{"id":"https://openalex.org/W7117555123","doi":"https://doi.org/10.1109/iccd65941.2025.00093","title":"TeraNOC: A Multi-Channel 32-Bit Fine-Grained, Hybrid Mesh-Crossbar Noc for Efficient Scale-Up of 1000+ Core Shared-L1-Memory Clusters","display_name":"TeraNOC: A Multi-Channel 32-Bit Fine-Grained, Hybrid Mesh-Crossbar Noc for Efficient Scale-Up of 1000+ Core Shared-L1-Memory Clusters","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W7117555123","doi":"https://doi.org/10.1109/iccd65941.2025.00093"},"language":"en","primary_location":{"id":"doi:10.1109/iccd65941.2025.00093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd65941.2025.00093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 43rd International Conference on Computer Design (ICCD)","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/A5121587721","display_name":"Yichao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yichao Zhang","raw_affiliation_strings":["IIS, ETH Z&#x00FC;rich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z&#x00FC;rich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092581645","display_name":"Fu Zexin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zexin Fu","raw_affiliation_strings":["IIS, ETH Z&#x00FC;rich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z&#x00FC;rich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121528923","display_name":"Tim Fischer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Fischer","raw_affiliation_strings":["IIS, ETH Z&#x00FC;rich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z&#x00FC;rich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121599309","display_name":"Yinrong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinrong Li","raw_affiliation_strings":["IIS, ETH Z&#x00FC;rich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z&#x00FC;rich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121533374","display_name":"Marco Bertuletti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Bertuletti","raw_affiliation_strings":["IIS, ETH Z&#x00FC;rich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z&#x00FC;rich","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979376","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0003-2214-6679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["IIS, ETH Z&#x00FC;rich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIS, ETH Z&#x00FC;rich","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58139602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"610","last_page":"617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9158999919891357,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9158999919891357,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.057100001722574234,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.00800000037997961,"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/bottleneck","display_name":"Bottleneck","score":0.6983000040054321},{"id":"https://openalex.org/keywords/crossbar-switch","display_name":"Crossbar switch","score":0.6897000074386597},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.6771000027656555},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6262000203132629},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.5401999950408936},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4410000145435333},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4343000054359436},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4077000021934509}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6983000040054321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899999976158142},{"id":"https://openalex.org/C29984679","wikidata":"https://www.wikidata.org/wiki/Q1929149","display_name":"Crossbar switch","level":2,"score":0.6897000074386597},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6262000203132629},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4693000018596649},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2983435990","wikidata":"https://www.wikidata.org/wiki/Q22725","display_name":"Network routing","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C128519102","wikidata":"https://www.wikidata.org/wiki/Q339554","display_name":"Network on a chip","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C159631557","wikidata":"https://www.wikidata.org/wiki/Q1546066","display_name":"Networking hardware","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2776832011","wikidata":"https://www.wikidata.org/wiki/Q6935099","display_name":"Multistage