{"id":"https://openalex.org/W4409248645","doi":"https://doi.org/10.1109/hpca61900.2025.00115","title":"Push Multicast: A Speculative and Coherent Interconnect for Mitigating Manycore CPU Communication Bottleneck","display_name":"Push Multicast: A Speculative and Coherent Interconnect for Mitigating Manycore CPU Communication Bottleneck","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4409248645","doi":"https://doi.org/10.1109/hpca61900.2025.00115"},"language":"en","primary_location":{"id":"doi:10.1109/hpca61900.2025.00115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca61900.2025.00115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on High Performance Computer Architecture (HPCA)","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/A5040392661","display_name":"Jiayi Huang","orcid":"https://orcid.org/0000-0003-4011-6668"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiayi Huang","raw_affiliation_strings":["HKUST(GZ)"],"affiliations":[{"raw_affiliation_string":"HKUST(GZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100615975","display_name":"Yanhua Chen","orcid":"https://orcid.org/0000-0002-4950-2090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhua Chen","raw_affiliation_strings":["HKUST(GZ)"],"affiliations":[{"raw_affiliation_string":"HKUST(GZ)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407669","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0003-2285-0295"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024082060","display_name":"Christopher J. Hughes","orcid":"https://orcid.org/0009-0009-2888-0314"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J. Hughes","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048052285","display_name":"Yufei Ding","orcid":"https://orcid.org/0000-0002-8716-5793"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["UC San Diego"],"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["HKUST"],"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040392661"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3949,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80497047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1541","last_page":"1556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9986000061035156,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8614659309387207},{"id":"https://openalex.org/keywords/multicast","display_name":"Multicast","score":0.8117417693138123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7564266324043274},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.5751266479492188},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47553443908691406},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4395805597305298},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3463955521583557},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.24518510699272156}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8614659309387207},{"id":"https://openalex.org/C32295351","wikidata":"https://www.wikidata.org/wiki/Q899288","display_name":"Multicast","level":2,"score":0.8117417693138123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564266324043274},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.5751266479492188},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47553443908691406},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4395805597305298},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3463955521583557},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.24518510699272156}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca61900.2025.00115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca61900.2025.00115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on High Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-161943","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-161943","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"As":[0],"CPUs":[1],"scale":[2],"up":[3],"to":[4,31,67,95,98,103,111,124,146],"many":[5],"cores,":[6],"the":[7,10,18,24,56,88,104,126,130,133,136],"bandwidth":[8,54,72,116,177,210],"of":[9,135,172,181,187,205,216,222],"network-on-chip":[11],"(NoC)":[12],"and":[13,52,65,70,83,114,148,162,184,219],"cache":[14,25,51,69,90],"can":[15,48],"soon":[16],"become":[17],"performance":[19],"bottleneck.":[20],"In":[21,36,74,196],"modern":[22],"processors,":[23],"hierarchy":[26],"plays":[27],"a":[28,81,92,141,154,179,185,192,197,214,220],"reactive":[29],"role":[30],"supply":[32],"data":[33,40,97,138,160],"upon":[34,101],"request.":[35],"parallel":[37],"programs,":[38],"shared":[39],"accesses":[41,61],"from":[42],"different":[43,46],"cores":[44],"at":[45],"times":[47],"consume":[49],"large":[50],"NoC":[53,71,115,176,209],"for":[55],"same":[57],"data.":[58],"These":[59],"same-data":[60],"inherently":[62],"have":[63],"redundancy":[64],"lead":[66],"inefficient":[68],"utilization.":[73],"this":[75],"work,":[76],"we":[77],"propose":[78],"Push":[79,167],"Multicast,":[80],"speculative":[82],"coherent":[84,119],"interconnect.":[85],"We":[86],"transform":[87],"last-level":[89],"into":[91],"proactive":[93],"agent":[94],"push":[96],"other":[99],"sharers":[100],"replying":[102],"demand":[105],"requester.":[106],"Pushing":[107],"enables":[108],"effective":[109],"multicasting":[110],"reduce":[112],"LLC":[113],"consumption.":[117],"A":[118],"innetwork":[120],"filter":[121],"is":[122,144],"proposed":[123],"prune":[125],"outstanding":[127],"requests":[128],"in":[129,191],"routers":[131],"along":[132,212],"way":[134],"pushed":[137],"delivery.":[139],"Moreover,":[140],"dynamic":[142],"mechanism":[143],"designed":[145],"pause":[147],"resume":[149],"pushing":[150],"adaptively.":[151],"Compared":[152],"with":[153,156,213],"system":[155],"an":[157,163,170,203],"L1":[158],"Bingo":[159],"prefetcher":[161],"L2":[164],"Stride":[165],"prefetcher,":[166],"Multicast":[168],"achieves":[169,202],"average":[171,204],"$\\mathbf{3":[173],"3":[174,207],"\\%}$":[175,208],"saving,":[178,211],"geomean":[180,215],"$1.02":[182],"\\times$":[183,189,218,224],"maximum":[186,221],"$1.56":[188],"speedup":[190],"16":[193],"-core":[194],"system.":[195],"64-core":[198],"system,":[199],"it":[200],"further":[201],"$\\mathbf{4":[206],"$1.11":[217],"$2.08":[223],"speedup.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
