{"id":"https://openalex.org/W4387321090","doi":"https://doi.org/10.1145/3600006.3613169","title":"UGACHE: A Unified GPU Cache for Embedding-based Deep Learning","display_name":"UGACHE: A Unified GPU Cache for Embedding-based Deep Learning","publication_year":2023,"publication_date":"2023-10-03","ids":{"openalex":"https://openalex.org/W4387321090","doi":"https://doi.org/10.1145/3600006.3613169"},"language":"en","primary_location":{"id":"doi:10.1145/3600006.3613169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600006.3613169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th Symposium on Operating Systems Principles","raw_type":"proceedings-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/A5087812146","display_name":"Xiaoniu Song","orcid":"https://orcid.org/0009-0009-1887-2636"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoniu Song","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-1887-2636","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041011260","display_name":"Yiwen Zhang","orcid":"https://orcid.org/0009-0002-0462-1288"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-0462-1288","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101543146","display_name":"Rong Chen","orcid":"https://orcid.org/0000-0002-6115-8130"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Chen","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6115-8130","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406215","display_name":"Haibo Chen","orcid":"https://orcid.org/0000-0002-9720-0361"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9720-0361","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087812146"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4391012619"],"apc_list":null,"apc_paid":null,"fwci":3.9311,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9410051,"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":"627","last_page":"641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.996999979019165,"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/T11478","display_name":"Caching and Content Delivery","score":0.996999979019165,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9940999746322632,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9833999872207642,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8903673887252808},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6962536573410034},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6908243298530579},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.680785596370697},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6724852323532104},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5752869844436646},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.513806164264679},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.48429766297340393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44740843772888184},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42880162596702576},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41182565689086914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3231470584869385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8903673887252808},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6962536573410034},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6908243298530579},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.680785596370697},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6724852323532104},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5752869844436646},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.513806164264679},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.48429766297340393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44740843772888184},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42880162596702576},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41182565689086914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3231470584869385},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3600006.3613169","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600006.3613169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th Symposium on Operating Systems Principles","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5763792105","display_name":null,"funder_award_id":"62272291","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7732961354","display_name":null,"funder_award_id":"2022YFB4500700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8677931172","display_name":null,"funder_award_id":"61925206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W131619556","https://openalex.org/W1986603225","https://openalex.org/W2964182926","https://openalex.org/W3096566397","https://openalex.org/W3152501898","https://openalex.org/W3159953606","https://openalex.org/W3197720002","https://openalex.org/W3198239267","https://openalex.org/W3200211247","https://openalex.org/W3201621211","https://openalex.org/W4214658871","https://openalex.org/W4220807331","https://openalex.org/W4220884018","https://openalex.org/W4226328099","https://openalex.org/W4282576620","https://openalex.org/W4282963011","https://openalex.org/W4290928031","https://openalex.org/W4296591836","https://openalex.org/W4296591840","https://openalex.org/W4387302734"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"UGache,":[3],"a":[4,35,56,63],"unified":[5],"multi-GPU":[6],"cache":[7,65],"system":[8],"for":[9],"embedding-based":[10],"deep":[11,106],"learning":[12,107],"(EmbDL).":[13],"UGache":[14,33,60,81,112],"is":[15],"primarily":[16],"motivated":[17],"by":[18,119],"the":[19,75],"unique":[20],"characteristics":[21],"of":[22,97,122],"EmbDL":[23,98],"applications,":[24,99],"namely":[25,100],"read-only,":[26],"batched,":[27],"skewed,":[28],"and":[29,52,70,82,90,105,116,124,129],"predictable":[30],"embedding":[31],"accesses.":[32],"introduces":[34],"novel":[36],"factored":[37],"extraction":[38,76],"mechanism":[39],"that":[40,67,111],"avoids":[41],"bandwidth":[42],"congestion":[43],"to":[44,73,127],"fully":[45],"exploit":[46],"high-speed":[47],"cross-GPU":[48],"interconnects":[49],"(e.g.,":[50],"NVLink":[51],"NVSwitch).":[53],"Based":[54],"on":[55],"new":[57],"hotness":[58],"metric,":[59],"also":[61],"provides":[62],"near-optimal":[64],"policy":[66],"balances":[68],"local":[69],"remote":[71],"access":[72],"minimize":[74],"time.":[77],"We":[78],"have":[79],"implemented":[80],"integrated":[83],"it":[84],"into":[85],"two":[86,94],"representative":[87],"frameworks,":[88],"TensorFlow":[89],"PyTorch.":[91],"Evaluation":[92],"using":[93],"typical":[95],"types":[96],"graph":[101],"neural":[102],"network":[103],"training":[104],"recommendation":[108],"inference,":[109],"shows":[110],"outperforms":[113],"state-of-the-art":[114],"replication":[115],"partition":[117],"designs":[118],"an":[120],"average":[121],"1.93\u00d7":[123],"1.63\u00d7":[125],"(up":[126],"5.25\u00d7":[128],"3.45\u00d7),":[130],"respectively.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}