{"id":"https://openalex.org/W2081228314","doi":"https://doi.org/10.1145/2463209.2488747","title":"Throughput-oriented kernel porting onto FPGAs","display_name":"Throughput-oriented kernel porting onto FPGAs","publication_year":2013,"publication_date":"2013-05-28","ids":{"openalex":"https://openalex.org/W2081228314","doi":"https://doi.org/10.1145/2463209.2488747","mag":"2081228314"},"language":"en","primary_location":{"id":"doi:10.1145/2463209.2488747","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463209.2488747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual Design Automation Conference","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","[ECE Department, University of Illinois, Urbana, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[ECE Department, University of Illinois, Urbana, IL, 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":["University of Illinois, Urbana-Champaign, IL","[ECE Department, University of Illinois, Urbana, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[ECE Department, University of Illinois, Urbana, IL, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","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 Hwu","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, IL","[ECE Department, University of Illinois, Urbana, IL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, IL","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[ECE Department, University of Illinois, Urbana, 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, California","[CS Department, University of California, Los Angeles, Los Angeles, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, California","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"[CS Department, University of California, Los Angeles, Los Angeles, CA, USA]","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Peking University, Beijing, China","EECS School, Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"EECS School, Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8349227905273438},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6817435026168823},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.6763030290603638},{"id":"https://openalex.org/keywords/tweaking","display_name":"Tweaking","score":0.660741925239563},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5830002427101135},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5543820858001709},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5215856432914734},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4738474488258362},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.46412304043769836},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4368625283241272},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4326934814453125},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.42508891224861145},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.4143919348716736},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.34136420488357544},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.21991464495658875},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16543835401535034},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16274097561836243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349227905273438},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6817435026168823},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.6763030290603638},{"id":"https://openalex.org/C2780200862","wikidata":"https://www.wikidata.org/wiki/Q4453309","display_name":"Tweaking","level":2,"score":0.660741925239563},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5830002427101135},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5543820858001709},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5215856432914734},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4738474488258362},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.46412304043769836},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4368625283241272},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4326934814453125},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.42508891224861145},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.4143919348716736},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.34136420488357544},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.21991464495658875},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16543835401535034},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16274097561836243},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2463209.2488747","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2463209.2488747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 50th Annual Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1500117749","https://openalex.org/W1987304299","https://openalex.org/W2021944457","https://openalex.org/W2044636417","https://openalex.org/W2045856677","https://openalex.org/W2047301304","https://openalex.org/W2055813380","https://openalex.org/W2082085231","https://openalex.org/W2108019747","https://openalex.org/W2111365507","https://openalex.org/W2114067856","https://openalex.org/W2124556751","https://openalex.org/W2141597697","https://openalex.org/W2171429297","https://openalex.org/W2191327475","https://openalex.org/W3001659479","https://openalex.org/W3148529197","https://openalex.org/W6677084613","https://openalex.org/W6687987274"],"related_works":["https://openalex.org/W2621501241","https://openalex.org/W2208757713","https://openalex.org/W3177128669","https://openalex.org/W2991848348","https://openalex.org/W2092972055","https://openalex.org/W2956082141","https://openalex.org/W4236300446","https://openalex.org/W3037515626","https://openalex.org/W4394633758","https://openalex.org/W2502510154"],"abstract_inverted_index":{"Reconfigurable":[0],"devices":[1,71],"are":[2,67],"often":[3],"employed":[4,115],"in":[5,72,103],"heterogeneous":[6,49],"systems":[7],"due":[8],"to":[9,41,74,116],"their":[10],"low":[11],"power":[12],"and":[13,62,108],"parallel":[14],"processing":[15],"advantages.":[16],"An":[17],"important":[18],"usability":[19],"requirement":[20],"is":[21,114],"the":[22,36,46,97,118],"support":[23],"of":[24,45,77,111],"a":[25,56],"homogeneous":[26,30],"programming":[27,31],"interface.":[28],"Nevertheless,":[29],"interfaces":[32],"do":[33],"not":[34],"eliminate":[35],"need":[37],"for":[38,69,120],"code":[39,57,92,106],"tweaking":[40,93],"enable":[42],"efficient":[43,87],"mapping":[44],"computation":[47],"across":[48],"architectures.":[50],"In":[51],"this":[52],"work":[53],"we":[54],"propose":[55],"optimization":[58],"framework":[59,85],"which":[60],"analyzes":[61],"restructures":[63],"CUDA":[64],"kernels":[65],"that":[66],"optimized":[68],"GPU":[70],"order":[73],"facilitate":[75],"synthesis":[76],"high-throughput":[78],"custom":[79],"accelerators":[80],"on":[81,124],"FPGAs.":[82,125],"The":[83],"proposed":[84],"enables":[86],"performance":[88],"porting":[89],"without":[90],"manual":[91],"or":[94],"annotation":[95],"by":[96],"user.":[98],"A":[99],"hierarchical":[100],"region":[101],"graph":[102,109],"tandem":[104],"with":[105],"motions":[107],"coloring":[110],"array":[112],"variables":[113],"restructure":[117],"kernel":[119],"high":[121],"throughput":[122],"execution":[123]},"counts_by_year":[{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}