{"id":"https://openalex.org/W4312060029","doi":"https://doi.org/10.1145/3567955.3567959","title":"Overlap Communication with Dependent Computation via Decomposition in Large Deep Learning Models","display_name":"Overlap Communication with Dependent Computation via Decomposition in Large Deep Learning Models","publication_year":2022,"publication_date":"2022-12-19","ids":{"openalex":"https://openalex.org/W4312060029","doi":"https://doi.org/10.1145/3567955.3567959"},"language":"en","primary_location":{"id":"doi:10.1145/3567955.3567959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3567955.3567959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3567955.3567959","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","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/10.1145/3567955.3567959","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100738091","display_name":"Shibo Wang","orcid":"https://orcid.org/0000-0001-9259-6806"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shibo Wang","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112647533","display_name":"Jinliang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinliang Wei","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000932612","display_name":"Amit Sabne","orcid":"https://orcid.org/0000-0002-2179-0078"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Sabne","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068599616","display_name":"Andy Davis","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andy Davis","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009468601","display_name":"Berkin Ilbeyi","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Berkin Ilbeyi","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005628986","display_name":"Blake A. Hechtman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Blake Hechtman","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074350356","display_name":"Dehao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dehao Chen","raw_affiliation_strings":["Waymo, USA"],"affiliations":[{"raw_affiliation_string":"Waymo, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110949807","display_name":"Karthik Murthy","orcid":"https://orcid.org/0000-0002-6063-9653"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Srinivasa Murthy","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051025765","display_name":"Marcello Maggioni","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcello Maggioni","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357522","display_name":"Qiao Zhang","orcid":"https://orcid.org/0000-0002-3509-8103"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiao Zhang","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070117771","display_name":"Sameer Kumar","orcid":"https://orcid.org/0000-0001-8697-7370"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Kumar","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112882155","display_name":"Tongfei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tongfei Guo","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081428852","display_name":"Yuanzhong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanzhong Xu","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084104975","display_name":"Zongwei Zhou","orcid":"https://orcid.org/0000-0002-3154-9851"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongwei Zhou","raw_affiliation_strings":["Google, USA"],"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5100738091"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":4.5939,"has_fulltext":true,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96041456,"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":"93","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8255494832992554},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.673729419708252},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6718379855155945},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6607174873352051},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.6386708617210388},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.629607617855072},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6126453280448914},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5548935532569885},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41104599833488464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39318978786468506},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3867383599281311},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1458282172679901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255494832992554},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.673729419708252},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6718379855155945},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6607174873352051},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.6386708617210388},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.629607617855072},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6126453280448914},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5548935532569885},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41104599833488464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39318978786468506},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3867383599281311},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1458282172679901},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3567955.3567959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3567955.3567959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3567955.3567959","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3567955.3567959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3567955.3567959","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3567955.3567959","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312060029.pdf","grobid_xml":"https://content.openalex.org/works/W4312060029.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1544467910","https://openalex.org/W1991300616","https://openalex.org/W1992836495","https://openalex.org/W2002505081","https://openalex.org/W2012652661","https://openalex.org/W2029342163","https://openalex.org/W2132777761","https://openalex.org/W2560452411","https://openalex.org/W2969388332","https://openalex.org/W3127736057","https://openalex.org/W3172942063","https://openalex.org/W3188065709"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1501159154","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W3170887803","https://openalex.org/W74409296","https://openalex.org/W3209384898","https://openalex.org/W4230999561","https://openalex.org/W1595672120"],"abstract_inverted_index":{"Large":[0],"deep":[1],"learning":[2],"models":[3,18],"have":[4],"shown":[5],"great":[6],"potential":[7],"with":[8],"state-of-the-art":[9],"results":[10],"in":[11,60],"many":[12],"tasks.":[13],"However,":[14],"running":[15],"these":[16,39],"large":[17],"is":[19,32,44],"quite":[20],"challenging":[21],"on":[22],"an":[23,45],"accelerator":[24,63],"(GPU":[25],"or":[26,55],"TPU)":[27],"because":[28],"the":[29,36,49,66,81,88],"on-device":[30],"memory":[31],"too":[33],"limited":[34],"for":[35],"size":[37],"of":[38,80],"models.":[40],"Intra-layer":[41],"model":[42,72],"parallelism":[43,73],"approach":[46],"to":[47,76],"address":[48],"issues":[50],"by":[51,70],"partitioning":[52],"individual":[53],"layers":[54],"operators":[56],"across":[57],"multiple":[58],"devices":[59],"a":[61,77],"distributed":[62],"cluster.":[64],"But,":[65],"data":[67],"communications":[68],"generated":[69],"intra-layer":[71],"can":[74],"contribute":[75],"significant":[78],"proportion":[79],"overall":[82],"execution":[83],"time":[84],"and":[85],"severely":[86],"hurt":[87],"computational":[89],"efficiency.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
