{"id":"https://openalex.org/W7148248894","doi":"https://doi.org/10.1109/hipcw66559.2025.00113","title":"Pushing Performance: Quantized BRGEMM Convolutions for Efficient Vision Inference on ARM","display_name":"Pushing Performance: Quantized BRGEMM Convolutions for Efficient Vision Inference on ARM","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7148248894","doi":"https://doi.org/10.1109/hipcw66559.2025.00113"},"language":null,"primary_location":{"id":"doi:10.1109/hipcw66559.2025.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5132770083","display_name":"Deeksha Kasture","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deeksha Kasture","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132805841","display_name":"Ashish Chopra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Chopra","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132798823","display_name":"Abhishek Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhishek Jain","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116479487","display_name":"Masahiro Doteguchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masahiro Doteguchi","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112225690","display_name":"A. Nukariya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsushi Nukariya","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132827667","display_name":"Priyanka Sharma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Priyanka Sharma","raw_affiliation_strings":["Fujitsu Research of India,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fujitsu Research of India,Bangalore,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.25459998846054077,"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":0.25459998846054077,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.10289999842643738,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08969999849796295,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3578000068664551},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3345000147819519},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2944999933242798},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26739999651908875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5649999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48159998655319214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4214000105857849},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3578000068664551},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.329800009727478},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26339998841285706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipcw66559.2025.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipcw66559.2025.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"deep":[1],"learning":[2],"models":[3],"require":[4],"faster":[5],"and":[6,40,72,92,98,113,137],"more":[7],"efficient":[8,59],"inference":[9,61,107,163],"solutions.":[10],"Recognizing":[11],"that":[12],"quantization":[13],"offers":[14,89],"a":[15,29,155],"key":[16],"strategy":[17],"to":[18,36,111,118,121,131,144],"meet":[19],"this":[20,26,87],"need,":[21],"particularly":[22],"on":[23,62,164],"resource-constrained":[24],"systems,":[25],"work":[27],"introduces":[28],"quantized":[30],"low-precision":[31],"computation":[32],"kernel":[33,135],"specifically":[34,56],"designed":[35],"significantly":[37],"enhance":[38],"throughput":[39],"reduce":[41],"latency.":[42],"Building":[43],"upon":[44],"prior":[45],"FP32":[46],"BRGEMM":[47],"convolution":[48],"support,":[49],"we":[50],"present":[51],"optimized":[52],"INT8":[53,146,161],"BRGEMM-based":[54],"convolutions,":[55],"engineered":[57],"for":[58,69,148,159],"model":[60,141],"Arm":[63,80,150],"CPUs,":[64],"which":[65],"incorporate":[66],"advanced":[67],"techniques":[68],"parallel":[70],"execution":[71],"reduced":[73],"arithmetic":[74],"redundancy,":[75],"ensuring":[76],"compatibility":[77],"with":[78],"energy-efficient":[79],"architectures.":[81],"Integrated":[82],"into":[83],"the":[84,134,140,149],"oneDNN":[85],"backend,":[86],"solution":[88,125,158],"seamless":[90],"portability":[91],"adoption":[93],"within":[94],"frameworks":[95],"like":[96],"PyTorch":[97],"TensorFlow.":[99],"Experimental":[100],"evaluations":[101],"demonstrate":[102],"substantial":[103],"performance":[104],"gains:":[105],"kernel-level":[106],"speedups":[108,115,128],"of":[109,116,129],"up":[110,117,130],"6x":[112],"model-level":[114],"2.5x":[119],"compared":[120],"FP32.":[122],"Furthermore,":[123],"our":[124],"achieves":[126],"remarkable":[127],"60x":[132],"at":[133,139],"level":[136,142],"14x":[138],"relative":[143],"existing":[145],"implementations":[147],"ecosystem.":[151],"This":[152],"research":[153],"delivers":[154],"practical,":[156],"high-performant":[157],"accelerating":[160],"convolutional":[162],"Arm-based":[165],"CPUs.":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-03T00:00:00"}