Onnx-to-hardware design flow for adaptive neural-network inference on fpgas

F Manca, F Ratto, F Palumbo - International Conference on Embedded …, 2024 - Springer
The challenges involved in executin Neural Networks (NNs) at the edge include providing
diversity, flexibility, and sustainability. That implies, for instance, supporting evolving …

Edge-to-Cloud Continuum Orchestrator for Distributed Video Applications

P Ruiu, C Rubattu, M Anedda, A Lagorio… - 2024 IEEE …, 2024 - ieeexplore.ieee.org
The current paper presents the implementation of an orchestrator for distributed edge-to-
cloud systems based on heterogeneous nodes in urban environments. The orchestrator …

[PDF][PDF] Leveraging the MLIR infrastructure for the computing continuum

J Bi, G Korol, J Castrillon - 2024 - cfaed.tu-dresden.de
With an ever-increasing number of connected devices (eg, IoT), cloud computing faces
efficiency challenges due to complex infrastructure, high communication costs, and privacy …

Timing enclaves for performance in Lingua Franca

J Robledo, C Menard, E Jellum, EA Lee… - 2024 Forum on …, 2024 - ieeexplore.ieee.org
The reactor model is a model of computation for concurrent systems that includes semantics
for time to guarantee deterministic execution of events. However, the guarantee of …