AsyMo
Manni Wang, Shaohua Ding, Ting Cao, Yunxin Liu, Fengyuan Xu
Abstract
On-device deep learning (DL) inference has attracted vast interest. Mobile CPUs are the most common hardware for on-device inference and many inference frameworks have been developed for them. Yet, due to the hardware complexity, DL inference on mobile CPUs suffers from two common issues: the poor performance scalability on the asymmetric multiprocessor, and energy inefficiency.
Topics & Concepts
InferenceComputer scienceScalabilityInefficiencyMultiprocessingMobile deviceComputer architectureArtificial intelligenceEmbedded systemDistributed computingParallel computingOperating systemMicroeconomicsEconomicsAdvanced Neural Network ApplicationsParallel Computing and Optimization TechniquesAdvanced Memory and Neural Computing