{"id":"https://openalex.org/W4297966109","doi":"https://doi.org/10.4230/oasics.parma-ditam.2026.6","title":"Accelerating GPGPU Simulation by Strategically Parallelizing the Compute Bottleneck","display_name":"Accelerating GPGPU Simulation by Strategically Parallelizing the Compute Bottleneck","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4297966109","doi":"https://doi.org/10.4230/oasics.parma-ditam.2026.6"},"language":"en","primary_location":{"id":"doi:10.4230/oasics.parma-ditam.2026.6","is_oa":true,"landing_page_url":"https://doi.org/10.4230/oasics.parma-ditam.2026.6","pdf_url":null,"source":{"id":"https://openalex.org/S7407052059","display_name":"Dagstuhl Research Online Publication Server","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.4230/oasics.parma-ditam.2026.6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sachs, Jakob","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sachs, Jakob","raw_affiliation_strings":["Hamburg University of Technology, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamburg University of Technology, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":null,"display_name":"L\u00fchnen, Tim","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"L\u00fchnen, Tim","raw_affiliation_strings":["Hamburg University of Technology, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamburg University of Technology, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lal, Sohan","orcid":"https://orcid.org/0000-0002-2325-1705"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lal, Sohan","raw_affiliation_strings":["Hamburg University of Technology, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2325-1705","affiliations":[{"raw_affiliation_string":"Hamburg University of Technology, Germany","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00024919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization 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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9977999925613403,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8792938590049744},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7328194975852966},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6953487396240234},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.6565038561820984},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5954562425613403},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5487478971481323},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5481238961219788},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.4826101064682007},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4488832354545593},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.39909717440605164},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36339887976646423},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3614715337753296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8792938590049744},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7328194975852966},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6953487396240234},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.6565038561820984},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5954562425613403},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5487478971481323},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5481238961219788},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.4826101064682007},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4488832354545593},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.39909717440605164},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36339887976646423},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3614715337753296},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4230/oasics.parma-ditam.2026.6","is_oa":true,"landing_page_url":"https://doi.org/10.4230/oasics.parma-ditam.2026.6","pdf_url":null,"source":{"id":"https://openalex.org/S7407052059","display_name":"Dagstuhl Research Online Publication Server","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.4230/oasics.parma-ditam.2026.6","is_oa":true,"landing_page_url":"https://doi.org/10.4230/oasics.parma-ditam.2026.6","pdf_url":null,"source":{"id":"https://openalex.org/S7407052059","display_name":"Dagstuhl Research Online Publication Server","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Cycle-accurate":[0],"GPGPU":[1,43],"simulators":[2],"like":[3],"GPGPU-Sim":[4,92],"provide":[5],"invaluable":[6],"insights":[7],"for":[8],"hardware":[9],"architecture":[10],"research":[11,19],"but":[12],"suffer":[13],"from":[14],"extremely":[15],"long":[16],"runtimes,":[17],"hindering":[18],"productivity.":[20],"This":[21],"paper":[22],"addresses":[23],"this":[24,71],"critical":[25],"bottleneck":[26],"by":[27],"proposing":[28],"a":[29,37,65,74,100,118,125],"strategy":[30],"to":[31,45,77,89,94,121],"accelerate":[32],"GPGPU-Sim.":[33],"We":[34],"first":[35],"perform":[36],"holistic":[38],"profiling":[39],"analysis":[40],"across":[41],"diverse":[42],"benchmarks":[44,135],"identify":[46],"the":[47,52,57,90],"primary":[48],"performance":[49],"bottleneck,":[50],"pinpointing":[51],"SIMT-Core":[53,82],"cluster":[54],"execution":[55,80],"within":[56],"CORE-clock":[58],"cycle.":[59],"Based":[60],"on":[61],"this,":[62],"we":[63],"implement":[64],"parallelization":[66],"scheme":[67],"that":[68],"strategically":[69],"targets":[70],"hotspot,":[72],"utilizing":[73],"thread":[75],"pool":[76],"manage":[78],"concurrent":[79],"of":[81,99,111,130],"clusters.":[83],"Our":[84],"approach":[85],"prioritizes":[86],"minimal":[87],"modifications":[88],"existing":[91],"codebase":[93],"ensure":[95],"long-term":[96],"maintainability.":[97],"Evaluation":[98],"simulated":[101],"NVIDIA":[102],"H100":[103],"model":[104],"demonstrates":[105],"an":[106],"average":[107],"simulation":[108],"wall-time":[109],"speedup":[110],"3.58\u00d7":[112],"with":[113,132],"8":[114],"worker":[115],"threads,":[116],"and":[117],"maximum":[119,126],"up":[120],"4.38\u00d7,":[122],"while":[123],"incurring":[124],"cycle":[127],"count":[128],"error":[129,138],"3.22%,":[131],"some":[133],"other":[134],"exhibiting":[136],"no":[137],"at":[139],"all.":[140]},"counts_by_year":[],"updated_date":"2026-04-12T06:05:19.336698","created_date":"2022-10-01T00:00:00"}