Toward Designing Thermally-Aware Memristance Decoder

Abstract

Memristors are intensively proposed in many applications, such as biosensors and machine learning. Regarding their analog characteristics, memristance decoder is, therefore, an essential part for every memristor-based system. As memristor is a temperature sensitive device, this paper proposes a memristance decoder circuit with the self-temperature calibration. Its main building block is a comparator that is based on current mode circuit to achieve high performance at low power. The design provides configurable precision based on the available energy and supports both synchronous and asynchronous schemes. Moreover, the VTEAM model is modified to include the temperature effect on the memristance in the analysis. The simulation results, based on UMC 65-nm low-leakage CMOS technology, show the following comparator’s characteristics: 1.70% maximum offset, 2.91-ns worst case latency, 343-MHz maximum frequency, and 48.79-fJ maximum energy per comparison. The Monte Carlo simulation shows the metastable state in determining the memristor value. This can be solved by extending the clock period or applying a metastability resolver. The proposed memristor model reveals that the memristance at high resistive state degrades quadratically with the rise of the temperature and at 85° C nearly reaches the memristance of low resistive state. The possibility of decoding error due to the temperature effect is demonstrated via simulations.