{"id":"https://openalex.org/W2952562588","doi":"https://doi.org/10.1145/3326124","title":"Coordinated CTA Combination and Bandwidth Partitioning for GPU Concurrent Kernel Execution","display_name":"Coordinated CTA Combination and Bandwidth Partitioning for GPU Concurrent Kernel Execution","publication_year":2019,"publication_date":"2019-06-17","ids":{"openalex":"https://openalex.org/W2952562588","doi":"https://doi.org/10.1145/3326124","mag":"2952562588"},"language":"en","primary_location":{"id":"doi:10.1145/3326124","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3326124","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3326124","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Architecture and Code Optimization","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/10.1145/3326124","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002035343","display_name":"Zhen Lin","orcid":"https://orcid.org/0000-0002-7131-0159"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Lin","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037376215","display_name":"Hongwen Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongwen Dai","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056016753","display_name":"Michael Mantor","orcid":null},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"Michael Mantor","raw_affiliation_strings":["Advanced Micro Devices, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Orlando, FL, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072755725","display_name":"Huiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyang Zhou","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002035343"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":1.4812,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81053031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"3","first_page":"1","last_page":"27"},"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/T10829","display_name":"Interconnection Networks and 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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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":0.8584100604057312},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.8060401678085327},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.7043269872665405},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6476456522941589},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5513866543769836},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5209209322929382},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.41002362966537476},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23798125982284546},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11520442366600037},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08110281825065613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8584100604057312},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.8060401678085327},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.7043269872665405},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6476456522941589},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5513866543769836},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5209209322929382},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41002362966537476},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23798125982284546},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11520442366600037},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08110281825065613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3326124","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3326124","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3326124","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3326124","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3326124","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3326124","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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 Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G1802226276","display_name":"SaTC: CORE: Small: Towards Smart and Secure Non Volatile Memory","funder_award_id":"1717550","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6994652891","display_name":null,"funder_award_id":"1618509","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952562588.pdf","grobid_xml":"https://content.openalex.org/works/W2952562588.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1890643295","https://openalex.org/W1968391520","https://openalex.org/W1993488239","https://openalex.org/W1994825940","https://openalex.org/W2028173051","https://openalex.org/W2038662769","https://openalex.org/W2061179133","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2098040113","https://openalex.org/W2100011668","https://openalex.org/W2102871765","https://openalex.org/W2121523570","https://openalex.org/W2128087858","https://openalex.org/W2129381159","https://openalex.org/W2130820665","https://openalex.org/W2130967222","https://openalex.org/W2140348470","https://openalex.org/W2143773524","https://openalex.org/W2159908132","https://openalex.org/W2163687928","https://openalex.org/W2166263440","https://openalex.org/W2238307037","https://openalex.org/W2323909431","https://openalex.org/W2412101011","https://openalex.org/W2604514113","https://openalex.org/W2605178034","https://openalex.org/W2618092901","https://openalex.org/W2625231790","https://openalex.org/W2791833900","https://openalex.org/W3112784795","https://openalex.org/W4210790398","https://openalex.org/W4234453167","https://openalex.org/W4234493895","https://openalex.org/W4242623795","https://openalex.org/W4244454515","https://openalex.org/W4253795537","https://openalex.org/W4254256063","https://openalex.org/W4255681033"],"related_works":["https://openalex.org/W3120961607","https://openalex.org/W3148568549","https://openalex.org/W2098207691","https://openalex.org/W2800626838","https://openalex.org/W2039378765","https://openalex.org/W1982351223","https://openalex.org/W2097757554","https://openalex.org/W2887282140","https://openalex.org/W2149537422","https://openalex.org/W2984139344"],"abstract_inverted_index":{"Contemporary":[0],"GPUs":[1],"support":[2],"multiple":[3],"kernels":[4,67,80,101,153,199],"to":[5,54,82,92,192,205,245,271],"run":[6],"concurrently":[7],"on":[8,37,275],"the":[9,33,39,43,50,133,162,172,234,246,266],"same":[10],"streaming":[11],"multiprocessors":[12],"(SMs).":[13],"Recent":[14],"studies":[15],"have":[16],"demonstrated":[17],"that":[18,75,119],"such":[19,120],"concurrent":[20],"kernel":[21],"execution":[22],"(CKE)":[23],"improves":[24,233,265],"both":[25,161,178],"resource":[26,216],"utilization":[27],"and":[28,61,131,145,165,200,228,240,273],"computational":[29],"throughput.":[30],"Most":[31],"of":[32,214],"prior":[34],"works":[35],"focus":[36],"partitioning":[38],"GPU":[40],"resources":[41,180,196,204],"at":[42],"cooperative":[44],"thread":[45],"array":[46],"(CTA)":[47],"level":[48,53],"or":[49,157],"warp":[51],"scheduler":[52],"improve":[55],"CKE.":[56],"However,":[57],"significant":[58],"performance":[59],"slowdown":[60],"unfairness":[62],"are":[63,252],"observed":[64],"when":[65],"latency-sensitive":[66,93,198],"co-run":[68],"with":[69,183,220],"bandwidth-intensive":[70,79,97],"ones.":[71,110],"The":[72,188],"reason":[73],"is":[74,89,191],"bandwidth":[76,107,146,158,164,169,179,203],"over-subscription":[77],"from":[78,254],"leads":[81],"much":[83,105],"aggravated":[84],"memory":[85],"access":[86],"latency,":[87],"which":[88,251],"highly":[90],"detrimental":[91],"kernels.":[94,207],"Even":[95,243],"among":[96,258],"kernels,":[98],"more":[99,194,201],"intensive":[100],"may":[102],"unfairly":[103],"consume":[104],"higher":[106],"than":[108],"less-intensive":[109],"In":[111],"this":[112],"article,":[113],"we":[114,137],"first":[115],"make":[116],"a":[117,139,212],"case":[118],"problems":[121],"cannot":[122],"be":[123,171],"sufficiently":[124],"solved":[125],"by":[126,238,269],"managing":[127],"CTA":[128,143,186,195,249,261],"combinations":[129],"alone":[130],"reveal":[132],"fundamental":[134],"reasons.":[135],"Then,":[136],"propose":[138],"coordinated":[140],"approach":[141,149,176,232,264],"for":[142,197],"combination":[144],"partitioning.":[147],"Our":[148],"dynamically":[150],"detects":[151],"co-running":[152],"as":[154],"latency":[155],"sensitive":[156],"intensive.":[159],"As":[160],"DRAM":[163],"L2-to-L1":[166],"Network-on-Chip":[167],"(NoC)":[168],"can":[170],"critical":[173],"resource,":[174],"our":[175,231,263],"partitions":[177],"coordinately":[181],"along":[182],"selecting":[184],"proper":[185],"combinations.":[187],"key":[189],"objective":[190],"allocate":[193],"NoC/DRAM":[202],"NoC-/DRAM-intensive":[206],"We":[208],"achieve":[209],"it":[210],"using":[211],"variation":[213],"dominant":[215],"fairness":[217],"(DRF).":[218],"Compared":[219],"two":[221],"state-of-the-art":[222],"CKE":[223],"optimization":[224],"schemes,":[225],"SMK":[226],"[52]":[227],"WS":[229],"[55],":[230],"average":[235],"harmonic":[236,267],"speedup":[237,268],"78%":[239],"39%,":[241],"respectively.":[242],"compared":[244],"best":[247],"possible":[248,260],"combinations,":[250,262],"obtained":[253],"an":[255],"exhaustive":[256],"search":[257],"all":[259],"up":[270],"51%":[272],"11%":[274],"average.":[276]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}