{"id":"https://openalex.org/W4411486418","doi":"https://doi.org/10.1145/3695053.3731061","title":"NUPEA: Optimizing Critical Loads on Spatial Dataflow Architectures via Non-Uniform Processing-Element Access","display_name":"NUPEA: Optimizing Critical Loads on Spatial Dataflow Architectures via Non-Uniform Processing-Element Access","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411486418","doi":"https://doi.org/10.1145/3695053.3731061"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731061","source":null,"license":null,"license_id":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731061","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102927798","display_name":"S. Ghosh","orcid":"https://orcid.org/0000-0002-0656-4726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Souradip Ghosh","raw_affiliation_strings":["Efficient Computer, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0656-4726","affiliations":[{"raw_affiliation_string":"Efficient Computer, Pittsburgh, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053911444","display_name":"Graham Gobieski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Graham Gobieski","raw_affiliation_strings":["Efficient Computer, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0005-5408-120X","affiliations":[{"raw_affiliation_string":"Efficient Computer, Pittsburgh, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101659460","display_name":"Keyi Zhang","orcid":"https://orcid.org/0000-0002-8902-2518"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keyi Zhang","raw_affiliation_strings":["Efficient Computer, San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8902-2518","affiliations":[{"raw_affiliation_string":"Efficient Computer, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076249757","display_name":"Brandon Lucia","orcid":"https://orcid.org/0000-0003-4130-1099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brandon Lucia","raw_affiliation_strings":["Efficient Computer, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4130-1099","affiliations":[{"raw_affiliation_string":"Efficient Computer, Pittsburgh, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008156365","display_name":"Nathan Beckmann","orcid":"https://orcid.org/0000-0001-6301-714X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan Beckmann","raw_affiliation_strings":["Efficient Computer, 0000-0001-6301-714X, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6301-714X","affiliations":[{"raw_affiliation_string":"Efficient Computer, 0000-0001-6301-714X, PA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006723758","display_name":"Tony Nowatzki","orcid":"https://orcid.org/0000-0001-8483-3824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tony Nowatzki","raw_affiliation_strings":["Efficient Computer, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8483-3824","affiliations":[{"raw_affiliation_string":"Efficient Computer, Los Angeles, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2382,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73027231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1627","last_page":"1640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9990000128746033,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.998199999332428,"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/dataflow","display_name":"Dataflow","score":0.9158222675323486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646575570106506},{"id":"https://openalex.org/keywords/element","display_name":"Element (criminal law)","score":0.5821370482444763},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.5377156734466553},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.454574316740036},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3986572325229645},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32252225279808044}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9158222675323486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646575570106506},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.5821370482444763},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.5377156734466553},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.454574316740036},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3986572325229645},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32252225279808044},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731061","source":null,"license":null,"license_id":null,"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:10.1145/3695053.3731061","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731061","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731061","source":null,"license":null,"license_id":null,"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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411486418.pdf","grobid_xml":"https://content.openalex.org/works/W4411486418.grobid-xml"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W105298322","https://openalex.org/W1581408681","https://openalex.org/W1967648049","https://openalex.org/W1969529818","https://openalex.org/W1981943579","https://openalex.org/W1982205631","https://openalex.org/W1982812416","https://openalex.org/W1995830264","https://openalex