.png){kind=icon}
返回
HZO-based FerroNEMS MAC for in-memory computing
.png){kind=icon}
OA
AI
DOI：10.1063/5.0120629.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper demonstrates a hafnium zirconium oxide (HZO)-based ferroelectric NEMS unimorph as the fundamental building block for very low-energy capacitive readout in-memory computing. The reported device consists of a 250 x 30 mu m(2) unimorph cantilever with 20-nm-thick ferroelectric HZO on 1 mu m SiO2. Partial ferroelectric switching in HZO achieves analog programmable control of the piezoelectric coefficient (d(31)), which serves as the computational weight for multiply accumulate (MAC) operations. The displacement of the piezoelectric unimorph was recorded by actuating the device with different input voltages V-in. The resulting displacement was measured as a function of the ferroelectric programming/poling voltage V P. The slopes of central beam displacement (delta(max)) vs V-in were measured to be between 182.9 nm/V (for -8 V-p) and -90.5 nm/V (for 8 V-p), which corresponds to displacement proportionality constant beta of 68 nm/V-2 for +ve V-p and 47 nm/V-2 for -ve V-p, demonstrating linear behavior of the multiplier unit. The resultant delta(max) from AC actuation is in the range of -18 to 36 nm and is a scaled product of V-in and programmed d(31) (governed by the V-p). The multiplication function serves as the fundamental unit for MAC operations with the ferroelectric NEMS unimorph. The displacement from many such beams can be added by summing the capacitance changes, providing a pathway to implement a multi-input and multi-weight neuron. A scaling and fabrication analysis suggests that this device can be CMOS compatible, achieving high in-memory computational throughput. Published under an exclusive license by AIP Publishing.
期刊
IF:
3.6
论文数:
10.4W
被引数:
17.8W
机构
引用论文
Ferroelectric Polarization Switching of Hafnium Zirconium Oxide in a Ferroelectric/Dielectric Stack铁电/电介质叠层中氧化铪锆的铁电极化转换
OAAI
OAAI分享收藏Evolution of phases and ferroelectric properties of thin Hf0.5Zr0.5O2 films according to the thickness and annealing temperature根据厚度和退火温度，Hf0.5Zr0.5O2薄膜的相演变和铁电性能
PREAI
分享收藏Spin-Orbit Torques in Heavy-Metal–Ferromagnet Bilayers with Varying Strengths of Interfacial Spin-Orbit Coupling具有不同强度的界面自旋轨道耦合的重金属铁磁体双层中的自旋轨道扭矩OAAI
OAAI分享收藏分享收藏The Next Generation of Deep Learning Hardware: Analog Computing下一代深度学习硬件: 模拟计算.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Memory devices and applications for in-memory computing用于内存计算的内存设备和应用NATURE NANOTECHNOLOGYOAAI
NATURE NANOTECHNOLOGYIF34.9
OAAI分享收藏
查看更多内容