A Quality-assured Approximate Hardware Accelerators–based on Machine Learning and Dynamic Partial Reconfiguration

Machine learning is widely used these days to extract meaningful information out of the Zettabytes of sensors data collected daily. All applications require analyzing and understanding the data to identify trends, e.g., surveillance, exhibit some error tolerance. Approximate computing has emerged as an energy-efficient design paradigm aiming to take advantage of the intrinsic error resilience in a wide set of error-tolerant applications. Thus, inexact results could reduce power consumption, delay, area, and execution time. To increase the energy-efficiency of machine learning on FPGA, we consider approximation at the hardware level, e.g., approximate multipliers. However, errors in approximate computing heavily depend on the application, the applied inputs, and user preferences. However, dynamic partial reconfiguration has been introduced, as a key differentiating capability in recent FPGAs, to significantly reduce design area, power consumption, and reconfiguration time by adaptively changing a selective part of the FPGA design without interrupting the remaining system. Thus, integrating “Dynamic Partial Reconfiguration” (DPR) with “Approximate Computing” (AC) will significantly ameliorate the efficiency of FPGA-based design approximation. In this article, we propose hardware-efficient quality-controlled approximate accelerators, which are suitable to be implemented in FPGA-based machine learning algorithms as well as any error-resilient applications. Experimental results using three case studies of image blending, audio blending, and image filtering applications demonstrate that the proposed adaptive approximate accelerator satisfies the required quality with an accuracy of 81.82%, 80.4%, and 89.4%, respectively. On average, the partial bitstream was found to be 28.6 smaller than the full bitstream .

High-Performance Data Compression-Based Design for Dynamic IoT Security Systems

IoT technology is evolving at a quick pace and is becoming an important part of everyday life. Consequently, IoT systems hold large amounts of data related to the user of the system that is vulnerable to security breaches. Thus, data collected by IoT systems need to be secured efficiently without affecting the IoT systems’ performance and without compromising security as well. In this paper, a high-performance dynamic security system is introduced. The system makes use of the ZedBoard’s dynamic partial reconfiguration capability to shift between three distinct cipher algorithms: AEGIS, ASCON, and DEOXYS-II. The switching between the three algorithms is performed using two different techniques: the algorithm hopping technique or the power adaptive technique. The choice of which technique to be used is dependent on whether the system needs to be focused on performance or power saving. The ciphers used are the CAESAR competition finalists that achieved the greatest results in each of the three competition categories, where each cipher algorithm has its own set of significant characteristics. The proposed design seeks to reduce the FPGA reconfiguration time by the application of LZ4 (Lempel-Ziv4) compression and decompression techniques on the ciphers’ bitstream files. The reconfiguration time decreased by a minimum of 38% in comparison to the state-of-the-art design, while the resource utilization increased by approximately 2%.

A Dynamic Reconfigurable Architecture for Hybrid Spiking and Convolutional FPGA-Based Neural Network Designs

This work presents a dynamically reconfigurable architecture for Neural Network (NN) accelerators implemented in Field-Programmable Gate Array (FPGA) that can be applied in a variety of application scenarios. Although the concept of Dynamic Partial Reconfiguration (DPR) is increasingly used in NN accelerators, the throughput is usually lower than pure static designs. This work presents a dynamically reconfigurable energy-efficient accelerator architecture that does not sacrifice throughput performance. The proposed accelerator comprises reconfigurable processing engines and dynamically utilizes the device resources according to model parameters. Using the proposed architecture with DPR, different NN types and architectures can be realized on the same FPGA. Moreover, the proposed architecture maximizes throughput performance with design optimizations while considering the available resources on the hardware platform. We evaluate our design with different NN architectures for two different tasks. The first task is the image classification of two distinct datasets, and this requires switching between Convolutional Neural Network (CNN) architectures having different layer structures. The second task requires switching between NN architectures, namely a CNN architecture with high accuracy and throughput and a hybrid architecture that combines convolutional layers and an optimized Spiking Neural Network (SNN) architecture. We demonstrate throughput results from quickly reprogramming only a tiny part of the FPGA hardware using DPR. Experimental results show that the implemented designs achieve a 7× faster frame rate than current FPGA accelerators while being extremely flexible and using comparable resources.

Evolvable Hardware-Based Data Security System Using Image Steganography Through Dynamic Partial Reconfiguration

A highly secure communication method is essential for end users for the exchange of information which is not interpreted by an intruder. Cryptography plays a crucial role in the current and upcoming digital worlds, for secure data transmission in wired and wireless networks. Asymmetric and symmetric cryptographic algorithms encrypt data against vulnerable attacks and transfer to authenticated users. Steganography is a method for providing secure information with the help of a carrier file (text, video, audio, image, etc.). This paper proposes Deoxyribonucleic Acid (DNA)-based asymmetric algorithm which is used to encrypt the patient’s secret information and its performance is compared with ElGamal, RSA and Diffie–Hellman (DH) cryptographic algorithms. The proposed asymmetric algorithm is applied to image steganography which is used for encrypting and concealing the patient’s secret information in a cover image. The proposed method consumes less hardware resources with improved latency. Dynamic Partial Reconfiguration (DPR) allows to transform a selective area rather than complete shutdown of the entire system during bitstream configuration. Cryptosystem with DPR is designed, synthesized in Xilinx Vivado and simulated in Vivado simulator. The design is targeted at Basys3, Nexys4 DDR and Zync-7000 all-programmable SOC (AP SoC) architectures and programmed with secure partial bit files to avoid vulnerable attacks in the channel.

An FPGA-based network system with service-uninterrupted remote functional update

The recent emergence of 5G network enables mass wireless sensors deployment for internet-of-things (IoT) applications. In many cases, IoT sensors in monitoring and data collection applications are required to operate continuously and active at all time (24/7) to ensure all data are sampled without loss. Field-programmable gate array (FPGA)-based systems exhibit a balanced processing throughput and datapath flexibility. Specifically, datapath flexibility is acquired from the FPGA-based system architecture that supports dynamic partial reconfiguration feature. However, device functional update can cause interruption to the application servicing, especially in an FPGA-based system. This paper presents a standalone FPGA-based system architecture that allows remote functional update without causing service interruption by adopting a redundancy mechanism in the application datapath. By utilizing dynamic partial reconfiguration, only the updating datapath is temporarily inactive while the rest of the circuitry, including the redundant datapath, remain active. Hence, there is no service interruption and downtime when a remote functional update takes place due to the existence of redundant application datapath, which is critical for network and communication systems. The proposed architecture has a significant impact for application in FPGA-based systems that have little or no tolerance in service interruption.