{"id":"https://openalex.org/W7162473068","doi":"https://doi.org/10.1145/3801489.3806915","title":"LPGSim: A Lightweight Parallel GPU Simulator Maximizing Speed with Trustworthy Simulation","display_name":"LPGSim: A Lightweight Parallel GPU Simulator Maximizing Speed with Trustworthy Simulation","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162473068","doi":"https://doi.org/10.1145/3801489.3806915"},"language":null,"primary_location":{"id":"doi:10.1145/3801489.3806915","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806915","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3801489.3806915","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130723065","display_name":"Hyunwoo Nam","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunwoo Nam","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-7774-8028","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087954884","display_name":"Jay Hwan Lee","orcid":"https://orcid.org/0000-0002-1975-2363"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jay Hwan Lee","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1975-2363","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489113","display_name":"Yeonsoo Kim","orcid":"https://orcid.org/0000-0002-9437-4665"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeonsoo Kim","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9437-4665","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089833906","display_name":"Mengzhao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mengzhao Zhang","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1500-9652","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041438270","display_name":"JeongGeun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeonggeun Kim","raw_affiliation_strings":["Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0264-0979","affiliations":[{"raw_affiliation_string":"Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012072107","display_name":"Bernd Burgstaller","orcid":"https://orcid.org/0000-0002-0374-8853"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bernd Burgstaller","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0374-8853","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.8471232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9661999940872192,"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":0.9661999940872192,"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/T14347","display_name":"Big Data and Digital Economy","score":0.00570000009611249,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.003100000089034438,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/scalability","display_name":"Scalability","score":0.7250999808311462},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6858000159263611},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5437999963760376},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.483599990606308},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/computer-architecture-simulator","display_name":"Computer architecture simulator","score":0.38609999418258667},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467000126838684},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7250999808311462},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6858000159263611},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.3490999937057495},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3057999908924103},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3801489.3806915","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806915","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3801489.3806915","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801489.3806915","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstracts of the 2026 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.42430800199508667,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2979340153","https://openalex.org/W3102510044","https://openalex.org/W3157055696"],"related_works":[],"abstract_inverted_index":{"In":[0],"designing":[1],"an":[2,139],"effective":[3],"GPU":[4,25,56,83,92,112,117,154],"for":[5,40,65],"large-scale":[6,66],"workloads,":[7],"a":[8,55,79,116,158],"trustworthy":[9],"and":[10,18,63,81,90,123,148],"fast":[11,89],"simulator":[12,57],"is":[13,48],"required":[14],"to":[15,33,50,87,132],"evaluate":[16],"performance":[17,53],"explore":[19],"the":[20,42,52,71,163],"design":[21],"space.":[22],"However,":[23],"existing":[24],"simulators":[26],"suffer":[27],"from":[28],"long":[29],"execution":[30],"times":[31],"due":[32],"detailed":[34],"component":[35],"simulation,":[36],"limiting":[37],"their":[38],"utility":[39],"evaluating":[41],"effects":[43],"of":[44,54,73],"architectural":[45],"modifications.":[46],"It":[47],"necessary":[49],"improve":[51],"such":[58],"that":[59,102],"quick":[60],"architecture":[61,118],"exploration":[62],"evaluation":[64],"workloads":[67],"are":[68],"available,":[69],"at":[70],"expense":[72],"accuracy.":[74,108,143],"This":[75],"paper":[76],"presents":[77],"LPGSim,":[78],"trace-driven":[80],"cycle-level":[82],"simulator.":[84,165],"LPGSim":[85,97,110,114,127,144],"aims":[86],"provide":[88],"accurate":[91],"simulation.":[93,113],"To":[94],"this":[95],"end,":[96],"first":[98],"eliminates":[99],"instruction":[100],"metadata":[101],"has":[103],"minimal":[104],"impact":[105],"on":[106,135],"simulation":[107],"Next,":[109],"parallelizes":[111],"partitions":[115],"into":[119],"three":[120,152],"parallelizable":[121],"subsystems":[122],"introduces":[124],"local-clock-based":[125],"parallelization.":[126],"further":[128],"employs":[129],"parallelization":[130],"methods":[131],"achieve":[133],"scalability":[134],"NUMA":[136],"systems":[137],"with":[138],"acceptable":[140],"trade-off":[141],"in":[142],"shows":[145],"21.4%,":[146],"23.3%,":[147],"22.7%":[149],"errors":[150],"across":[151],"different":[153],"architectures,":[155],"while":[156],"achieving":[157],"total":[159],"197.4x":[160],"speedup":[161],"over":[162],"state-of-the-art":[164]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-27T00:00:00"}