{"id":"https://openalex.org/W4415583225","doi":"https://doi.org/10.1145/3755881.3755887","title":"Take Kernel Stack Overhead Out: eBPF-Enhanced Network Acceleration for Distributed Training within Ethernet","display_name":"Take Kernel Stack Overhead Out: eBPF-Enhanced Network Acceleration for Distributed Training within Ethernet","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4415583225","doi":"https://doi.org/10.1145/3755881.3755887"},"language":null,"primary_location":{"id":"doi:10.1145/3755881.3755887","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3755881.3755887","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755887","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Internetware","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755887","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104189238","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0009-0002-5130-0567"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0002-5130-0567","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335060","display_name":"Pengfei Chen","orcid":"https://orcid.org/0000-0003-0972-6900"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0003-0972-6900","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075077822","display_name":"Guangba Yu","orcid":"https://orcid.org/0000-0001-6195-9088"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangba Yu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6195-9088","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669271","display_name":"Zilong He","orcid":"https://orcid.org/0000-0001-7963-082X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilong He","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-7963-082X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100781895","display_name":"Xiaoyun Li","orcid":"https://orcid.org/0000-0001-5730-2972"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyun Li","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-5730-2972","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36994799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12216","display_name":"Network Time Synchronization Technologies","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12216","display_name":"Network Time Synchronization Technologies","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10847","display_name":"Advanced Optical Network Technologies","score":0.9905999898910522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ethernet","display_name":"Ethernet","score":0.5654000043869019},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5083000063896179},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5027999877929688},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45249998569488525},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.45089998841285706},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.387800008058548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546000242233276},{"id":"https://openalex.org/C172173386","wikidata":"https://www.wikidata.org/wiki/Q79984","display_name":"Ethernet","level":2,"score":0.5654000043869019},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.41940000653266907},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39739999175071716},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C167151114","wikidata":"https://www.wikidata.org/wiki/Q1661930","display_name":"Industrial Ethernet","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C68178114","wikidata":"https://www.wikidata.org/wiki/Q5403359","display_name":"Ethernet flow control","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C137471899","wikidata":"https://www.wikidata.org/wiki/Q11381","display_name":"Local area network","level":2,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3755881.3755887","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3755881.3755887","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755887","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Internetware","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3755881.3755887","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3755881.3755887","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755887","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Internetware","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2477268016","display_name":null,"funder_award_id":"2024YFB4505904","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4914517125","display_name":null,"funder_award_id":"2023B1515020054","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415583225.pdf","grobid_xml":"https://content.openalex.org/works/W4415583225.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2057332538","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2903038868","https://openalex.org/W2949161920","https://openalex.org/W2963341956","https://openalex.org/W3047002910","https://openalex.org/W3086105743","https://openalex.org/W3091097978","https://openalex.org/W4312933868","https://openalex.org/W4327911839","https://openalex.org/W4366493286","https://openalex.org/W4385993956","https://openalex.org/W4386131770","https://openalex.org/W4389722097","https://openalex.org/W4401508321","https://openalex.org/W4408869788"],"related_works":[],"abstract_inverted_index":{"As":[0],"deep":[1,68],"neural":[2,69],"networks":[3,70],"(DNN)":[4,71],"continue":[5,72],"to":[6,11,23,54,65,73,78,90,96,116,127,159,188,207,210],"scale":[7,74],"up":[8,75,206],"in":[9,35,76,104,151,234],"size":[10,77],"achieve":[12,79],"greater":[13,80],"capabilities,":[14,81],"distributed":[15,82],"training":[16,26,66,83,93,128],"(DT)":[17,84],"has":[18,85,170],"become":[19,86],"the":[20,25,46,57,87,92,100,108,119,131,135,165,171,194,202,214,218],"prevailing":[21,88],"approach":[22,89],"accelerate":[24,91],"process.Through":[27],"measurements":[28],"and":[29,163,176],"analysis":[30],"of":[31,56,118,167,173],"network":[32,49,101,111,137,168,220],"communication":[33,59,102,121,203],"overheads":[34,103],"DT":[36,105,149,232],"scenarios":[37],"within":[38,106],"traditional":[39,152,189],"Ethernet-based":[40,153],"data":[41,154,236],"centers,":[42],"we":[43,139,222],"observe":[44],"that":[45],"Linux":[47,109],"kernel":[48,110,136,160,219],"stack":[50,112],"accounts":[51,113],"for":[52,114,148,231],"30%":[53,115],"40%":[55,117],"total":[58,120],"time,":[60,122],"posing":[61,123],"a":[62,124],"significant":[63,125],"bottleneck":[64,126],"efficiency.As":[67],"process.However,":[94],"according":[95],"our":[97],"observation":[98],"on":[99,180],"Ethernet,":[107],"efficiency.To":[129],"mitigate":[130,213],"overhead":[132,166,215],"introduced":[133,216],"by":[134,198,205,217],"stack,":[138,221],"propose":[140,223],"eRAR,":[141,224],"an":[142,225],"eBPF-based":[143,226],"gradient":[144,157,195,227],"aggregation":[145,158,196,228],"over":[146,229],"Ring-AR":[147,230],"tasks":[150,233],"centers.eRAR":[155],"offloads":[156],"using":[161],"eBPF":[162],"avoids":[164],"stack.eRAR":[169],"advantages":[172],"hardwareagnostic,":[174],"network-topology-independent,":[175],"resource-efficient.Our":[177],"experimental":[178],"results":[179],"four":[181],"popular":[182],"DNN":[183],"models":[184],"demonstrate":[185],"that,":[186],"compared":[187,209],"TCP-based":[190],"aggregation,":[191],"eRAR":[192,200],"improves":[193],"throughput":[197],"77.2%.Furthermore,":[199],"reduces":[201],"time":[204],"37.4%":[208],"existing":[211],"systems.To":[212],"commodity":[235],"centers.":[237]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-28T00:00:00"}
