{"id":"https://openalex.org/W4392910976","doi":"https://doi.org/10.1145/3653019","title":"Cross-core Data Sharing for Energy-efficient GPUs","display_name":"Cross-core Data Sharing for Energy-efficient GPUs","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910976","doi":"https://doi.org/10.1145/3653019"},"language":"en","primary_location":{"id":"doi:10.1145/3653019","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3653019","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3653019","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3653019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019048190","display_name":"Hajar Falahati","orcid":"https://orcid.org/0000-0001-8375-3339"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]},{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hajar Falahati","raw_affiliation_strings":["Sharif University of Technology, School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0001-8375-3339","affiliations":[{"raw_affiliation_string":"Sharif University of Technology, School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran","institution_ids":["https://openalex.org/I4210146419","https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008240365","display_name":"Mohammad Sadrosadati","orcid":"https://orcid.org/0000-0002-4029-0175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Sadrosadati","raw_affiliation_strings":["School of Computer Science, IPM, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0002-4029-0175","affiliations":[{"raw_affiliation_string":"School of Computer Science, IPM, Tehran, Iran","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101023755","display_name":"Qiumin Xu","orcid":"https://orcid.org/0000-0003-1391-3397"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiumin Xu","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0003-1391-3397","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044416322","display_name":"Juan G\u00f3mez-Luna","orcid":"https://orcid.org/0000-0002-6514-1571"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Juan G\u00f3mez-Luna","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6514-1571","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038401622","display_name":"Banafsheh Saber Latibari","orcid":"https://orcid.org/0000-0003-3735-9191"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Banafsheh Saber Latibari","raw_affiliation_strings":["Sharif University of Technology, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0003-3735-9191","affiliations":[{"raw_affiliation_string":"Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081531196","display_name":"Hyeran Jeon","orcid":"https://orcid.org/0000-0002-1767-8198"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyeran Jeon","raw_affiliation_strings":["San Jos\u00e9 State University, San Jose, USA"],"raw_orcid":"https://orcid.org/0000-0002-1767-8198","affiliations":[{"raw_affiliation_string":"San Jos\u00e9 State University, San Jose, USA","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094180545","display_name":"Shaahin Hesaabi","orcid":null},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Shaahin Hesaabi","raw_affiliation_strings":["Sharif University of Technology, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0003-3193-2567","affiliations":[{"raw_affiliation_string":"Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040238844","display_name":"Hamid Sarbazi\u2010Azad","orcid":"https://orcid.org/0000-0003-4079-8603"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hamid Sarbazi-Azad","raw_affiliation_strings":["Sharif University of Technology, School of Computer Science, IPM, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0003-4079-8603","affiliations":[{"raw_affiliation_string":"Sharif University of Technology, School of Computer Science, IPM, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050695684","display_name":"Onur Mutlu","orcid":"https://orcid.org/0000-0002-0075-2312"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Onur Mutlu","raw_affiliation_strings":["ETH Z\u00fcrich, Carnegie Mellon University, Z\u00fcrich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-0075-2312","affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Carnegie Mellon University, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018033573","display_name":"Murali Annavaram","orcid":"https://orcid.org/0000-0002-4633-6867"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Annavaram","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-4633-6867","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057050874","display_name":"Masoud Pedram","orcid":"https://orcid.org/0000-0002-9422-1001"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masoud Pedram","raw_affiliation_strings":["University of Southern California, Los Angeles, USA"],"raw_orcid":"https://orcid.org/0000-0002-2677-7307","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5439,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93554396,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"21","issue":"3","first_page":"1","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8120335340499878},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5802884101867676},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4306448698043823},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.43018803000450134},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4240574538707733},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3896644711494446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120335340499878},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5802884101867676},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4306448698043823},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.43018803000450134},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4240574538707733},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3896644711494446},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3653019","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3653019","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3653019","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:scholarworks.sjsu.edu:faculty_rsca-6689","is_oa":true,"landing_page_url":"https://scholarworks.sjsu.edu/faculty_rsca/5690","pdf_url":null,"source":{"id":"https://openalex.org/S4377196389","display_name":"San