Thermal Heating in ReRAM Crossbar Arrays: Challenges and Solutions

TL;DR

This paper reviews the thermal challenges in ReRAM crossbar arrays used for AI accelerators, discussing their impact on accuracy and reliability, and surveys solutions including temperature-aware optimization and resilient training methods.

Contribution

It classifies thermal challenges in ReRAM arrays and provides a comprehensive review of existing mitigation techniques and their advantages and limitations.

Findings

Temperature variations reduce ReRAM accuracy and reliability.

Temperature-aware optimization improves accuracy and lifetime.

Emerging temperature-resilient training methods offer promising solutions.

Abstract

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.