Project deliverable Open Access
The aim of the AI-SPRINT project is to implement a design and runtime framework to accelerate the development of AI applications whose components are spread across the edge-cloud computing continuum.
AI-SPRINT tools will allow trading-off application performance (in terms of end-to-end latency or throughput), energy efficiency, and AI models accuracy while providing security and privacy guarantees.
This document, in particular, describes the first release and evaluation of the design tools of the AI-SPRINT platform, while the second release and evaluation are due at M24.
The first release includes programming abstractions that hide the communications across components and transparently implement the parallelization of the compute-intensive part of the application; quality annotations to enrich applications with constraints on performance and security; performance models to support AI components execution time prediction (both for inference and training tasks); AI Models Network Architecture Search providing solutions to enable developers with limited Machine Learning (ML) expertise to train high-quality models specific to their needs also in terms of Quality of Service (QoS) requirements;
Applications design space exploration tools to evaluate multiple alternative candidate deployments for complex applications involving many components.
The main results of this release include:
For each of the above-mentioned components, an evaluation section is also provided to discuss preliminary results on the adopted technologies and to evaluate the integration of the components according to the project’s milestones.
D2.1 - First release and evaluation of the AI-SPRINT design tools.pdf