Search for: All records

The recent advance in the post-quantum cryptography (PQC) field has gradually shifted from the theory to the implementation of the cryptosystem, especially on the hardware platforms. Following this trend, in this paper, we aim to present efficient implementations of the finite field arithmetic (key component) for the binary Ring-Learning-with-Errors (Ring-LWE) PQC through a novel lookup-table (LUT)-like method. In total, we have carried out four stages of interdependent efforts: (i) an algorithm-hardware co-design driven derivation of the proposed LUT-like method is provided detailedly for the key arithmetic of the BRLWE scheme; (ii) the proposed hardware architecture is then presented along with the internal structural description; (iii) we have also presented a novel hybrid size structure suitable for flexible operation, which is the first report in the literature; (iv) the final implementation and comparison processes have also been given, demonstrating that our proposed structures deliver significant improved performance over the state-of-the-art solutions. The proposed designs are highly efficient and are expected to be employed in many emerging applications.

Hardware accelerators are essential to the accommodation of ever-increasing Deep Neural Network (DNN) workloads on the resource-constrained embedded devices. While accelerators facilitate fast and energy-efficient DNN operations, their accuracy is threatened by faults in their on-chip and off-chip memories, where millions of DNN weights are held. The use of emerging Non-Volatile Memories (NVM) further exposes DNN accelerators to a non-negligible rate of permanent defects due to immature fabrication, limited endurance, and aging. To tolerate defects in NVM-based DNN accelerators, previous work either requires extra redundancy in hardware or performs defect-aware retraining, imposing significant overhead. In comparison, this paper proposes a set of algorithms that exploit the flexibility in setting the fault-free bits in weight memory to effectively approximate weight values, so as to mitigate defect-induced accuracy drop. These algorithms can be applied as a one-step solution when loading the weights to embedded devices. They only require trivial hardware support and impose negligible run-time overhead. Experiments on popular DNN models show that the proposed techniques successfully boost inference accuracy even in the face of elevated defect rates in the weight memory.