{"id":"https://openalex.org/W2322798958","doi":"https://doi.org/10.1145/2884045.2884052","title":"Implementing directed acyclic graphs with the heterogeneous system architecture","display_name":"Implementing directed acyclic graphs with the heterogeneous system architecture","publication_year":2016,"publication_date":"2016-03-04","ids":{"openalex":"https://openalex.org/W2322798958","doi":"https://doi.org/10.1145/2884045.2884052","mag":"2322798958"},"language":"en","primary_location":{"id":"doi:10.1145/2884045.2884052","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884045.2884052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Annual Workshop on General Purpose Processing using Graphics Processing Unit","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024878606","display_name":"Sooraj Puthoor","orcid":"https://orcid.org/0000-0003-0285-5742"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sooraj Puthoor","raw_affiliation_strings":["AMD Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091417392","display_name":"Ashwin M. Aji","orcid":"https://orcid.org/0000-0002-5467-8357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashwin M. Aji","raw_affiliation_strings":["AMD Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018356320","display_name":"Shuai Che","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Che","raw_affiliation_strings":["AMD Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081713520","display_name":"Mayank Daga","orcid":"https://orcid.org/0000-0002-2637-302X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mayank Daga","raw_affiliation_strings":["AMD Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027254893","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-2750-6365"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["The University of Tennessee, Knoxville"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tennessee, Knoxville","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077056823","display_name":"Bradford M. Beckmann","orcid":"https://orcid.org/0000-0002-5444-6521"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bradford M. Beckmann","raw_affiliation_strings":["AMD Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073649394","display_name":"Gregory Rodgers","orcid":"https://orcid.org/0009-0007-3549-8135"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gregory Rodgers","raw_affiliation_strings":["AMD Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4654,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88919396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.8813329339027405},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.8134438991546631},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7360001802444458},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6225993633270264},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5868421792984009},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5025177001953125},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5021300315856934},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.45349204540252686},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.44633516669273376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43586400151252747},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42879438400268555},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.41799771785736084},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.4156857430934906},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32503455877304077},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2620401382446289},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24522143602371216},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21340566873550415},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.18076834082603455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8813329339027405},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.8134438991546631},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7360001802444458},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6225993633270264},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5868421792984009},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5025177001953125},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5021300315856934},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.45349204540252686},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.44633516669273376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43586400151252747},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42879438400268555},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.41799771785736084},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.4156857430934906},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32503455877304077},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2620401382446289},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24522143602371216},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21340566873550415},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.18076834082603455},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2884045.2884052","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2884045.2884052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Annual Workshop on General Purpose Processing using Graphics Processing Unit","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W180452353","https://openalex.org/W337664247","https://openalex.org/W817236362","https://openalex.org/W1480928214","https://openalex.org/W1485346187","https://openalex.org/W1531079003","https://openalex.org/W1558138778","https://openalex.org/W1589508078","https://openalex.org/W1981534910","https://openalex.org/W1984848758","https://openalex.org/W2016279572","https://openalex.org/W2016706026","https://openalex.org/W2020165759","https://openalex.org/W2025516544","https://openalex.org/W2036551003","https://openalex.org/W2045271686","https://openalex.org/W2072725684","https://openalex.org/W2074231493","https://openalex.org/W2080592089","https://openalex.org/W2104861744","https://openalex.org/W2121893797","https://openalex.org/W2171399035","https://openalex.org/W2279353332","https://openalex.org/W2464859674","https://openalex.org/W2914767399","https://openalex.org/W7028799193"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W2072751097","https://openalex.org/W2015567081","https://openalex.org/W4237177615","https://openalex.org/W4225773259"],"abstract_inverted_index":{"Achieving":[0],"optimal":[1],"performance":[2],"on":[3],"heterogeneous":[4],"computing":[5],"systems":[6],"requires":[7],"a":[8,22,42],"programming":[9,32],"model":[10,33],"that":[11,34],"supports":[12],"the":[13,36,53,76],"execution":[14],"of":[15,57],"asynchronous,":[16],"multi-stream,":[17],"and":[18,47,93,101],"out-of-order":[19],"tasks":[20],"in":[21],"shared":[23],"memory":[24],"environment.":[25],"Asynchronous":[26],"dependency-driven":[27],"tasking":[28],"is":[29],"one":[30],"such":[31,86],"allows":[35],"computation":[37],"to":[38,52,59,65,75,96],"be":[39],"expressed":[40],"as":[41,87],"directed":[43],"acyclic":[44],"graph":[45],"(DAG)":[46],"exposes":[48],"fine-grain":[49],"task":[50,89,99],"management":[51],"programmer.":[54],"The":[55],"use":[56],"DAGs":[58],"extract":[60],"parallelism":[61],"also":[62],"enables":[63],"runtimes":[64],"perform":[66],"dynamic":[67],"load-balancing,":[68],"thereby":[69],"achieving":[70],"higher":[71],"throughput":[72],"when":[73],"compared":[74],"traditional":[77],"bulk-synchronous":[78],"execution.":[79],"However,":[80],"efficient":[81],"DAG":[82],"implementations":[83],"require":[84],"features":[85],"user-level":[88],"dispatch,":[90],"hardware":[91],"signalling":[92],"local":[94],"barriers":[95],"achieve":[97],"low-overhead":[98],"dispatch":[100],"dependency":[102],"resolution.":[103]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}