{"id":"https://openalex.org/W1861262881","doi":"https://doi.org/10.1109/ipdps.2004.1303135","title":"Analysis of high-performance floating-point arithmetic on FPGAs","display_name":"Analysis of high-performance floating-point arithmetic on FPGAs","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W1861262881","doi":"https://doi.org/10.1109/ipdps.2004.1303135","mag":"1861262881"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2004.1303135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","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/A5084637859","display_name":"Gokul Govindu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"G. Govindu","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029288518","display_name":"Ling Zhuo","orcid":"https://orcid.org/0000-0001-9244-0115"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Zhuo","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109895640","display_name":"Seonil Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seonil Choi","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033166029","display_name":"Viktor K. Prasanna","orcid":"https://orcid.org/0000-0002-1609-8589"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V. Prasanna","raw_affiliation_strings":["Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Dept. of Electr. Eng. Univ. of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084637859"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":15.5568,"has_fulltext":false,"cited_by_count":138,"citation_normalized_percentile":{"value":0.99407328,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9961000084877014,"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":0.989799976348877,"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/flops","display_name":"FLOPS","score":0.8209342360496521},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.8041287660598755},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.7964755296707153},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.7593839764595032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7174285054206848},{"id":"https://openalex.org/keywords/adder","display_name":"Adder","score":0.6908817887306213},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6419034600257874},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6186236143112183},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5900499820709229},{"id":"https://openalex.org/keywords/floating-point-unit","display_name":"Floating-point unit","score":0.5887974500656128},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5324310660362244},{"id":"https://openalex.org/keywords/subtractor","display_name":"Subtractor","score":0.5076838731765747},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.48851215839385986},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.48275917768478394},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4615146815776825},{"id":"https://openalex.org/keywords/arithmetic-logic-unit","display_name":"Arithmetic logic unit","score":0.42976728081703186},{"id":"https://openalex.org/keywords/ieee-floating-point","display_name":"IEEE floating point","score":0.42533084750175476},{"id":"https://openalex.org/keywords/multiplier","display_name":"Multiplier (economics)","score":0.415240615606308},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3735135793685913},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21678724884986877},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16104546189308167},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.13704133033752441}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.8209342360496521},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.8041287660598755},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.7964755296707153},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.7593839764595032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174285054206848},{"id":"https://openalex.org/C164620267","wikidata":"https://www.wikidata.org/wiki/Q376953","display_name":"Adder","level":3,"score":0.6908817887306213},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6419034600257874},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6186236143112183},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5900499820709229},{"id":"https://openalex.org/C110305270","wikidata":"https://www.wikidata.org/wiki/Q733507","display_name":"Floating-point unit","level":3,"score":0.5887974500656128},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5324310660362244},{"id":"https://openalex.org/C187805909","wikidata":"https://www.wikidata.org/wiki/Q1142401","display_name":"Subtractor","level":4,"score":0.5076838731765747},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.48851215839385986},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.48275917768478394},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4615146815776825},{"id":"https://openalex.org/C100276221","wikidata":"https://www.wikidata.org/wiki/Q192903","display_name":"Arithmetic logic unit","level":2,"score":0.42976728081703186},{"id":"https://openalex.org/C137231763","wikidata":"https://www.wikidata.org/wiki/Q828287","display_name":"IEEE floating point","level":3,"score":0.42533084750175476},{"id":"https://openalex.org/C124584101","wikidata":"https://www.wikidata.org/wiki/Q1053266","display_name":"Multiplier (economics)","level":2,"score":0.415240615606308},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3735135793685913},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21678724884986877},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16104546189308167},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.13704133033752441},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2004.1303135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.5299","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.5299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://halcyon.usc.edu/~pk/prasannawebsite/papers/govindu_raw04b.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"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":11,"referenced_works":["https://openalex.org/W112541915","https://openalex.org/W1511216606","https://openalex.org/W1555915743","https://openalex.org/W1568503047","https://openalex.org/W2120978237","https://openalex.org/W2121332089","https://openalex.org/W2725179571","https://openalex.org/W4285719527","https://openalex.org/W6604555392","https://openalex.org/W6634007925","https://openalex.org/W6678452266"],"related_works":["https://openalex.org/W2596474508","https://openalex.org/W2797902698","https://openalex.org/W3215589575","https://openalex.org/W2551364683","https://openalex.org/W4243574357","https://openalex.org/W2363539709","https://openalex.org/W2116803521","https://openalex.org/W4383333895","https://openalex.org/W2585218747","https://openalex.org/W2405380156"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"FPGAs":[4,122],"are":[5,123],"increasingly":[6],"being":[7],"used":[8],"in":[9,134],"the":[10,25,33,39,48,69,73,76,110,137,153,159,167],"high":[11],"performance":[12],"and":[13,28,44,93],"scientific":[14],"computing":[15],"community":[16],"to":[17,128],"implement":[18,83],"floating-point":[19,26,77,91,114,156],"based":[20,88,115],"hardware":[21],"accelerators.":[22],"We":[23,50,118,150],"analyze":[24],"multiplier":[27],"adder/subtractor":[29],"units":[30,40,78,92,157],"by":[31,66],"considering":[32],"number":[34],"of":[35,38,54,75,102,125,136,146,155,161],"pipeline":[36],"stages":[37],"as":[41,47],"a":[42,80,84,96],"parameter":[43],"use":[45],"throughput/area":[46],"metric.":[49],"achieve":[51],"throughput":[52],"rates":[53],"more":[55],"than":[56],"240":[57],"Mhz":[58],"(200":[59],"Mhz)":[60],"for":[61,109,166],"single":[62,111,132],"(double)":[63,112],"precision":[64,113],"operations":[65],"deeply":[67],"pipelining":[68],"units.":[70],"To":[71],"illustrate":[72],"impact":[74,154],"on":[79,89,158],"kernel,":[81],"we":[82],"matrix":[85,116,168],"multiplication":[86],"kernel":[87],"our":[90],"show":[94,120],"that":[95,121,145],"state-of-the-art":[97],"FPGA":[98],"device":[99],"is":[100],"capable":[101,124],"achieving":[103,126],"about":[104],"15":[105],"GFLOPS":[106],"(8":[107],"GFLOPS)":[108],"multiplication.":[117],"also":[119],"up":[127],"6x":[129],"improvement":[130],"(for":[131],"precision)":[133],"terms":[135],"GFLOPS/W":[138],"(performance":[139],"per":[140],"unit":[141],"power)":[142],"metric":[143],"over":[144],"general":[147],"purpose":[148],"processors.":[149],"then":[151],"discuss":[152],"design":[160],"an":[162],"energy":[163],"efficient":[164],"architecture":[165],"multiply":[169],"kernel.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}