{"id":"https://openalex.org/W7164123379","doi":"https://doi.org/10.1109/fccm68464.2026.00075","title":"Reconfigurable Computing Challenge: Deploying SmolVLA Model on an AMD XDNA NPU","display_name":"Reconfigurable Computing Challenge: Deploying SmolVLA Model on an AMD XDNA NPU","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7164123379","doi":"https://doi.org/10.1109/fccm68464.2026.00075"},"language":null,"primary_location":{"id":"doi:10.1109/fccm68464.2026.00075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","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/A5010907150","display_name":"Xiaoyu Liang","orcid":"https://orcid.org/0000-0002-5134-7501"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Liang","raw_affiliation_strings":["Cornell University,School of ECE,Ithaca,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of ECE,Ithaca,New York,USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138291546","display_name":"Elaine Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Cao","raw_affiliation_strings":["Cornell University,School of ECE,Ithaca,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of ECE,Ithaca,New York,USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136695710","display_name":"Chun-Ning Kao","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Ning Kao","raw_affiliation_strings":["Cornell University,School of ECE,Ithaca,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of ECE,Ithaca,New York,USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138335557","display_name":"David Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Lin","raw_affiliation_strings":["Cornell University,School of ECE,Ithaca,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of ECE,Ithaca,New York,USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138383740","display_name":"Jiajie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajie Li","raw_affiliation_strings":["Cornell University,School of ECE,Ithaca,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of ECE,Ithaca,New York,USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009797301","display_name":"Z L Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiru Zhang","raw_affiliation_strings":["Cornell University,School of ECE,Ithaca,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University,School of ECE,Ithaca,New York,USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86132175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"294","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.5763999819755554,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.5763999819755554,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.10599999874830246,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.06310000270605087,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3084000051021576},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.3082999885082245},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.27410000562667847},{"id":"https://openalex.org/keywords/opc-data-access","display_name":"OPC Data Access","score":0.2362000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609499990940094},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2809000015258789},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.24160000681877136},{"id":"https://openalex.org/C73952413","wikidata":"https://www.wikidata.org/wiki/Q7072811","display_name":"OPC Data Access","level":3,"score":0.2362000048160553},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2313999980688095}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fccm68464.2026.00075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm68464.2026.00075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 34th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","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":5,"referenced_works":["https://openalex.org/W4394661856","https://openalex.org/W4400489024","https://openalex.org/W4407874080","https://openalex.org/W4410810249","https://openalex.org/W4416748653"],"related_works":[],"abstract_inverted_index":{"Vision\u2013Language\u2013Action":[0],"(VLA)":[1],"models":[2],"have":[3],"demonstrated":[4],"strong":[5],"generalization":[6],"across":[7],"robotic":[8],"tasks":[9],"and":[10,53,69,94,102,122],"embodiments.":[11],"However,":[12],"current":[13,120],"deployments":[14],"rely":[15],"on":[16,46,129],"GPU-based":[17],"inference":[18],"that":[19],"is":[20],"power":[21],"inefficient":[22],"for":[23],"edge":[24],"platforms,":[25],"motivating":[26],"the":[27,40,66,70],"exploration":[28,38],"of":[29,39,42],"more":[30],"efficient":[31],"hardware":[32],"targets.":[33],"We":[34],"present":[35],"an":[36,47,89,114],"initial":[37,115],"deployment":[41,128],"a":[43,56,83,108],"VLA":[44,127],"model":[45],"AMD":[48],"XDNA1":[49],"NPU,":[50],"targeting":[51],"SmolVLA":[52],"using":[54],"Allo,":[55],"Python-based":[57],"dataflow":[58],"DSL.":[59],"Operational":[60],"intensity":[61],"profiling":[62,85],"identifies":[63],"GEMM":[64],"as":[65],"dominant":[67],"kernel":[68],"primary":[71],"NPU":[72],"target.":[73],"To":[74],"support":[75],"SmolVLA\u2019s":[76],"wide":[77],"dynamic":[78],"shape":[79],"variation,":[80],"we":[81,117],"develop":[82],"pre-cached":[84],"database":[86],"augmented":[87],"by":[88],"LLM-assisted":[90],"tiling":[91],"agent.":[92],"Normalization":[93],"activation":[95],"kernels":[96],"are":[97],"further":[98],"optimized":[99],"through":[100],"vectorization":[101],"approximations.":[103],"This":[104],"work":[105],"results":[106],"in":[107],"functionally":[109],"correct":[110],"end-to-end":[111],"prototype.":[112],"As":[113],"exploration,":[116],"also":[118],"discuss":[119],"limitations":[121],"optimization":[123],"opportunities":[124],"toward":[125],"practical":[126],"NPUs.":[130]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-06-11T00:00:00"}
