This paper provides an overview of the ongoing work to enable novel modalities of passive monocular neuromorphic vision in the NimbleAI sensing-processing architecture; namely, foveated and light-field event-driven vision with selective visual attention. The latter vision modality encodes 3D visual surroundings as sparse visual events in a 4D spatiotemporal domain, adding depth to current representation of visual information delivered by Dynamic Vision Sensors (DVS). The NimbleAI architecture implements hardware support for efficient execution of mainstream computer vision algorithms and AI models using these visual inputs. The architecture is designed to harness the latest advancements in 3D silicon integration, making it possible to squeeze sensing and spiking circuitry, memory, and processing engines into a miniature silicon volume.

In today’s digital landscape, cryptography plays a vital role in ensuring communication security through encryption and authentication algorithms. While traditional cryptographic methods rely on hard mathematical problems for security, the rise of quantum computing threatens their effectiveness. Post-Quantum Cryptography (PQC) algorithms, like CRYSTALSKyber, aim to withstand quantum attacks. Recently standardized, CRYSTALS-Kyber is a lattice-based algorithm designed to resist quantum attacks. However, its implementation faces computational challenges, particularly with Keccak-based functions, which are crucial for security and upon which the FIPS 202 standard is based. Our paper addresses this technological challenge by designing a FIPS 202 hardware accelerator to enhance CRYSTALS-Kyber efficiency and security. We chose to implement the entire FIPS 202 standard in hardware in order to widen the applicability of the accelerator to all possible algorithms that rely on such hash functions, taking care to provide realistic assumptions on system-level integration inside a System-on-Chip (SoC). We provide results in terms of area, frequency, and clock cycles for both ASIC and FPGA targets. An area reduction of up to $22.3 \%$ is achieved with respect to state-ofthe-art solutions. In addition, we integrated the accelerator inside a 32-bit RISC-V based security-oriented SoC, where we show a strong performance gain on CRYSTALS-Kyber execution. The design presented in this paper performs better in all Kyber1024 primitives, with an improvement up to $3.21 \times$ in Kyber-KeyGen.

A key concern in the field of scientific computation is the convergence of numerical solvers when applied to large problems. The numerical workarounds used to improve convergence are often problem specific, time consuming and require skilled numerical analysts. An alternative is to simply increase the working precision of the computation, but this is difficult due to the lack of efficient hardware support for extended precision. We proposeXvpfloat, a RISC-V ISA extension for dynamically variable and extended precision computation, a hardware implementation and a full software stack. Our architecture provides a comprehensive implementation of this ISA, with up to 512 bits of significand, including full support for common rounding modes and heterogeneous precision arithmetic operations. The memory subsystem handles IEEE 754 extendable formats, and features specialized indexed loads and stores with hardware-assisted prefetching. This processor can either operate standalone or as an accelerator for a general purpose host. We demonstrate that the number of solver iterations can be reduced up to 5× and, for certain, difficult problems, convergence is only possible with very high precision (≥384 bits). This accelerator provides a new approach to accelerate large scale scientific computing.

Linear algebra kernels such as linear solvers, eigen-solvers are the actual working engine underneath many scientific applications. The growing scale of these applications has led researchers to rely on high-precision computing for improving their efficiency and their stability. In this work, we investigate the impact of arbitrary extended precision on multiple variants of the Conjugate Gradient method (CG). We show how our VRP processor improves the convergence and the efficiency of these kernels. We also illustrate how our set of tools (library, software environment) enables to migrate legacy applications in a fast and intuitive way while preserving high-performance. We observe up to an 8X improvements on kernel iteration count, and up to a 40 % improvement on latency. Nevertheless, the main benefit is the stability gained with the precision. It makes it possible to resolve larger and ill-conditioned systems without costly compensating techniques.