{"id":"https://openalex.org/W2037978941","doi":"https://doi.org/10.1145/1542275.1542357","title":"High-performance CUDA kernel execution on FPGAs","display_name":"High-performance CUDA kernel execution on FPGAs","publication_year":2009,"publication_date":"2009-06-08","ids":{"openalex":"https://openalex.org/W2037978941","doi":"https://doi.org/10.1145/1542275.1542357","mag":"2037978941"},"language":"en","primary_location":{"id":"doi:10.1145/1542275.1542357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103718660","display_name":"Alexandros Papakonstantinou","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":"Alexandros Papakonstantinou","raw_affiliation_strings":["University of Illinois, Urbana - Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana - Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111994199","display_name":"Karthik Gururaj","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Gururaj","raw_affiliation_strings":["University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034958091","display_name":"John A. Stratton","orcid":"https://orcid.org/0000-0002-3625-9781"},"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":"John A. Stratton","raw_affiliation_strings":["University of Illinois, Urbana - Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana - Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Deming Chen","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":"Deming Chen","raw_affiliation_strings":["University of Illinois, Urbana - Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana - Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["University of California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"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 W. Hwu","raw_affiliation_strings":["University of Illinois, Urbana - Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana - Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design 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/T10904","display_name":"Embedded Systems Design 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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9980999827384949,"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/cuda","display_name":"CUDA","score":0.9150160551071167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8097530603408813},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7020682692527771},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.644212007522583},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.504529595375061},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4516073167324066},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.44135671854019165},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.30563804507255554},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1656036376953125},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12438353896141052}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9150160551071167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097530603408813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7020682692527771},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.644212007522583},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.504529595375061},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4516073167324066},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.44135671854019165},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30563804507255554},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1656036376953125},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12438353896141052},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":1,"locations":[{"id":"doi:10.1145/1542275.1542357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1502558230","https://openalex.org/W1517684295"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W2076165488","https://openalex.org/W4236300446"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,80],"propose":[4],"a":[5,53,97],"new":[6],"FPGA":[7,86],"design":[8],"flow":[9,93,118],"that":[10,100],"combines":[11],"the":[12,19,22,33,45,50,74,85,102,121,126],"CUDA":[13,37,46,104],"programming":[14,47,55],"model":[15,48],"from":[16,28],"Nvidia":[17],"with":[18],"state":[20],"of":[21,44,52,65,78,84,115,125],"art":[23],"high-level":[24],"synthesis":[25,76],"tool":[26],"AutoPilot":[27,79],"AutoESL,":[29],"to":[30],"efficiently":[31],"map":[32],"exposed":[34],"parallelism":[35,59],"in":[36],"kernels":[38],"onto":[39],"reconfigurable":[40],"devices.":[41],"The":[42],"use":[43],"offers":[49],"advantage":[51],"common":[54],"interface":[56],"for":[57,88],"exploiting":[58],"on":[60,96],"two":[61],"very":[62],"different":[63],"types":[64],"accelerators":[66],"--":[67],"FPGAs":[68],"and":[69,119],"GPUs.":[70],"Moreover,":[71],"by":[72],"leveraging":[73],"advanced":[75],"capabilities":[77],"enable":[81],"efficient":[82],"exploitation":[83],"configurability":[87],"application":[89],"specific":[90],"acceleration.":[91],"Our":[92],"is":[94],"based":[95],"compilation":[98],"process":[99],"transforms":[101],"SPMD":[103],"thread":[105],"blocks":[106],"into":[107],"high-concurrency":[108],"AutoPilot-C":[109],"code.":[110],"We":[111],"provide":[112],"an":[113],"overview":[114],"our":[116],"CUDA-to-FPGA":[117],"demonstrate":[120],"highly":[122],"competitive":[123],"performance":[124],"generated":[127],"multi-core":[128],"accelerators.":[129]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}