Hardware/Software Co-Exploration of Neural Architectures
This work addresses the challenge of optimizing neural networks for hardware efficiency, which is crucial for deploying AI in resource-constrained environments, and it represents a novel co-exploration approach rather than an incremental improvement.
The authors tackled the problem of neural architecture search (NAS) by simultaneously exploring both neural architectures and hardware designs, resulting in a framework that achieved the same accuracy with 35.24% higher throughput, 54.05% higher energy efficiency, and 136x reduced search time compared to state-of-the-art hardware-aware NAS on ImageNet.
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS). Different from existing hardware-aware NAS which assumes a fixed hardware design and explores the neural architecture search space only, our framework simultaneously explores both the architecture search space and the hardware design space to identify the best neural architecture and hardware pairs that maximize both test accuracy and hardware efficiency. Such a practice greatly opens up the design freedom and pushes forward the Pareto frontier between hardware efficiency and test accuracy for better design tradeoffs. The framework iteratively performs a two-level (fast and slow) exploration. Without lengthy training, the fast exploration can effectively fine-tune hyperparameters and prune inferior architectures in terms of hardware specifications, which significantly accelerates the NAS process. Then, the slow exploration trains candidates on a validation set and updates a controller using the reinforcement learning to maximize the expected accuracy together with the hardware efficiency. Experiments on ImageNet show that our co-exploration NAS can find the neural architectures and associated hardware design with the same accuracy, 35.24% higher throughput, 54.05% higher energy efficiency and 136x reduced search time, compared with the state-of-the-art hardware-aware NAS.