GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs
GPU加速稀疏全同态加密DNN
机构 * University of Glasgow(格拉斯哥大学) ; University of Murcia(穆尔西亚大学) ; Northeastern University(东北大学) ; AMD(超威半导体公司)
AI总结 本文提出在AMD GPU上加速深度神经网络中矩阵乘法的方法,利用FIDESlib库优化稀疏矩阵运算,提升运行效率并降低时间复杂度。
Comments Accepted to the 6th Workshop on Machine Learning and Systems (EuroMLSys) co-located with EuroSys '26