Although offering great potential for energy-efficient edge-AI, memristor-based CIM accelerators are severely hindered by IR drop induced errors. To tackle this, we propose a low-cost mitigation technique by first quantifying the impact of IR drop on the accuracy. Then, a mitigation strategy is developed to compensate for IR drop-induced inference accuracy reduction by combining an optimized mapping scheme with a fine-tuned calibration of the ADC. Results show the proposed solution can effectively mitigate IR drop with a negligible overhead.

Compute-in-memory (CIM) AI accelerators using non-volatile memories like RRAM enable energy-efficient edge inference by executing Multiply-Accumulate (MAC) operations directly in memory in a single cycle. These designs modify memory cells and analog-to-digital converters (ADCs), introducing faults not seen in standard memories. We present the first structural testing methodology and framework for RRAM-based CIM MAC circuits, including defect and fault models for memory cells and ADCs. Our robust inference-driven tests exercise full MAC functionality, significantly reducing test time compared to traditional methods, and integrating cell and peripheral testing to ensure high reliability, defect coverage, and operational efficiency.

This study introduces a design methodology pertaining to analog hardware architecture for the implementation of the learning vector quantization (LVQ) algorithm. It consists of three main approaches that are separated based on the distance calculation circuit (DCC) and, more specifically; Euclidean distance, Sigmoid function, and Squarer circuits. The main building blocks of each approach are the DCC and the current comparator (CC). The operational principles of the architecture are extensively elucidated and put into practice through a power-efficient configuration (operating less than 650 nW) within a low-voltage setup (0.6 V). Each specific implementation is tested on a brain tumor classification task achieving more than 96.00% classification accuracy. The designs are realized using a 90-nm CMOS process and developed utilizing the Cadence IC Suite for both schematic and physical design. Through a comparative analysis of postlayout simulation outcomes with an equivalent software-based classifier and related works, the accuracy of the applied modeling and design methodologies is validated.