{"id":"https://openalex.org/W4377224985","doi":"https://doi.org/10.1145/3589974","title":"SplitRPC: A {Control + Data} Path Splitting RPC Stack for ML Inference Serving","display_name":"SplitRPC: A {Control + Data} Path Splitting RPC Stack for ML Inference Serving","publication_year":2023,"publication_date":"2023-05-19","ids":{"openalex":"https://openalex.org/W4377224985","doi":"https://doi.org/10.1145/3589974"},"language":"en","primary_location":{"id":"doi:10.1145/3589974","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589974","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"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":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-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/A5018757871","display_name":"Adithya Kumar","orcid":"https://orcid.org/0009-0005-3876-0624"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adithya Kumar","raw_affiliation_strings":["The Pennsylvania State University, University Park, USA"],"raw_orcid":"https://orcid.org/0009-0005-3876-0624","affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033253809","display_name":"Anand Sivasubramaniam","orcid":"https://orcid.org/0000-0001-6173-687X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Sivasubramaniam","raw_affiliation_strings":["Penn State University, University Park, USA"],"raw_orcid":"https://orcid.org/0000-0001-6173-687X","affiliations":[{"raw_affiliation_string":"Penn State University, University Park, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024530225","display_name":"Timothy Zhu","orcid":"https://orcid.org/0000-0001-8394-8953"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy Zhu","raw_affiliation_strings":["The Pennsylvania State University, University park, USA"],"raw_orcid":"https://orcid.org/0000-0001-8394-8953","affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University park, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":1.0603,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7309185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"7","issue":"2","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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":0.8675987720489502},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5831458568572998},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.38766998052597046},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3842781186103821},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3827572464942932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8675987720489502},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5831458568572998},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.38766998052597046},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3842781186103821},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3827572464942932}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589974","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589974","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"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":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3023408722","display_name":"SHF: Medium: Embracing Architectural Heterogeneity through Hardware-Software Co-design","funder_award_id":"1763681","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4021869465","display_name":null,"funder_award_id":"1909004, 1714389, 1912495, 1629915, 1629129, 1763681","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4257531402","display_name":"CI-New: GEMDROID: A Comprehensive Platform for Studying Architectural Issues for Next Generation Mobile Systems","funder_award_id":"1629915","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5192582966","display_name":"SHF: Medium: Exploring an Edge Platform Design Trajectory for Next Generation XR Applications","funder_award_id":"2211018","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5681901375","display_name":"FoMR: Shrinking the Control and Data Flow Latencies of Single Thread Executions for Emerging Workloads","funder_award_id":"1912495","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6216537686","display_name":"CNS Core: Small: A Multi-Stakeholder Integrated Approach to Reduce Tail Latency Using Heterogeneity","funder_award_id":"1909004","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7045959657","display_name":"XPS: FULL: A Fresh Look at Near Data Computing: Coordinated Data and Computation Government","funder_award_id":"1629129","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7069098112","display_name":"SHF:Small: Integrated Hardware-Software Power Regulation, Allocation and Isolation in Consolidated Servers","funder_award_id":"1714389","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G877853932","display_name":null,"funder_award_id":"2211018, 