A 2-Transistor-2-Capacitor Ferroelectric Edge Compute-in-Memory Scheme With Disturb-Free Inference and High Endurance
Xiaoyang Ma, Shan Deng, Juejian Wu, Zijian Zhao, David Lehninger, Tarek Ali, Konrad Seidel, Sourav De, Xiyu He, Yiming Chen, Huazhong Yang, Vijaykrishnan Narayanan, Suman Datta, Thomas Kämpfe, Qing Luo, Kai Ni, Xueqing Li
Abstract
This letter proposes C <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> FeRAM, a 2T2C/cell ferroelectric compute-in-memory (CiM) scheme for energy-efficient and high-reliability edge inference and transfer learning. With certain area overhead, C <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> FeRAM achieves the following highlights: (i) compared with FeFET/FeMFET, it achieves disturb-free CiM and much higher write endurance (equal to FeRAM), leading to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$100\times $ </tex-math></inline-formula> inference time with < 1% accuracy drop for VGG8 in CIFAR-10 dataset, along with the enhanced endurance for weight updates, e.g., CiM-based transfer learning; (ii) compared with 1T1C FeRAM inference cache, the achieved disturb-free feature and CiM capability in C <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> FeRAM lead to improvements of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4\times $ </tex-math></inline-formula> energy, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$200\times $ </tex-math></inline-formula> speed, and 3.2e <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5\times $ </tex-math></inline-formula> life cycles. Such benefits highlight an intriguing solution for future intelligent edge AI.