{"id":"https://openalex.org/W2006153695","doi":"https://doi.org/10.1109/asap.2013.6567570","title":"A practical measure of FPGA floating point acceleration for High Performance Computing","display_name":"A practical measure of FPGA floating point acceleration for High Performance Computing","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W2006153695","doi":"https://doi.org/10.1109/asap.2013.6567570","mag":"2006153695"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2013.6567570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2013.6567570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors","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/A5080993754","display_name":"John D. Cappello","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164786","display_name":"Optimal Solutions (United States)","ror":"https://ror.org/05t1cnz26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164786"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John D. Cappello","raw_affiliation_strings":["Optimal Design, Inc., Sewell, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Optimal Design, Inc., Sewell, NJ, USA","institution_ids":["https://openalex.org/I4210164786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045415745","display_name":"Dave Strenski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dave Strenski","raw_affiliation_strings":["Cray, Inc., Ypsilanti, MI, USA"],"affiliations":[{"raw_affiliation_string":"Cray, Inc., Ypsilanti, MI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080993754"],"corresponding_institution_ids":["https://openalex.org/I4210164786"],"apc_list":null,"apc_paid":null,"fwci":3.2629,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91782859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"160","last_page":"167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9958999752998352,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8584033846855164},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.8491629362106323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7755964994430542},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.6541144847869873},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5276062488555908},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5140991806983948},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.45506522059440613},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4392229914665222},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.43871426582336426},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.42736685276031494},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.4259454309940338},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.42123883962631226},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4176831543445587},{"id":"https://openalex.org/keywords/virtex","display_name":"Virtex","score":0.4140453040599823},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3457968533039093},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13675493001937866},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10000297427177429}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8584033846855164},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8491629362106323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755964994430542},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.6541144847869873},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5276062488555908},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5140991806983948},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.45506522059440613},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4392229914665222},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.43871426582336426},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.42736685276031494},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.4259454309940338},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.42123883962631226},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4176831543445587},{"id":"https://openalex.org/C2777674469","wikidata":"https://www.wikidata.org/wiki/Q20741011","display_name":"Virtex","level":3,"score":0.4140453040599823},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3457968533039093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13675493001937866},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10000297427177429},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2013.6567570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2013.6567570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W114677020","https://openalex.org/W1995812446","https://openalex.org/W2004402373","https://openalex.org/W2020015841","https://openalex.org/W2022020111","https://openalex.org/W2061624656","https://openalex.org/W2072172623","https://openalex.org/W2096280516","https://openalex.org/W2119834363","https://openalex.org/W2124408528","https://openalex.org/W2135440091","https://openalex.org/W2166000469"],"related_works":["https://openalex.org/W2560894929","https://openalex.org/W2156524298","https://openalex.org/W2152567198","https://openalex.org/W2058520863","https://openalex.org/W1519183141","https://openalex.org/W3151101169","https://openalex.org/W4252744808","https://openalex.org/W2106942255","https://openalex.org/W2017144313","https://openalex.org/W2142315955"],"abstract_inverted_index":{"A":[0],"key":[1],"enabler":[2],"for":[3,39,115],"Field":[4],"Programmable":[5],"Gate":[6],"Arrays":[7],"(FPGAs)":[8],"in":[9,50],"High":[10],"Performance":[11],"Computing":[12],"(HPC)":[13],"has":[14],"been":[15],"the":[16,78,97,117,136],"addition":[17],"of":[18,24,63,96,120,131,141],"hard":[19],"arithmetic":[20],"cores.":[21],"These":[22],"\u201cslices":[23],"DSP\u201d":[25],"dedicated":[26],"to":[27,33,57,91,105,135],"accelerated":[28],"number":[29],"crunching":[30],"allow":[31],"FPGAs":[32],"deliver":[34],"more":[35],"computing":[36],"muscle,":[37],"especially":[38],"floating":[40,65],"point":[41,66],"algorithms.":[42],"This":[43],"paper":[44],"compares":[45],"how":[46],"an":[47],"FPGA's":[48],"performance":[49,129],"a":[51,64,72,102,113,126],"practical":[52],"HPC":[53],"application":[54],"measures":[55],"up":[56],"its":[58],"theoretical":[59],"capacity.":[60],"The":[61,123],"implementation":[62],"matrix":[67],"multiplication":[68],"algorithm":[69],"based":[70],"on":[71],"12x12":[73],"MAC":[74],"(MultiplyAccumulate)":[75],"array":[76,98],"targeting":[77],"Xilinx":[79],"Virtex":[80],"7":[81],"XT":[82],"family":[83],"is":[84,125],"described.":[85],"Several":[86],"design":[87],"techniques":[88],"were":[89],"used":[90],"ensure":[92],"uninterrupted":[93],"systolic":[94],"operation":[95],"throughout":[99],"execution,":[100],"including":[101],"novel":[103],"approach":[104],"handling":[106],"heavily":[107],"pipelined":[108],"accumulators,":[109],"as":[110,112],"well":[111],"scheme":[114],"overcoming":[116],"inherent":[118],"inefficiencies":[119],"DDR3":[121],"memory.":[122],"result":[124],"sustained":[127],"\"practical\"":[128],"range":[130,140],"144-180":[132],"GFLOPS,":[133],"compared":[134],"target":[137],"device's":[138],"\"theoretical\"":[139],"257-290":[142],"GFLOPS.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}