Recently there is an increasing interest in the use of artificial intelligence for on-board processing as indicated by the latest space missions, which cannot be satisfied by existing low-performance space-qualified processors. Although COTS AI accelerators can provide the required performance, they are not designed to meet space requirements. In this work, we co-design a low-cost SIMD micro-architecture integrated in a space qualified processor, which can significantly increase its performance. Our solution has no impact on the processor's 100 MHz frequency and consumes minimal area thanks to its innovative design compared to conventional vector micro-architectures. For the minimum configuration of our baseline space processor, our results indicate a performance boost of up to 9.3× for commonly used AI-related and image processing algorithms and 5.5× faster for a complex, space-relevant inference application with just 30% area increase.

This work was supported by ESA through the GPU4S (GPU for Space) project, the Spanish Ministry of Economy and Competitiveness under grants PID2019- 107255GB and FJCI-2017-34095 (Spanish State Research Agency / http://dx.doi.org/10.13039/501100011033), the European Commission’s Horizon 2020 programme under the UP2DATE project (grant agreement 871465), the HiPEAC Network of Excellence and a first prize in Xilinx’s University Open Hardware Competition 2021 in the student category.

Peer Reviewed