{"id":"https://openalex.org/W3200558682","doi":"https://doi.org/10.1109/tc.2021.3111761","title":"A Comprehensive Methodology to Optimize FPGA Designs via the Roofline Model","display_name":"A Comprehensive Methodology to Optimize FPGA Designs via the Roofline Model","publication_year":2021,"publication_date":"2021-09-10","ids":{"openalex":"https://openalex.org/W3200558682","doi":"https://doi.org/10.1109/tc.2021.3111761","mag":"3200558682"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2021.3111761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3111761","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11311/1207688","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053721069","display_name":"Marco Siracusa","orcid":"https://orcid.org/0000-0003-2782-837X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Siracusa","raw_affiliation_strings":["DEIB of Politecnico di Milano, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2782-837X","affiliations":[{"raw_affiliation_string":"DEIB of Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083420180","display_name":"Emanuele Del Sozzo","orcid":"https://orcid.org/0000-0003-3101-8118"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Del Sozzo","raw_affiliation_strings":["DEIB of Politecnico di Milano, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3101-8118","affiliations":[{"raw_affiliation_string":"DEIB of Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008834768","display_name":"Marco Rabozzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Rabozzi","raw_affiliation_strings":["Huxelerate S.R.L., Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huxelerate S.R.L., Milano, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109198457","display_name":"Lorenzo Di Tucci","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorenzo Di Tucci","raw_affiliation_strings":["Huxelerate S.R.L., Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huxelerate S.R.L., Milano, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["CRD of the Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRD of the Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014181688","display_name":"Donatella Sciuto","orcid":"https://orcid.org/0000-0001-9030-6940"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Donatella Sciuto","raw_affiliation_strings":["DEIB of Politecnico di Milano, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9030-6940","affiliations":[{"raw_affiliation_string":"DEIB of Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010543929","display_name":"Marco D. Santambrogio","orcid":"https://orcid.org/0000-0002-9883-9693"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Domenico Santambrogio","raw_affiliation_strings":["DEIB of Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DEIB of Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6739,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97134117,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"71","issue":"8","first_page":"1903","last_page":"1915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9993000030517578,"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":0.832996129989624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7927735447883606},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.6649976372718811},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.5066805481910706},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.48927876353263855},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4695758521556854},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44788098335266113},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4405588209629059},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4355563819408417}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.832996129989624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7927735447883606},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.6649976372718811},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.5066805481910706},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.48927876353263855},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4695758521556854},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44788098335266113},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4405588209629059},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4355563819408417}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tc.2021.3111761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3111761","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt6m06x3xv","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/6m06x3xv","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Computers, vol PP, iss 99","raw_type":"article"},{"id":"pmh:oai:re.public.polimi.it:11311/1207688","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1207688","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1207688","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1207688","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1569546679","https://openalex.org/W1583136220","https://openalex.org/W1790810173","https://openalex.org/W1990832096","https://openalex.org/W2002555321","https://openalex.org/W2004250488","https://openalex.org/W2005055779","https://openalex.org/W2019176653","https://openalex.org/W2087064593","https://openalex.org/W2128853364","https://openalex.org/W2130097981","https://openalex.org/W2147127704","https://openalex.org/W2166029537","https://openalex.org/W2343695530","https://openalex.org/W2398354748","https://openalex.org/W2529487057","https://openalex.org/W2613537099","https://openalex.org/W2795301672","https://openalex.org/W2807205576","https://openalex.org/W2889517658","https://openalex.org/W2979747168","https://openalex.org/W2983865192","https://openalex.org/W3015498000","https://openalex.org/W3083504653","https://openalex.org/W3090815597","https://openalex.org/W3122998669","https://openalex.org/W3126890733","https://openalex.org/W3152199537","https://openalex.org/W4229673714","https://openalex.org/W4252821989","https://openalex.org/W4292169167","https://openalex.org/W6693974865"],"related_works":["https://openalex.org/W4281926497","https://openalex.org/W2269990635","https://openalex.org/W2612099726","https://openalex.org/W2108242004","https://openalex.org/W4283730710","https://openalex.org/W2042762783","https://openalex.org/W2014165129","https://openalex.org/W2367348190","https://openalex.org/W594316872","https://openalex.org/W4281784598"],"abstract_inverted_index":{"With":[0],"reconfigurable":[1],"fabrics":[2],"delivering":[3],"increasing":[4],"performance":[5,96,155],"over":[6],"the":[7,35,80,85,123,142,176,195],"years,":[8],"Field-Programmable":[9,39],"Gate":[10,40],"Arrays":[11],"(FPGAs)":[12],"are":[13,75,120,130],"becoming":[14],"an":[15],"appealing":[16],"solution":[17],"for":[18,84,105],"next-generation":[19],"High-Performance":[20],"Computing":[21],"(HPC)":[22],"systems.":[23],"However,":[24],"in":[25,194],"order":[26],"to":[27,48,63,78,147,152,190],"gain":[28],"traction":[29],"among":[30],"traditional":[31],"von":[32],"Neumann":[33],"architectures,":[34],"optimization":[36,97],"process":[37],"of":[38,159],"Array":[41],"(FPGA)":[42],"designs":[43],"should":[44],"be":[45],"further":[46],"abstracted":[47],"a":[49,60,94,101,134,156,184],"higher":[50],"level.":[51],"In":[52,171],"fact,":[53],"while":[54],"High-Level":[55],"Synthesis":[56],"(HLS)":[57],"already":[58],"provides":[59],"handy":[61],"way":[62,143],"write":[64],"FPGA":[65,82,124],"code":[66],"with":[67],"common":[68],"high-level":[69],"languages,":[70],"substantial":[71],"effort":[72],"and":[73,108,116,150,167],"expertise":[74],"still":[76],"required":[77],"optimize":[79,151],"resulting":[81],"design":[83],"underlying":[86],"hardware.":[87],"To":[88],"overcome":[89],"this":[90,144],"problem,":[91],"we":[92,173],"propose":[93],"semi-automated":[95],"methodology":[98,145],"based":[99],"on":[100],"Hierarchical":[102],"Roofline":[103,125],"model":[104,126],"FPGAs.":[106],"System-wide":[107],"applications-specific":[109],"optimizations":[110,119,129],"such":[111],"as":[112],"off-chip":[113],"memory":[114],"transfer":[115],"data":[117],"locality":[118],"guided":[121],"by":[122,133],"whereas":[127],"FPGA-specific":[128],"automatically":[131],"searched":[132],"Design":[135,178],"Space":[136,179],"Exploration":[137,180],"(DSE)":[138,181],"engine.":[139],"We":[140],"demonstrate":[141],"allows":[146],"easily":[148],"analyze":[149],"peak":[153],"system":[154],"wide":[157],"set":[158],"applications":[160],"ranging":[161],"from":[162],"particle":[163],"methods,":[164],"wavefront":[165],"algorithms,":[166],"sparse":[168],"arithmetic":[169],"computations.":[170],"addition,":[172],"prove":[174],"that":[175],"integrated":[177],"engine":[182],"achieves":[183],"14.36x":[185],"maximum":[186],"speedup":[187],"if":[188],"compared":[189],"previous":[191],"automated":[192],"solutions":[193],"literature.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
