Flash-based content addressable memory with L2 distance for memory-augmented neural network

Haozhang Yang; Peng Huang; Ruiyi Li; Nan Tang; Yizhou Zhang; Zheng Zhou; Lifeng Liu; Xiaoyan Liu; Jinfeng Kang

doi:10.1016/j.isci.2023.108371

Flash-based content addressable memory with L2 distance for memory-augmented neural network

iScience. 2023 Oct 31;26(12):108371. doi: 10.1016/j.isci.2023.108371. eCollection 2023 Dec 15.

Authors

Haozhang Yang^{1

2}, Peng Huang^{1

2}, Ruiyi Li^{1

2}, Nan Tang^{1

2}, Yizhou Zhang^{1

2}, Zheng Zhou^{1

2}, Lifeng Liu^{1

2}, Xiaoyan Liu^{1

2}, Jinfeng Kang^{1

2}

Affiliations

¹ School of Integrated Circuits, Peking University, Beijing 100871, China.
² Beijing Advanced Innovation Center for Integrated Circuits, Beijing 100871, China.

Abstract

Memory-augmented neural network (MANN) has received increasing attention as a promising approach to achieve lifelong on-device learning, of which implementation of the explicit memory is vital. Content addressable memory (CAM) has been designed to accelerate the explicit memory by harnessing the in-memory-computing capability. In this work, a CAM cell with quadratic code is proposed, and a 1Mb Flash-based multi-bit CAM chip capable of computing Euclidean (L2) distance is fabricated. Compared with ternary CAM, the latency and energy are significantly reduced by 5.3- and 46.6-fold, respectively, for the MANN on Omniglot dataset. Besides, the recognition accuracy has slight degradation (<1%) even after baking for 10⁵ s at 200°C, demonstrating the robustness to environmental disturbance. Performance evaluation indicates a reduction of 471-fold in latency and 1267-fold in energy compared with GPU for search operation. The proposed robust and energy-efficient CAM provides a promising solution to implement lifelong on-device machine intelligence.

Keywords: Computer architecture; Computer hardware; Computer science; Neuroscience.