{"id":"https://openalex.org/W7162792328","doi":"https://doi.org/10.1145/3805642","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":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162792328","doi":"https://doi.org/10.1145/3805642"},"language":"en","primary_location":{"id":"doi:10.1145/3805642","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805642","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3805642","any_repository_has_fulltext":false},"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":0.87133145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"2","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.977400004863739,"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":0.977400004863739,"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":0.00430000014603138,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0026000000070780516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7044000029563904},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5888000130653381},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.436599999666214},{"id":"https://openalex.org/keywords/computer-architecture-simulator","display_name":"Computer architecture simulator","score":0.4189999997615814},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.384799987077713},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.35920000076293945},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3587000072002411},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.35019999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8773000240325928},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7044000029563904},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4943999946117401},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C201203610","wikidata":"https://www.wikidata.org/wiki/Q5157524","display_name":"Computer architecture simulator","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C544400634","wikidata":"https://www.wikidata.org/wiki/Q188695","display_name":"DirectX","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C147203929","wikidata":"https://www.wikidata.org/wiki/Q574814","display_name":"Discrete event simulation","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C159023740","wikidata":"https://www.wikidata.org/wiki/Q623276","display_name":"Deadlock","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805642","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805642","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3805642","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805642","pdf_url":null,"source":{"id":"https://openalex.org/S4210193547","display_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","issn_l":"2476-1249","issn":["2476-1249"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Measurement and Analysis of Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G198881990","display_name":null,"funder_award_id":"RS-2024-00414964","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7296649959","display_name":null,"funder_award_id":"IO201209-07887-01","funder_id":"https://openalex.org/F4320332195","funder_display_name":"Samsung"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1601084247","https://openalex.org/W1979527452","https://openalex.org/W2033486618","https://openalex.org/W2038666141","https://openalex.org/W2038932419","https://openalex.org/W2064373756","https://openalex.org/W2080592089","https://openalex.org/W2090678868","https://openalex.org/W2096864363","https://openalex.org/W2106562406","https://openalex.org/W2112029501","https://openalex.org/W2119160628","https://openalex.org/W2128120785","https://openalex.org/W2130336316","https://openalex.org/W2134860672","https://openalex.org/W2138146350","https://openalex.org/W2144264070","https://openalex.org/W2147657366","https://openalex.org/W2150871235","https://openalex.org/W2151195685","https://openalex.org/W2167334577","https://openalex.org/W2204664557","https://openalex.org/W2417175077","https://openalex.org/W2608738900","https://openalex.org/W2610232516","https://openalex.org/W2736244279","https://openalex.org/W2768146426","https://openalex.org/W2901073342","https://openalex.org/W2934426651","https://openalex.org/W2949486320","https://openalex.org/W2963989532","https://openalex.org/W2969414999","https://openalex.org/W2979340153","https://openalex.org/W3006586535","https://openalex.org/W3015498000","https://openalex.org/W3043571714","https://openalex.org/W3102510044","https://openalex.org/W3104094521","https