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.

A lot of research has been spent on improving the reliability and extending the lifetime of ASIC and SoC devices, but only little on improving the long-term reliability of dynamically reconfigurable systems. In order to increase the lifetime of a reconfigurable device, we propose a placement strategy to distribute the stress equally on the reconfigurable resources at runtime such that all have a similar level of degradation. Thereby, we present a new aging model which is applied to estimate the influence of aging effects on dynamically reconfigurable devices, and which can be evaluated at runtime, while providing quite accurate aging results. Furthermore, we present a new stress-aware placement algorithm that takes the degradation of the reconfigurable resources into account and can significantly extend the lifetime of reconfigurable devices.

Monolithic three-dimensional integrated circuits (M3D ICs) have emerged as an innovative solution to overcome the limitations of traditional 2D scaling, of

Exchanging FPGA-based implementations of cryptographic algorithms during run-time using netlist randomized versions has been introduced recently as a unique countermeasure against side channel attacks. Using partial reconfiguration, it is possible to shuffle between structurally different but functionally similar versions of a cryptographic implementation. The resulting varying power profile enhances the resistance against power-based side channel attacks. While side channel leakage is reduced, costs in terms of additional resources and/or lowered throughput are often increased due to the overheads of the required online partial reconfiguration. In this work, we provide an in-depth evaluation of the leakage-area-throughput trade-off.

The dependence of power-consumption on the processed data is a known vulnerability of CMOS circuits, resulting in side channels which can be exploited by power-based side channel attacks (SCAs). These attacks can extract sensitive information, such as secret keys, from the implementation of cryptographic algorithms. Existing countermeasures against power-based side channel attacks focus on analyzing information leakage at the byte level. However, this approach neglects the impact of individual bits on the overall resistance of a cryptographic implementation. In this work, we present a countermeasure based on single-bit leakage. The results suggest that the proposed countermeasure cannot be broken by attacks using conventional SCA leakage models.