A Precision-Scalable RISC-V DNN Processor with On-Device Learning Capability at the Extreme Edge

TL;DR

This paper introduces a RISC-V based DNN processor capable of multi-precision inference and on-device learning, significantly improving throughput and energy efficiency for edge applications with limited resources.

Contribution

It presents a novel precision-scalable RISC-V DNN processor with enhanced on-device learning support, optimized for extreme edge platforms.

Findings

Increases inference throughput by up to 14.6×

Improves energy efficiency by up to 14.6×

Achieves 16.5× higher FP throughput for on-device learning

Abstract

Extreme edge platforms, such as in-vehicle smart devices, require efficient deployment of quantized deep neural networks (DNNs) to enable intelligent applications with limited amounts of energy, memory, and computing resources. However, many edge devices struggle to boost inference throughput of various quantized DNNs due to the varying quantization levels, and these devices lack floating-point (FP) support for on-device learning, which prevents them from improving model accuracy while ensuring data privacy. To tackle the challenges above, we propose a precision-scalable RISC-V DNN processor with on-device learning capability. It facilitates diverse precision levels of fixed-point DNN inference, spanning from 2-bit to 16-bit, and enhances on-device learning through improved support with FP16 operations. Moreover, we employ multiple methods such as FP16 multiplier reuse and multi-precision integer multiplier reuse, along with balanced mapping of FPGA resources, to significantly improve hardware resource utilization. Experimental results on the Xilinx ZCU102 FPGA show that our processor significantly improves inference throughput by 1.6$\sim$14.6$\times$ and energy efficiency by 1.1$\sim$14.6$\times$ across various DNNs, compared to the prior art, XpulpNN. Additionally, our processor achieves a 16.5$\times$ higher FP throughput for on-device learning.