skip to main content

This content will become publicly available on December 1, 2023

Title: Hardware implementation of Bayesian network based on two-dimensional memtransistors
Abstract Bayesian networks (BNs) find widespread application in many real-world probabilistic problems including diagnostics, forecasting, computer vision, etc. The basic computing primitive for BNs is a stochastic bit (s-bit) generator that can control the probability of obtaining ‘1’ in a binary bit-stream. While silicon-based complementary metal-oxide-semiconductor (CMOS) technology can be used for hardware implementation of BNs, the lack of inherent stochasticity makes it area and energy inefficient. On the other hand, memristors and spintronic devices offer inherent stochasticity but lack computing ability beyond simple vector matrix multiplication due to their two-terminal nature and rely on extensive CMOS peripherals for BN implementation, which limits area and energy efficiency. Here, we circumvent these challenges by introducing a hardware platform based on 2D memtransistors. First, we experimentally demonstrate a low-power and compact s-bit generator circuit that exploits cycle-to-cycle fluctuation in the post-programmed conductance state of 2D memtransistors. Next, the s-bit generators are monolithically integrated with 2D memtransistor-based logic gates to implement BNs. Our findings highlight the potential for 2D memtransistor-based integrated circuits for non-von Neumann computing applications.
; ; ; ; ;
Award ID(s):
2042154 2039351
Publication Date:
Journal Name:
Nature Communications
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract Artificial neural networks have demonstrated superiority over traditional computing architectures in tasks such as pattern classification and learning. However, they do not measure uncertainty in predictions, and hence they can make wrong predictions with high confidence, which can be detrimental for many mission-critical applications. In contrast, Bayesian neural networks (BNNs) naturally include such uncertainty in their model, as the weights are represented by probability distributions (e.g. Gaussian distribution). Here we introduce three-terminal memtransistors based on two-dimensional (2D) materials, which can emulate both probabilistic synapses as well as reconfigurable neurons. The cycle-to-cycle variation in the programming of the 2D memtransistor is exploited to achieve Gaussian random number generator-based synapses, whereas 2D memtransistor based integrated circuits are used to obtain neurons with hyperbolic tangent and sigmoid activation functions. Finally, memtransistor-based synapses and neurons are combined in a crossbar array architecture to realize a BNN accelerator for a data classification task.
  2. Hardware Trojans (HTs) have emerged as a major security threat for integrated circuits (ICs) owing to the involvement of untrustworthy actors in the globally distributed semiconductor supply chain. HTs are intentional malicious modifications, which remain undetectable through simple electrical measurements but can cause catastrophic failure in the functioning of ICs in mission critical applications. In this article, we show how two-dimensional (2D) material based in-memory computing elements such as memtransistors can be used as hardware Trojans. We found that logic gates based on 2D memtransistors can be made to malfunction by exploiting their inherent programming capabilities. While we use 2D memtransistor-based ICs as the testbed for our demonstration, the results are equally applicable to any state-of-the-art and emerging in-memory computing technologies.
  3. A low-energy hardware implementation of deep belief network (DBN) architecture is developed using near-zero energy barrier probabilistic spin logic devices (p-bits), which are modeled to real- ize an intrinsic sigmoidal activation function. A CMOS/spin based weighted array structure is designed to implement a restricted Boltzmann machine (RBM). Device-level simulations based on precise physics relations are used to validate the sigmoidal relation between the output probability of a p-bit and its input currents. Characteristics of the resistive networks and p-bits are modeled in SPICE to perform a circuit-level simulation investigating the performance, area, and power consumption tradeoffs of the weighted array. In the application-level simulation, a DBN is implemented in MATLAB for digit recognition using the extracted device and circuit behavioral models. The MNIST data set is used to assess the accuracy of the DBN using 5,000 training images for five distinct network topologies. The results indicate that a baseline error rate of 36.8% for a 784x10 DBN trained by 100 samples can be reduced to only 3.7% using a 784x800x800x10 DBN trained by 5,000 input samples. Finally, Power dissipation and accuracy tradeoffs for probabilistic computing mechanisms using resistive devices are identified.
  4. In this paper, we propose MRIMA, as a novel MRAM-based In-Memory Accelerator for non-volatile, flexible, and efficient in-memory computing. MRIMA transforms current Spin Transfer Torque Magnetic Random Access Memory (STT-MRAM) arrays to massively parallel computational units capable of working as both non-volatile memory and in-memory logic. Instead of integrating complex logic units in cost-sensitive memory, MRIMA exploits hardware-friendly bit-line computing methods to implement complete Boolean logic functions between operands within a memory array in a single clock cycle, overcoming the multi-cycle logic issue in contemporary Processing-In-Memory (PIM) platforms. We present practical case studies to demonstrate MRIMA’s acceleration for binary-weight and low bit-width Convolutional Neural Networks (CNN) as well as data encryption. Our device-to-architecture co-simulation results on CNN acceleration demonstrate that MRIMA can obtain 1.7× better energy-efficiency and 11.2× speed-up compared to ASICs, and, 1.8× better energy-efficiency and 2.4× speed-up over the best DRAM-based PIM solutions. As an AES in-memory encryption engine, MRIMA shows 77% and 21% lower energy consumption compared to CMOS-ASIC and recent domain wall-based design, respectively.
  5. Battery-free and intermittently powered devices offer long lifetimes and enable deployment in new applications and environments. Unfortunately, developing sophisticated inference-capable applications is still challenging due to the lack of platform support for more advanced (32-bit) microprocessors and specialized accelerators---which can execute data-intensive machine learning tasks, but add complexity across the stack when dealing with intermittent power. We present Protean to bridge the platform gap for inference-capable battery-free sensors. Designed for runtime scalability, meeting the dynamic range of energy harvesters with matching heterogeneous processing elements like neural network accelerators. We develop a modular "plug-and-play" hardware platform, SuperSensor, with a reconfigurable energy storage circuit that powers a 32-bit ARM-based microcontroller with a convolutional neural network accelerator. An adaptive task-based runtime system, Chameleon, provides intermittency-proof execution of machine learning tasks across heterogeneous processing elements. The runtime automatically scales and dispatches these tasks based on incoming energy, current state, and programmer annotations. A code generator, Metamorph, automates conversion of ML models to intermittent safe execution across heterogeneous compute elements. We evaluate Protean with audio and image workloads and demonstrate up to 666x improvement in inference energy efficiency by enabling usage of modern computational elements within intermittent computing. Further, Protean provides up to 166% highermore »throughput compared to non-adaptive baselines.« less