Collaborative Research: Energy Efficient Voltage Controlled Non-volatile Domain Wall Devices for Neural Networks

合作研究:用于神经网络的节能压控非易失性畴壁器件

基本信息

  • 批准号:
    1954589
  • 负责人:
  • 金额:
    $ 22.5万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2020
  • 资助国家:
    美国
  • 起止时间:
    2020-05-01 至 2024-04-30
  • 项目状态:
    已结题

项目摘要

As Deep Neural Networks (DNNs) are increasingly deployed in low power embedded device and Internet of Things (IoT) applications. They need to be able to learn in real time while also being energy efficient. This necessitates the use of multi-state memory which is more than the conventional binary “0” and “1” states, is non-volatile such that information is retained when power is turned off, and can be programmed with very little energy. The goal of this project is to study and demonstrate synaptic elements of a neural network, which can store the weights updated during learning using voltage-controlled magnetic domain wall (DW) devices. Information is encoded as the position of a DW in a narrow magnetic wire. Specifically, the research will focus on using the strain generated by application of a small voltage to a thin piezoelectric layer and transferred to a magnetic wire deposited on it to control DW position in an extremely energy efficient manner. This research could lead to a dense, energy efficient and robust hardware paradigm for implementing DNNs. Two graduate students, one at Virginia Commonwealth University (VCU) and one at Massachusetts Institute of Technology (MIT), will gain multidisciplinary skills in advanced nanofabrication, nano-characterization and modeling. The VCU-PI and MIT- Co-PI will incorporate domain wall technology for memory and computing in the courses they teach. The PI and Co-PI plan to host research interns in their labs recruited from outreach programs for underrepresented groups in their respective universities. The students will be trained on nanofabrication of nanomagnets and other aspects of magnetic technology. The PI and Co-PI also plans to hold nanomagnetism workshops for high school students and teachers in their Universities collaboratively. This collaborative effort between VCU and MIT work will study and demonstrate the use of racetracks comprised of magnetostrictive metals such as CoFe, where DWs are moved using Spin Orbit Torque (SOT) from an adjoining Pt layer and arrested deterministically using voltage generated strain from a piezoelectric layer underneath that modulate perpendicular magnetic anisotropy (PMA) in different regions of a racetrack. The research team further plan to explore the use of magnetostrictive Rare Earth Iron Garnets (REIG) that have lower saturation magnetization and low damping, allowing for lower SOT applied for lesser time due to large DW velocities in order to improve the energy efficiency of DW devices. The proposed work will consist of complementary materials growth, characterization, nanofabrication, advanced magnetic visualization, modeling and simulation that includes: (i) Growth of metallic ferromagnetic and insulating ferrimagnets (ii) Study of SOT-driven DW velocity in magnetostrictive racetracks and proof-of-concept demonstration of arresting SOT-driven DW motion with a voltage induced strain (iii) Performing micromagnetic modeling of domain wall motion with SOT and its control with voltage-induced strain in the presence of notches, edge effects and room temperature thermal noise and evaluating the overall performance benefit of the proposed device in implementing DNNs. The research in this project will advance the knowledge of DW dynamics under local voltage- induced variations in anisotropy, in heterostructures that exhibit rich physics of SOT and the presence of chiral DWs. It will also provide a proof-of-concept demonstration of synaptic and neuron devices that could pave the way for energy-efficient hardware implementation of DNNs.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
由于深度神经网络(DNN)越来越多地部署在低功率嵌入式设备和物联网(IoT)应用程序中。他们需要能够实时学习,同时又可以节能。这需要使用多状态内存,而多状态内存比传统的二进制“ 0”和“ 1”状态更具挥发性,以便在关闭功率时保留信息,并且可以用很少的能量进行编程。该项目的目的是研究和证明神经元网络的突触元素,该网络可以使用电压控制的磁性域壁(DW)设备来存储在学习过程中更新的权重。信息被编码为DW在狭窄的磁线中的位置。具体而言,该研究将集中于使用将小电压应用于薄的压电层产生的应变,并将其转移到沉积在其上的磁线以以极高的节能方式控制DW位置。这项研究可能导致用于实施DNN的密集,节能和健壮的硬件范式。两名研究生,一名在弗吉尼亚联邦大学(VCU),马萨诸塞州理工学院(MIT)的一名研究生将获得高级纳米制作,纳米特征和建模的多学科技能。 VCU-PI和MIT-CO-PI将在其教学课程中融合用于记忆和计算的域墙技术。 PI和Co-Pi计划在其实验室中接待研究实习生,该实习生是从各自大学中代表性不足的群体的外展计划中招募的。这些学生将接受纳米磁体和磁技术其他方面的纳米化培训。 PI和Co-Pi还计划为大学中的高中生和老师协作举办纳米磁性研讨会。 This collaborative effort between VCU and MIT work will study and demonstrate the use of racetracks included of magnetic dimensional metals such as CoFe, where DWs are moved using Spin Orbit Torque (SOT) from an adjoining Pt layer and arrested deterministically using voltage generated strain from a piezoelectric layer underneath that modulate perpendicular magnetic anisotropy (PMA) in different regions of a racetrack.研究团队进一步计划探索磁性稀土石榴石(REIG)的使用,这些石榴石(REIG)具有较低的饱和度磁力化和低舞蹈,从而使SOT较低的SOT由于较大的DW速度而在较小的时间内施加,以提高DW设备的能源效率。拟议的工作将包括完整的材料增长,表征,纳米化,先进的磁性可视化,建模和模拟,其中包括:(i)金属铁磁性和绝缘铁磁铁(II)研究SOT驱动的DW速度在磁性磁磁赛车和范围内的限量性运动DW的DW速度研究,以进行II型DW的运动,以证明II的运动。在存在缺口,边缘效应和室温热噪声的情况下,具有SOT的域壁运动的微磁性建模及其控制,并评估所提出的设备在实现DNN方面的总体性能益处。该项目的研究将在局部电压诱导的各向异性变化下,在暴露于SOT丰富的物理学和手性DWS的存在下,提高DW动力学的知识。它还将提供概念概念的证明,以证明突触和神经退行版,可以为DNN的节能硬件实施铺平道路。该奖项反映了NSF的法定任务,并被认为是通过基金会的智力优点和更广泛的影响标准通过评估来获得的支持。

