{"id":"https://openalex.org/W2021944457","doi":"https://doi.org/10.1145/2514641.2514652","title":"Efficient compilation of CUDA kernels for high-performance computing on FPGAs","display_name":"Efficient compilation of CUDA kernels for high-performance computing on FPGAs","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2021944457","doi":"https://doi.org/10.1145/2514641.2514652","mag":"2021944457"},"language":"en","primary_location":{"id":"doi:10.1145/2514641.2514652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2514641.2514652","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"type":"article","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":true,"raw_author_name":"Alexandros Papakonstantinou","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL","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","University of California, Los Angeles. CA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles. CA","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 at Urbana-Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL","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":["University of Illinois at Urbana-Champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL","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","University of California, Los Angeles. CA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles. CA","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 at Urbana-champaign, IL"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-champaign, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103718660"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":5.3915,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.95573163,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"13","issue":"2","first_page":"1","last_page":"26"},"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":0.9998000264167786,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.9413343667984009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8544838428497314},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.690339982509613},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6708559989929199},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5814263224601746},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5187520980834961},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4533197581768036},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4352284073829651},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4295646846294403},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36626893281936646},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.26612383127212524},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.16539952158927917},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1302585005760193},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12827613949775696}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9413343667984009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8544838428497314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.690339982509613},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6708559989929199},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5814263224601746},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5187520980834961},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4533197581768036},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4352284073829651},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4295646846294403},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36626893281936646},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26612383127212524},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.16539952158927917},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1302585005760193},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12827613949775696}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2514641.2514652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2514641.2514652","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W118713324","https://openalex.org/W180636684","https://openalex.org/W1494930385","https://openalex.org/W1500117749","https://openalex.org/W1502558230","https://openalex.org/W1517684295","https://openalex.org/W1772887859","https://openalex.org/W1979081194","https://openalex.org/W2082085231","https://openalex.org/W2082956176","https://openalex.org/W2089641827","https://openalex.org/W2098606213","https://openalex.org/W2113755305","https://openalex.org/W2123173853","https://openalex.org/W2131355383","https://openalex.org/W2146851106","https://openalex.org/W2166029537","https://openalex.org/W2170675383","https://openalex.org/W2171429297","https://openalex.org/W2191327475","https://openalex.org/W2270278874","https://openalex.org/W6607324002"],"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/W3037515626"],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,18,32,48,79,180,190,200,216],"multicore":[3,195],"architectures":[4],"across":[5],"all":[6],"computing":[7,71,224],"domains":[8],"has":[9],"opened":[10],"the":[11,28,70,77,88,107,122,131,161,178,186,191,198,205,211,218],"door":[12],"to":[13,25,85,209],"heterogeneous":[14,62],"multiprocessors,":[15],"where":[16],"processors":[17],"different":[19,33],"compute":[20],"characteristics":[21],"can":[22],"be":[23],"combined":[24],"effectively":[26],"boost":[27],"performance":[29,189],"per":[30],"watt":[31],"application":[34],"kernels.":[35],"GPUs,":[36],"in":[37,69,128,225],"particular,":[38],"are":[39,66],"becoming":[40],"very":[41],"popular":[42],"for":[43,174,222],"speeding":[44],"up":[45],"compute-intensive":[46],"kernels":[47],"scientific,":[49],"imaging,":[50],"and":[51,124,184,213],"simulation":[52],"applications.":[53],"New":[54],"programming":[55,89,109,220],"models":[56,95],"that":[57,159],"facilitate":[58],"parallel":[59,171],"processing":[60],"on":[61,155],"systems":[63],"containing":[64],"GPUs":[65],"spreading":[67],"rapidly":[68],"community.":[72],"By":[73],"leveraging":[74],"these":[75],"investments,":[76],"developers":[78],"other":[80],"accelerators":[81],"have":[82],"an":[83,139],"opportunity":[84],"significantly":[86],"reduce":[87],"effort":[90],"by":[91],"supporting":[92],"those":[93],"accelerator":[94],"already":[96],"gaining":[97],"popularity.":[98],"In":[99],"this":[100,203],"work,":[101],"we":[102],"adapt":[103],"one":[104],"such":[105],"language,":[106],"CUDA":[108,129,167,219],"model,":[110],"into":[111,169],"a":[112,156],"new":[113],"FPGA":[114,150,194],"design":[115],"flow":[116,136,183,208],"called":[117],"FCUDA,":[118],"which":[119,147],"efficiently":[120],"maps":[121],"coarse-":[123],"fine-grained":[125],"parallelism":[126],"exposed":[127],"onto":[130],"reconfigurable":[132],"fabric.":[133],"Our":[134],"CUDA-to-FPGA":[135,182,207],"employs":[137],"AutoPilot,":[138],"advanced":[140],"high-level":[141],"synthesis":[142],"tool":[143],"(available":[144],"from":[145],"Xilinx)":[146],"enables":[148],"high-abstraction":[149],"programming.":[151],"FCUDA":[152],"is":[153,204],"based":[154],"source-to-source":[157],"compilation":[158],"transforms":[160],"SIMT":[162],"(Single":[163],"Instruction,":[164],"Multiple":[165],"Thread)":[166],"code":[168,173],"task-level":[170],"C":[172],"AutoPilot.":[175],"We":[176],"describe":[177],"details":[179],"our":[181,201],"demonstrate":[185,210],"highly":[187],"competitive":[188],"resulting":[192],"customized":[193],"accelerators.":[196],"To":[197],"best":[199],"knowledge,":[202],"first":[206],"applicability":[212],"potential":[214],"advantage":[215],"using":[217],"model":[221],"high-performance":[223],"FPGAs.":[226]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}