{"id":"https://openalex.org/W2798291715","doi":"https://doi.org/10.1145/3190508.3190541","title":"Low latency RNN inference with cellular batching","display_name":"Low latency RNN inference with cellular batching","publication_year":2018,"publication_date":"2018-04-18","ids":{"openalex":"https://openalex.org/W2798291715","doi":"https://doi.org/10.1145/3190508.3190541","mag":"2798291715"},"language":"en","primary_location":{"id":"doi:10.1145/3190508.3190541","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3190508.3190541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth EuroSys Conference","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/A5103148668","display_name":"Pin Gao","orcid":"https://orcid.org/0000-0003-2664-8588"},"institutions":[{"id":"https://openalex.org/I2802444338","display_name":"King Center","ror":"https://ror.org/03nxex423","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802444338"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pin Gao","raw_affiliation_strings":["Tsinghua University and New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University and New York University","institution_ids":["https://openalex.org/I2802444338","https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052479606","display_name":"Lingfan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lingfan Yu","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602897","display_name":"Yongwei Wu","orcid":"https://orcid.org/0000-0002-6651-7032"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwei Wu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100320430","display_name":"Jinyang Li","orcid":"https://orcid.org/0000-0002-1900-0719"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyang Li","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.662,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.94175869,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9983999729156494,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9980999827384949,"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":0.8559831380844116},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.7931119203567505},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7336651086807251},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7220367193222046},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.645976185798645},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5736072659492493},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5368661284446716},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.478975772857666},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41691187024116516},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.34370627999305725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29123276472091675},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.24962171912193298},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07055076956748962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8559831380844116},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7931119203567505},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7336651086807251},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7220367193222046},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.645976185798645},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5736072659492493},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5368661284446716},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.478975772857666},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41691187024116516},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.34370627999305725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29123276472091675},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.24962171912193298},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07055076956748962},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3190508.3190541","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3190508.3190541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth EuroSys Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1423339008","https://openalex.org/W1516184288","https://openalex.org/W1895577753","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2089347259","https://openalex.org/W2093217068","https://openalex.org/W2100099053","https://openalex.org/W2103216163","https://openalex.org/W2117538598","https://openalex.org/W2126022651","https://openalex.org/W2131400476","https://openalex.org/W2133564696","https://openalex.org/W2150606131","https://openalex.org/W2152175008","https://openalex.org/W2155893237","https://openalex.org/W2166706824","https://openalex.org/W2186615578","https://openalex.org/W2193413348","https://openalex.org/W2251869843","https://openalex.org/W2251939518","https://openalex.org/W2402144811","https://openalex.org/W2474388053","https://openalex.org/W2525778437","https://openalex.org/W2565600385","https://openalex.org/W2586850891","https://openalex.org/W2619269479","https://openalex.org/W2751799266","https://openalex.org/W2779888504","https://openalex.org/W2949888546","https://openalex.org/W2953384591","https://openalex.org/W2963288913","https://openalex.org/W2963355447","https://openalex.org/W2963546833","https://openalex.org/W4244634541","https://openalex.org/W4299828299","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640"],"abstract_inverted_index":{"Performing":[0],"inference":[1],"on":[2],"pre-trained":[3],"neural":[4],"network":[5],"models":[6],"must":[7],"meet":[8],"the":[9,47,55,79,103],"requirement":[10],"of":[11,49,59,70,81],"low-latency,":[12],"which":[13,31,52],"is":[14],"often":[15],"at":[16,78],"odds":[17],"with":[18,41,87],"achieving":[19],"high":[20],"throughput.":[21],"Existing":[22],"deep":[23],"learning":[24],"systems":[25,64],"use":[26],"batching":[27,74,76],"to":[28],"improve":[29],"throughput,":[30],"do":[32],"not":[33],"perform":[34],"well":[35],"when":[36],"serving":[37],"Recurrent":[38],"Neural":[39],"Networks":[40],"dynamic":[42],"dataflow":[43,71],"graphs.":[44],"We":[45,105],"propose":[46],"technique":[48],"cellular":[50,73],"batching,":[51],"improves":[53],"both":[54],"latency":[56,121],"and":[57,90,101,122],"throughput":[58,125],"RNN":[60,83],"inference.":[61],"Unlike":[62],"existing":[63,127],"that":[65,116],"batch":[66],"a":[67,93,110],"fixed":[68],"set":[69],"graphs,":[72],"makes":[75],"decisions":[77],"granularity":[80],"an":[82],"\"cell\"":[84],"(a":[85],"subgraph":[86],"shared":[88],"weights)":[89],"dynamically":[91],"assembles":[92],"batched":[94],"cell":[95],"for":[96],"execution":[97],"as":[98],"requests":[99],"join":[100],"leave":[102],"system.":[104],"implemented":[106],"our":[107],"approach":[108],"in":[109],"system":[111],"called":[112],"BatchMaker.":[113],"Experiments":[114],"show":[115],"BatchMaker":[117],"achieves":[118],"much":[119],"lower":[120],"also":[123],"higher":[124],"than":[126],"systems.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}