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.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Low-Power Adiabatic/MTJ LIM-Based XNOR/XOR Synapse and Neuron for Binarized Neural Networks
Using binarized neural network (BNN) as an alternative to the conventional convolutional neural network is a promising candidate to answer the demand of using human brain-inspired in applications with limited hardware and power resources, such as biomedical devices, IoT edge sensors, and other battery-operated devices. Using nonvolatile memory elements like MTJ devices in a LiM-based architecture can eliminate the need to access and use external memory which can significantly reduce the power consumption and area overhead. In addition, by using adiabatic-based designs, a significant part of the consumed power can be recovered to the power source which leads to a huge reduction in power consumption which is vital in applications with limited power and hardware resources. In this paper by using nonvolatile MTJ devices in a LiM architecture and using adiabatic-based circuits, an XNOR/XOR synapse and neuron is proposed. The proposed design offers 97% improvement in comparison with its state-of-the-art counterparts in case of power consumption. Also, it achieves at least 7% lower area compared to other counterparts which makes the proposed design a promising candidate for hardware implementation of BNNs.  more » « less
Award ID(s):
2232235
PAR ID:
10608251
Author(s) / Creator(s):
;
Publisher / Repository:
IEEE
Date Published:
ISBN:
979-8-3503-3346-6
Page Range / eLocation ID:
649 to 654
Format(s):
Medium: X
Location:
Jeju City, Korea, Republic of
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, IEEE)
    Energy efficiency and security against side-channel attacks (like power analysis attacks) in modern and battery-operated applications like IoT and medical applications are vital. On the other hand, FPGAs are widely used as a hardware platform for these applications. Accordingly, energy-efficient and power analysis attack-resilient design for FPGA is required. This paper proposes an energy-efficient power analysis attack-resilient adiabatic nonvolatile hybrid MTJ/CMOS LiM-based CLB. The simulation results show that the proposed design has 98.72%, 98.72%, 98.69%, 98.61 %, 98.43%, and 98.11 % (at least 84.69%, 84.74%, 84.28%, 83.19%, 80.70%, and 77%) lower energy consumption compared to its CMOS counterpart (adiabatic counterparts) for frequencies of 1, 2.5, 5, 10, 20, and 40 MHz, respectively. Also, the proposed design keeps its energy consumption superiority for different TMR and power supply voltages, compared to its counterparts. The NED and NSD values of different designs have been calculated and used as power analysis attack-resiliency metrics. The results show that the proposed design has 1053x and 1628x (at least 23x and 14x) lower NED and NSD values compared to its CMOS counterpart (adiabatic counterparts). Furthermore, the NED and NSD values of the proposed design stay in the same range (10−4) for different frequencies, power supply voltages, and TMR. 
    more » « less
  2. ; ; (, IEEE)
    High flexibility, infinite reconfigurability, and fast design-to-market of FPGAs make them a promising platform for modern applications, such as IoT, medical, and automotive applications. Energy and area limitations are challenging in these applications since many of these applications have limited power and hardware resources. Accordingly, the energy- and area-efficient design of FPGAs is of great importance. In this paper, an adiabatic non-volatile hybrid CMOS/MT J logic-in-memory-based configurable logic block (CLB) has been proposed and compared to its state-of-the-art counterparts. The simulation results show that the proposed design has 98%, 98%, 97%, 97%, 96%, and 92 % lower energy consumption compared to CMOS counterparts for frequencies of 1, 2.5, 5,10,20, and 40 MHz. Also, compared to its adiabatic counterparts, the proposed design has at least 74%, 70%, 69%, 69%, and 46% lower energy consumption for frequencies of 1, 2.5, 5, 10, and 20 MHz, respectively. Also, the proposed design has at least 74% fewer transistors compared to its counterparts. Furthermore, the energy saving of the proposed design for different tunnel magnetoresistance (TMR) is almost consistent. In addition, the proposed design keeps its superiority in energy saving over its counterparts for different power supply voltages. 
    more » « less
  3. ; ; ; ; ; (, SPIE Spintronics XII)
    Advances in machine intelligence have sparked interest in hardware accelerators to implement these algorithms, yet embedded electronics have stringent power, area budgets, and speed requirements that may limit nonvolatile memory (NVM) integration. In this context, the development of fast nanomagnetic neural networks using minimal training data is attractive. Here, we extend an inference-only proposal using the intrinsic physics of domain-wall MTJ (DW-MTJ) neurons for online learning to implement fully unsupervised pattern recognition operation, using winner-take-all networks that contain either random or plastic synapses (weights). Meanwhile, a read-out layer trains in a supervised fashion. We find our proposed design can approach state-of-the-art success on the task relative to competing memristive neural network proposals, while eliminating much of the area and energy overhead that would typically be required to build the neuronal layers with CMOS devices. 
    more » « less
  4. ; (, Sensors)
    Internet of Things (IoT) devices have strict energy constraints as they often operate on a battery supply. The cryptographic operations within IoT devices consume substantial energy and are vulnerable to a class of hardware attacks known as side-channel attacks. To reduce the energy consumption and defend against side-channel attacks, we propose combining adiabatic logic and Magnetic Tunnel Junctions to form our novel Energy Efficient-Adiabatic CMOS/MTJ Logic (EE-ACML). EE-ACML is shown to be both low energy and secure when compared to existing CMOS/MTJ architectures. EE-ACML reduces dynamic energy consumption with adiabatic logic, while MTJs reduce the leakage power of a circuit. To show practical functionality and energy savings, we designed one round of PRESENT-80 with the proposed EE-ACML integrated with an adiabatic clock generator. The proposed EE-ACML-based PRESENT-80 showed energy savings of 67.24% at 25 MHz and 86.5% at 100 MHz when compared with a previously proposed CMOS/MTJ circuit. Furthermore, we performed a CPA attack on our proposed design, and the key was kept secret. 
    more » « less
  5. ; ; ; ; (, IEEE/ACM International Conference on Computer-Aided Design (ICCAD ’24))
    Spiking neural networks (SNNs) are powerful models of spatiotemporal computation and are well suited for deployment on resource-constrained edge devices and neuromorphic hardware due to their low power consumption. Leveraging attention mechanisms similar to those found in their artificial neural network counterparts, recently emerged spiking transformers have showcased promising performance and efficiency by capitalizing on the binary nature of spiking operations. Recognizing the current lack of dedicated hardware support for spiking transformers, this paper presents the first work on 3D spiking transformer hardware architecture and design methodology. We present an architecture and physical design co-optimization approach tailored specifically for spiking transformers. Through memory-on-logic and logic-on-logic stacking enabled by 3D integration, we demonstrate significant energy and delay improvements compared to conventional 2D CMOS integration. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email