{"id":"https://openalex.org/W2930869794","doi":"https://doi.org/10.1145/3297663.3310299","title":"Evaluating Characteristics of CUDA Communication Primitives on High-Bandwidth Interconnects","display_name":"Evaluating Characteristics of CUDA Communication Primitives on High-Bandwidth Interconnects","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2930869794","doi":"https://doi.org/10.1145/3297663.3310299","mag":"2930869794"},"language":"en","primary_location":{"id":"doi:10.1145/3297663.3310299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297663.3310299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297663.3310299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3297663.3310299","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032990831","display_name":"Carl Pearson","orcid":"https://orcid.org/0000-0001-6481-970X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carl Pearson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024517637","display_name":"Abdul Dakkak","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdul Dakkak","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018217287","display_name":"Sarah Hashash","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Hashash","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354297","display_name":"Cheng Li","orcid":"https://orcid.org/0000-0003-3424-2414"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng Li","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108479300","display_name":"I\u2010Hsin Chung","orcid":"https://orcid.org/0000-0003-4555-9257"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-Hsin Chung","raw_affiliation_strings":["IBM T.J. Watson Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030156276","display_name":"Jinjun Xiong","orcid":"https://orcid.org/0000-0002-2620-4859"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinjun Xiong","raw_affiliation_strings":["IBM T.J. Watson Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Mei Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5032990831"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.703,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93456524,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"209","last_page":"218"},"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":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8340480327606201},{"id":"https://openalex.org/keywords/virtual-memory","display_name":"Virtual memory","score":0.5310020446777344},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5260493755340576},{"id":"https://openalex.org/keywords/paging","display_name":"Paging","score":0.48736053705215454},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.4722292423248291},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46937087178230286},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.44708895683288574},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4396688938140869},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3908999264240265},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36897730827331543},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31028300523757935},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22803527116775513},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.22666692733764648},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2060515284538269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8340480327606201},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.5310020446777344},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5260493755340576},{"id":"https://openalex.org/C50954386","wikidata":"https://www.wikidata.org/wiki/Q656083","display_name":"Paging","level":2,"score":0.48736053705215454},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.4722292423248291},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46937087178230286},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.44708895683288574},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4396688938140869},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3908999264240265},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36897730827331543},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31028300523757935},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22803527116775513},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.22666692733764648},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2060515284538269}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3297663.3310299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297663.3310299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297663.3310299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3297663.3310299","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3297663.3310299","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3297663.3310299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1448048428","display_name":null,"funder_award_id":"0725070","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5367696895","display_name":null,"funder_award_id":"OCI-0725070","funder_id":"https://openalex.org/F4320332222","funder_display_name":"University of Illinois at Urbana-Champaign"},{"id":"https://openalex.org/G8082577388","display_name":null,"funder_award_id":"OCI-0725070","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320316786","display_name":"Center for Cognitive Computing Systems Research","ror":null},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2930869794.pdf","grobid_xml":"https://content.openalex.org/works/W2930869794.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1980759071","https://openalex.org/W2041679393","https://openalex.org/W2048346240","https://openalex.org/W2149234156","https://openalex.org/W2186615578","https://openalex.org/W2416330002","https://openalex.org/W2581090187","https://openalex.org/W2777078856","https://openalex.org/W2903901007"],"related_works":["https://openalex.org/W2357520409","https://openalex.org/W4241723377","https://openalex.org/W2155379745","https://openalex.org/W4235954812","https://openalex.org/W2093630148","https://openalex.org/W4242544852","https://openalex.org/W2041497765","https://openalex.org/W4246134203","https://openalex.org/W3000731046","https://openalex.org/W2099380135"],"abstract_inverted_index":{"Data-intensive":[0],"applications":[1],"such":[2,85],"as":[3,86],"machine":[4],"learning":[5],"and":[6,21,46,53,89,125],"analytics":[7],"have":[8],"created":[9],"a":[10,65],"demand":[11],"for":[12,28],"faster":[13],"interconnects":[14],"to":[15,24,56],"avert":[16],"the":[17,49,57,70],"memory":[18,88,122],"bandwidth":[19],"wall":[20],"allow":[22],"GPUs":[23],"be":[25],"effectively":[26],"leveraged":[27],"lower":[29],"compute":[30],"intensity":[31],"tasks.":[32],"This":[33],"has":[34,47],"resulted":[35],"in":[36],"wide":[37],"adoption":[38],"of":[39,51,75],"heterogeneous":[40],"systems":[41,97],"with":[42,82],"varying":[43],"underlying":[44],"interconnects,":[45],"delegated":[48],"task":[50],"understanding":[52],"copying":[54],"data":[55,76,105,126],"system":[58,108],"or":[59,72],"application":[60,78],"developer.":[61],"No":[62],"longer":[63],"is":[64,98],"malloc":[66],"followed":[67],"by":[68,101],"memcpy":[69],"only":[71],"dominating":[73],"modality":[74],"transfer;":[77],"developers":[79],"are":[80],"faced":[81],"additional":[83],"options":[84],"unified":[87],"zero-copy":[90],"memory.":[91],"Data":[92],"transfer":[93,106],"performance":[94],"on":[95],"these":[96],"now":[99],"impacted":[100],"many":[102],"factors":[103],"including":[104],"modality,":[107],"interconnect":[109],"hardware":[110],"details,":[111],"CPU":[112,115],"caching":[113],"state,":[114,118],"power":[116],"management":[117],"driver":[119],"policies,":[120],"virtual":[121],"paging":[123],"efficiency,":[124],"placement.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
