","doi":"https://doi.org/10.1145/2927964.2927972","title":"A Transfer-Aware Runtime System for Heterogeneous Asynchronous Parallel Execution","display_name":"A Transfer-Aware Runtime System for Heterogeneous Asynchronous Parallel Execution","publication_year":2016,"publication_date":"2016-04-22","ids":{"openalex":"https://openalex.org/W2343940989","doi":"https://doi.org/10.1145/2927964.2927972","mag":"2343940989"},"language":"en","primary_location":{"id":"doi:10.1145/2927964.2927972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2927964.2927972","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","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/A5007030057","display_name":"Soukaina N. Hmid","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Soukaina N. Hmid","raw_affiliation_strings":["Imperial College London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103260538","display_name":"Jos\u00e9 G. F. Coutinho","orcid":"https://orcid.org/0000-0003-4138-3709"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jose G.F. Coutinho","raw_affiliation_strings":["Imperial College London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057940557","display_name":"Wayne Luk","orcid":"https://orcid.org/0000-0002-6750-927X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wayne Luk","raw_affiliation_strings":["Imperial College London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.6248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65555764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"43","issue":"4","first_page":"40","last_page":"45"},"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":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","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":0.8896993398666382},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6817870140075684},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.6645503044128418},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6373705267906189},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5253103375434875},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48233339190483093},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45527878403663635},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4450478255748749},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.43691834807395935},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4209161698818207},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32392874360084534},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11266511678695679},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1002899706363678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8896993398666382},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6817870140075684},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.6645503044128418},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6373705267906189},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5253103375434875},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48233339190483093},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45527878403663635},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4450478255748749},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.43691834807395935},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4209161698818207},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32392874360084534},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11266511678695679},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1002899706363678},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2927964.2927972","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2927964.2927972","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2054786475","https://openalex.org/W2109426995","https://openalex.org/W2121893797","https://openalex.org/W2127844926","https://openalex.org/W2142677441","https://openalex.org/W2159153788","https://openalex.org/W2162979096"],"related_works":["https://openalex.org/W2403987929","https://openalex.org/W2039814159","https://openalex.org/W2374847384","https://openalex.org/W2063512590","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2107649022","https://openalex.org/W2356488190","https://openalex.org/W2966537581","https://openalex.org/W3012895752"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,24],"novel":[4],"resource":[5],"management":[6],"approach":[7,28,60,111],"for":[8,35,119,142],"efficiently":[9],"managing":[10],"the":[11,14,18,89,109,129,139],"computation":[12],"and":[13,20,39,55,104],"data":[15,50,52,56],"movements":[16],"between":[17],"host":[19],"its":[21],"accelerators":[22],"in":[23],"heterogeneous":[25],"platform.":[26],"Our":[27],"is":[29,61,86,132],"based":[30,44],"on":[31,45],"OmpSs,":[32],"with":[33,69,125],"support":[34],"multi-core":[36],"CPUs,":[37],"GPGPUs":[38],"Maxeler":[40],"Data":[41],"Flow":[42],"Engines":[43],"FPGA":[46,130],"technology;":[47],"it":[48],"exploits":[49],"locality,":[51],"transfer":[53],"costs":[54],"dependencies.":[57],"The":[58,106],"proposed":[59,110],"supported":[62],"by":[63],"an":[64,123],"offline":[65],"learning":[66,78],"process":[67],"coupled":[68],"online":[70],"monitoring,":[71],"allowing":[72],"performance":[73,85],"to":[74,115,134],"be":[75],"estimated":[76],"while":[77],"from":[79],"past":[80],"observations":[81],"during":[82],"execution.":[83],"Its":[84],"compared":[87],"against":[88],"current":[90],"OmpSs":[91],"scheduler":[92],"using":[93],"five":[94],"benchmarks:":[95],"matrix":[96],"multiplication,":[97],"bitonic":[98],"sort,":[99],"N-body":[100],"simulation,":[101],"Cholesky":[102,120],"decomposition":[103],"AdPredictor.":[105],"results":[107],"show":[108],"can":[112],"achieve":[113],"up":[114,133],"4.25":[116],"times":[117,136],"speed-up":[118],"decomposition.":[121],"Moreover,":[122],"evaluation":[124],"AdPredictor":[126],"indicates":[127],"that":[128],"version":[131,141],"46":[135],"faster":[137],"than":[138],"CPU":[140],"large":[143],"task":[144],"sizes.":[145]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}