X-Fault: Impact of Faults on Binary Neural Networks in Memristor-Crossbar Arrays with Logic-in-Memory Computation (2204.01501v1)

Abstract: Memristor-based crossbar arrays represent a promising emerging memory technology to replace conventional memories by offering a high density and enabling computing-in-memory (CIM) paradigms. While analog computing provides the best performance, non-idealities and ADC/DAC conversion limit memristor-based CIM. Logic-in-Memory (LIM) presents another flavor of CIM, in which the memristors are used in a binary manner to implement logic gates. Since binary neural networks (BNNs) use binary logic gates as the dominant operation, they can benefit from the massively parallel execution of binary operations and better resilience to variations of the memristors. Although conventional neural networks have been thoroughly investigated, the impact of faults on memristor-based BNNs remains unclear. Therefore, we analyze the impact of faults on logic gates in memristor-based crossbar arrays for BNNs. We propose a simulation framework that simulates different traditional faults to examine the accuracy loss of BNNs on memristive crossbar arrays. In addition, we compare different logic families based on the robustness and feasibility to accelerate AI applications.