{"id":"https://openalex.org/W2141597697","doi":"https://doi.org/10.1109/sasp.2009.5226333","title":"FCUDA: Enabling efficient compilation of CUDA kernels onto FPGAs","display_name":"FCUDA: Enabling efficient compilation of CUDA kernels onto FPGAs","publication_year":2009,"publication_date":"2009-07-01","ids":{"openalex":"https://openalex.org/W2141597697","doi":"https://doi.org/10.1109/sasp.2009.5226333","mag":"2141597697"},"language":"en","primary_location":{"id":"doi:10.1109/sasp.2009.5226333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2009.5226333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 7th Symposium on Application Specific Processors","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":["Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, 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":["Computer Science Dept, University of California, Los Angeles, CA, USA","[Computer Science Department, University of California, Los Angeles, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"[Computer Science Department, University of California, Los Angeles, 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":["Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"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":["Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, 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":["Computer Science Dept, University of California, Los Angeles, CA, USA","[Computer Science Department, University of California, Los Angeles, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"[Computer Science Department, University of California, Los Angeles, 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":["Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Electrical and Computer Engineering Dept., University of Illinois, Urbana-Champaign, 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":161,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10904","display_name":"Embedded Systems Design 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/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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":0.861457109451294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8369854688644409},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7525084018707275},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5633204579353333},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5337154865264893},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4448801279067993},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.43633025884628296},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4280015528202057},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.4198855757713318},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4169186055660248},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.27958178520202637},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11257845163345337}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.861457109451294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8369854688644409},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7525084018707275},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5633204579353333},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5337154865264893},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4448801279067993},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.43633025884628296},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4280015528202057},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.4198855757713318},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4169186055660248},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27958178520202637},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11257845163345337}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sasp.2009.5226333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2009.5226333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 7th Symposium on Application Specific Processors","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W118713324","https://openalex.org/W180636684","https://openalex.org/W1502558230","https://openalex.org/W1517684295","https://openalex.org/W1772887859","https://openalex.org/W1979081194","https://openalex.org/W1991973578","https://openalex.org/W2042421148","https://openalex.org/W2098606213","https://openalex.org/W2113755305","https://openalex.org/W2123173853","https://openalex.org/W2170675383","https://openalex.org/W2191327475","https://openalex.org/W2270278874","https://openalex.org/W6604839928","https://openalex.org/W6607324002","https://openalex.org/W6630937574","https://openalex.org/W6638172817","https://openalex.org/W6660828548","https://openalex.org/W6678437948","https://openalex.org/W6694235415"],"related_works":["https://openalex.org/W2162273319","https://openalex.org/W2482815832","https://openalex.org/W2294358097","https://openalex.org/W2189498595","https://openalex.org/W1993191611","https://openalex.org/W1999755551","https://openalex.org/W2150820374","https://openalex.org/W2578331457","https://openalex.org/W2029518214","https://openalex.org/W4238392246"],"abstract_inverted_index":{"As":[0],"growing":[1],"power":[2],"dissipation":[3],"and":[4,13,70,89,131,153,180,236,265],"thermal":[5],"effects":[6],"disrupted":[7],"the":[8,19,44,61,110,123,128,150,163,178,188,217,230,238,243,250,257,263,270],"rising":[9],"clock":[10],"frequency":[11],"trend":[12],"threatened":[14],"to":[15,26,46,58,126,261],"annul":[16],"Moore's":[17],"law,":[18],"computing":[20,41,144,276],"industry":[21,152],"has":[22,42,125],"switched":[23],"its":[24],"route":[25],"higher":[27],"performance":[28,62,241],"through":[29],"parallel":[30,106,143,223],"processing.":[31],"The":[32],"rise":[33],"of":[34,40,51,65,86,96,232,242,252,268],"multicore":[35],"systems":[36,79],"in":[37,76,113,185,277],"all":[38],"domains":[39],"opened":[43],"door":[45],"heterogeneous":[47,78],"multiprocessor,":[48],"where":[49],"processors":[50],"different":[52,66],"compute":[53,83],"characteristics":[54],"can":[55,93],"be":[56],"combined":[57],"effectively":[59],"boost":[60],"per":[63],"watt":[64],"application":[67],"kernels.":[68,107],"GPUs":[69,92],"FPGAs":[71,100],"are":[72],"becoming":[73],"very":[74],"popular":[75],"PC-based":[77],"for":[80,104,226,274],"speeding":[81],"up":[82],"intensive":[84],"kernels":[85],"scientific,":[87],"imaging":[88],"simulation":[90],"applications.":[91],"execute":[94],"hundreds":[95],"concurrent":[97],"threads,":[98],"while":[99],"provide":[101],"customized":[102,245],"concurrency":[103],"highly":[105,239],"However,":[108],"exploiting":[109],"parallelism":[111,134,183],"available":[112],"these":[114],"applications":[115],"is":[116,140,147,154,209,256],"currently":[117],"not":[118],"a":[119,142,168,212],"push-button":[120],"task.":[121],"Often":[122],"programmer":[124],"expose":[127],"application's":[129],"fine":[130,181],"coarse":[132,179],"grained":[133,182],"by":[135,149],"using":[136,269],"special":[137],"APIs.":[138],"CUDA":[139,164,186,219,271],"such":[141],"API":[145],"that":[146,215],"driven":[148],"GPU":[151],"gaining":[155],"significant":[156],"popularity.":[157],"In":[158],"this":[159,255],"work,":[160],"we":[161],"adapt":[162],"programming":[165,272],"model":[166,273],"into":[167,222],"new":[169],"FPGA":[170,206,246],"design":[171],"flow":[172,193,235,260],"called":[173],"FCUDA,":[174],"which":[175,202],"efficiently":[176],"maps":[177],"exposed":[184],"onto":[187],"reconfigurable":[189],"fabric.":[190],"Our":[191],"CUDA-to-FPGA":[192,234,259],"employs":[194],"autopilot,":[195],"an":[196],"advanced":[197],"high":[198,204],"level":[199],"synthesis":[200],"tool":[201],"enables":[203],"abstraction":[205],"programming.":[207],"FCUDA":[208],"based":[210],"on":[211],"source-to-source":[213],"compilation":[214],"transforms":[216],"SPMD":[218],"thread":[220],"blocks":[221],"C":[224],"code":[225],"autopilot.":[227],"We":[228],"describe":[229],"details":[231],"our":[233,253],"demonstrate":[237,262],"competitive":[240],"resulting":[244],"multi-core":[247],"accelerators.":[248],"To":[249],"best":[251],"knowledge,":[254],"first":[258],"applicability":[264],"potential":[266],"advantage":[267],"high-performance":[275],"FPGAs.":[278]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":19}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}