{"id":"https://openalex.org/W7154887590","doi":"https://doi.org/10.1007/s11554-026-01889-x","title":"Throughput impact of software multithreading for deep-learning inference on the AMD Kria KV260","display_name":"Throughput impact of software multithreading for deep-learning inference on the AMD Kria KV260","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7154887590","doi":"https://doi.org/10.1007/s11554-026-01889-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11554-026-01889-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11554-026-01889-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11554-026-01889-x.pdf","source":{"id":"https://openalex.org/S11282291","display_name":"Journal of Real-Time Image Processing","issn_l":"1861-8200","issn":["1861-8200","1861-8219"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Real-Time Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11554-026-01889-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101991003","display_name":"Claudino Costa","orcid":"https://orcid.org/0000-0003-3524-3670"},"institutions":[{"id":"https://openalex.org/I185808892","display_name":"Polytechnic Institute of C\u00e1vado and Ave","ror":"https://ror.org/0448qsq10","country_code":"PT","type":"education","lineage":["https://openalex.org/I185808892"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Claudino Costa","raw_affiliation_strings":["2Ai - School of Technology, IPCA, Barcelos, Portugal"],"raw_orcid":"https://orcid.org/0000-0003-3524-3670","affiliations":[{"raw_affiliation_string":"2Ai - School of Technology, IPCA, Barcelos, Portugal","institution_ids":["https://openalex.org/I185808892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025384684","display_name":"Jos\u00e9 Henrique Brito","orcid":"https://orcid.org/0000-0002-4544-4698"},"institutions":[{"id":"https://openalex.org/I185808892","display_name":"Polytechnic Institute of C\u00e1vado and Ave","ror":"https://ror.org/0448qsq10","country_code":"PT","type":"education","lineage":["https://openalex.org/I185808892"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Henrique Brito","raw_affiliation_strings":["2Ai - School of Technology, IPCA, Barcelos, Portugal","LASI - Associate Laboratory of Intelligent Systems, Guimar\u00e3es, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-4544-4698","affiliations":[{"raw_affiliation_string":"2Ai - School of Technology, IPCA, Barcelos, Portugal","institution_ids":["https://openalex.org/I185808892"]},{"raw_affiliation_string":"LASI - Associate Laboratory of Intelligent Systems, Guimar\u00e3es, Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101991003"],"corresponding_institution_ids":["https://openalex.org/I185808892"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8755258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7781000137329102,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7781000137329102,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03660000115633011,"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":0.03610000014305115,"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/multithreading","display_name":"Multithreading","score":0.8970999717712402},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7554000020027161},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.6880999803543091},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6801999807357788},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5942999720573425},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5787000060081482},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.48510000109672546},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4578999876976013},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.8970999717712402},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825999855995178},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7554000020027161},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.6880999803543091},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6801999807357788},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5787000060081482},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.48510000109672546},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41440001130104065},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.35260000824928284},{"id":"https://openalex.org/C2778787235","wikidata":"https://www.wikidata.org/wiki/Q49007","display_name":"Yarn","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C2984968299","wikidata":"https://www.wikidata.org/wiki/Q1077784","display_name":"Software tool","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.259799987077713},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11554-026-01889-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11554-026-01889-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11554-026-01889-x.pdf","source":{"id":"https://openalex.org/S11282291","display_name":"Journal