An ADC-Less RRAM-Based Computing-in-Memory Macro With Binary CNN for Efficient Edge AI

Authors:
Publisher website
Google Scholar
Abstract
Resistive random-access memory (RRAM) based non-volatile computing-in-memory (nvCIM) has been regarded as a promising solution to enable efficient data-intensive artificial intelligence (AI) applications on resource-limited edge systems. However, existing weighted-current summation-based nvCIM suffers from device non-idealities and significant time, storage, and energy overheads when processing high-precision analog signals. To address these issues, we propose a 3T2R digital nvCIM macro for a fully hardware-implemented binary convolutional neural network (HBCNN), focusing on accelerating edge AI applications at low weight precision. By quantizing the voltage-division results of RRAMs through inverters, the 3T2R macro provides a stable rail-to-rail output without analog-to-digital converters or sensing amplifiers. Moreover, both batch normalization and sign activation are integrated on-chip. The hybrid simulation results show that the proposed 3T2R digital macro achieves an 86.2% (95.6%) accuracy on the CIFAR-10 (MNIST) dataset, corresponding to a 4.7% (1.9%) accuracy loss compared to the software baselines, which also feature a peak energy efficiency of 51.3 TOPS/W and a minimum latency of 8 ns, realizing an energy-efficient, low-latency, and robust AI processor.
Funding Information
  • National Key Research and Development Program and NSFC of China (2018YFA0701500)
  • National Natural Science Foundation of China (61874138, 61888102, 61834009, 62025406, 62122004)
  • Strategic Priority Research Program of the Chinese Academy of Sciences (XDB44000000)
  • Major Scientific Research Project of Zhejiang Lab (2019KC0AD02)
  • Hong Kong RGC (27206321, 17205922)
  • ACCESS—AI Chip Center for Emerging Smart Systems, sponsored by Innovation and Technology Fund (ITF), Hong Kong, SAR

This publication has 12 references indexed in Scilit: