Quantized AI Inference on Constrained Embedded Platforms for Small-Satellite Settings

In resource-constrained small-satellite settings, AI inference can operate under tight size, power, and payload budgets, which tend to limit onboard compute capability and data handling. These conditions motivate establishing a clear baseline for quantized AI inference under bounded compute and memory resources. To instantiate this baseline, a representative embedded-vision neural-network workload serves as the reference case.

With this motivation, this paper presents a measurement-based characterization of quantized execution for this AI workload on highly constrained embedded platforms (for instance, Cortex-M), grounded as a lower-bound operating point. In this regime, scaling tends to rely on explicit orchestration rather than OS-managed, transparent multicore scheduling, and timing behavior is shaped by instruction efficiency and memory movement. As a result, the characterization provides a structured reference for estimating execution time across orchestrated configurations (e.g., multiple cores and/or devices), treating orchestration and architectural variation as explicit design choices.

We report latency and timing-variability metrics alongside memory-traffic observations, and interpret these measurements in light of ALU/SIMD utilization under quantized arithmetic for the Cortex-M. Finally, we outline how this baseline provides a reference point for moving toward more space-typical embedded processor classes (e.g., LEON/NOEL-V) and heterogeneous configurations that incorporate embedded FPGA compute.