EXTRACT project coordinator, Dr Eduardo Quiñones was invited to give a keynote speech at the Adaptive Machine Learning at the Network Edge (AMLE) Summer School in Lorient, France. His presentation on the 20th of September 2023, entitled, “Task-based Parallel Programming Models: The Convergence of High-Performance and Edge Computing Domains” was eagerly received by the PhDs and early-career researchers attending this summer school.
The AMLE summer school covered key concepts and methods in design and implementation of edge processing systems for AI applications. It involved lectures and hands-on laboratory sessions on topics that include parallel programming for embedded multiprocessor systems-on-chip (MPSoCs); technology, architecture and organization of memories used at the edge; hardware accelerators for edge processing; real-time scheduling analysis; hardware-friendly reinforcement learning; and Markov decision processes for power/performance optimization. The summer school concluded with a two-day hackathon organized by the EU-funded Rising Stars project.
The summer school focused on the migration of AI applications toward the network edge and the potential advantages offered by edge processing. Among these, are the potential to reduce delays associated with network communication, enhance privacy, and improve reliability and predictability in scenarios where network performance exhibits significant variation.
The keynote delivered by Dr Quiñones emphasized:
- The need for parallel programming models: OpenMP
- Modelling a real-time system with OpenMP
- Main Factors Impacting Parallel Execution
- Runtime optimization for real-time systems