interconnection networks","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C113508815","wikidata":"https://www.wikidata.org/wiki/Q193446","display_name":"Packet switching","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccd65941.2025.00093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd65941.2025.00093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 43rd International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/1040902","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/1040902","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2066162922","https://openalex.org/W2071815918","https://openalex.org/W2132829148","https://openalex.org/W2167308910","https://openalex.org/W2613438563","https://openalex.org/W3135242540","https://openalex.org/W4206371601","https://openalex.org/W4207072548","https://openalex.org/W4396816723","https://openalex.org/W4399391441","https://openalex.org/W4401211850","https://openalex.org/W4406047641","https://openalex.org/W4406727864","https://openalex.org/W4414079201"],"related_works":[],"abstract_inverted_index":{"A":[0,146],"key":[1,227],"challenge":[2],"in":[3,176,224,239,247],"on-chip":[4],"interconnect":[5,76,114,156,213],"design":[6],"is":[7,149],"to":[8,151,221,254,274],"scale":[9,21],"up":[10,220,273],"bandwidth":[11,200,207],"while":[12,122,276],"maintaining":[13,123],"low":[14,23,52,120,125,212],"latency":[15,32],"and":[16,26,70,94,103,119,137,194,204,245,265],"high":[17,216,250],"area":[18,25,262,267],"efficiency.":[19],"2D-meshes":[20,136],"with":[22,34,60,164,249],"wiring":[24,185],"congestion":[27],"overhead;":[28],"however,":[29],"their":[30,55],"end-to-end":[31],"increases":[33],"the":[35,47,61,79,99,140,182,235,281],"number":[36,62,191],"of":[37,63,81,101,143,184,192,201,208,219,234,280],"hops,":[38],"making":[39],"them":[40],"unsuitable":[41],"for":[42],"latency-sensitive":[43],"core-to-L1-memory":[44],"access.":[45],"On":[46],"other":[48],"hand,":[49],"crossbars":[50],"offer":[51],"latency,":[53,121],"but":[54],"routing":[56,68,126],"complexity":[57],"grows":[58],"quadratically":[59],"I/Os,":[64],"requiring":[65],"large":[66],"physical":[67],"resources":[69,186],"limiting":[71],"area-efficient":[72,141],"scalability.":[73],"This":[74],"two-sided":[75],"bottleneck":[77],"hinders":[78],"scale-up":[80,142],"many-core,":[82],"lowlatency,":[83],"tightly":[84],"coupled":[85,96],"shared-memory":[86,144],"clusters,":[87,97],"pushing":[88],"designers":[89],"toward":[90],"instantiating":[91],"many":[92],"smaller":[93],"loosely":[95],"at":[98],"cost":[100],"hardware":[102],"software":[104],"overheads.":[105],"We":[106,180],"present":[107],"TeraNoC,":[108,159],"an":[109],"open-source,":[110],"hybrid":[111],"mesh-crossbar":[112],"onchip":[113],"that":[115,169],"offers":[116],"both":[117],"scalability":[118],"very":[124],"overhead.":[127],"The":[128,211],"topology,":[129],"built":[130],"on":[131],"32":[132],"bit":[133],"word-width":[134],"multi-channel":[135],"crossbars,":[138],"enables":[139],"clusters.":[145],"router":[147],"remapper":[148],"designed":[150],"balance":[152],"traffic":[153],"load":[154],"across":[155],"channels.":[157],"Using":[158],"we":[160],"build":[161],"a":[162,171,189,198,205,255],"cluster":[163,237],"1024":[165],"singlestage,":[166],"single-issue":[167],"cores":[168],"share":[170],"4096-banked":[172],"L1":[173],"memory,":[174],"implemented":[175],"12":[177],"nm":[178],"technology.":[179],"maximize":[181],"utilization":[183,218],"by":[187,242,263,272],"using":[188],"configurable":[190],"read":[193],"write":[195],"channels,":[196],"achieving":[197],"peak":[199],"3.74":[202],"TiB/s":[203],"bisection":[206],"0.47":[209],"TiB/s.":[210],"stalls":[214],"enable":[215],"compute":[217],"0.85":[222],"IPC":[223],"compute-intensive,":[225],"dataparallel":[226],"GenAI":[228],"kernels.":[229],"TeraNoC":[230,259],"only":[231,278],"consumes":[232],"7.6%":[233],"total":[236],"power":[238],"kernels":[240,248],"dominated":[241],"crossbar":[243],"accesses,":[244],"22.7%":[246],"2D-mesh":[251],"traffic.":[252],"Compared":[253],"hierarchical":[256],"crossbar-only":[257],"cluster,":[258],"reduces":[260],"die":[261],"37.8%":[264],"improves":[266],"efficiency":[268],"(GFLOP/s/mm<sup":[269],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[270],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>)":[271],"98.7%,":[275],"occupying":[277],"10.9%":[279],"logic":[282],"area.":[283]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-12-30T00:00:00"}
