{"id":"https://openalex.org/W4416963202","doi":"https://doi.org/10.1109/islped65674.2025.11261765","title":"Repurpose Accel-Sim for Next Generation NVIDIA Jetson GPU Architectural Design","display_name":"Repurpose Accel-Sim for Next Generation NVIDIA Jetson GPU Architectural Design","publication_year":2025,"publication_date":"2025-08-06","ids":{"openalex":"https://openalex.org/W4416963202","doi":"https://doi.org/10.1109/islped65674.2025.11261765"},"language":null,"primary_location":{"id":"doi:10.1109/islped65674.2025.11261765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/islped65674.2025.11261765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)","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/A5061112518","display_name":"Tianhao Huang","orcid":"https://orcid.org/0000-0001-9424-9250"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianhao Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188024","display_name":"Lingyu Sun","orcid":"https://orcid.org/0000-0002-1326-2654"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Sun","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675801","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-2259-196X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073267234","display_name":"Xiaofeng Hou","orcid":"https://orcid.org/0000-0003-4372-7851"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Hou","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088206241","display_name":"Yaqian Zhao","orcid":"https://orcid.org/0000-0002-2449-4370"},"institutions":[{"id":"https://openalex.org/I4210125930","display_name":"Ionic Systems (United States)","ror":"https://ror.org/02bax5p58","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaqian Zhao","raw_affiliation_strings":["IEIT SYSTEMS Co., Ltd.,China"],"affiliations":[{"raw_affiliation_string":"IEIT SYSTEMS Co., Ltd.,China","institution_ids":["https://openalex.org/I4210125930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361217","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-6680-5886"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Computer Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5061112518"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41186195,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.84170001745224,"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":0.84170001745224,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.04809999838471413,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.016899999231100082,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4918999969959259},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.44040000438690186},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.439300000667572},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.3239000141620636},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.31839999556541443},{"id":"https://openalex.org/keywords/computational-lithography","display_name":"Computational lithography","score":0.314300000667572},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.2946000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650000214576721},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C182873914","wikidata":"https://www.wikidata.org/wiki/Q5157329","display_name":"Computational lithography","level":5,"score":0.314300000667572},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C62064638","wikidata":"https://www.wikidata.org/wiki/Q553878","display_name":"Design for manufacturability","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2777466363","wikidata":"https://www.wikidata.org/wiki/Q17008971","display_name":"Design tool","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.25360000133514404},{"id":"https://openalex.org/C2780974030","wikidata":"https://www.wikidata.org/wiki/Q16951926","display_name":"Co-simulation","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/islped65674.2025.11261765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/islped65674.2025.11261765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2027806965","https://openalex.org/W2080592089","https://openalex.org/W2103760115","https://openalex.org/W2132258839","https://openalex.org/W2979340153","https://openalex.org/W3033124768","https://openalex.org/W3102510044","https://openalex.org/W3157055696","https://openalex.org/W3206857466","https://openalex.org/W3210604792","https://openalex.org/W4225793049","https://openalex.org/W4308083836","https://openalex.org/W4308090436","https://openalex.org/W4310887948","https://openalex.org/W4380874622","https://openalex.org/W4391583791","https://openalex.org/W4399163708","https://openalex.org/W4399282654","https://openalex.org/W4401211619","https://openalex.org/W4404482212","https://openalex.org/W4404955793","https://openalex.org/W4405219754"],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"adoption":[2],"of":[3,57,192,226],"NVIDIA":[4,52,86],"Jetson":[5,38,62,87,111,193,202,234],"devices":[6],"in":[7,148,230],"edge-AI":[8,72],"applications":[9],"highlights":[10],"the":[11,45,60,78,124,166,181,188,214,222,227,231],"need":[12],"for":[13,51,59,69,141,155,213,237],"accurate":[14],"architecture":[15,167],"simulation":[16,83,113,116,149],"tools":[17],"on":[18,123,132,158],"their":[19],"integrated":[20,39,63],"GPUs.":[21,40,88],"Existing":[22],"cycle-accurate":[23],"GPU":[24,53,112,173,235],"simulators":[25],"primarily":[26],"target":[27],"traditional":[28,176],"discrete":[29,211],"GPUs":[30,64,143,203,212],"and":[31,104,127,174,196,240],"exhibit":[32],"significant":[33],"inaccuracies":[34],"when":[35],"applied":[36],"to":[37,85,121,130,153],"While":[41],"Accel-Sim":[42,82,93],"serves":[43],"as":[44],"most":[46],"widely":[47],"used":[48],"academic":[49],"simulator":[50],"research,":[54],"its":[55],"lack":[56],"support":[58,140],"latest":[61],"severely":[65],"hinders":[66],"architectural":[67,139],"exploration":[68],"next":[70,232],"generation":[71,233],"devices.We":[73],"propose":[74],"Accel-Sim-J,":[75,159],"which":[76],"bridges":[77],"gap":[79],"by":[80,96,186],"repurposing":[81],"framework":[84,94],"We":[89,199,217],"refine":[90],"three":[91],"major":[92],"components":[95],"applying":[97],"tuner":[98],"modifications,":[99],"GPGPU-Sim":[100],"performance":[101,239],"model":[102],"enhancements,":[103],"correlator":[105],"adjustments.":[106],"These":[107],"improvements":[108],"enable":[109],"precise":[110],"support,":[114],"reducing":[115],"cycle":[117],"errors":[118],"from":[119,128],"29.0%":[120],"22.7%":[122],"Rodinia":[125],"benchmark":[126],"26.1%":[129],"16.1%":[131],"a":[133,145,162,175,205],"transformer":[134],"block.":[135],"Furthermore,":[136],"our":[137],"enhanced":[138],"Ampere":[142],"achieves":[144],"considerable":[146],"reduction":[147],"error":[150],"(from":[151],"140.1%":[152],"50.2%)":[154],"GEMM":[156],"kernels.Based":[157],"we":[160,179],"conduct":[161],"case":[163],"study":[164],"investigating":[165],"design":[168,236],"difference":[169],"between":[170],"an":[171],"edge":[172],"one.":[177],"Specifically,":[178],"compare":[180],"optimal":[182,207],"Compute-to-Cache":[183],"(C2C)":[184],"ratio":[185,209],"changing":[187],"L2":[189,228],"cache":[190,229],"size":[191],"AGX":[194],"Orin":[195],"RTX":[197],"3090.":[198],"conclude":[200],"that":[201,219],"demonstrate":[204],"higher":[206],"C2C":[208],"than":[210],"same":[215],"workloads.":[216],"suggest":[218],"designers":[220],"reduce":[221],"on-chip":[223],"area":[224],"proportion":[225],"better":[238],"efficiency.":[241]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-03T00:00:00"}