Fault Injection in Native Logic-in-Memory Computation on Neuromorphic Hardware

2023/02/15 by Felix Staudigl, Thorben Fetz, Staudigl, Felix +11 · 1 citation
Engineering · Neuroscience · #Advanced Memory and Neural Computing #Ferroelectric and Negative Capacitance Devices #Neuroscience and Neural Engineering

paper · pdf · doi:10.48550/arxiv.2302.07655

Abstract

Logic-in-memory (LIM) describes the execution of logic gates within memristive crossbar structures, promising to improve performance and energy efficiency. Utilizing only binary values, LIM particularly excels in accelerating binary neural networks, shifting it in the focus of edge applications. Considering its potential, the impact of faults on BNNs accelerated with LIM still lacks investigation. In this paper, we propose faulty logic-in-memory (FLIM), a fault injection platform capable of executing full-fledged BNNs on LIM while injecting in-field faults. The results show that FLIM runs a single MNIST picture 66754x faster than the state of the art by offering a fine-grained fault injection methodology.

Cited by

• SafeCiM: Investigating Resilience of Hybrid Floating-Point Compute-in-Memory Deep Learning Accelerators

Related

• X-Fault: Impact of Faults on Binary Neural Networks in Memristor-Crossbar Arrays with Logic-in-Memory Computation
• A Survey on Impact of Transient Faults on BNN Inference Accelerators
• Analyzing the Single Event Upset Vulnerability of Binarized Neural Networks on SRAM FPGAs
• Late Breaking Result: FPGA-Based Emulation and Fault Injection for CNN Inference Accelerators
• Fault Injectors for TensorFlow: Evaluation of the Impact of Random Hardware Faults on Deep CNNs