://openalex.org/W3130554079","https://openalex.org/W3157055696","https://openalex.org/W3189983613","https://openalex.org/W3206857466","https://openalex.org/W3207572920","https://openalex.org/W3210604792","https://openalex.org/W4234833047","https://openalex.org/W4237229330","https://openalex.org/W4245923077","https://openalex.org/W4253029824","https://openalex.org/W4280502333","https://openalex.org/W4281689389","https://openalex.org/W4295679041","https://openalex.org/W4318256787","https://openalex.org/W4379115871","https://openalex.org/W4381389673","https://openalex.org/W4381894551","https://openalex.org/W4381894570","https://openalex.org/W4388429187","https://openalex.org/W4388757726","https://openalex.org/W4390263770","https://openalex.org/W4393145114","https://openalex.org/W4394947044","https://openalex.org/W4404955793","https://openalex.org/W4412986865","https://openalex.org/W4412987300","https://openalex.org/W7141345210"],"related_works":[],"abstract_inverted_index":{"The":[0],"demands":[1],"of":[2,9,17,80,93,112,202,249,265],"large-scale":[3,26,53,84,105,315],"workloads":[4,54,106],"have":[5],"driven":[6],"the":[7,14,38,78,91,110,156,159,166,200,267,276,296],"evolution":[8],"GPUs,":[10],"placing":[11],"them":[12],"in":[13,178,209,227,235,238,244],"mainstream":[15],"scope":[16],"computing":[18],"architectures.":[19,262],"To":[20,133],"design":[21,39],"an":[22,224,301],"effective":[23],"GPU":[24,42,61,95,122,131,183,188,261,278],"for":[25,52,76,104,240,290,314],"workloads,":[27],"a":[28,56,94,118,164,175,187,232,241,272,282,286,291],"trustworthy":[29],"simulator":[30,96],"is":[31,87,169,311],"required":[32],"to":[33,48,69,89,126,158,198,217],"evaluate":[34,49],"performance":[35,92],"and":[36,102,120,129,194,205,255],"explore":[37],"space.":[40],"Additionally,":[41],"simulators":[43,62],"must":[44],"be":[45],"fast":[46,128],"enough":[47],"architectural":[50,81],"modifications":[51,82],"within":[55],"reasonable":[57],"time.":[58],"However,":[59],"existing":[60,210],"suffer":[63],"from":[64],"long":[65],"execution":[66,207],"times":[67],"due":[68],"detailed":[70],"component":[71],"simulation,":[72],"limiting":[73],"their":[74],"utility":[75],"evaluating":[77],"effects":[79],"on":[83,145,220,285],"workloads.":[85,316],"It":[86],"necessary":[88],"improve":[90],"such":[97],"that":[98,141,309],"quick":[99],"architecture":[100,189],"exploration":[101],"evaluation":[103,230],"are":[107],"available,":[108],"at":[109,174],"expense":[111],"accuracy.":[113,147,179,228],"This":[114,148],"paper":[115],"presents":[116],"LPGSim,":[117],"trace-driven":[119],"cycle-level":[121],"simulator.":[123,279,298],"LPGSim":[124,136,181,185,212,251,269],"aims":[125],"provide":[127],"accurate":[130],"simulation.":[132,184],"this":[134],"end,":[135],"first":[137],"eliminates":[138],"instruction":[139],"metadata":[140],"has":[142],"minimal":[143],"impact":[144],"simulation":[146,172,236,245,270,310],"approach":[149],"enables":[150],"coalescing":[151],"compute":[152],"instructions":[153],"while":[154],"preserving":[155],"dependencies":[157],"preceding":[160],"memory":[161],"instruction.":[162],"As":[163],"consequence,":[165],"core":[167],"pipeline":[168],"simplified,":[170],"improving":[171],"speed":[173],"marginal":[176],"cost":[177],"Next,":[180],"parallelizes":[182],"partitions":[186],"into":[190],"three":[191,259],"parallelizable":[192],"subsystems":[193],"introduces":[195],"local-clock-based":[196],"parallelization":[197,215],"reduce":[199],"overhead":[201],"global":[203],"synchronization":[204],"sequential":[206],"paths":[208],"methods.":[211],"further":[213],"employs":[214],"methods":[216],"achieve":[218],"scalability":[219],"NUMA":[221],"systems":[222],"with":[223],"acceptable":[225],"trade-off":[226],"Our":[229],"shows":[231],"modest":[233],"decrease":[234],"accuracy":[237,303],"return":[239],"substantial":[242],"improvement":[243],"speed.":[246],"In":[247,263],"terms":[248,264],"accuracy,":[250],"achieves":[252,281],"21.4%,":[253],"23.3%,":[254],"22.7%":[256],"errors":[257],"across":[258],"different":[260],"speed,":[266],"single-threaded":[268],"yields":[271],"9.97x":[273],"speedup":[274,284,294],"over":[275,295],"state-of-the-art":[277,297],"Parallelization":[280,299],"19.8x":[283],"two-socket":[287],"56-thread":[288],"system,":[289],"total":[292],"197.4x":[293],"incurs":[300],"additional":[302],"loss,":[304],"but":[305],"our":[306],"experiments":[307],"indicate":[308],"still":[312],"reliable":[313]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-30T00:00:00"}