{"id":"https://openalex.org/W4387823818","doi":"https://doi.org/10.1145/3629521","title":"Characterizing Multi-Chip GPU Data Sharing","display_name":"Characterizing Multi-Chip GPU Data Sharing","publication_year":2023,"publication_date":"2023-10-20","ids":{"openalex":"https://openalex.org/W4387823818","doi":"https://doi.org/10.1145/3629521"},"language":"en","primary_location":{"id":"doi:10.1145/3629521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629521","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/10.1145/3629521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101891026","display_name":"Shiqing Zhang","orcid":"https://orcid.org/0000-0002-6690-3718"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Shiqing Zhang","raw_affiliation_strings":["Ghent University, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053780310","display_name":"Mahmood Naderan-Tahan","orcid":"https://orcid.org/0009-0007-7762-2878"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Mahmood Naderan-Tahan","raw_affiliation_strings":["Ghent University, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067108530","display_name":"Magnus Jahre","orcid":"https://orcid.org/0000-0001-9147-5228"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Magnus Jahre","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU), Norway"],"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033119975","display_name":"Lieven Eeckhout","orcid":"https://orcid.org/0000-0001-8792-4473"},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Lieven Eeckhout","raw_affiliation_strings":["Ghent University, Belgium"],"affiliations":[{"raw_affiliation_string":"Ghent University, Belgium","institution_ids":["https://openalex.org/I2801227569"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101891026"],"corresponding_institution_ids":["https://openalex.org/I2801227569"],"apc_list":null,"apc_paid":null,"fwci":0.9054,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72432185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9980000257492065,"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":0.8665285706520081},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.6015174388885498},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5916780829429626},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5440255403518677},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.52130126953125},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.5028523802757263},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.48399993777275085},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41812440752983093},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.35377413034439087},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.2830626368522644},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.18528392910957336},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15233629941940308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665285706520081},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.6015174388885498},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5916780829429626},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5440255403518677},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.52130126953125},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.5028523802757263},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.48399993777275085},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41812440752983093},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.35377413034439087},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2830626368522644},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.18528392910957336},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15233629941940308},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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:10.1145/3629521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629521","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:archive.ugent.be:01HQ0ZA2ZTM7GQ6RTY4JA8Z0GB","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HQ0ZA2ZTM7GQ6RTY4JA8Z0GB","pdf_url":"https://biblio.ugent.be/publication/01HQ0ZA2ZTM7GQ6RTY4JA8Z0GB/file/01HQ0ZB8RFTVXZWWMMM902VJGG.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1544-3973","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3629521","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3629521","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3629521","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":[],"awards":[{"id":"https://openalex.org/G1426318481","display_name":null,"funder_award_id":"grant","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G2730306035","display_name":null,"funder_award_id":"BOF-GOA","funder_id":"https://openalex.org/F4320322603","funder_display_name":"Universiteit Gent"},{"id":"https://openalex.org/G3748656914","display_name":null,"funder_award_id":"Norway","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"},{"id":"https://openalex.org/G4132985236","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G5524483453","display_name":null,"funder_award_id":"286596","funder_id":"https://openalex.org/F4320323299","funder_display_name":"Norges Forskningsr\u00e5d"}],"funders":[{"id":"https://openalex.org/F4320322603","display_name":"Universiteit Gent","ror":"https://ror.org/00cv9y106"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387823818.pdf","grobid_xml":"https://content.openalex.org/works/W4387823818.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2045275492","https://openalex.org/W2080592089","https://openalex.org/W2273440736","https://openalex.org/W2767106296","https://openalex.org/W2884108789","https://openalex.org/W2952269378","https://openalex.org/W3098136731"],"related_works":["https://openalex.org/W1979099492","https://openalex.org/W2145592252","https://openalex.org/W4255008187","https://openalex.org/W2407815036","https://openalex.org/W4250205214","https://openalex.org/W2036306661","https://openalex.org/W2143087414","https://openalex.org/W1797968800","https://openalex.org/W2105141138","https://openalex.org/W3216777841"],"abstract_inverted_index":{"Multi-chip":[0],"Graphics":[1],"Processing":[2],"Unit":[3],"(GPU)":[4],"systems":[5],"are":[6],"critical":[7],"to":[8,33,44,119],"scale":[9],"performance":[10,56],"beyond":[11],"a":[12,17,54,143,158],"single":[13],"GPU":[14],"chip":[15],"for":[16,27],"wide":[18],"variety":[19,134],"of":[20,85],"important":[21],"emerging":[22],"applications.":[23],"A":[24],"key":[25],"challenge":[26,57],"multi-chip":[28,81,182],"GPUs,":[29,183],"though,":[30],"is":[31,116],"how":[32,93,111,168],"overcome":[34],"the":[35,66,77,94,105,113,120,169,173,198,201],"bandwidth":[36],"gap":[37],"between":[38],"inter-chip":[39,67],"and":[40,69,109,126,191],"intra-chip":[41],"communication.":[42],"Accesses":[43],"shared":[45,78,90,95,106,114,144,170],"data,":[46,91],"i.e.,":[47,123],"data":[48],"accessed":[49],"by":[50],"multiple":[51],"chips,":[52],"pose":[53],"major":[55],"as":[58,184,186],"they":[59],"incur":[60],"remote":[61],"memory":[62,188],"accesses":[63],"possibly":[64],"congesting":[65],"links":[68],"degrading":[70],"overall":[71],"system":[72],"performance.":[73],"This":[74],"article":[75],"characterizes":[76],"dataset":[79,96,107,115,145,171],"in":[80,83,128,135,181],"GPUs":[82],"terms":[84],"(1)":[86],"truly":[87],"versus":[88,179],"falsely":[89],"(2)":[92],"scales":[97,147],"with":[98,117,149],"input":[99,150],"size,":[100,151],"(3)":[101],"along":[102],"which":[103],"dimensions":[104],"scales,":[108],"(4)":[110],"sensitive":[112],"respect":[118],"input\u2019s":[121],"characteristics,":[122],"node":[124],"degree":[125],"connectivity":[127],"graph":[129],"workloads.":[130],"We":[131,165],"observe":[132],"significant":[133],"scaling":[136,156],"behavior":[137],"across":[138,200],"workloads:":[139],"some":[140],"workloads":[141],"feature":[142,154],"that":[146],"linearly":[148],"whereas":[152],"others":[153],"sublinear":[155],"(following":[157],"\\(\\sqrt":[159,162],"{2}\\)":[160],"or":[161],"[3]{2}\\)":[163],"relationship).":[164],"further":[166],"demonstrate":[167,197],"affects":[172],"optimum":[174,187],"last-level":[175],"cache":[176],"organization":[177],"(memory-side":[178],"SM-side)":[180],"well":[185],"page":[189],"allocation":[190],"thread":[192],"scheduling":[193],"policy.":[194],"Sensitivity":[195],"analyses":[196],"insights":[199],"broad":[202],"design":[203],"space.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}