Polara-Keras2c: Supporting Vectorized AI Models on RISC-V Edge Devices

Abstract

The rise of edge computing has introduced unique challenges for deploying efficient AI solutions in resource-limited environments. While traditional AI frameworks are powerful, they often fall short in meeting the requirements of edge computing, such as low latency, constrained computational power, and energy efficiency. This paper presents Polara-Keras2c, an optimized evolution of Keras2c designed specifically for edge computing. Polara-Keras2c enhances compatibility with bare-metal systems, incorporates RISC-V vector extension optimization, and is customized for the Polara architecture. By converting pre-trained Keras models into optimized C code for bare-metal execution on edge devices, Polara-Keras2c enables advanced AI models to operate efficiently in resource-constrained environments. The framework supports fixed-point arithmetic, achieving a minimal accuracy impact of only 0.03% when tested on the MNIST dataset, and offers a streamlined approach for rapid prototyping. Experimental results reveal that Polara-Keras2c achieves up to 4.81 times faster convolution processing with a $64\times 64$ input size compared to scalar processing, significantly enhancing computational efficiency and reducing energy consumption. These capabilities position Polara-Keras2c as a transformative tool in real-time, energy-efficient AI processing for edge devices, pushing forward the evolution of edge computing.

Keywords

• Vector processor
• artificial intelligence
• bare metal
• real-time
• edge computing
• embedded systems