skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


This content will become publicly available on June 1, 2026

Title: WinEdge: Low-Power Winograd CNN Execution with Transposed MRAM for Edge Devices
This paper presents a novel transposed MRAM architecture (WinEdge) specifically optimized for Winograd convolution acceleration in edge computing devices. Leveraging Magnetic Tunnel Junctions (MTJs) with Spin Hall Effect (SHE)-assisted Spin-Transfer Torque (STT) writing, the proposed design enables a single SHE current to simultaneously write data to four MTJs, substantially reducing power consumption. Additionally, the integration of stacked MTJs significantly improves storage density. The proposed WinEdge efficiently supports both standard and transposed data access modes regardless of bit-width, achieving up to 36% lower power, 47% reduced energy consumption, and 28% faster processing speed compared to existing designs. Simulations conducted in 45 nm CMOS technology validate its superiority over conventional SRAM-based solutions for convolutional neural network (CNN) acceleration in resource-constrained edge environments.  more » « less
Award ID(s):
2448133
PAR ID:
10634963
Author(s) / Creator(s):
; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Electronics
Volume:
14
Issue:
12
ISSN:
2079-9292
Page Range / eLocation ID:
2485
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. In this paper, we develop a 6-input fracturable non-volatile Clockless LUT (C-LUT) using spin Hall effect (SHE)-based Magnetic Tunnel Junctions (MTJs) and provide a detailed comparison between the SHE-MTJ-based C-LUT and Spin Transfer Torque (STT)-MTJ-based C-LUT. The proposed C-LUT offers an attractive alternative for implementing combinational logic as well as sequential logic versus previous spin-based LUT designs in the literature. Foremost, C-LUT eliminates the sense amplifier typically employed by using a differential polarity dual MTJ design, as opposed to a static reference resistance MTJ. This realizes a much wider read margin and the Monte Carlo simulation of the proposed fracturable C-LUT indicates no read and write errors in the presence of a variety of process variations scenarios involving MOS transistors as well as MTJs. Additionally, simulation results indicate that the proposed C-LUT reduces the standby power dissipation by $5.4$-fold compared to the SRAM-based LUT. Furthermore, the proposed SHE-MTJ-based C-LUT reduces the area by 1.3-fold and 2-fold compared to the SRAM-based LUT and the STT-MTJ-based C-LUT, respectively. 
    more » « less
  2. Abstract Spin-orbit torques (SOT) enable efficient electrical control of the magnetic state of ferromagnets, ferrimagnets and antiferromagnets. However, the conventional SOT has severe limitation that only in-plane spins accumulate near the surface, whether interpreted as a spin Hall effect (SHE) or as an Edelstein effect. Such a SOT is not suitable for controlling perpendicular magnetization, which would be more beneficial for realizing low-power-consumption memory devices. Here we report the observation of a giant magnetic-field-like SOT in a topological antiferromagnet Mn3Sn, whose direction and size can be tuned by changing the order parameter direction of the antiferromagnet. To understand the magnetic SHE (MSHE)- and the conventional SHE-induced SOTs on an equal footing, we formulate them as interface spin-electric-field responses and analyzed using a macroscopic symmetry analysis and a complementary microscopic quantum kinetic theory. In this framework, the large out-of-plane spin accumulation due to the MSHE has an inter-band origin and is likely to be caused by the large momentum-dependent spin splitting in Mn3Sn. Our work demonstrates the unique potential of antiferromagnetic Weyl semimetals in overcoming the limitations of conventional SOTs and in realizing low-power spintronics devices with new functionalities. 
    more » « less
  3. Abstract Magnetic random-access memory (MRAM) based on voltage-controlled magnetic anisotropy in magnetic tunnel junctions (MTJs) is a promising candidate for high-performance computing applications, due to its lower power consumption, higher bit density, and the ability to reduce the access transistor size when compared to conventional current-controlled spin-transfer torque MRAM. The key to realizing these advantages is to have a low MTJ switching voltage. Here, we report a perpendicular MTJ structure with a high voltage-controlled magnetic anisotropy coefficient ~130 fJ/Vm and high tunnel magnetoresistance exceeding 150%. Owing to the high voltage-controlled magnetic anisotropy coefficient, we demonstrate sub-nanosecond precessional switching of nanoscale MTJs with diameters of 50 and 70 nm, using a voltage lower than 1 V. We also show scaling of this switching mechanism down to 30 nm MTJs, with voltages close to 2 V. The results pave the path for the future development and application of voltage-controlled MRAMs and spintronic devices in emerging computing systems. 
    more » « less
  4. null (Ed.)
    With the deployment of artificial intelligent (AI) algorithms in a large variety of applications, there creates an increasing need for high-performance computing capabilities. As a result, different hardware platforms have been utilized for acceleration purposes. Among these hardware-based accelerators, the field-programmable gate arrays (FPGAs) have gained a lot of attention due to their re-programmable characteristics, which provide customized control logic and computing operators. For example, FPGAs have recently been adopted for on-demand cloud services by the leading cloud providers like Amazon and Microsoft, providing acceleration for various compute-intensive tasks. While the co-residency of multiple tenants on a cloud FPGA chip increases the efficiency of resource utilization, it also creates unique attack surfaces that are under-explored. In this paper, we exploit the vulnerability associated with the shared power distribution network on cloud FPGAs. We present a stealthy power attack that can be remotely launched by a malicious tenant, shutting down the entire chip and resulting in denial-of-service for other co-located benign tenants. Specifically, we propose stealthy-shutdown: a well-timed power attack that can be implemented in two steps: (1) an attacker monitors the realtime FPGA power-consumption detected by ring-oscillator-based voltage sensors, and (2) when capturing high power-consuming moments, i.e., the power consumption by other tenants is above a certain threshold, she/he injects a well-timed power load to shut down the FPGA system. Note that in the proposed attack strategy, the power load injected by the attacker only accounts for a small portion of the overall power consumption; therefore, such attack strategy remains stealthy to the cloud FPGA operator. We successfully implement and validate the proposed attack on three FPGA evaluation kits with running real-world applications. The proposed attack results in a stealthy-shutdown, demonstrating severe security concerns of co-tenancy on cloud FPGAs. We also offer two countermeasures that can mitigate such power attacks. 
    more » « less
  5. Abstract Magnetic tunnel junctions (MTJs) in the field of spintronics have received enormous attention owing to their fascinating spin phenomena for fundamental physics and potential applications. MTJs exhibit a large tunnel magnetoresistance (TMR) at room temperature. However, TMR depends strongly on the bias voltage, which reduces the magnitude of TMR. On the other hand, tunnel magnetocapacitance (TMC), which has also been observed in MTJs, can be increased when subjecting to a biasing voltage, thus exhibiting one of the most interesting spin phenomena. Here we report a large voltage-induced TMC beyond 330% in MgO-based MTJs, which is the largest value ever reported for MTJs. The voltage dependence and frequency characteristics of TMC can be explained by the newly proposed Debye-Fröhlich model using Zhang-sigmoid theory, parabolic barrier approximation, and spin-dependent drift diffusion model. Moreover, we predict that the voltage-induced TMC ratio could reach over 3000% in MTJs. It is a reality now that MTJs can be used as capacitors that are small in size, broadly ranged in frequencies and controllable by a voltage. Our theoretical and experimental findings provide a deeper understanding on the exact mechanism of voltage-induced AC spin transports in spintronic devices. Our research may open new avenues to the development of spintronics applications, such as highly sensitive magnetic sensors, high performance non-volatile memories, multi-functional spin logic devices, voltage controlled electronic components, and energy storage devices. 
    more » « less