Mix-GEMM: Extending RISC-V CPUs for Energy-Efficient Mixed-Precision DNN Inference Using Binary Segmentation
Jordi ForntEnrico ReggianiPau Fontova-MustéNarcís RodasAlessandro PappalardoOsman ÜnsalAdrián CristalJosep AltetFrancesc MollJaume Abella
Abstract
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Metrics
Citation History
Topics
Related Documents
Extending RISC-V for Efficient Overflow Recovery in Mixed-Precision Computations
Bertaccini, LucaShen, SiyuanHoefler, TorstenBenini, Luca
Extending RISC-V for Efficient Overflow Recovery in Mixed-Precision Computations
Luca BertacciniSiyuan ShenTorsten HoeflerLuca Benini
Efficient Flexible Edge Inference for Mixed-Precision Quantized DNN using Customized RISC-V Core
Tsung-Che LuJiangyang DingHuachen ZhangBowen JiangWei XuZhilei Chai
Benchmarking Deep Learning Inference on RISC-V CPUs
Ivan MukhinYury RodimkovEvgeny VasilievValentin VolokitinAlla SidorovaEvgeny KozinovIosif MeyerovВалентина Кустикова
EVO-QNN: Efficient Mixed-Precision Quantization Inference on RISC-V-Based Edge Device
Tenglong LuJianyang DingHuachen ZhangBowen JiangXu WeiZhilei Chai