项目成果

期刊论文数量(5)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Secure Logic Locking with Strain-Protected Nanomagnet Logic
具有应变保护纳米磁体逻辑的安全逻辑锁定
  • DOI:
    10.1109/dac18074.2021.9586258
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Hassan, Naimul;Edwards, Alexander J.;Bhattacharya, Dhritiman;Shihab, Mustafa M.;Venkat, Varun;Zhou, Peng;Hu, Xuan;Kundu, Shamik;Kuruvila, Abraham P.;Basu, Kanad
  • 通讯作者:
    Basu, Kanad
Voltage modulated magnetic anisotropy of rare earth iron garnet thin films on a piezoelectric substrate
  • DOI:
    10.1063/5.0128842
  • 发表时间:
    2022-12-19
  • 期刊:
  • 影响因子:
    4
  • 作者:
    Gross,Miela J.;Misba,Walid A.;Ross,Caroline A.
  • 通讯作者:
    Ross,Caroline A.
Voltage-Controlled Energy-Efficient Domain Wall Synapses With Stochastic Distribution of Quantized Weights in the Presence of Thermal Noise and Edge Roughness
  • DOI:
    10.1109/ted.2021.3111846
  • 发表时间:
    2020-10
  • 期刊:
  • 影响因子:
    3.1
  • 作者:
    W. A. Misba;Tahmid Kaisar;Dhritiman Bhattacharya;J. Atulasimha
  • 通讯作者:
    W. A. Misba;Tahmid Kaisar;Dhritiman Bhattacharya;J. Atulasimha
Magnetic straintronics: Manipulating the magnetization of magnetostrictive nanomagnets with strain for energy-efficient applications
  • DOI:
    10.1063/5.0062993
  • 发表时间:
    2021-12-01
  • 期刊:
  • 影响因子:
    15
  • 作者:
    Bandyopadhyay,Supriyo;Atulasimha,Jayasimha;Barman,Anjan
  • 通讯作者:
    Barman,Anjan
Energy Efficient Learning With Low Resolution Stochastic Domain Wall Synapse for Deep Neural Networks
用于深度神经网络的低分辨率随机畴壁突触的节能学习
  • DOI:
    10.1109/access.2022.3196688
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    3.9
  • 作者:
    Misba, Walid Al;Lozano, Mark;Querlioz, Damien;Atulasimha, Jayasimha
  • 通讯作者:
    Atulasimha, Jayasimha
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Jayasimha Atulasimha其他文献

Jayasimha Atulasimha的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Jayasimha Atulasimha', 18)}}的其他基金

