{"id":"https://openalex.org/W2885901248","doi":"https://doi.org/10.1145/3225058.3225107","title":"UHCL-Darknet","display_name":"UHCL-Darknet","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2885901248","doi":"https://doi.org/10.1145/3225058.3225107","mag":"2885901248"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-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/A5018057133","display_name":"Longlong Liao","orcid":"https://orcid.org/0000-0002-1311-7115"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longlong Liao","raw_affiliation_strings":["National University of Defense Technology, State Key Laboratory of High Performance Computing, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, State Key Laboratory of High Performance Computing, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["Hunan University, National Supercomputing Center in Changsha, Changsha, Hunan, China","State University of New York, National Supercomputing Center in Changsha, New Paltz, USA"],"affiliations":[{"raw_affiliation_string":"Hunan University, National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"State University of New York, National Supercomputing Center in Changsha, New Paltz, USA","institution_ids":["https://openalex.org/I1327163397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087894632","display_name":"Keqin Li","orcid":"https://orcid.org/0000-0001-5224-4048"},"institutions":[{"id":"https://openalex.org/I1327163397","display_name":"State University of New York","ror":"https://ror.org/01q1z8k08","country_code":"US","type":"education","lineage":["https://openalex.org/I1327163397"]},{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Keqin Li","raw_affiliation_strings":["Hunan University, National Supercomputing Center in Changsha, Changsha, Hunan, China","State University of New York, National Supercomputing Center in Changsha, New Paltz, USA"],"affiliations":[{"raw_affiliation_string":"Hunan University, National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"State University of New York, National Supercomputing Center in Changsha, New Paltz, USA","institution_ids":["https://openalex.org/I1327163397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101044975","display_name":"Canqun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Canqun Yang","raw_affiliation_strings":["National University of Defense Technology, State Key Laboratory of High Performance Computing, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, State Key Laboratory of High Performance Computing, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0009-0003-2676-5300"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["University of Texas at San Antonio, San Antonio, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at San Antonio, San Antonio, USA","institution_ids":["https://openalex.org/I45438204"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018057133"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.0446,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82317597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9130947589874268},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.6495814323425293},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6277758479118347},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5950424671173096},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5939112901687622},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5838638544082642},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5321143269538879},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.48525428771972656},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.46245670318603516},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.43451520800590515},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3519124388694763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24500420689582825},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20740526914596558},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13430282473564148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9130947589874268},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.6495814323425293},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6277758479118347},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5950424671173096},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5939112901687622},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5838638544082642},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5321143269538879},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.48525428771972656},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.46245670318603516},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.43451520800590515},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3519124388694763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24500420689582825},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20740526914596558},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13430282473564148}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1743745388","https://openalex.org/W1825216778","https://openalex.org/W2010936531","https://openalex.org/W2048520013","https://openalex.org/W2055289854","https://openalex.org/W2062368747","https://openalex.org/W2097197727","https://openalex.org/W2120351018","https://openalex.org/W2121855070","https://openalex.org/W2155893237","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2346804249","https://openalex.org/W2412412354","https://openalex.org/W2418688212","https://openalex.org/W2432982300","https://openalex.org/W2522062623","https://openalex.org/W2523064693","https://openalex.org/W2542223201","https://openalex.org/W2566887379","https://openalex.org/W2567335190","https://openalex.org/W2570343428","https://openalex.org/W2580688187","https://openalex.org/W2611626712","https://openalex.org/W2612482223","https://openalex.org/W2758013740","https://openalex.org/W2783772867","https://openalex.org/W2784409032","https://openalex.org/W2786956436","https://openalex.org/W2953384591","https://openalex.org/W2962911728","https://openalex.org/W2963446712","https://openalex.org/W3103983137","https://openalex.org/W4298438326"],"related_works":["https://openalex.org/W159577597","https://openalex.org/W2056717482","https://openalex.org/W2025467172","https://openalex.org/W3101208208","https://openalex.org/W2068528924","https://openalex.org/W1449833061","https://openalex.org/W2017587301","https://openalex.org/W619618554","https://openalex.org/W2049347805","https://openalex.org/W2030707850"],"abstract_inverted_index":{"As":[0],"the":[1,35,68,79,97,108,167,176],"majority":[2],"of":[3,39,88,92,111,127,170],"popular":[4],"deep":[5],"neural":[6],"network":[7],"(DNN)":[8],"frameworks":[9],"focus":[10],"on":[11,18,138,163,175],"a":[12,62,89,148],"closed":[13],"format":[14],"CUDA":[15],"implementations":[16],"based":[17],"one":[19],"or":[20],"more":[21],"NVIDIA":[22,42],"GPUs,":[23],"they":[24],"cannot":[25],"efficiently":[26],"leverage":[27],"other":[28],"devices":[29,95],"in":[30,96],"cluster":[31,70],"mode":[32],"to":[33,104],"accelerate":[34,45],"training":[36,124,172],"and":[37,73,118,125,134,150,157,160,173],"inference":[38,126,174],"DNNs":[40,46],"except":[41],"GPUs.":[43],"To":[44],"using":[47],"heterogeneous":[48,69,98,141,155,178],"multi-/many-core":[49],"clusters,":[50,156],"we":[51,60,101],"propose":[52],"an":[53,74,139],"OpenCL-based":[54],"DNN":[55,129,152],"framework":[56,153],"called":[57,71],"UHCL-Darknet.":[58],"First,":[59],"design":[61],"unified":[63],"OpenCL":[64,94,121],"platform":[65],"model":[66],"for":[67,83,154,166],"UHCL,":[72,84],"adaptive":[75],"runtime":[76],"system":[77],"with":[78],"affinity-based":[80],"dynamic":[81],"scheduler":[82],"enabling":[85],"transparent":[86],"utilization":[87],"wide":[90],"variety":[91],"vendor-specific":[93],"cluster.":[99,142,179],"Then,":[100],"extend":[102],"Darknet":[103],"UHCL":[105],"by":[106],"introducing":[107],"parallel":[109],"optimization":[110],"DNNs,":[112],"such":[113],"as":[114],"paralleling":[115],"Winogrand-based":[116],"convolutions":[117],"auto-tuning":[119],"parameterized":[120],"kernels.":[122],"The":[123],"art-of-data":[128],"models":[130],"(e.g.,":[131],"YOLOv2,":[132],"ResNet-50,":[133],"DenseNet-201)":[135],"are":[136],"executed":[137],"experimental":[140,177],"Results":[143],"show":[144],"that":[145],"UHCL-Darknet":[146],"is":[147],"scalable":[149],"portable":[151],"achieves":[158],"1.9x":[159],"2.2x":[161],"speedups":[162],"average":[164],"respectively":[165],"image":[168],"throughput":[169],"data-parallel":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-08-22T00:00:00"}