{"id":"https://openalex.org/W2615291565","doi":"https://doi.org/10.1109/fpt.2016.7929185","title":"Integer computations with soft GPGPU on FPGAs","display_name":"Integer computations with soft GPGPU on FPGAs","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2615291565","doi":"https://doi.org/10.1109/fpt.2016.7929185","mag":"2615291565"},"language":"en","primary_location":{"id":"doi:10.1109/fpt.2016.7929185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2016.7929185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Field-Programmable Technology (FPT)","raw_type":"proceedings-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/A5003242515","display_name":"Muhammed Al Kadi","orcid":"https://orcid.org/0000-0003-0365-730X"},"institutions":[{"id":"https://openalex.org/I4210145666","display_name":"Embedded Systems (United States)","ror":"https://ror.org/04742eh45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210145666"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muhammed Al Kadi","raw_affiliation_strings":["Chair for Embedded Systems for Information Technology, Ruhr University of Bochum"],"affiliations":[{"raw_affiliation_string":"Chair for Embedded Systems for Information Technology, Ruhr University of Bochum","institution_ids":["https://openalex.org/I4210145666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114423005","display_name":"Michael Huebner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145666","display_name":"Embedded Systems (United States)","ror":"https://ror.org/04742eh45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210145666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Huebner","raw_affiliation_strings":["Chair for Embedded Systems for Information Technology, Ruhr University of Bochum"],"affiliations":[{"raw_affiliation_string":"Chair for Embedded Systems for Information Technology, Ruhr University of Bochum","institution_ids":["https://openalex.org/I4210145666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003242515"],"corresponding_institution_ids":["https://openalex.org/I4210145666"],"apc_list":null,"apc_paid":null,"fwci":0.6307,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70801204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"35"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9969000220298767,"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/coprocessor","display_name":"Coprocessor","score":0.8070725202560425},{"id":"https://openalex.org/keywords/microblaze","display_name":"MicroBlaze","score":0.7784104347229004},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615656852722168},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6879181265830994},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.66786789894104},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6332496404647827},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5611183047294617},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.5467345714569092},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5171208381652832},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5007460117340088},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.366626501083374},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09943285584449768}],"concepts":[{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.8070725202560425},{"id":"https://openalex.org/C2777575374","wikidata":"https://www.wikidata.org/wiki/Q1644704","display_name":"MicroBlaze","level":3,"score":0.7784104347229004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615656852722168},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6879181265830994},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.66786789894104},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6332496404647827},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5611183047294617},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.5467345714569092},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5171208381652832},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5007460117340088},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.366626501083374},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09943285584449768},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpt.2016.7929185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpt.2016.7929185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Field-Programmable Technology (FPT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W799594534","https://openalex.org/W1987163471","https://openalex.org/W2025981567","https://openalex.org/W2048166678","https://openalex.org/W2081286217","https://openalex.org/W2110202147","https://openalex.org/W2294577437","https://openalex.org/W2296385998","https://openalex.org/W2407650548","https://openalex.org/W2469289833","https://openalex.org/W4241765343","https://openalex.org/W4246166885","https://openalex.org/W6720453427"],"related_works":["https://openalex.org/W2166107669","https://openalex.org/W2213533160","https://openalex.org/W2154961667","https://openalex.org/W2467043670","https://openalex.org/W3203561460","https://openalex.org/W4252450863","https://openalex.org/W2022867993","https://openalex.org/W2051078434","https://openalex.org/W1554208380","https://openalex.org/W2682544458"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,56,64,90,108,113,116,120,123,141,155,166],"capabilities":[4],"and":[5,28,50,62,94,110,122],"limitations":[6],"of":[7,105,136],"soft":[8,21,84,125,143],"GPGPU-based":[9],"computing":[10],"on":[11,18,148],"fixed-point":[12],"arithmetic.":[13],"The":[14,44,72],"work":[15],"is":[16,42,75],"based":[17],"an":[19,60,69,101,133],"existing":[20],"GPU":[22,126],"architecture":[23,74],"which":[24],"has":[25],"been":[26],"improved":[27,73],"extended":[29,55],"to":[30,67,140,153,165],"cover":[31],"broader":[32],"benchmarks.":[33],"A":[34],"generic":[35],"ALU":[36],"design":[37],"for":[38,119],"modern":[39],"FPGA":[40],"architectures":[41],"presented.":[43],"enhanced":[45],"ISA":[46],"includes":[47],"conditional":[48],"instructions":[49],"global":[51],"atomic":[52],"operations.":[53],"We":[54,98,158],"tool":[57],"flow":[58],"with":[59,89,115],"LLVM-Backend":[61],"used":[63],"clang":[65],"frontend":[66],"provide":[68],"OpenCL":[70],"compiler.":[71],"evaluated":[76],"against":[77],"multiple":[78],"other":[79],"solutions:":[80],"a":[81,86],"single":[82,142],"MicroBlaze":[83,109],"processor,":[85],"Cortex-A9":[87],"ARM":[88,114],"NEON":[91,117],"vector":[92],"coprocessor":[93],"equivalent":[95],"HLS":[96,167],"implementations.":[97,168],"have":[99,132],"recorded":[100],"average":[102,149],"speed":[103],"up":[104],"10-47\u00d7":[106],"over":[107,112],"0.6-3.4\u00d7":[111],"engine":[118],"smallest":[121],"biggest":[124],"cores,":[127],"respectively.":[128],"Although":[129],"these":[130],"cores":[131],"area":[134],"overhead":[135],"6-22\u00d7":[137],"in":[138,163],"comparison":[139,164],"processor":[144],"solution,":[145],"they":[146],"consumed":[147],"2.8-7.1\u00d7":[150],"less":[151],"energy":[152],"perform":[154],"same":[156],"tasks.":[157],"noticed":[159],"no":[160],"performance":[161],"degradation":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}