{"id":"https://openalex.org/W4411486393","doi":"https://doi.org/10.1145/3695053.3731055","title":"FRED: A Wafer-scale Fabric for 3D Parallel DNN Training","display_name":"FRED: A Wafer-scale Fabric for 3D Parallel DNN Training","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411486393","doi":"https://doi.org/10.1145/3695053.3731055"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731055","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","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/10.1145/3695053.3731055","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088899364","display_name":"Saeed Rashidi","orcid":"https://orcid.org/0000-0002-6472-9920"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saeed Rashidi","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6472-9920","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068175490","display_name":"William Won","orcid":"https://orcid.org/0000-0002-1715-9144"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Won","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1715-9144","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065143008","display_name":"Sudarshan Srinivasan","orcid":"https://orcid.org/0009-0002-8662-5820"},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudarshan Srinivasan","raw_affiliation_strings":["Intel, Bangalore, Karnataka, India"],"raw_orcid":"https://orcid.org/0009-0002-8662-5820","affiliations":[{"raw_affiliation_string":"Intel, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I4210146682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084229134","display_name":"Puneet Gupta","orcid":"https://orcid.org/0000-0002-6188-1134"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puneet Gupta","raw_affiliation_strings":["UCLA, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6188-1134","affiliations":[{"raw_affiliation_string":"UCLA, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034089074","display_name":"Tushar Krishna","orcid":"https://orcid.org/0000-0001-5738-6942"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Krishna","raw_affiliation_strings":["Georgia Tech, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5738-6942","affiliations":[{"raw_affiliation_string":"Georgia Tech, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4323,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94640535,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9976000189781189,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9976000189781189,"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/T11932","display_name":"Wireless Body Area Networks","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9431999921798706,"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/wafer","display_name":"Wafer","score":0.6027399897575378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6020814776420593},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.548555850982666},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5388016700744629},{"id":"https://openalex.org/keywords/wafer-scale-integration","display_name":"Wafer-scale integration","score":0.4275689721107483},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38002461194992065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3462998867034912},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2616981863975525},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17622491717338562},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17283755540847778},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.1412329375743866}],"concepts":[{"id":"https://openalex.org/C160671074","wikidata":"https://www.wikidata.org/wiki/Q267131","display_name":"Wafer","level":2,"score":0.6027399897575378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6020814776420593},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.548555850982666},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5388016700744629},{"id":"https://openalex.org/C2778638305","wikidata":"https://www.wikidata.org/wiki/Q7406100","display_name":"Wafer-scale integration","level":3,"score":0.4275689721107483},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38002461194992065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3462998867034912},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2616981863975525},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17622491717338562},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17283755540847778},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.1412329375743866},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731055","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3695053.3731055","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731055","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731055","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411486393.pdf","grobid_xml":"https://content.openalex.org/works/W4411486393.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1994926493","https://openalex.org/W2009571103","https://openalex.org/W2051971152","https://openalex.org/W2096313289","https://openalex.org/W2108960957","https://openalex.org/W2131613942","https://openalex.org/W2170796499","https://openalex.org/W2626429347","https://openalex.org/W2790925711","https://openalex.org/W2929862812","https://openalex.org/W2945146780","https://openalex.org/W2946710043","https://openalex.org/W2949161920","https://openalex.org/W2969388332","https://openalex.org/W2980104813","https://openalex.org/W2981114289","https://openalex.org/W2991040477","https://openalex.org/W3016542674","https://openalex.org/W3037585619","https://openalex.org/W3040573126","https://openalex.org/W3042495273","https://openalex.org/W3043522163","https://openalex.org/W3085163101","https://openalex.org/W3096425133","https://openalex.org/W3111562648","https://openalex.org/W3129831491","https://openalex.org/W3188065709","https://openalex.org/W3204998121","https://openalex.org/W3211730428","https://openalex.org/W4210798668","https://openalex.org/W4281790033","https://openalex.org/W4327930477","https://openalex.org/W4376652719","https://openalex.org/W4386763434","https://openalex.org/W4390533494","https://openalex.org/W4393406935","https://openalex.org/W4401176799"],"related_works":["https://openalex.org/W2970498257","https://openalex.org/W2140660040","https://openalex.org/W2036313051","https://openalex.org/W4400034431","https://openalex.org/W2065601166","https://openalex.org/W2146366317","https://openalex.org/W993605666","https://openalex.org/W2160598879","https://openalex.org/W2145903584","https://openalex.org/W2164231539"],"abstract_inverted_index":{"Wafer-scale":[0],"systems":[1],"are":[2],"an":[3],"emerging":[4],"technology":[5],"that":[6,93],"tightly":[7],"integrates":[8],"high-end":[9],"accelerator":[10],"chiplets":[11],"with":[12,72],"high-speed":[13],"wafer-scale":[14,55,123],"interconnects,":[15],"enabling":[16,87],"low-latency":[17],"and":[18,86,110,116],"high-bandwidth":[19],"connectivity.This":[20],"makes":[21],"them":[22],"a":[23,54,68,121],"promising":[24],"platform":[25],"for":[26,78,94],"deep":[27],"neural":[28],"network":[29],"(DNN)":[30],"training.However,":[31],"current":[32],"network-on-wafer":[33],"topologies,":[34],"such":[35],"as":[36],"2D":[37],"Meshes,":[38],"lack":[39],"the":[40,60,101],"flexibility":[41],"needed":[42],"to":[43,59,120],"support":[44],"various":[45],"parallelization":[46,96],"strategies":[47],"effectively.In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"Fred,":[53],"fabric":[56],"architecture":[57],"tailored":[58],"unique":[61],"communication":[62],"needs":[63],"of":[64,84,106],"DNN":[65],"training.Fred":[66],"creates":[67],"distributed":[69],"on-wafer":[70],"topology":[71],"tiny":[73],"microswitches,":[74],"providing":[75],"nonblocking":[76],"connectivity":[77],"collective":[79,89],"communications":[80],"between":[81],"arbitrary":[82],"groups":[83],"accelerators":[85],"in-switch":[88],"support.Our":[90],"results":[91],"show":[92],"sample":[95],"strategies,":[97],"Fred":[98],"can":[99],"improve":[100],"average":[102],"end-to-end":[103],"training":[104],"time":[105],"ResNet-152,":[107],"Transformer-17B,":[108],"GPT-3,":[109],"Transformer-1T":[111],"by":[112],"1.76,":[113],"1.87,":[114],"1.34,":[115],"1.4,":[117],"respectively,":[118],"compared":[119],"baseline":[122],"Mesh.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}