.org/W2025787141","https://openalex.org/W2035924020","https://openalex.org/W2074812550","https://openalex.org/W2083868341","https://openalex.org/W2086112773","https://openalex.org/W2090068045","https://openalex.org/W2095679548","https://openalex.org/W2099958604","https://openalex.org/W2109065830","https://openalex.org/W2122992089","https://openalex.org/W2126372249","https://openalex.org/W2139637699","https://openalex.org/W2142501475","https://openalex.org/W2151233837","https://openalex.org/W2152609355","https://openalex.org/W2157373341","https://openalex.org/W2161825883","https://openalex.org/W2164988937","https://openalex.org/W2169339215","https://openalex.org/W2169665207","https://openalex.org/W2171164959","https://openalex.org/W2175048909","https://openalex.org/W2290773042","https://openalex.org/W2324320295","https://openalex.org/W2590246587","https://openalex.org/W2626186664","https://openalex.org/W2626211758","https://openalex.org/W2626953429","https://openalex.org/W2725179571","https://openalex.org/W2733054703","https://openalex.org/W2767588966","https://openalex.org/W2798482398","https://openalex.org/W2897997157","https://openalex.org/W2911393769","https://openalex.org/W2911669905","https://openalex.org/W2950138172","https://openalex.org/W2951091066","https://openalex.org/W2953184160","https://openalex.org/W2980270412","https://openalex.org/W3011446983","https://openalex.org/W3016769527","https://openalex.org/W3017066768","https://openalex.org/W3019560945","https://openalex.org/W3122286897","https://openalex.org/W3155004489","https://openalex.org/W3157391606","https://openalex.org/W3158233278","https://openalex.org/W3159763498","https://openalex.org/W3190578104","https://openalex.org/W3207932494","https://openalex.org/W3208226200","https://openalex.org/W4214694693","https://openalex.org/W4214725219","https://openalex.org/W4232904085","https://openalex.org/W4234107648","https://openalex.org/W4236272793","https://openalex.org/W4242368470","https://openalex.org/W4250857881","https://openalex.org/W4280590405","https://openalex.org/W4285049632","https://openalex.org/W4308083596","https://openalex.org/W4308084052","https://openalex.org/W4321500415","https://openalex.org/W4327911471","https://openalex.org/W4327930430","https://openalex.org/W4327930465","https://openalex.org/W4360831841","https://openalex.org/W4389476181","https://openalex.org/W4389491925","https://openalex.org/W4393407315","https://openalex.org/W4400944869","https://openalex.org/W4404954970","https://openalex.org/W4410810611"],"related_works":["https://openalex.org/W2564598376","https://openalex.org/W1484403103","https://openalex.org/W2584408851","https://openalex.org/W2115158825","https://openalex.org/W2101960124","https://openalex.org/W4377693460","https://openalex.org/W2033683327","https://openalex.org/W2783505431","https://openalex.org/W2521947294","https://openalex.org/W4236419692"],"abstract_inverted_index":{"Data":[0],"movement":[1,16,96],"is":[2,45,122,142],"the":[3,126,133,156],"dominant":[4],"energy,":[5],"performance,":[6],"and":[7,37,47,108,147,152,160,187],"scalability":[8],"bottleneck":[9],"in":[10],"modern":[11],"architectures.Systems":[12],"have":[13],"tackled":[14],"data":[15,29,36,43,59,95,117,134],"by":[17,166],"distributing":[18],"data,":[19],"e.g.,":[20,98],"via":[21],"non-uniform":[22,86],"memory":[23,80],"access":[24,88],"(NUMA)":[25],"architectures.However,":[26],"to":[27,41,57,79,85,103,115,128],"reduce":[28,94],"movement,":[30],"these":[31],"architectures":[32,51],"must":[33],"identify":[34,129],"critical":[35,100,130],"place":[38],"it":[39,110,121],"closer":[40,78],"compute.Clever":[42],"placement":[44,91],"complex":[46],"often":[48,123],"ineffective.Spatial":[49],"dataflow":[50],"(SDAs)":[52],"present":[53,144],"a":[54,65,171,183,193],"new":[55],"opportunity":[56],"tackle":[58],"movement.SDAs":[60],"distribute":[61],"program":[62],"instructions":[63],"across":[64,170],"spatial":[66],"fabric":[67],"of":[68,173],"processing":[69],"elements":[70],"(PEs).On":[71],"large":[72],"SDAs,":[73],"some":[74],"PEs":[75],"are":[76],"necessarily":[77],"than":[81,132],"others,":[82],"giving":[83],"rise":[84],"processing-element":[87],"(NUPEA).Clever":[89],"instruction":[90],"can":[92],"thus":[93],"by,":[97],"placing":[99],"loads":[101,131],"close":[102],"memory.This":[104],"paper":[105],"introduces":[106],"NUPEA":[107,138,151,176],"contrasts":[109],"with":[111,196],"prior":[112],"datacentric":[113],"approaches":[114],"scaling":[116],"movement.We":[118],"find":[119],"that":[120],"easier":[124],"for":[125,150],"compiler":[127,148],"they":[135],"access,":[136],"making":[137],"applicable":[139],"where":[140],"NUMA":[141],"not.We":[143],"simple":[145],"architecture":[146,159],"optimizations":[149],"implement":[153],"them":[154],"on":[155],"Monaco":[157],"SDA":[158,186,195],"effcc":[161],"compiler,":[162],"both":[163],"industry":[164],"products":[165],"Efficient":[167],"Computer.On":[168],"Monaco,":[169],"range":[172],"important":[174],"kernels,":[175],"yields":[177],"an":[178,188],"avg":[179,189],"28%":[180],"speedup":[181],"over":[182,192],"uniform-PE-access":[184],"(UPEA)":[185],"20%":[190],"speed":[191],"UPEA":[194],"NUMA.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}