{"id":"https://openalex.org/W4379780947","doi":"https://doi.org/10.1109/tpds.2023.3279255","title":"P4SGD: Programmable Switch Enhanced Model-Parallel Training on Generalized Linear Models on Distributed FPGAs","display_name":"P4SGD: Programmable Switch Enhanced Model-Parallel Training on Generalized Linear Models on Distributed FPGAs","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379780947","doi":"https://doi.org/10.1109/tpds.2023.3279255"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3279255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3279255","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed 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/A5008542198","display_name":"Hongjing Huang","orcid":"https://orcid.org/0000-0003-1387-7955"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjing Huang","raw_affiliation_strings":["Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-1387-7955","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101537937","display_name":"Yingtao Li","orcid":"https://orcid.org/0009-0003-6497-6782"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingtao Li","raw_affiliation_strings":["Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0003-6497-6782","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004274","display_name":"Jie Sun","orcid":"https://orcid.org/0000-0001-7030-0146"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Sun","raw_affiliation_strings":["Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China","Alibaba group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7030-0146","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]},{"raw_affiliation_string":"Alibaba group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015651732","display_name":"Xueying Zhu","orcid":"https://orcid.org/0000-0001-7550-9379"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueying Zhu","raw_affiliation_strings":["Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-7550-9379","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436858","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1720-3704"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-1720-3704","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101955837","display_name":"Liang Luo","orcid":"https://orcid.org/0009-0003-7949-708X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Luo","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0003-7949-708X","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329093","display_name":"Jialin Li","orcid":"https://orcid.org/0000-0003-3530-7662"},"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":"Jialin Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3530-7662","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004837462","display_name":"Zeke Wang","orcid":"https://orcid.org/0000-0001-8550-9241"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeke Wang","raw_affiliation_strings":["Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-8550-9241","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Artificial Intelligence, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7445,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.72286903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"34","issue":"8","first_page":"2311","last_page":"2324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976999759674072,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.860883355140686},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7754218578338623},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6882014274597168},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6317837834358215},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5331038236618042},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4285561442375183},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2782455086708069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.860883355140686},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7754218578338623},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6882014274597168},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6317837834358215},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5331038236618042},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4285561442375183},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2782455086708069},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2023.3279255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3279255","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8417679201","display_name":null,"funder_award_id":"226-2022-00151","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1598866093","https://openalex.org/W1968188490","https://openalex.org/W2003728480","https://openalex.org/W2005487033","https://openalex.org/W2060393849","https://openalex.org/W2132737349","https://openalex.org/W2153635508","https://openalex.org/W2161238936","https://openalex.org/W2261808795","https://openalex.org/W2295739661","https://openalex.org/W2339765813","https://openalex.org/W2535724050","https://openalex.org/W2552372042","https://openalex.org/W2647836899","https://openalex.org/W2732291649","https://openalex.org/W2782800349","https://openalex.org/W2789305180","https://openalex.org/W2798956872","https://openalex.org/W2801000640","https://openalex.org/W2810704618","https://openalex.org/W2883929540","https://openalex.org/W2903735800","https://openalex.org/W2904773682","https://openalex.org/W2922527104","https://openalex.org/W2961280047","https://openalex.org/W2973727699","https://openalex.org/W2991040477","https://openalex.org/W3024077315","https://openalex.org/W3029379969","https://openalex.org/W3037847693","https://openalex.org/W3046414203","https://openalex.org/W3092260380","https://openalex.org/W3092501829","https://openalex.org/W3121313599","https://openalex.org/W3130395060","https://openalex.org/W3132082152","https://openalex.org/W3153854431","https://openalex.org/W3163465001","https://openalex.org/W4226479682","https://openalex.org/W4239385313","https://openalex.org/W4242577057","https://openalex.org/W4242634435","https://openalex.org/W4287774547","https://openalex.org/W4288487491","https://openalex.org/W4289401659","https://openalex.org/W6635810480","https://openalex.org/W6679393576","https://openalex.org/W6753584990","https://openalex.org/W6756718674","https://openalex.org/W6760703128","https://openalex.org/W6767997687","https://openalex.org/W6778651901","https://openalex.org/W6778729859","https://openalex.org/W6790615949","https://openalex.org/W6790665546","https://openalex.org/W6794216301","https://openalex.org/W6795581714","https://openalex.org/W6811928498"],"related_works":["https://openalex.org/W2364921833","https://openalex.org/W2385146268","https://openalex.org/W1569389315","https://openalex.org/W2503642292","https://openalex.org/W2380023786","https://openalex.org/W2546696010","https://openalex.org/W1992741870","https://openalex.org/W2063935754","https://openalex.org/W2271471376","https://openalex.org/W2298102683"],"abstract_inverted_index":{"Generalized":[0],"linear":[1,72,147],"models":[2,12],"(GLMs)":[3],"are":[4],"a":[5,38,81,86,112,131,164],"widely":[6],"utilized":[7],"family":[8],"of":[9,122],"machine":[10],"learning":[11],"in":[13],"real-world":[14],"applications.":[15],"As":[16,80,134],"data":[17],"size":[18,77],"increases,":[19],"it":[20],"is":[21,140],"essential":[22],"to":[23,49,70,118,136,174],"perform":[24],"efficient":[25,63],"distributed":[26,35,64,87,99,127,150],"training":[27,36,66,89],"for":[28,34,41,61],"these":[29],"models.":[30],"However,":[31],"existing":[32],"systems":[33],"have":[37],"high":[39],"cost":[40],"communication":[42],"and":[43,52,101,163],"often":[44],"use":[45],"large":[46],"batch":[47,76],"sizes":[48],"balance":[50],"computation":[51],"communication,":[53],"which":[54],"negatively":[55],"affects":[56],"convergence.":[57],"Therefore,":[58],"we":[59,83,110],"argue":[60],"an":[62,107],"GLM":[65],"system":[67,90],"that":[68,91,144],"strives":[69],"achieve":[71],"scalability,":[73],"while":[74],"keeping":[75],"reasonably":[78],"low.":[79],"start,":[82],"propose":[84,111],"P4SGD,":[85],"heterogeneous":[88],"efficiently":[92],"trains":[93],"GLMs":[94],"through":[95,102,152],"model":[96,153],"parallelism":[97,105],"between":[98,126,149],"FPGAs":[100,162],"forward-communication-backward":[103],"pipeline":[104],"within":[106],"FPGA.":[108],"Moreover,":[109],"light-weight,":[113],"latency-centric":[114],"in-switch":[115],"aggregation":[116],"protocol":[117],"minimize":[119],"the":[120,123,141,178],"latency":[121],"AllReduce":[124],"operation":[125],"FPGAs,":[128],"powered":[129],"by":[130],"programmable":[132],"switch.":[133,167],"such,":[135],"our":[137],"knowledge,":[138],"P4SGD":[139,157,171],"first":[142],"solution":[143],"achieves":[145],"almost":[146],"scalability":[148],"accelerators":[151],"parallelism.":[154],"We":[155],"implement":[156],"on":[158],"eight":[159],"Xilinx":[160],"U280":[161],"Tofino":[165],"P4":[166],"Our":[168],"experiments":[169],"show":[170],"converges":[172],"up":[173],"6.5X":[175],"faster":[176],"than":[177],"state-of-the-art":[179],"GPU":[180],"counterpart.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}