MPAI: A Co-Processing Architecture with MPSoC & AI Accelerators for Vision Applications in Space

TL;DR

This paper presents MPAI, a heterogeneous co-processing architecture combining MPSoC and AI accelerators to enhance on-board spacecraft AI/ML deployment, optimizing for speed, power, and accuracy.

Contribution

The work introduces MPAI, a novel architecture integrating MPSoC with commercial AI accelerators for space applications, enabling flexible and efficient AI processing.

Findings

Preliminary experimental results demonstrate the architecture's effectiveness.

MPAI handles diverse neural network complexities efficiently.

The architecture offers favorable speed-accuracy-energy trade-offs.

Abstract

The emerging need for fast and power-efficient AI/ML deployment on-board spacecraft has forced the space industry to examine specialized accelerators, which have been successfully used in terrestrial applications. Towards this direction, the current work introduces a very heterogeneous co-processing architecture that is built around UltraScale+ MPSoC and its programmable DPU, as well as commercial AI/ML accelerators such as MyriadX VPU and Edge TPU. The proposed architecture, called MPAI, handles networks of different size/complexity and accommodates speed-accuracy-energy trade-offs by exploiting the diversity of accelerators in precision and computational power. This brief provides technical background and reports preliminary experimental results and outcomes.