{"id":"https://openalex.org/W2574462121","doi":"https://doi.org/10.3233/978-1-61499-621-7-683","title":"Using Task-Based Parallelism Directly on the GPU for Automated Asynchronous Data Transfer","display_name":"Using Task-Based Parallelism Directly on the GPU for Automated Asynchronous Data Transfer","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2574462121","doi":"https://doi.org/10.3233/978-1-61499-621-7-683","mag":"2574462121"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-621-7-683","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-621-7-683","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},"type":"book-chapter","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/A5008678823","display_name":"Aidan B. G. Chalk","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Chalk Aidan B.G.","raw_affiliation_strings":["Durham University, Durham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University, Durham, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043020378","display_name":"Pedro Gonnet","orcid":"https://orcid.org/0000-0003-4509-7291"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gonnet Pedro","raw_affiliation_strings":["Durham University, Durham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University, Durham, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059148355","display_name":"Matthieu Schaller","orcid":"https://orcid.org/0000-0002-2395-4902"},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Schaller Matthieu","raw_affiliation_strings":["Durham University, Durham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Durham University, Durham, United Kingdom","institution_ids":["https://openalex.org/I190082696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008678823"],"corresponding_institution_ids":["https://openalex.org/I190082696"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2891791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"683","last_page":"696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9661999940872192,"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":0.9661999940872192,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9545999765396118,"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":0.8204967975616455},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7601326704025269},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7422002553939819},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6801967024803162},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.6676468253135681},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5751455426216125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5692113041877747},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.44943228363990784},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0413612425327301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204967975616455},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7601326704025269},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7422002553939819},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6801967024803162},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.6676468253135681},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5751455426216125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5692113041877747},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.44943228363990784},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0413612425327301},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-621-7-683","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-621-7-683","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},{"id":"mag:2574462121","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/parco/parco2015.html#ChalkGS15","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Parallel Computing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W2468095077","https://openalex.org/W29548032","https://openalex.org/W2593878938","https://openalex.org/W305742777"],"abstract_inverted_index":{"We":[0,86],"present":[1],"a":[2,31,88,92,127,141],"framework,":[3],"based":[4],"on":[5,16,132],"the":[6,56,73,76,104,116,119],"QuickSched":[7],"[1]":[8],"library,":[9],"that":[10,40,123],"implements":[11],"priority-aware":[12],"task-based":[13,105,124],"parallelism":[14,125],"directly":[15],"CUDA":[17],"GPUs.":[18],"This":[19,121],"allows":[20],"large":[21],"computations":[22],"with":[23],"complex":[24],"data":[25,51,84,113,142],"dependencies":[26],"to":[27,53,112],"be":[28,43],"executed":[29,71],"in":[30],"single":[32],"GPU":[33,57,117],"kernel":[34,46],"call,":[35],"removing":[36],"any":[37,109],"synchronization":[38],"points":[39],"might":[41],"otherwise":[42],"required":[44],"between":[45,115],"calls.":[47],"Using":[48],"this":[49],"paradigm,":[50],"transfers":[52,114],"and":[54,62,70,82,91,118,134,144],"from":[55,139],"are":[58,67],"modelled":[59],"as":[60],"load":[61],"unload":[63],"tasks.":[64],"These":[65],"tasks":[66],"automatically":[68],"generated":[69],"alongside":[72],"rest":[74],"of":[75,97],"computational":[77],"tasks,":[78],"allowing":[79],"fully":[80],"asynchronous":[81],"concurrent":[83],"transfers.":[85],"implemented":[87],"tiled-QR":[89],"decomposition,":[90],"Barnes-Hut":[93],"gravity":[94],"calculation,":[95],"both":[96,140],"which":[98],"show":[99],"significant":[100,137],"improvement":[101],"when":[102],"utilising":[103],"setup,":[106],"effectively":[107],"eliminating":[108],"latencies":[110],"due":[111],"CPU.":[120],"shows":[122],"is":[126],"valid":[128],"alternative":[129],"programming":[130],"paradigm":[131],"GPUs,":[133],"can":[135],"provide":[136],"gains":[138],"transfer":[143],"ease-of-use":[145],"perspective.":[146]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2017-01-26T00:00:00"}