DeepAI AI Chat
Log In Sign Up

Rethinking Co-design of Neural Architectures and Hardware Accelerators

by   Yanqi Zhou, et al.

Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed model architecture or model architecture given fixed hardware. And the dominant hardware architecture explored in this prior work is FPGAs. In our work, we target the optimization of hardware and software configurations on an industry-standard edge accelerator. We systematically study the importance and strategies of co-designing neural architectures and hardware accelerators. We make three observations: 1) the software search space has to be customized to fully leverage the targeted hardware architecture, 2) the search for the model architecture and hardware architecture should be done jointly to achieve the best of both worlds, and 3) different use cases lead to very different search outcomes. Our experiments show that the joint search method consistently outperforms previous platform-aware neural architecture search, manually crafted models, and the state-of-the-art EfficientNet on all latency targets by around 1 energy consumption of an edge accelerator by up to 2x under the same accuracy constraint, when co-adapting the model architecture and hardware accelerator configurations.


page 1

page 2

page 3

page 4


A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators

In view of the performance limitations of fully-decoupled designs for ne...

Accelerator-aware Neural Network Design using AutoML

While neural network hardware accelerators provide a substantial amount ...

Discovering Multi-Hardware Mobile Models via Architecture Search

Developing efficient models for mobile phones or other on-device deploym...

Learned Hardware/Software Co-Design of Neural Accelerators

The use of deep learning has grown at an exponential rate, giving rise t...

Apollo: Transferable Architecture Exploration

The looming end of Moore's Law and ascending use of deep learning drives...

Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search

Modern day computing increasingly relies on specialization to satiate gr...

HW-Aware Initialization of DNN Auto-Tuning to Improve Exploration Time and Robustness

The process of optimizing the latency of DNN operators with ML models an...