{"id":"https://openalex.org/W7155352851","doi":"https://doi.org/10.1145/3777884.3797814","title":"Illuminating Multi-GPU Data Movement","display_name":"Illuminating Multi-GPU Data Movement","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155352851","doi":"https://doi.org/10.1145/3777884.3797814"},"language":null,"primary_location":{"id":"doi:10.1145/3777884.3797814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797814","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th 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://doi.org/10.1145/3777884.3797814","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040713791","display_name":"Didem Unat","orcid":"https://orcid.org/0000-0002-2351-0770"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Didem Unat","raw_affiliation_strings":["Computer Engineering, Ko\u00e7 University, Istanbul, Turkiye"],"raw_orcid":"https://orcid.org/0000-0002-2351-0770","affiliations":[{"raw_affiliation_string":"Computer Engineering, Ko\u00e7 University, Istanbul, Turkiye","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040713791"],"corresponding_institution_ids":["https://openalex.org/I1351752"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94811776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.48899999260902405,"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":0.48899999260902405,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.24950000643730164,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.0608999989926815,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8741999864578247},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7696999907493591},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5817999839782715},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.44620001316070557},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.36880001425743103}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8741999864578247},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7696999907493591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675999999046326},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.506600022315979},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3777884.3797814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797814","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3777884.3797814","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3777884.3797814","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM/SPEC International Conference on Performance Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5662274956703186}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W4381327256","https://openalex.org/W4399282121","https://openalex.org/W4402897082","https://openalex.org/W4403752062","https://openalex.org/W4410153188"],"related_works":[],"abstract_inverted_index":{"GPUs":[0],"have":[1],"become":[2],"the":[3,94,137,140],"accelerators":[4],"of":[5,57,139],"choice":[6],"for":[7,72,96],"HPC":[8],"and":[9,18,28,45,61,68,83,100,108,113,135],"machine":[10],"learning":[11],"applications,":[12],"thanks":[13],"to":[14,32,131],"their":[15],"massive":[16],"parallelism":[17],"high":[19],"memory":[20],"bandwidth.":[21],"However,":[22],"as":[23,38],"GPU":[24,75],"counts":[25],"per":[26],"node":[27],"across":[29,62,117],"clusters":[30],"continue":[31],"grow,":[33],"inter-GPU":[34],"communication":[35,59,105],"has":[36],"emerged":[37],"a":[39],"major":[40],"scalability":[41],"bottleneck,":[42],"requiring":[43],"debugging":[44],"profiling":[46,73,88,99],"tool":[47,70],"support.":[48],"In":[49],"this":[50],"talk,":[51],"I":[52,77,91,119],"will":[53,78,92,120],"provide":[54],"an":[55],"overview":[56],"GPU-centric":[58],"within":[60],"compute":[63],"nodes,":[64],"highlighting":[65],"vendor":[66],"mechanisms":[67],"existing":[69],"support":[71],"multi-":[74],"communication.":[76],"then":[79],"discuss":[80],"research":[81],"challenges":[82,134],"opportunities":[84],"in":[85,126],"developing":[86],"modern":[87],"tools.":[89],"Finally,":[90],"emphasize":[93],"need":[95],"more":[97],"user-friendly":[98],"analysis":[101],"frameworks":[102],"that":[103],"illuminate":[104],"data":[106,115],"paths":[107],"help":[109],"developers":[110],"better":[111],"understand":[112],"optimize":[114],"movement":[116],"networks.":[118],"conclude":[121],"by":[122],"outlining":[123],"ongoing":[124],"efforts":[125],"our":[127],"re-":[128],"search":[129],"group":[130],"address":[132],"these":[133],"advance":[136],"state":[138],"art.":[141]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-04-24T00:00:00"}
