Analogue signal and image processing with large memristor crossbars

作者：Li, Can; Hu, Miao; Li, Yunning; Jiang, Hao; Ge, Ning; Montgomery, Eric; Zhang, Jiaming; Song, Wenhao; Davila, Noraica; Graves, Catherine E.; Li, Zhiyong; Strachan, John Paul^*; Lin, Peng; Wang, Zhongrui; Barnell, Mark; Wu, Qing; Williams, R. Stanley; Yang, J. Joshua^*; Xia, Qiangfei^*

来源：Nature Electronics, 2018, 1(1): 52-59.

DOI：10.1038/s41928-017-0002-z

• QUANTIZED CONDUCTANCE
• ARRAY
• ARCHITECTURE
• PERFORMANCE
• REDUCTION
• ELEMENTS
• ENGINE
• MEMORY
• POWER

Memristor crossbars offer reconfigurable non-volatile resistance states and could remove the speed and energy efficiency bottleneck in vector-matrix multiplication, a core computing task in signal and image processing. Using such systems to multiply an analogue-voltage-amplitude-vector by an analogue-conductance-matrix at a reasonably large scale has, however, proved challenging due to difficulties in device engineering and array integration. Here we show that reconfigurable memristor crossbars composed of hafnium oxide memristors on top of metal-oxide-semiconductor transistors are capable of analogue vector-matrix multiplication with array sizes of up to 128 x 64 cells. Our output precision (5-8 bits, depending on the array size) is the result of high device yield (99.8%) and the multilevel, stable states of the memristors, while the linear device current-voltage characteristics and low wire resistance between cells leads to high accuracy. With the large memristor crossbars, we demonstrate signal processing, image compression and convolutional filtering, which are expected to be important applications in the development of the Internet of Things (IoT) and edge computing.

• 出版日期2018-1