Device-physics co-design of hybrid RRAM-MRAM crossbars: Overcoming stochastic non-idealities for energy efficient edge speech recognition

Yu Li, Yifan Zhang, Xinying Wang, Zhihao Zhao, Guoliang Xing, Longchao Liu, Feng Dong, Zhipeng Guo, Xingyu Gao, Guozhong XingJournal of Applied Physics 2025 · DOI

Abstract

Memristive in-memory computing leverages intrinsic device physics to overcome von Neumann bottlenecks in edge artificial intelligence (AI), yet non-idealities in resistive switching materials limit deployment robustness. Here, we demonstrate a physics-guided hybrid memristor architecture integrating resistive random-access memory (RRAM) and magnetoresistive random-access memory (MRAM) for energy-efficient keyword spotting. By co-designing a binarized depthwise separable convolutional neural network (790-bit model) with device-aware algorithms, we exploit the complementary physical properties of RRAM (high density, filamentary switching) and MRAM (high endurance, spintronic switching). Convolutional layers are mapped to RRAM crossbars for parallel analog vector-matrix multiplication via Ohm's law, while fully connected layers utilize MRAM's endurance for in situ training. A statistic-aware training strategy incorporates device stochasticity (Gaussian resistance variation, shorts/opens) during backpropagation, enhancing fault tolerance. Implemented on a 1 kb TiN/HfOx/TaOx RRAM and CoFeB/MgO-based MRAM array, the system achieves 3.72 ms latency and 14.95 μW power at >85% accuracy under 20% defect rates. This work establishes a device-physics-driven framework for reliable edge AI accelerators.
BibTeX
@article{li2025device,
  author = {Yu Li and Yifan Zhang and Xinying Wang and Zhihao Zhao and Guoliang Xing and Longchao Liu and Feng Dong and Zhipeng Guo and Xingyu Gao and Guozhong Xing},
  title = {{Device-physics co-design of hybrid RRAM-MRAM crossbars: Overcoming stochastic non-idealities for energy efficient edge speech recognition}},
  journal = {Journal of Applied Physics},
  year = {2025},
  doi = {10.1063/5.0293805},
}

Loading related content...

Figure