ExpandQISE: Track 1: Energy Efficient Quantum Control of Robust Spin Ensemble Qubits (EQ2)
ExpandQISE:轨道 1:鲁棒自旋系综量子位的节能量子控制 (EQ2)
  • 批准号:
    2231356
  • 财政年份:
    2022
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
ECCS-EPSRC: Collaborative Research: Acoustically induced Ferromagnetic Resonance (FMR) assisted Energy Efficient Spin Torque memory devices
ECCS-EPSRC:合作研究:声感应铁磁谐振 (FMR) 辅助节能自旋转矩存储器件
  • 批准号:
    2152601
  • 财政年份:
    2022
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
MRI: Acquisition of a Magneto Optic Kerr Effect (MOKE) Microscope for Research and Teaching
MRI:购买磁光克尔效应 (MOKE) 显微镜用于研究和教学
  • 批准号:
    2117646
  • 财政年份:
    2021
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
SHF: Small: Collaborative Research: Skyrmion Mediated Eenergy-efficient VCMA Switching of 2-Terminal p-MTJ Memory
SHF:小型:合作研究:Skyrmion 介导的 2 端 p-MTJ 存储器的节能 VCMA 切换
  • 批准号:
    1909030
  • 财政年份:
    2019
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
SHF: Small: Collaborative Research: Energy Efficient Strain Assisted Spin Transfer Torque Memory
SHF:小型:合作研究:节能应变辅助自旋转移扭矩存储器
  • 批准号:
    1815033
  • 财政年份:
    2018
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
CAREER: Reliable and Fault Tolerant Super Energy Efficient Nanomagnetic Computing in the Presence of Thermal Noise
职业:存在热噪声时可靠且容错的超能效纳米磁计算
  • 批准号:
    1253370
  • 财政年份:
    2013
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Continuing Grant
Ultra-Low Power and Ultra-Sensitive Spintronic Nanowire Strain Sensor
超低功耗、超灵敏自旋电子纳米线应变传感器
  • 批准号:
    1301013
  • 财政年份:
    2013
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
SHF: Small: Pipelined and wireless ultra-low power straintronics: An acoustically clocked combinational and sequential nanomagnetic architecture
SHF:小型:管道式和无线超低功耗应变电子学:声学时钟组合和顺序纳米磁性架构
  • 批准号:
    1216614
  • 财政年份:
    2012
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant

相似国自然基金

miPEP398-miR398诱导亚低温条件下番茄种子活力的机制研究
  • 批准号:
    32372677
  • 批准年份:
    2023
  • 资助金额:
    50 万元
  • 项目类别:
    面上项目
生物钟核受体Rev-erbα在缺血性卒中神经元能量代谢中的改善作用及机制研究
  • 批准号:
    82371332
  • 批准年份:
    2023
  • 资助金额:
    49.00 万元
  • 项目类别:
    面上项目
脐带间充质干细胞微囊联合低能量冲击波治疗神经损伤性ED的机制研究
  • 批准号:
    82371631
  • 批准年份:
    2023
  • 资助金额:
    49.00 万元
  • 项目类别:
    面上项目
协同多精度活力测度的高密度城区公园供需评价与调控研究
  • 批准号:
    52308066
  • 批准年份:
    2023
  • 资助金额:
    30.00 万元
  • 项目类别:
    青年科学基金项目
山地社区公共空间驻留活力的时空分布特征与影响机制研究
  • 批准号:
    52308007
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

Collaborative Research: Material Simulation-driven Electrolyte Designs in Intermediate-temperature Na-K / S Batteries for Long-duration Energy Storage
合作研究:用于长期储能的中温Na-K / S电池中材料模拟驱动的电解质设计
  • 批准号:
    2341994
  • 财政年份:
    2024
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
Collaborative Research: Environmentally Sustainable Anode Materials for Electrochemical Energy Storage using Particulate Matter Waste from the Combustion of Fossil Fuels
合作研究:利用化石燃料燃烧产生的颗粒物废物进行电化学储能的环境可持续阳极材料
  • 批准号:
    2344722
  • 财政年份:
    2024
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
Collaborative Research: EAGER: Energy for persistent sensing of carbon dioxide under near shore waves.
合作研究:EAGER:近岸波浪下持续感知二氧化碳的能量。
  • 批准号:
    2339062
  • 财政年份:
    2024
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
Collaborative Research: Reversible Computing and Reservoir Computing with Magnetic Skyrmions for Energy-Efficient Boolean Logic and Artificial Intelligence Hardware
合作研究:用于节能布尔逻辑和人工智能硬件的磁斯格明子可逆计算和储层计算
  • 批准号:
    2343606
  • 财政年份:
    2024
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
Collaborative Research: Environmentally Sustainable Anode Materials for Electrochemical Energy Storage using Particulate Matter Waste from the Combustion of Fossil Fuels
合作研究:利用化石燃料燃烧产生的颗粒物废物进行电化学储能的环境可持续阳极材料
  • 批准号:
    2344723
  • 财政年份:
    2024
  • 资助金额:
    $ 22.5万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了