{"id":"https://openalex.org/W4401455086","doi":"https://doi.org/10.1145/3677333.3678267","title":"Alleviating All-to-All Communication for Deep Learning Recommendation Model Inference","display_name":"Alleviating All-to-All Communication for Deep Learning Recommendation Model Inference","publication_year":2024,"publication_date":"2024-08-09","ids":{"openalex":"https://openalex.org/W4401455086","doi":"https://doi.org/10.1145/3677333.3678267"},"language":"en","primary_location":{"id":"doi:10.1145/3677333.3678267","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677333.3678267","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677333.3678267","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 53rd International Conference on Parallel Processing Workshops","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3677333.3678267","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Songjun Huang","orcid":"https://orcid.org/0009-0009-7005-3902"},"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":true,"raw_author_name":"Songjun Huang","raw_affiliation_strings":["Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0009-0009-7005-3902","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937305","display_name":"Yihong Li","orcid":"https://orcid.org/0000-0002-0622-1969"},"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":"Yihong Li","raw_affiliation_strings":["Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0002-0622-1969","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029638279","display_name":"L P Chen","orcid":null},"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":"Liangkun Chen","raw_affiliation_strings":["Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0009-0007-3743-2199","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763625","display_name":"Xiaoxi Zhang","orcid":"https://orcid.org/0000-0003-0751-2773"},"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":"Xiaoxi Zhang","raw_affiliation_strings":["Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0003-0751-2773","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026622212","display_name":"Shuo Liu","orcid":"https://orcid.org/0000-0002-3546-4070"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Liu","raw_affiliation_strings":["Huawei, China"],"raw_orcid":"https://orcid.org/0000-0002-3546-4070","affiliations":[{"raw_affiliation_string":"Huawei, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016658545","display_name":"Jingpu Duan","orcid":"https://orcid.org/0000-0001-7507-2197"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingpu Duan","raw_affiliation_strings":["Peng Cheng Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0001-7507-2197","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031365162","display_name":"Wenfei Wu","orcid":"https://orcid.org/0000-0002-1357-3137"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Wu","raw_affiliation_strings":["Peking University, China"],"raw_orcid":"https://orcid.org/0000-0002-1357-3137","affiliations":[{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385692","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-9943-6020"},"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":"Xu Chen","raw_affiliation_strings":["Sun Yat-sen University, China"],"raw_orcid":"https://orcid.org/0000-0001-9943-6020","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18814074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9972000122070312,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9970999956130981,"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/bottleneck","display_name":"Bottleneck","score":0.8819723725318909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8369426727294922},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7050793170928955},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6956108808517456},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6313348412513733},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6309880614280701},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5512118339538574},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42476871609687805},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.35340791940689087},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3476039469242096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33417850732803345},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.19115084409713745},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.179984450340271},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1220005452632904}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8819723725318909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8369426727294922},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7050793170928955},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6956108808517456},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6313348412513733},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6309880614280701},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5512118339538574},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42476871609687805},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.35340791940689087},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3476039469242096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33417850732803345},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.19115084409713745},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.179984450340271},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1220005452632904}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677333.3678267","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677333.3678267","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677333.3678267","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 53rd International Conference on Parallel Processing Workshops","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3677333.3678267","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677333.3678267","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677333.3678267","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 53rd International Conference on Parallel Processing Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401455086.pdf"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W3030235304","https://openalex.org/W3197870239","https://openalex.org/W4200559323","https://openalex.org/W4381327166"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"Massive":[0],"DLRMs":[1],"require":[2],"large-scale":[3],"multi-node":[4],"systems":[5],"for":[6,46],"distributed":[7],"training":[8],"and":[9,41],"inference,":[10],"thus":[11],"suffering":[12],"from":[13],"the":[14,25,29],"all-to-all":[15],"communication":[16],"bottleneck.":[17],"We":[18],"propose":[19],"an":[20],"architecture,":[21],"EmbedSwitch,":[22],"that":[23],"offloads":[24],"cache":[26],"function":[27],"of":[28],"embedding":[30,47],"table":[31,48],"vectors":[32],"to":[33,37],"a":[34],"programmable":[35],"switch,":[36],"overcome":[38],"this":[39],"bottleneck":[40],"provide":[42],"switch-level":[43],"response":[44],"latency":[45],"vector":[49],"requests.":[50]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}