{"id":"https://openalex.org/W2887504043","doi":"https://doi.org/10.1145/3225058.3225077","title":"GLP4NN","display_name":"GLP4NN","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2887504043","doi":"https://doi.org/10.1145/3225058.3225077","mag":"2887504043"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225077","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/A5103050216","display_name":"Hao Fu","orcid":"https://orcid.org/0009-0000-8086-7779"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Fu","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010031092","display_name":"Shanjiang Tang","orcid":"https://orcid.org/0000-0001-9533-9899"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanjiang Tang","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039946576","display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055658279","display_name":"Ce Yu","orcid":"https://orcid.org/0000-0003-2416-4547"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ce Yu","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100882285","display_name":"Jizhou Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhou Sun","raw_affiliation_strings":["Tianjin University"],"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103050216"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.4178,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66811557,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":1.0,"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":1.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9979000091552734,"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":0.892059862613678},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6658178567886353},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6294670104980469},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6256923079490662},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5595758557319641},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.42012906074523926},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4112512469291687},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4058692753314972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.892059862613678},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6658178567886353},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6294670104980469},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6256923079490662},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5595758557319641},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.42012906074523926},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4112512469291687},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4058692753314972},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225077","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225077","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":47,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1598866093","https://openalex.org/W1619486754","https://openalex.org/W1652793671","https://openalex.org/W1667652561","https://openalex.org/W1789336918","https://openalex.org/W1833917188","https://openalex.org/W1922123711","https://openalex.org/W1964073652","https://openalex.org/W1982767656","https://openalex.org/W2069682406","https://openalex.org/W2083842231","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2124964692","https://openalex.org/W2132737349","https://openalex.org/W2140348470","https://openalex.org/W2142769604","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2172654076","https://openalex.org/W2186615578","https://openalex.org/W2254715784","https://openalex.org/W2277932597","https://openalex.org/W2335835108","https://openalex.org/W2336650964","https://openalex.org/W2339765813","https://openalex.org/W2342922783","https://openalex.org/W2489529491","https://openalex.org/W2504108613","https://openalex.org/W2565079991","https://openalex.org/W2579247884","https://openalex.org/W2622849229","https://openalex.org/W2734941459","https://openalex.org/W2886958107","https://openalex.org/W2914304175","https://openalex.org/W2951810231","https://openalex.org/W2953384591","https://openalex.org/W2962885409","https://openalex.org/W2964046515","https://openalex.org/W2964174152","https://openalex.org/W3118608800","https://openalex.org/W6636806777","https://openalex.org/W6691839725","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2187181201","https://openalex.org/W2168758875","https://openalex.org/W4246549241","https://openalex.org/W2410733619","https://openalex.org/W2963483475","https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053"],"abstract_inverted_index":{"In":[0,112],"this":[1],"paper,":[2],"we":[3,44,115],"propose":[4],"a":[5,56,81,86,140],"network-agnostic":[6],"and":[7,54,75,85],"convergence-invariant":[8],"light-weight":[9],"parallelization":[10],"framework,":[11],"namely":[12],"GLP4NN,":[13],"to":[14,97,109,120,138,144],"accelerate":[15,121],"the":[16,36,42,50,62,122,147,154],"training":[17,124],"of":[18,26,38,70,125,142,157],"Deep":[19],"Neural":[20],"Networks":[21],"(DNNs)":[22],"by":[23],"taking":[24],"advantage":[25],"emerging":[27],"GPU":[28,92,110],"features,":[29],"especially":[30],"concurrent":[31,39],"kernel":[32,51],"execution.":[33],"To":[34],"determine":[35],"number":[37],"kernels":[40,71],"on":[41,129],"fly,":[43],"design":[45],"an":[46],"analytical":[47],"model":[48],"in":[49,61,95],"analyzer":[52],"module":[53,65,84],"integrate":[55,116],"compact":[57],"asynchronous":[58],"resource":[59,63],"tracker":[60,64],"for":[66,90],"collecting":[67],"runtime":[68,82],"configurations":[69],"with":[72],"low":[73],"memory":[74],"time":[76],"overheads.":[77],"We":[78],"further":[79],"develop":[80],"scheduler":[83],"pool-based":[87],"stream":[88],"manager":[89],"handling":[91],"work":[93],"queues":[94],"GLP4NN":[96,117,135],"avoid":[98],"consuming":[99],"too":[100],"many":[101],"CPU":[102],"threads":[103],"or":[104],"processes":[105],"while":[106],"dispatching":[107],"workloads":[108],"devices.":[111],"our":[113],"experiments,":[114],"into":[118],"Caffe":[119],"batch-based":[123],"four":[126],"well-known":[127],"networks":[128],"NVIDIA":[130],"GPUs.":[131],"Experimental":[132],"results":[133],"show":[134],"is":[136],"able":[137],"achieve":[139],"speedup":[141],"up":[143],"4X":[145],"over":[146],"original":[148],"implementation":[149],"as":[150,152],"well":[151],"keep":[153],"convergence":[155],"property":[156],"networks.":[158]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-08-22T00:00:00"}