{"id":"https://openalex.org/W4321782107","doi":"https://doi.org/10.1145/3582514.3582517","title":"Harmonic CUDA: Asynchronous Programming on GPUs","display_name":"Harmonic CUDA: Asynchronous Programming on GPUs","publication_year":2023,"publication_date":"2023-02-24","ids":{"openalex":"https://openalex.org/W4321782107","doi":"https://doi.org/10.1145/3582514.3582517"},"language":"en","primary_location":{"id":"doi:10.1145/3582514.3582517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3582514.3582517","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 14th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3582514.3582517","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080166082","display_name":"Jonathan D. Wapman","orcid":"https://orcid.org/0000-0001-7397-3012"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan D. Wapman","raw_affiliation_strings":["University of California, Davis, Davis, CA, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7397-3012","affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, United States of America","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005774998","display_name":"Sean Treichler","orcid":"https://orcid.org/0000-0003-2189-4026"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Treichler","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2189-4026","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, United States of America","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014094561","display_name":"Serban D. Porumbescu","orcid":"https://orcid.org/0000-0003-1523-9199"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Serban D. Porumbescu","raw_affiliation_strings":["University of California, Davis, Davis, CA, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-1523-9199","affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, United States of America","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028662746","display_name":"John D. Owens","orcid":"https://orcid.org/0000-0001-6582-8237"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John D. Owens","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6582-8237","affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8337,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73092926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.996999979019165,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9954000115394592,"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/cuda","display_name":"CUDA","score":0.8766701817512512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7912529706954956},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7009813785552979},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6127992272377014},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5692877769470215},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5238559246063232},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4829406142234802},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34477734565734863},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2730487883090973},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10911825299263},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08222424983978271}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8766701817512512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912529706954956},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7009813785552979},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6127992272377014},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5692877769470215},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5238559246063232},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4829406142234802},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34477734565734863},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2730487883090973},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10911825299263},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08222424983978271},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3582514.3582517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3582514.3582517","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 14th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt9539763j","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9539763j","pdf_url":"https://escholarship.org/content/qt9539763j/qt9539763j.pdf?t=sat71j","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"","raw_type":"article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt9bd4t6v7","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9bd4t6v7","pdf_url":"https://escholarship.org/uc/item/9bd4t6v7","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"}],"best_oa_location":{"id":"doi:10.1145/3582514.3582517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3582514.3582517","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 14th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W751071243","https://openalex.org/W1568192366","https://openalex.org/W1968492450","https://openalex.org/W2049875313","https://openalex.org/W2055312318","https://openalex.org/W2171399035","https://openalex.org/W2798724095","https://openalex.org/W2925491732","https://openalex.org/W2979310060","https://openalex.org/W3217045543","https://openalex.org/W4206576098","https://openalex.org/W4241140669","https://openalex.org/W4281561529"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"We":[0,136],"introduce":[1],"Harmonic":[2,52,161],"CUDA,":[3,53],"a":[4,17,69,84,145,150],"dataflow":[5],"programming":[6,175],"model":[7],"for":[8,31,41],"GPUs":[9],"that":[10,82],"allows":[11],"programmers":[12,42],"to":[13,43,94,107,144,149,172],"describe":[14],"algorithms":[15],"as":[16,100,102,131],"dependency":[18],"graph":[19,30],"of":[20,34,87,89,105,140,160],"producers":[21],"and":[22,48,61,92,117,158,168],"consumers":[23],"where":[24],"data":[25],"flows":[26],"continuously":[27],"through":[28],"the":[29,32,35,111,127,132,156,174],"duration":[33],"kernel.":[36,135],"This":[37,153],"makes":[38],"it":[39],"easier":[40],"exploit":[44],"asynchrony,":[45],"warp":[46,118],"specialization,":[47],"hardware":[49],"acceleration.":[50],"Using":[51],"we":[54],"implement":[55],"two":[56],"example":[57],"applications:":[58],"Matrix":[59],"Multiplication":[60],"GraphSage.":[62],"The":[63],"matrix":[64,133],"multiplication":[65,134],"kernel":[66,71],"demonstrates":[67],"how":[68,106,115],"key":[70],"can":[72,120],"break":[73],"down":[74],"into":[75],"more":[76],"granular":[77],"building":[78,129],"blocks,":[79],"with":[80],"results":[81],"show":[83,137],"geomean":[85],"average":[86],"80%":[88],"cuBLAS":[90],"performance,":[91],"up":[93],"92%":[95],"when":[96],"omitting":[97],"small":[98],"matrices,":[99],"well":[101],"an":[103],"analysis":[104],"improve":[108,173],"performance":[109,123,138],"in":[110],"future.":[112],"GraphSage":[113],"shows":[114],"asynchrony":[116],"specialization":[119],"provide":[121],"significant":[122],"improvements":[124,139],"by":[125,142],"reusing":[126],"same":[128],"blocks":[130],"34%":[141],"changing":[143],"warp-specialized":[146],"version":[147],"compared":[148],"bulk-synchronous":[151],"implementation.":[152],"paper":[154],"evaluates":[155],"strengths":[157],"weaknesses":[159],"CUDA":[162],"based":[163],"on":[164],"these":[165],"test":[166],"cases":[167],"suggests":[169],"future":[170],"work":[171],"model.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}