Thermal Heating in ReRAM Crossbar Arrays: Challenges and Solutions
This is an incremental review paper that summarizes challenges and solutions for improving thermal resilience in ReRAM-based AI accelerators, targeting hardware designers and researchers.
The paper addresses the problem of thermal heating in ReRAM crossbar arrays, which degrades accuracy and reliability, and reviews solutions that have reported up to 58% accuracy improvement and 2.39x lifetime enhancement.
The higher speed, scalability and parallelism offered by ReRAM crossbar arrays foster development of ReRAM-based next generation AI accelerators. At the same time, sensitivity of ReRAM to temperature variations decreases R_on/Roff ratio and negatively affects the achieved accuracy and reliability of the hardware. Various works on temperature-aware optimization and remapping in ReRAM crossbar arrays reported up to 58\% improvement in accuracy and 2.39$\times$ ReRAM lifetime enhancement. This paper classifies the challenges caused by thermal heat, starting from constraints in ReRAM cells' dimensions and characteristics to their placement in the architecture. In addition, it reviews available solutions designed to mitigate the impact of these challenges, including emerging temperature-resilient DNN training methods. Our work also provides a summary of the techniques and their advantages and limitations.