{"id":"https://openalex.org/W2883965613","doi":"https://doi.org/10.1145/3203217.3203243","title":"Taming irregular applications via advanced dynamic parallelism on GPUs","display_name":"Taming irregular applications via advanced dynamic parallelism on GPUs","publication_year":2018,"publication_date":"2018-05-08","ids":{"openalex":"https://openalex.org/W2883965613","doi":"https://doi.org/10.1145/3203217.3203243","mag":"2883965613"},"language":"en","primary_location":{"id":"doi:10.1145/3203217.3203243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3203217.3203243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Computing Frontiers","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/A5100345360","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-0553-3557"},"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":"Jing Zhang","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/A5091417392","display_name":"Ashwin M. Aji","orcid":"https://orcid.org/0000-0002-5467-8357"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Ashwin M. Aji","raw_affiliation_strings":["AMD Research Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008855369","display_name":"Michael Chu","orcid":"https://orcid.org/0009-0005-0849-9293"},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Michael L. Chu","raw_affiliation_strings":["AMD Research Advanced Micro Devices, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMD Research Advanced Micro Devices, Inc","institution_ids":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080102032","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-7594-7387"},"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":"Hao Wang","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"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":"Wu-chun Feng","raw_affiliation_strings":["Virginia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7625,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84493227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.994700014591217,"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":0.8426167964935303},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7971415519714355},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7870222330093384},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7538906335830688},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.7357577085494995},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7259514927864075},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5939158797264099},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4285208582878113},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.41015028953552246},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37705492973327637},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3311637043952942},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22061866521835327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8426167964935303},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7971415519714355},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7870222330093384},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7538906335830688},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.7357577085494995},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7259514927864075},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5939158797264099},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4285208582878113},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.41015028953552246},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37705492973327637},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3311637043952942},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22061866521835327},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3203217.3203243","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3203217.3203243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1554944419","https://openalex.org/W1997162567","https://openalex.org/W2009858916","https://openalex.org/W2029940394","https://openalex.org/W2038666141","https://openalex.org/W2047060659","https://openalex.org/W2061672277","https://openalex.org/W2090278477","https://openalex.org/W2091973955","https://openalex.org/W2122297544","https://openalex.org/W2123440268","https://openalex.org/W2130336316","https://openalex.org/W2143700077","https://openalex.org/W2152513418","https://openalex.org/W2153190325","https://openalex.org/W2171033594","https://openalex.org/W2186072464","https://openalex.org/W2238700765","https://openalex.org/W2260499435","https://openalex.org/W2411480360","https://openalex.org/W2422616509","https://openalex.org/W2474844316","https://openalex.org/W2475875537","https://openalex.org/W2480662436","https://openalex.org/W2511683765","https://openalex.org/W2567317362","https://openalex.org/W2621889996","https://openalex.org/W2728563803","https://openalex.org/W2911964244","https://openalex.org/W4231529766","https://openalex.org/W4242867698","https://openalex.org/W4255962840","https://openalex.org/W6681132279"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W3170887803","https://openalex.org/W74409296","https://openalex.org/W3209384898","https://openalex.org/W4400951174","https://openalex.org/W1595834484","https://openalex.org/W1991844655"],"abstract_inverted_index":{"On":[0],"recent":[1],"GPU":[2,14,39],"architectures,":[3],"dynamic":[4,44],"parallelism,":[5],"which":[6],"enables":[7],"the":[8,13,23,68,73,87],"launching":[9],"of":[10,25,89],"kernels":[11,31,93],"from":[12],"without":[15],"CPU":[16],"involvement,":[17],"provides":[18],"a":[19,95],"way":[20],"to":[21,33,51,80,91],"improve":[22,38,48],"performance":[24,49,97],"irregular":[26],"applications":[27],"by":[28],"generating":[29],"child":[30,58,92],"dynamically":[32],"reduce":[34],"workload":[35],"imbalance":[36],"and":[37,56,83],"utilization.":[40],"However,":[41],"in":[42],"practice,":[43],"parallelism":[45],"does":[46],"not":[47],"due":[50,79],"high":[52],"kernel":[53,59,69,74],"launch":[54,70,75],"overhead":[55,76],"low":[57],"occupancy.":[60],"Consequently,":[61],"most":[62],"existing":[63],"studies":[64],"focus":[65],"on":[66],"mitigating":[67],"overhead.":[71],"As":[72],"has":[77],"decreased":[78],"algorithmic":[81],"redesigns":[82],"hardware":[84],"architectural":[85],"innovations,":[86],"organization":[88],"subtasks":[90],"becomes":[94],"new":[96],"bottleneck.":[98]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}