Neural Network Inference on Mobile SoCs
This addresses the need for efficient ML inference on mobile devices, but it is incremental as it builds on existing heterogeneous SoC architectures.
The paper tackled the problem of optimizing neural network inference on mobile SoCs by evaluating the power-performance characteristics of different components like CPU, GPU, and accelerators, and found that engaging all components concurrently provides up to 2x improvement in performance compared to using a single component.
The ever-increasing demand from mobile Machine Learning (ML) applications calls for evermore powerful on-chip computing resources. Mobile devices are empowered with heterogeneous multi-processor Systems-on-Chips (SoCs) to process ML workloads such as Convolutional Neural Network (CNN) inference. Mobile SoCs house several different types of ML capable components on-die, such as CPU, GPU, and accelerators. These different components are capable of independently performing inference but with very different power-performance characteristics. In this article, we provide a quantitative evaluation of the inference capabilities of the different components on mobile SoCs. We also present insights behind their respective power-performance behavior. Finally, we explore the performance limit of the mobile SoCs by synergistically engaging all the components concurrently. We observe that a mobile SoC provides up to 2x improvement with parallel inference when all its components are engaged, as opposed to engaging only one component.