Hardware/Software Co-Exploration of Neural Architectures

Abstract

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.

arXiv comment10 pages

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Neural Architecture Search with Reinforcement Learning
• Horovod: fast and easy distributed deep learning in TensorFlow
• Efficient Architecture Search by Network Transformation
• Hierarchical Representations for Efficient Architecture Search
• FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
• Automated flow for compressing convolution neural networks for efficient edge-computation with FPGA

Cited by in corpus (4)

• Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference
• DNA: Differentiable Network-Accelerator Co-Search
• Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks
• Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators