{"id":"https://openalex.org/W4417402822","doi":"https://doi.org/10.1109/sbesc68008.2025.11288900","title":"Go Fast: GPU Optimizer for FPGA-LUT Approximate Simulation and Tuning","display_name":"Go Fast: GPU Optimizer for FPGA-LUT Approximate Simulation and Tuning","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4417402822","doi":"https://doi.org/10.1109/sbesc68008.2025.11288900"},"language":null,"primary_location":{"id":"doi:10.1109/sbesc68008.2025.11288900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbesc68008.2025.11288900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 XV Symposium on Computing Systems Engineering (SBESC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/SBESC68008.2025.11288900","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086043265","display_name":"Olavo Barros","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olavo Barros","raw_affiliation_strings":["Universidade Federal de Viçosa,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Viçosa,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110266994","display_name":"Isabela Moreira de Freitas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Isabela Freitas","raw_affiliation_strings":["Universidade Federal de Viçosa,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Viçosa,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117094397","display_name":"Pedro Coura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro Coura","raw_affiliation_strings":["Universidade Federal de Viçosa,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Viçosa,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068177643","display_name":"Jos\u00e9 Augusto M. Nacif","orcid":"https://orcid.org/0000-0003-0703-5620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Augusto M. Nacif","raw_affiliation_strings":["Universidade Federal de Viçosa,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Viçosa,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016370549","display_name":"Ricardo Ferreira","orcid":"https://orcid.org/0000-0003-1802-7829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricardo Ferreira","raw_affiliation_strings":["Universidade Federal de Viçosa,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Viçosa,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017351180","display_name":"Adri\u00e1n Alcolea","orcid":"https://orcid.org/0000-0002-7057-4283"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Alcolea","raw_affiliation_strings":["Universidad de Zaragoza,Instituto de Investigación en Ingeniería de Araggemaón,Dept. de Informatica e Ingenieria de Sistemas,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Zaragoza,Instituto de Investigación en Ingeniería de Araggemaón,Dept. de Informatica e Ingenieria de Sistemas,Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078942832","display_name":"Mar\u00eda Villarroya-Gaud\u00f3","orcid":null},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mar\u00eda Villarroya-Gaud\u00f3","raw_affiliation_strings":["Universidad de Zaragoza,Instituto de Investigación en Ingeniería de Araggemaón,Dept. de Informatica e Ingenieria de Sistemas,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Zaragoza,Instituto de Investigación en Ingeniería de Araggemaón,Dept. de Informatica e Ingenieria de Sistemas,Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003490802","display_name":"Javier Resano","orcid":"https://orcid.org/0000-0002-7532-2720"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Resano","raw_affiliation_strings":["Universidad de Zaragoza,Instituto de Investigación en Ingeniería de Araggemaón,Dept. de Informatica e Ingenieria de Sistemas,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad de Zaragoza,Instituto de Investigación en Ingeniería de Araggemaón,Dept. de Informatica e Ingenieria de Sistemas,Spain","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44197138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.17800000309944153,"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":0.17800000309944153,"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":0.16030000150203705,"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"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.15330000221729279,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7143999934196472},{"id":"https://openalex.org/keywords/logic-simulation","display_name":"Logic simulation","score":0.5662000179290771},{"id":"https://openalex.org/keywords/digital-electronics","display_name":"Digital electronics","score":0.5321999788284302},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5192000269889832},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.47429999709129333},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.46140000224113464},{"id":"https://openalex.org/keywords/electronic-circuit","display_name":"Electronic circuit","score":0.43700000643730164},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.38499999046325684},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.37070000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385000228881836},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.794700026512146},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7143999934196472},{"id":"https://openalex.org/C64859876","wikidata":"https://www.wikidata.org/wiki/Q173673","display_name":"Logic simulation","level":3,"score":0.5662000179290771},{"id":"https://openalex.org/C81843906","wikidata":"https://www.wikidata.org/wiki/Q173156","display_name":"Digital electronics","level":3,"score":0.5321999788284302},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5192000269889832},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C134146338","wikidata":"https://www.wikidata.org/wiki/Q1815901","display_name":"Electronic circuit","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3806000053882599},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35109999775886536},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C187075797","wikidata":"https://www.wikidata.org/wiki/Q173245","display_name":"Sequential logic","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C157922185","wikidata":"https://www.wikidata.org/wiki/Q173198","display_name":"Logic synthesis","level":3,"score":0.2928999960422516},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.28060001134872437},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2547999918460846},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sbesc68008.2025.11288900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbesc68008.2025.11288900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 XV Symposium on Computing Systems Engineering (SBESC)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:18421618","is_oa":true,"landing_page_url":"https://doi.org/10.1109/SBESC68008.2025.11288900","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:18421618","is_oa":true,"landing_page_url":"https://doi.org/10.1109/SBESC68008.2025.11288900","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,82],"paper":[1],"introduces":[2],"Go-Fast,":[3],"a":[4],"novel":[5],"approach":[6,84],"that":[7,23,90],"accelerates":[8],"the":[9,100],"simulation":[10,34,59],"and":[11,54,60,76,103],"optimization":[12],"of":[13,97],"LUT-based":[14],"FPGA":[15],"circuits":[16,27],"using":[17],"GPUs.":[18],"Unlike":[19],"previous":[20],"GPU-based":[21],"simulators":[22],"target":[24],"general":[25],"digital":[26],"with":[28],"event-driven":[29],"approaches,":[30],"Go-Fast":[31,63],"employs":[32],"batch":[33],"techniques":[35],"specifically":[36],"optimized":[37,109],"for":[38,57],"approximate":[39],"computing":[40],"scenarios.":[41],"The":[42],"system":[43],"utilizes":[44],"both":[45],"data":[46],"parallelism":[47,56],"to":[48,105],"execute":[49],"testbenches":[50],"across":[51],"numerous":[52],"threads":[53],"structural":[55],"simultaneous":[58],"logic":[61],"pruning.":[62],"fully":[64],"exploits":[65],"GPU":[66],"architectural":[67],"features":[68],"by":[69],"maximizing":[70],"register":[71],"usage,":[72],"minimizing":[73],"memory":[74],"access,":[75],"allocating":[77],"more":[78],"work":[79],"per":[80],"thread.":[81],"domain-specific":[83],"generates":[85],"efficient":[86],"source-to-source":[87],"CUDA":[88],"code":[89],"achieves":[91],"significant":[92],"performance":[93],"improvements:":[94],"five":[95],"orders":[96,107],"magnitude":[98],"over":[99,108],"Verilator":[101],"simulator":[102],"two":[104],"three":[106],"multi-core":[110],"implementations.":[111]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-16T00:00:00"}