{"id":"https://openalex.org/W4410518888","doi":"https://doi.org/10.1145/3736175","title":"Deep Learning Workload Mapping Optimization on Jetson Platforms","display_name":"Deep Learning Workload Mapping Optimization on Jetson Platforms","publication_year":2025,"publication_date":"2025-05-20","ids":{"openalex":"https://openalex.org/W4410518888","doi":"https://doi.org/10.1145/3736175"},"language":"en","primary_location":{"id":"doi:10.1145/3736175","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736175","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736175","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3736175","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042525070","display_name":"Farui Wang","orcid":"https://orcid.org/0000-0002-2478-2153"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Farui Wang","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen","Harbin Institute of Technology Shenzhen,  Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2478-2153","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen,  Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060954730","display_name":"Meng Hao","orcid":"https://orcid.org/0000-0003-0043-4370"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Hao","raw_affiliation_strings":["Harbin Institute of Technology","Harbin Institute of Technology,  Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-0043-4370","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology,  Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyu Yang","orcid":"https://orcid.org/0009-0000-0071-6218"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyu Yang","raw_affiliation_strings":["Computer Science and Technology, Harbin Institute of Technology","Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0000-0071-6218","affiliations":[{"raw_affiliation_string":"Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085221201","display_name":"Weizhe Zhang","orcid":"https://orcid.org/0000-0003-4783-876X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhe Zhang","raw_affiliation_strings":["Harbin Institute of Technology Shenzhen","Harbin Institute of Technology Shenzhen,  Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4783-876X","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Shenzhen,  Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":6.7708,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.95734484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"22","issue":"2","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11701","display_name":"Space Satellite Systems and Control","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11701","display_name":"Space Satellite Systems and Control","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11325","display_name":"Inertial Sensor and Navigation","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9465000033378601,"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/computer-science","display_name":"Computer science","score":0.7770671844482422},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6069337725639343},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4694867730140686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44987359642982483},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2611704468727112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770671844482422},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6069337725639343},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4694867730140686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44987359642982483},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2611704468727112}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3736175","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736175","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736175","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3736175","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3736175","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3736175","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G752701465","display_name":null,"funder_award_id":"U22A2036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8725492322","display_name":null,"funder_award_id":"62202123","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410518888.pdf","grobid_xml":"https://content.openalex.org/works/W4410518888.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2919115771","https://openalex.org/W2919358988","https://openalex.org/W2962814013","https://openalex.org/W2963163009","https://openalex.org/W2963351448","https://openalex.org/W2983440318","https://openalex.org/W3010466514","https://openalex.org/W3012249773","https://openalex.org/W3016430712","https://openalex.org/W3070733705","https://openalex.org/W3091023227","https://openalex.org/W3098486933","https://openalex.org/W3112293503","https://openalex.org/W3169512402","https://openalex.org/W4200155228","https://openalex.org/W4210338699","https://openalex.org/W4210621820","https://openalex.org/W4281932226","https://openalex.org/W4291972732","https://openalex.org/W4293024010","https://openalex.org/W4312235386","https://openalex.org/W4319068657","https://openalex.org/W4372263903","https://openalex.org/W4378976287","https://openalex.org/W4386568606","https://openalex.org/W4386764053","https://openalex.org/W4389500478","https://openalex.org/W4392200220","https://openalex.org/W6752057402"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"To":[0],"improve":[1,62,84],"the":[2,95,99,107,116,123,130,136,141,185,204],"performance":[3],"and":[4,27,42,87,98,140,171,174,192,195],"energy":[5,64,85,173,194],"efficiency":[6,86],"of":[7,49,94,110,118,144],"deep":[8,43],"learning":[9,44],"(DL)":[10],"applications,":[11],"recent":[12],"edge":[13],"computing":[14],"platforms":[15,38],"have":[16],"built-in":[17],"heterogeneous":[18],"accelerators,":[19],"such":[20],"as":[21],"general-purpose":[22],"graphics":[23],"processing":[24,29],"units":[25,30],"(GPUs)":[26],"neural":[28],"(NPUs).":[31],"For":[32],"example,":[33],"widely":[34],"used":[35],"NVIDIA":[36],"Jetson":[37,159],"contain":[39],"CPU,":[40],"GPU,":[41],"accelerator":[45],"(DLA),":[46],"a":[47,74,111,158],"type":[48],"NPU.":[50],"It":[51],"is":[52],"non-trivial":[53],"to":[54,58,61,82,106,134,153,184,202,208,220],"map":[55],"DL":[56,112,155],"workloads":[57],"suitable":[59],"accelerators":[60],"performance,":[63],"efficiency,":[65],"or":[66],"even":[67],"both.":[68],"This":[69],"article":[70],"presents":[71],"JDIMO,":[72],"1":[73],"Jetson-aware":[75],"deep-learning":[76],"inference":[77],"workload":[78],"mapping":[79,138],"optimization":[80,215],"framework,":[81],"simultaneously":[83],"performance.":[88],"JDIMO":[89,149,164,188,211],"first":[90],"measures":[91],"energy-performance":[92,121],"data":[93],"fundamental":[96],"nodes":[97],"sub-networks":[100],"with":[101],"energy-efficiency":[102],"improvement":[103],"potential":[104],"according":[105],"topology":[108],"structure":[109],"network.":[113],"Then,":[114],"under":[115],"guidance":[117],"an":[119,126],"analytical":[120],"model,":[122],"framework":[124],"exploits":[125],"algorithm":[127],"based":[128],"on":[129,157,181,199,217],"variable-length":[131],"sliding":[132],"window":[133],"find":[135],"optimal":[137,142],"configuration":[139],"number":[143],"CUDA":[145],"streams.":[146],"We":[147],"evaluate":[148],"by":[150],"applying":[151],"it":[152],"seven":[154],"applications":[156],"Orin":[160],"NX":[161],"(16GB)":[162],"platform.":[163],"saves":[165,189],"47.5%":[166],"EDP":[167,191],"(energy":[168],"delay":[169],"product)":[170],"22.6%":[172],"improves":[175,196],"138.3%":[176],"QPS":[177,198],"(queries":[178],"per":[179],"second)":[180],"average":[182,200,218],"compared":[183,201,219],"DLA-possible":[186],"configuration.":[187],"22.5%":[190],"12.6%":[193],"13.5%":[197],"JEDI,":[203],"most":[205],"similar":[206],"work":[207],"ours.":[209],"Meanwhile,":[210],"also":[212],"reduces":[213],"93.8%":[214],"time":[216],"JEDI.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}