{"id":"https://openalex.org/W4415250787","doi":"https://doi.org/10.1109/hpec67600.2025.11196471","title":"A Scalable Code Generation Flow for Heterogeneous Parallel RTL Simulation using MLIR","display_name":"A Scalable Code Generation Flow for Heterogeneous Parallel RTL Simulation using MLIR","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250787","doi":"https://doi.org/10.1109/hpec67600.2025.11196471"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101866946","display_name":"Jie Tong","orcid":"https://orcid.org/0009-0005-7643-0642"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jie Tong","raw_affiliation_strings":["University of Wisconsin-Madison,Madison,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016863481","display_name":"Zhengxiong Li","orcid":"https://orcid.org/0000-0003-1880-5096"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengxiong Li","raw_affiliation_strings":["University of Wisconsin-Madison,Madison,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084255924","display_name":"\u00dcmit Y. Ogras","orcid":"https://orcid.org/0000-0002-5045-5535"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umit Yusuf Ogras","raw_affiliation_strings":["University of Wisconsin-Madison,Madison,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088685794","display_name":"Tsung\u2010Wei Huang","orcid":"https://orcid.org/0000-0001-9768-3378"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsung-Wei Huang","raw_affiliation_strings":["University of Wisconsin-Madison,Madison,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,Madison,USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101866946"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31359421,"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":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10125","display_name":"Advanced Wireless Communication Techniques","score":0.9620000123977661,"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"}},"topics":[{"id":"https://openalex.org/T10125","display_name":"Advanced Wireless Communication Techniques","score":0.9620000123977661,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9492999911308289,"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/T12162","display_name":"Cellular Automata and Applications","score":0.9271000027656555,"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/scalability","display_name":"Scalability","score":0.7430999875068665},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5759000182151794},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5662000179290771},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.44859999418258667},{"id":"https://openalex.org/keywords/design-flow","display_name":"Design flow","score":0.4472000002861023},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41760000586509705},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3675000071525574},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.3109000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8647000193595886},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7430999875068665},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6571999788284302},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5759000182151794},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5662000179290771},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.44859999418258667},{"id":"https://openalex.org/C37135326","wikidata":"https://www.wikidata.org/wiki/Q931942","display_name":"Design flow","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C64260653","wikidata":"https://www.wikidata.org/wiki/Q1194864","display_name":"Electronic design automation","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C34854456","wikidata":"https://www.wikidata.org/wiki/Q1484552","display_name":"Register-transfer level","level":4,"score":0.2824999988079071},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C187303228","wikidata":"https://www.wikidata.org/wiki/Q867330","display_name":"Cyclomatic