Jos\u00e9 State University ScholarWorks (San Jose State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51504820","host_organization_name":"San Jose State University","host_organization_lineage":["https://openalex.org/I51504820"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Research, Scholarly, and Creative Activity","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3653019","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3653019","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3653019","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392910976.pdf","grobid_xml":"https://content.openalex.org/works/W4392910976.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W850361703","https://openalex.org/W1535409234","https://openalex.org/W1968775993","https://openalex.org/W1979527452","https://openalex.org/W1982439128","https://openalex.org/W1982996921","https://openalex.org/W2009946006","https://openalex.org/W2018658595","https://openalex.org/W2020634604","https://openalex.org/W2021211271","https://openalex.org/W2026186397","https://openalex.org/W2038178246","https://openalex.org/W2053744175","https://openalex.org/W2055844022","https://openalex.org/W2072837011","https://openalex.org/W2080592089","https://openalex.org/W2084309410","https://openalex.org/W2100011668","https://openalex.org/W2128120785","https://openalex.org/W2129817042","https://openalex.org/W2141973190","https://openalex.org/W2142119745","https://openalex.org/W2150073849","https://openalex.org/W2166918318","https://openalex.org/W2170666978","https://openalex.org/W2273440736","https://openalex.org/W2289349364","https://openalex.org/W2294241027","https://openalex.org/W2326078278","https://openalex.org/W2342496780","https://openalex.org/W2412101011","https://openalex.org/W2521924282","https://openalex.org/W2566040696","https://openalex.org/W2605751925","https://openalex.org/W2766210752","https://openalex.org/W2895553128","https://openalex.org/W2917720315","https://openalex.org/W3102510044","https://openalex.org/W3117273852","https://openalex.org/W3120481279","https://openalex.org/W3181975841","https://openalex.org/W4213435190","https://openalex.org/W4243058626","https://openalex.org/W6704339568"],"related_works":["https://openalex.org/W3158538495","https://openalex.org/W2045815042","https://openalex.org/W2092226129","https://openalex.org/W2913619905","https://openalex.org/W3125758369","https://openalex.org/W4249307902","https://openalex.org/W2375898439","https://openalex.org/W2069382761","https://openalex.org/W2028287801","https://openalex.org/W2049400599"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4,55,136],"the":[5,48,75,84,99,109,125,130,134,138,148,151,159,166,192,195,220,229,242,245,249,274,279],"accelerator":[6],"of":[7,12,68,89,124,168,256],"choice":[8],"in":[9,50,87,137,165,225,235],"a":[10,66,203,215,254],"variety":[11],"application":[13],"domains,":[14],"because":[15],"they":[16,71,127],"can":[17,23],"accelerate":[18],"massively":[19],"parallel":[20],"workloads":[21,258],"and":[22,34,83,265,269,287,291],"be":[24,162],"easily":[25],"programmed":[26],"using":[27],"general-purpose":[28],"programming":[29],"frameworks":[30],"such":[31],"as":[32,70,133,182,184],"CUDA":[33],"OpenCL.":[35],"Each":[36],"Streaming":[37],"Multiprocessor":[38],"(SM)":[39],"contains":[40],"an":[41,80],"L1":[42],"data":[43,51,126,146,160,243],"cache":[44,77,222],"(L1D)":[45],"to":[46,73,107,174,186,191,217,233,273,278],"exploit":[47],"locality":[49],"accesses.":[52],"L1D":[53,63,93,167,176,246],"misses":[54,64,94,178],"costly":[56,189],"for":[57,59],"GPUs":[58],"two":[60],"reasons.":[61],"First,":[62],"consume":[65],"lot":[67],"energy":[69,264,286],"need":[72],"access":[74,112],"L2":[76,90,149,193],"(L2)":[78],"via":[79,179],"on-chip":[81],"network":[82],"off-chip":[85,152,196],"DRAM":[86],"case":[88],"misses.":[91],"Second,":[92],"impose":[95],"performance":[96,266,288],"overhead":[97],"if":[98],"GPU":[100],"does":[101],"not":[102],"have":[103],"enough":[104],"active":[105],"warps":[106],"hide":[108],"long":[110],"memory":[111,140,153],"latency.":[113],"We":[114],"observe":[115],"that":[116,247,260],"threads":[117],"running":[118],"on":[119,253],"different":[120],"SMs":[121],"share":[122],"55%":[123],"read":[128,177],"from":[129,147,244],"memory.":[131],"Unfortunately,":[132],"L1Ds":[135],"non-coherent":[139],"domain,":[141],"each":[142],"SM":[143],"independently":[144],"fetches":[145,241],"or":[150,194],"into":[154],"its":[155],"L1D,":[156,238],"even":[157],"though":[158],"may":[161],"currently":[163],"available":[164],"another":[169,226,236],"SM.":[170,227],"Our":[171,251],"goal":[172],"is":[173,231],"service":[175],"other":[180],"SMs,":[181],"much":[183],"possible,":[185],"cut":[187],"down":[188],"accesses":[190],"DRAM.":[197],"To":[198],"this":[199],"end,":[200],"we":[201],"propose":[202],"new":[204],"data-sharing":[205,281],"mechanism,":[206,282],"called":[207],"Cross-Core":[208],"Data":[209],"Sharing":[210],"(CCDS)":[211],".":[212],"CCDS":[213,240,261,283],"employs":[214],"predictor":[216],"estimate":[218],"whether":[219],"required":[221],"block":[223,230],"exists":[224],"If":[228],"predicted":[232],"exist":[234],"SM\u2019s":[237],"then":[239],"contain":[248],"block.":[250],"experiments":[252],"suite":[255],"26":[257],"show":[259],"improves":[262,284],"average":[263,285],"by":[267,289],"1.30\u00d7":[268],"1.20\u00d7,":[270],"respectively,":[271],"compared":[272],"baseline":[275],"GPU.":[276],"Compared":[277],"state-of-the-art":[280],"1.37\u00d7":[290],"1.11\u00d7,":[292],"respectively.":[293]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}