A RISC-V Multicore and GPU SoC Platform with a Qualifiable Software Stack for Safety Critical Systems

TL;DR

The paper tackles enabling high-performance AI-enabled hardware in safety-critical space systems by presenting the METASAT prototype, a RISC-V multicore CPU with an integrated SPARROW AI accelerator and a Vortex GPU on a single FPGA platform. It details a qualifiable software stack (bare-metal, RTEMS, and XtratuM hypervisor) and the necessary toolchains, drivers, and constraints to support multiple partitions sharing hardware resources. Two space-focused AI use cases—cloud screening and ship detection—are ported via TensorFlow Lite Micro to run across CPU, SPARROW, and Vortex backends, with a GPU management scheme to ensure safe multi-partition access. Evaluation shows that while speed-ups are backend- and workload-dependent, the platform demonstrates feasible qualifiable execution and highlights trade-offs in GPU sharing and digital-twin simulation. The work advances the practical path toward high-performance, qualifiable space computers and provides a foundation for open-source deployment.

Abstract

In the context of the Horizon Europe project, METASAT, a hardware platform was developed as a prototype of future space systems. The platform is based on a multiprocessor NOEL-V, an established space-grade processor, which is integrated with the SPARROW AI accelerator and connected to a GPU, Vortex. Both processing systems follow the RISC-V specification. This is a novel hardware architecture for the space domain as the use of massive parallel processing units, such as GPUs, is starting to be considered for upcoming space missions due to the increased performance required to future space-related workloads, in particular, related to AI. However, such solutions are only currently adopted for New Space, since their limitations come not only from the hardware, but also from the software, which needs to be qualified before being deployed on an institutional mission. For this reason, the METASAT platform is one of the first endeavors towards enabling the use of high performance hardware in a qualifiable environment for safety critical systems. The software stack is based on baremetal, RTEMS and the XtratuM hypervisor, providing different options for applications of various degrees of criticality.

Figures (3)

• Figure 1: Example of cloud segmentation
• Figure 2: Example of ship detection
• Figure 3: Execution time of two XtratuM partitions with cloud screening and ship detection using SPARROW and the GPU and compared with each partition execution time in isolation