of Real-Time Image Processing","issn_l":"1861-8200","issn":["1861-8200","1861-8219"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Real-Time Image Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11554-026-01889-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11554-026-01889-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11554-026-01889-x.pdf","source":{"id":"https://openalex.org/S11282291","display_name":"Journal of Real-Time Image Processing","issn_l":"1861-8200","issn":["1861-8200","1861-8219"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Real-Time Image Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1125761991","display_name":null,"funder_award_id":"UIDP/05549/2020","funder_id":"https://openalex.org/F4320323642","funder_display_name":"Minist\u00e9rio da Ci\u00eancia, Tecnologia e Ensino Superior"},{"id":"https://openalex.org/G510732750","display_name":"Applied Artificial Intelligence Laboratory","funder_award_id":"UIDP/05549/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5352183728","display_name":"Multimodal Deep Learning for Real-time Inference on Edge Devices","funder_award_id":"UI/BD/154670/2023","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8519435835","display_name":"Applied Artificial Intelligence Laboratory","funder_award_id":"UIDB/05549/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G8580564290","display_name":null,"funder_award_id":"UIDB/05549/2020","funder_id":"https://openalex.org/F4320323642","funder_display_name":"Minist\u00e9rio da Ci\u00eancia, Tecnologia e Ensino Superior"}],"funders":[{"id":"https://openalex.org/F4320323642","display_name":"Minist\u00e9rio da Ci\u00eancia, Tecnologia e Ensino Superior","ror":"https://ror.org/045b9pr88"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7154887590.pdf","grobid_xml":"https://content.openalex.org/works/W7154887590.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2960833983","https://openalex.org/W2963163009","https://openalex.org/W2980786075","https://openalex.org/W2981341989","https://openalex.org/W2982424334","https://openalex.org/W2996485093","https://openalex.org/W2998506323","https://openalex.org/W3042905487","https://openalex.org/W3043571714","https://openalex.org/W3110974438","https://openalex.org/W3165689947","https://openalex.org/W3216299549","https://openalex.org/W4206336135","https://openalex.org/W4280500134","https://openalex.org/W4280555890","https://openalex.org/W4308090791","https://openalex.org/W4312705522","https://openalex.org/W4317727238","https://openalex.org/W4322761281","https://openalex.org/W4327969081","https://openalex.org/W4386422402","https://openalex.org/W4390188552","https://openalex.org/W4401814120","https://openalex.org/W4403535680"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Efficient":[1],"use":[2],"of":[3,5,24,68,83,106,119,145,167],"resources":[4],"FPGA-based":[6],"system-on-modules":[7],"(SoMs)":[8],"is":[9],"critical":[10],"for":[11,70],"deploying":[12],"deep":[13],"neural":[14],"networks":[15],"at":[16],"the":[17,22,28,66,84,97,110,137,150,168],"edge.":[18],"This":[19],"work":[20],"quantifies":[21],"impact":[23],"software":[25,160],"multithreading":[26,161],"on":[27,46,92,103],"AMD":[29],"Kria":[30],"KV260,":[31],"built":[32],"around":[33],"a":[34,39,43,93,104,116,164],"Zynq":[35],"UltraScale+":[36],"MPSoC":[37],"with":[38],"Quad-Core":[40],"Cortex-A53":[41],"and":[42,57,87,96],"DPU":[44],"accelerator,":[45],"an":[47,76,142],"image":[48,52],"classification":[49,53],"task.":[50],"Three":[51],"models":[54,89],"(MobileNetV2,":[55],"ResNet-50,":[56],"SqueezeNet)":[58],"were":[59,90],"benchmarked":[60],"under":[61],"identical":[62],"conditions,":[63],"while":[64],"varying":[65],"number":[67],"threads":[69,147],"each":[71],"test.":[72],"Each":[73],"thread":[74],"drives":[75],"independent":[77],"Vitis-AI":[78],"runner":[79],"instance.":[80],"The":[81],"accuracies":[82],"floating":[85],"point":[86],"quantized":[88],"recorded":[91],"host":[94],"PC,":[95],"KV260":[98,169],"inference":[99],"throughput":[100,117],"was":[101],"evaluated":[102],"subset":[105],"500":[107],"images":[108],"from":[109],"ImageNet":[111],"dataset.":[112],"Thread":[113],"concurrency":[114],"delivered":[115],"gain":[118],"approximately":[120],"3.1":[121],"$$\\times":[122,130],"$$":[123,131],"<mml:math":[124,132],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[125,133],"<mml:mo>\u00d7</mml:mo>":[126,134],"</mml:math>":[127,135],"to":[128,141],"3.67":[129],"across":[136],"three":[138],"models,":[139],"up":[140],"optimal":[143],"threshold":[144],"four":[146],"without":[148],"degrading":[149],"models\u2019":[151],"Top-1":[152],"accuracy.":[153],"Results":[154],"provide":[155],"board-specific":[156],"evidence":[157],"that":[158],"lightweight":[159],"can":[162],"unlock":[163],"significant":[165],"portion":[166],"performance.":[170]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-04-20T00:00:00"}