Accelerated Digital Twin Learning for Edge AI: A Comparison of FPGA and Mobile GPU

TL;DR

This paper introduces a hardware-accelerated digital twin learning framework optimized for edge AI, comparing FPGA and mobile GPU implementations, demonstrating significant improvements in speed, energy efficiency, and resource usage for healthcare applications.

Contribution

The paper presents a novel FPGA-based digital twin learning framework that outperforms mobile GPU and cloud GPU in speed and energy efficiency, tailored for real-time healthcare applications.

Findings

FPGA achieves 8.8x better performance-per-watt than mobile GPU.

FPGA reduces DRAM footprint by 28.5x compared to mobile GPU.

FPGA is 1.67x faster than cloud GPU in runtime.

Abstract

Digital twins (DTs) can enable precision healthcare by continually learning a mathematical representation of patient-specific dynamics. However, mission critical healthcare applications require fast, resource-efficient DT learning, which is often infeasible with existing model recovery (MR) techniques due to their reliance on iterative solvers and high compute/memory demands. In this paper, we present a general DT learning framework that is amenable to acceleration on reconfigurable hardware such as FPGAs, enabling substantial speedup and energy efficiency. We compare our FPGA-based implementation with a multi-processing implementation in mobile GPU, which is a popular choice for AI in edge devices. Further, we compare both edge AI implementations with cloud GPU baseline. Specifically, our FPGA implementation achieves an 8.8x improvement in \text{performance-per-watt} for the MR task, a 28.5x reduction in DRAM footprint, and a 1.67x runtime speedup compared to cloud GPU baselines. On the other hand, mobile GPU achieves 2x better performance per watts but has 2x increase in runtime and 10x more DRAM footprint than FPGA. We show the usage of this technique in DT guided synthetic data generation for Type 1 Diabetes and proactive coronary artery disease detection.