Projects

Marko Bertogna is leading the Research Unit of Modena for the FP7 project P-SOCRATES.

P-SOCRATES: Parallel Software Framework for Time-Critical Many-Core Systems  P-SOCRATES logo

P-SOCRATES is an European (STREP) project under the 7th Framework Program, in the Information and Communication Technologies objective “Advanced Computing Embedded and Control Systems”. The project started October 1st, 2013, and has a duration of 36 months.

P-SOCRATES will allow current and future applications with high-performance and real-time requirements to fully exploit the huge performance opportunities brought by the most advanced many-core processors, whilst ensuring a predictable performance and maintaining (or even reducing) development costs of applications. The purpose of P-SOCRATES is to develop an entirely new design framework, from the conceptual design of the system functionality to its physical implementation, to facilitate the deployment of standardized parallel architectures in all kinds of systems.

The main role in this project will be to develop real-time scheduling algorithms, along with the associated schedulability analysis, that will allow unleashing the tremendous capabilities of many-core platforms in a predictable way. 


Past projects:

7th Framework Program: ACTORS and PREDATOR.

ACTORS: Adaptivity and Control of Resources in Embedded Systems 

ACTORS addresses design of resource-constrained software-intensive embedded systems with high requirements on adaptivity and efficiency. Three techniques will be combined:

The main role in this project will be to analyze virtualization techniques such as reservation-based scheduling to provide spatial and temporal separation of concerns and enforce dependability and predictability. Reservations can be composed, are easier to develop and test, and provide security support.

We plan to extend the state-of-art in reservation-based algorithms for single and multiprocessor platforms, analyzing and comparing existing techniques to propose a homogenous framework that could be used as a reference point when selecting the most appropriate reservation mechanisms.

 

PREDATOR: Design for predictability and efficiency 

The project is concerned with embedded systems that are characterised by efficiency requirements on the one hand and critical constraints on the other. This combination of requirements typically occurs in application domains such as automotive, aeronautics, multi-media and industrial automation. The project aims at

My main contribution in this project will be the developement of efficient scheduling algorithms that are able to reduce the schedulability impact of unpredictable factors, like cache misses. A possibility to achieve this goal is using a scheduler with a small number of preemptions/migrations. In particular, we plan to investigate the limited-preemption EDF algorithm, an algorithm that is able to reduce the number of context changes without any schedulability penalty. Extensions to this approach are currently under evaluation, together with the application of similar techniques to static priority scheduling.