AFarePart: Accuracy-aware Fault-resilient Partitioner for DNN Edge Accelerators

TL;DR

This paper introduces AFarePart, a fault-resilient DNN partitioning framework that optimizes accuracy, energy, and latency for edge accelerators, improving fault tolerance with minimal overhead.

Contribution

It proposes a novel multi-objective optimization framework using NSGA-II that incorporates fault resilience directly into DNN partitioning for edge systems.

Findings

Achieves up to 27.7% improvement in fault tolerance.

Demonstrates minimal performance overhead.

Validates on benchmark CNNs like AlexNet, SqueezeNet, ResNet18.

Abstract

Deep Neural Networks (DNNs) are increasingly deployed across distributed and resource-constrained platforms, such as System-on-Chip (SoC) accelerators and edge-cloud systems. DNNs are often partitioned and executed across heterogeneous processing units to optimize latency and energy. However, the reliability of these partitioned models under hardware faults and communication errors remains a critical yet underexplored topic, especially in safety-critical applications. In this paper, we propose an accuracy-aware, fault-resilient DNN partitioning framework targeting multi-objective optimization using NSGA-II, where accuracy degradation under fault conditions is introduced as a core metric alongside energy and latency. Our framework performs runtime fault injection during optimization and utilizes a feedback loop to prioritize fault-tolerant partitioning. We evaluate our approach on benchmark CNNs including AlexNet, SqueezeNet and ResNet18 on hardware accelerators, and demonstrate up to 27.7% improvement in fault tolerance with minimal increase in performance overhead. Our results highlight the importance of incorporating resilience into DNN partitioning, and thereby paving the way for robust AI inference in error-prone environments.