{"id":"https://openalex.org/W3046770934","doi":"https://doi.org/10.1109/ipdpsw50202.2020.00087","title":"Understanding the Performance of Elementary NLA Kernels in FPGAs","display_name":"Understanding the Performance of Elementary NLA Kernels in FPGAs","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3046770934","doi":"https://doi.org/10.1109/ipdpsw50202.2020.00087","mag":"3046770934"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw50202.2020.00087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw50202.2020.00087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","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/A5029471905","display_name":"Federico Favaro","orcid":"https://orcid.org/0000-0002-5506-0540"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":true,"raw_author_name":"Federico Favaro","raw_affiliation_strings":["Instituto de Ingenier\u00eda El\u00e9ctrica Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay"],"affiliations":[{"raw_affiliation_string":"Instituto de Ingenier\u00eda El\u00e9ctrica Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039260419","display_name":"Juan Pablo Oliver","orcid":"https://orcid.org/0000-0001-7098-674X"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Juan P. Oliver","raw_affiliation_strings":["Instituto de Ingenier\u00eda El\u00e9ctrica Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay"],"affiliations":[{"raw_affiliation_string":"Instituto de Ingenier\u00eda El\u00e9ctrica Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020768637","display_name":"Ernesto Dufrechou","orcid":"https://orcid.org/0000-0003-4971-340X"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Ernesto Dufrechou","raw_affiliation_strings":["Instituto de Computaci\u00f3n Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay"],"affiliations":[{"raw_affiliation_string":"Instituto de Computaci\u00f3n Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039665879","display_name":"Pablo Ezzatti","orcid":"https://orcid.org/0000-0002-2368-8907"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Pablo Ezzatti","raw_affiliation_strings":["Instituto de Computaci\u00f3n Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay"],"affiliations":[{"raw_affiliation_string":"Instituto de Computaci\u00f3n Facultad de Ingenier\u00eda, Universidad de la Rep\u00fablica Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029471905"],"corresponding_institution_ids":["https://openalex.org/I180910786"],"apc_list":null,"apc_paid":null,"fwci":0.4222,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68193227,"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":"479","last_page":"482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9980999827384949,"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":0.9980999827384949,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9979000091552734,"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":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8339904546737671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822855710983276},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7036093473434448},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6455283164978027},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6334257125854492},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5702796578407288},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5682845711708069},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5508567690849304},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.48688068985939026},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4281983971595764},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4142572581768036},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4100250005722046},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4086691737174988},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.36359703540802},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2905656695365906},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18345433473587036},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.10039225220680237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09245958924293518}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8339904546737671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822855710983276},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7036093473434448},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6455283164978027},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6334257125854492},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5702796578407288},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5682845711708069},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5508567690849304},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.48688068985939026},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4281983971595764},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4142572581768036},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4100250005722046},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4086691737174988},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.36359703540802},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2905656695365906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18345433473587036},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.10039225220680237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09245958924293518},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw50202.2020.00087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw50202.2020.00087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W235440760","https://openalex.org/W2030909247","https://openalex.org/W2059117794","https://openalex.org/W2106111377","https://openalex.org/W2128853364","https://openalex.org/W2160106215","https://openalex.org/W2615755298","https://openalex.org/W2901970548","https://openalex.org/W2940895522","https://openalex.org/W4312258136","https://openalex.org/W6756481336"],"related_works":["https://openalex.org/W1975364444","https://openalex.org/W2293771254","https://openalex.org/W2119413962","https://openalex.org/W4381050447","https://openalex.org/W2030992542","https://openalex.org/W3121314575","https://openalex.org/W1835670156","https://openalex.org/W3121828480","https://openalex.org/W3147497457","https://openalex.org/W2039875226"],"abstract_inverted_index":{"Our":[0],"work":[1],"compares":[2],"the":[3,20,43,48,51,57,64,77,99],"use":[4],"of":[5,22,42,68,80,106],"multi-core":[6,28],"hardware":[7],"and":[8,31,56,70,88,108],"FPGAs":[9],"to":[10],"address":[11],"Numerical":[12],"Linear":[13],"Algebra":[14],"(NLA)":[15],"kernels.":[16],"Specifically,":[17],"we":[18,39,75],"study":[19],"behavior":[21],"highly":[23],"tuned":[24],"kernels":[25,46,67],"in":[26,47,98,104],"a":[27,84],"CPU":[29],"processor":[30],"OpenCL":[32],"implementations":[33,82,90],"on":[34,83],"FPGAs.":[35],"For":[36],"this":[37],"purpose,":[38],"select":[40],"two":[41],"most":[44,65],"significant":[45],"NLA":[49,72],"field,":[50],"general":[52],"matrix":[53],"multiplication":[54,60],"(GEMM)":[55],"sparse":[58,71],"matrix-vector":[59],"(SPMV),":[61],"which":[62],"are":[63],"characteristic":[66],"dense":[69],"respectively.":[73],"Finally,":[74],"perform":[76],"experimental":[78],"evaluation":[79],"our":[81],"low-end":[85],"FPGA":[86],"platform,":[87],"state-of-the-art":[89],"for":[91],"traditional":[92],"CPUs,":[93],"such":[94],"as":[95],"those":[96],"included":[97],"Intel":[100],"MKL":[101],"library,":[102],"both":[103],"terms":[105],"runtime":[107],"energy":[109],"consumption.":[110]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
