{"id":"https://openalex.org/W2296385998","doi":"https://doi.org/10.1145/2847263.2847273","title":"FGPU","display_name":"FGPU","publication_year":2016,"publication_date":"2016-02-04","ids":{"openalex":"https://openalex.org/W2296385998","doi":"https://doi.org/10.1145/2847263.2847273","mag":"2296385998"},"language":"en","primary_location":{"id":"doi:10.1145/2847263.2847273","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2847263.2847273","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2847263.2847273","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2847263.2847273","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003242515","display_name":"Muhammed Al Kadi","orcid":"https://orcid.org/0000-0003-0365-730X"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Muhammed Al Kadi","raw_affiliation_strings":["Ruhr University of Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr University of Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014124149","display_name":"Benedikt Jan\u00dfen","orcid":"https://orcid.org/0000-0002-4512-9268"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benedikt Janssen","raw_affiliation_strings":["Ruhr University of Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr University of Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114423005","display_name":"Michael Huebner","orcid":null},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Huebner","raw_affiliation_strings":["Ruhr University of Bochum, Bochum, Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr University of Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003242515"],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":3.784,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.93097611,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"254","last_page":"263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization 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/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/T10829","display_name":"Interconnection Networks and Systems","score":0.9991999864578247,"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/microblaze","display_name":"MicroBlaze","score":0.8489683866500854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.802406370639801},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6701151132583618},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6358058452606201},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6307913064956665},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6203694343566895},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6168121099472046},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5956443548202515},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5264323949813843},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5190796852111816},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.47649091482162476},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.47174155712127686},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.42746835947036743},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1776818037033081}],"concepts":[{"id":"https://openalex.org/C2777575374","wikidata":"https://www.wikidata.org/wiki/Q1644704","display_name":"MicroBlaze","level":3,"score":0.8489683866500854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802406370639801},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6701151132583618},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6358058452606201},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6307913064956665},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6203694343566895},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6168121099472046},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5956443548202515},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5264323949813843},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5190796852111816},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.47649091482162476},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.47174155712127686},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.42746835947036743},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1776818037033081},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2847263.2847273","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2847263.2847273","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2847263.2847273","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2847263.2847273","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2847263.2847273","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2847263.2847273","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2296385998.pdf","grobid_xml":"https://content.openalex.org/works/W2296385998.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W799594534","https://openalex.org/W1973012690","https://openalex.org/W1978078023","https://openalex.org/W1987163471","https://openalex.org/W2025981567","https://openalex.org/W2037748535","https://openalex.org/W2054951389","https://openalex.org/W2055644941","https://openalex.org/W2075329791","https://openalex.org/W2078555859","https://openalex.org/W2081286217","https://openalex.org/W2099084006","https://openalex.org/W2102325484","https://openalex.org/W2141597697","https://openalex.org/W2157855196","https://openalex.org/W2160126455","https://openalex.org/W2171429297"],"related_works":["https://openalex.org/W2291943064","https://openalex.org/W2166107669","https://openalex.org/W2154961667","https://openalex.org/W2209727271","https://openalex.org/W2113902926","https://openalex.org/W2027176516","https://openalex.org/W3012895752","https://openalex.org/W2001957815","https://openalex.org/W2143461502","https://openalex.org/W1511993241"],"abstract_inverted_index":{"Driven":[0],"by":[1],"its":[2],"high":[3],"flexibility,":[4],"good":[5],"performance":[6],"and":[7,34,42,75,113],"energy":[8],"efficiency,":[9],"GPGPU":[10],"has":[11],"taken":[12],"on":[13,58],"an":[14,83,90,100],"increasingly":[15],"important":[16],"role":[17],"in":[18,40],"embedded":[19],"systems.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24,98],"present":[25],"the":[26,59,62,106],"basic":[27],"core":[28,65],"of":[29,66,73,80,86,103],"FGPU:":[30],"a":[31,48,54,76,94],"GPU-like,":[32],"scalable":[33],"portable":[35],"integer":[36],"soft":[37],"SIMT-processor":[38],"implemented":[39,64],"RTL":[41],"optimized":[43],"for":[44],"FPGA":[45],"synthesis":[46],"with":[47,82,93],"single-level":[49],"cache":[50],"system.":[51],"Compared":[52,88],"to":[53,89],"performance-optimized":[55],"MicroBlaze":[56],"implementation":[57],"same":[60],"FPGA,":[61],"biggest":[63],"FGPU":[67,109],"achieves":[68],"average":[69,101],"wall":[70],"clock":[71],"speedups":[72],"49x":[74],"measured":[77,99],"power":[78],"saving":[79],"3.7x":[81],"area":[84],"overhead":[85],"17.7x.":[87],"ARM":[91],"CPU":[92],"NEON":[95],"vector":[96],"processor,":[97],"speedup":[102],"3.5x":[104],"over":[105],"used":[107],"benchmark.":[108],"is":[110],"highly":[111],"parametrizable":[112],"it":[114],"does":[115],"not":[116],"contain":[117],"any":[118],"manufacturer-specific":[119],"IP-cores":[120],"or":[121],"primitives.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}