1912495, 1909004, 1714389, 1912495, 1629915, 1629129, 1763681","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"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W87357050","https://openalex.org/W1515979307","https://openalex.org/W2074516327","https://openalex.org/W2134427337","https://openalex.org/W2402285027","https://openalex.org/W2442974303","https://openalex.org/W2521121845","https://openalex.org/W2734941459","https://openalex.org/W2772948367","https://openalex.org/W2903278032","https://openalex.org/W2941938531","https://openalex.org/W2968450015","https://openalex.org/W2981758446","https://openalex.org/W2982157693","https://openalex.org/W3012088208","https://openalex.org/W3042846511","https://openalex.org/W3043571714","https://openalex.org/W3095348600","https://openalex.org/W3095488153","https://openalex.org/W3097411828","https://openalex.org/W3101836229","https://openalex.org/W3133131678","https://openalex.org/W3139274998","https://openalex.org/W3153563908","https://openalex.org/W3159576817","https://openalex.org/W3166537212","https://openalex.org/W3171093681","https://openalex.org/W3174529902","https://openalex.org/W3205377733","https://openalex.org/W3205539956","https://openalex.org/W3205928774","https://openalex.org/W3212650987","https://openalex.org/W4214540558","https://openalex.org/W4214573349","https://openalex.org/W4220924023","https://openalex.org/W4308083596"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3096456556","https://openalex.org/W4240253816","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2020341030","https://openalex.org/W2749133591","https://openalex.org/W2367473450","https://openalex.org/W23346600"],"abstract_inverted_index":{"The":[0,57],"growing":[1],"adoption":[2],"of":[3,115,136,161,226],"hardware":[4],"accelerators":[5],"driven":[6],"by":[7,46],"their":[8,22],"intelligent":[9],"compiler":[10],"and":[11,19,41,72,112,130,166,209,211,251],"runtime":[12],"system":[13],"counterparts":[14],"has":[15],"democratized":[16],"ML":[17,36,100,179,215,227],"services":[18,37,69,216],"precipitously":[20],"reduced":[21],"execution":[23],"times.":[24],"This":[25],"motivates":[26],"us":[27,184],"to":[28,32,88,107,126,143,148,185,189,197],"shift":[29],"our":[30],"attention":[31],"efficiently":[33,139],"serve":[34],"these":[35,116,153,162],"under":[38],"distributed":[39],"settings":[40],"characterize":[42],"the":[43,47,62,66,70,110,113,128,141,144,157,187,190,195,242],"overheads":[44],"imposed":[45],"RPC":[48,58,176,243],"mechanism":[49,177],"('RPC":[50],"tax')":[51],"when":[52],"serving":[53,98],"them":[54],"on":[55,75,90,205],"accelerators.":[56,117],"implementations":[59],"designed":[60],"over":[61,253],"years":[63],"implicitly":[64],"assume":[65],"host":[67],"CPU":[68,196],"requests,":[71],"we":[73,164,234],"focus":[74],"expanding":[76],"such":[77],"works":[78],"towards":[79],"accelerator-based":[80],"services.":[81],"While":[82],"recent":[83],"proposals":[84],"calling":[85],"for":[86,95,133,178],"SmartNICs":[87,210],"take":[89],"this":[91],"task":[92],"are":[93],"reasonable":[94],"simple":[96],"kernels,":[97],"complex":[99],"models":[101,228],"requires":[102],"a":[103,170,224],"more":[104],"nuanced":[105],"view":[106],"optimize":[108,186],"both":[109,206],"data-path":[111],"control/orchestration":[114],"We":[118,202],"program":[119],"today's":[120],"commodity":[121,207],"network":[122],"interface":[123],"cards":[124],"(NICs)":[125],"split":[127],"control":[129,137,171],"data":[131,173],"paths":[132,154],"effective":[134,239],"transfer":[135],"while":[138,192,245],"transferring":[140],"payload":[142],"accelerator.":[145],"As":[146],"opposed":[147],"unified":[149],"approaches":[150],"that":[151,236],"bundle":[152],"together,":[155],"limiting":[156],"flexibility":[158],"in":[159,240,249],"each":[160],"paths,":[163],"design":[165],"implement":[167,203],"SplitRPC":[168,182,204,237],"-":[169],"+":[172],"path":[174],"optimizing":[175],"inference":[180,232],"serving.":[181],"allows":[183],"datapath":[188],"accelerator":[191],"simultaneously":[193],"allowing":[194],"maintain":[198],"full":[199],"orchestration":[200],"capabilities.":[201],"NICs":[208],"demonstrate":[212,235],"how":[213],"GPU-based":[214],"running":[217],"different":[218,231],"compiler/runtime":[219],"systems":[220],"can":[221],"benefit.":[222],"For":[223],"variety":[225],"served":[229],"using":[230],"runtimes,":[233],"is":[238],"minimizing":[241],"tax":[244],"providing":[246],"significant":[247],"gains":[248],"throughput":[250],"latency":[252],"existing":[254],"kernel":[255],"by-pass":[256],"approaches,":[257],"without":[258],"requiring":[259],"expensive":[260],"SmartNIC":[261],"devices.":[262]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}