complexity","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":83,"referenced_works":["https://openalex.org/W2397503904","https://openalex.org/W2624783959","https://openalex.org/W2799567470","https://openalex.org/W2806717795","https://openalex.org/W2895790300","https://openalex.org/W2945038515","https://openalex.org/W2946553399","https://openalex.org/W2963366311","https://openalex.org/W2982022996","https://openalex.org/W2991469820","https://openalex.org/W3016542674","https://openalex.org/W3041526861","https://openalex.org/W3091980371","https://openalex.org/W3092265192","https://openalex.org/W3111098492","https://openalex.org/W3113443077","https://openalex.org/W3120604107","https://openalex.org/W3122286897","https://openalex.org/W3134181251","https://openalex.org/W3165412222","https://openalex.org/W3188917597","https://openalex.org/W3197809542","https://openalex.org/W3198396679","https://openalex.org/W3211750799","https://openalex.org/W3212403328","https://openalex.org/W3212679119","https://openalex.org/W3213528054","https://openalex.org/W4200009287","https://openalex.org/W4200128939","https://openalex.org/W4200319213","https://openalex.org/W4200368805","https://openalex.org/W4200601188","https://openalex.org/W4205834599","https://openalex.org/W4213040020","https://openalex.org/W4226016128","https://openalex.org/W4237927338","https://openalex.org/W4240172596","https://openalex.org/W4246166885","https://openalex.org/W4283390926","https://openalex.org/W4293025123","https://openalex.org/W4308090426","https://openalex.org/W4308090451","https://openalex.org/W4320067872","https://openalex.org/W4327911467","https://openalex.org/W4376460962","https://openalex.org/W4379115843","https://openalex.org/W4380607252","https://openalex.org/W4380874786","https://openalex.org/W4384705351","https://openalex.org/W4385585512","https://openalex.org/W4386106276","https://openalex.org/W4386709670","https://openalex.org/W4386763846","https://openalex.org/W4389162805","https://openalex.org/W4389491860","https://openalex.org/W4390188200","https://openalex.org/W4390189010","https://openalex.org/W4392680736","https://openalex.org/W4393141077","https://openalex.org/W4401408705","https://openalex.org/W4401408736","https://openalex.org/W4401568604","https://openalex.org/W4401861817","https://openalex.org/W4402835351","https://openalex.org/W4402835630","https://openalex.org/W4402835794","https://openalex.org/W4404133525","https://openalex.org/W4404133674","https://openalex.org/W4404134028","https://openalex.org/W4404134132","https://openalex.org/W4408151632","https://openalex.org/W4408151763","https://openalex.org/W4408163936","https://openalex.org/W4408895076","https://openalex.org/W4409131806","https://openalex.org/W4409282527","https://openalex.org/W4409328887","https://openalex.org/W4410095894","https://openalex.org/W4413374402","https://openalex.org/W4413673202","https://openalex.org/W4414198759","https://openalex.org/W4414198981","https://openalex.org/W4415003549"],"related_works":[],"abstract_inverted_index":{"As":[0],"hardware":[1],"design":[2,19],"complexity":[3],"increases,":[4],"efficient":[5,150],"Register":[6],"Transfer":[7],"Level":[8],"(RTL)":[9],"simulation":[10,39,135,151,175],"becomes":[11],"critical":[12],"for":[13,42,118],"reducing":[14],"the":[15,87,91,126,134],"long":[16,34],"runtime":[17],"of":[18,161,166],"and":[20,37,46,54,82,138,148,168,173],"verification.":[21],"Although":[22],"several":[23],"parallel":[24,115],"RTL":[25,116,131],"simulators":[26,62,117],"have":[27],"been":[28],"developed,":[29],"they":[30,79],"often":[31],"suffer":[32],"from":[33],"compilation":[35,146,159],"times":[36],"slow":[38],"performance,":[40],"especially":[41],"large-scale":[43],"heterogeneous":[44,67,119],"architectures":[45,68],"deep":[47,96,120],"learning":[48,97,121],"SoC":[49],"designs":[50],"that":[51,111],"exhibit":[52],"repetitive":[53],"hierarchical":[55],"structures.":[56],"These":[57],"limitations":[58],"arise":[59],"because":[60],"existing":[61],"fail":[63],"to":[64,89,144,154,163,171],"effectively":[65],"map":[66],"onto":[69],"CPU-GPU":[70,114],"platforms,":[71],"resulting":[72],"in":[73,95],"underutilized":[74],"compute":[75],"resources.":[76],"In":[77],"addition,":[78],"repeatedly":[80],"regenerate":[81],"recompile":[83],"redundant":[84],"code,":[85],"missing":[86],"opportunity":[88],"exploit":[90],"structural":[92,142],"parallelism":[93],"inherent":[94],"accelerators.":[98],"To":[99],"address":[100],"these":[101],"challenges,":[102],"we":[103],"propose":[104],"HeteroRTL,":[105],"a":[106],"scalable":[107],"code":[108],"generation":[109],"flow":[110],"produces":[112],"hybrid":[113],"accelerator":[122],"SoCs.":[123],"Built":[124],"on":[125],"MLIR":[127],"infrastructure,":[128],"HeteroRTL":[129,157],"analyzes":[130],"designs,":[132],"partitions":[133],"between":[136],"CPU":[137],"GPU":[139],"targets,":[140],"identifies":[141],"repetition":[143],"reduce":[145],"overhead,":[147],"generates":[149],"executables.":[152],"Compared":[153],"state-of-the-art":[155],"simulators,":[156],"achieves":[158],"speedups":[160,176],"three":[162],"five":[164],"orders":[165],"magnitude":[167],"delivers":[169],"up":[170],"9\u00d7":[172],"122\u00d7":[174],"across":[177],"various":[178],"designs.":[179]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}