MSc (by research) involving RTEMS | University of York

Hesham Moustafa heshamelmatary at gmail.com
Mon Oct 27 20:48:55 UTC 2014


Hi Cláudio,

On Mon, Oct 27, 2014 at 4:04 PM, Cláudio Silva <claudiodcsilva at gmail.com>
wrote:

> Hi Hesham,
>
> There are several commercially available MPSoCs:
>   - MPPA from Kalray
>   - TILE 64 from Tilera and it's Radiation Tolerant version Maestro
>   - Xentium from Recore Systems
> but you need to investigate their OS support. Most of them should
> support some form of Linux SMP. Xentium supports RTEMS, but solely in
> the Leon core used to drive the system. These were used in several
> projects, so a simple google search should yield some interesting
> results.
>
> In terms of research, there are several EC funded projects that
> research time-predictability and MPSoCs/CMPs. I will leave links to a
> few of them as they might be of interest to your research:
>
> - T-CREST Time-Predictable Multi-Core Architecture for Embedded
> Systems: http://www.t-crest.org/
> - P-SOCRATES (Parallel Software Framework for Time-Critical Many-core
> Systems): http://www.p-socrates.eu/
> - PREDATOR: http://www.predator-project.eu/
> - MERASA (Multi-Core Execution of Hard Real-Time Applications
> Supporting Analysability):
> http://ginkgo.informatik.uni-augsburg.de/merasa-web/
> -parMERASA (Multi-Core Execution of Parallelised Hard Real-Time
> Applications Supporting Analysability):
> - CompSOC: http://compsoc.eu/
>
> Although none of them focuses on the operating system itself, some
> include operating system ports and reason about the issues found in
> these kinds of systems.
> The T-CREST project includes a fully open source MPSoC
> (https://github.com/t-crest/) that can be instantiated in a Xilinx
> platform. In addition, RTEMS is ported to the T-CREST MPSoC
> (https://github.com/t-crest/rtems) but solely in "pure" AMP
> configurations (fully decoupled and independent RTEMS instances
> running in each core). Nevertheless, I think adding support for RTEMS'
> multiprocessor extensions should be fairly easy.
>
> On the other hand, P-SOCRATES' objective is to develop a software
> stack aimed at bridging the gap between the application design and an
> hardware many-core platform. I guess this includes scheduling and
> operating system mappings, so it should be more aligned with your
> research.
>
> Great projects out there, I will have to see if I can use any of these
projects, one or more of them maybe better than what my supervisor has
suggested. Thanks!

> Best Regards,
> Cláudio
>

Regards,
Hesham

>
> On Mon, Oct 27, 2014 at 10:04 AM, Hesham Moustafa
> <heshamelmatary at gmail.com> wrote:
> > Hi all,
> >
> > This year, I am studying MSc (by research) degree at the University of
> York.
> > My thesis proposal title is "REAL-TIME OPERATING SYSTEMS FOR LARGE SCALE
> > MANY-CORE NETWORK-ON-CHIP ARCHITECTURES." Part of this research will
> include
> > some work with RTEMS.
> >
> > That said, I'd appreciate any materials (papers, publications,
> references,
> > tutorials, etc) that might be of help regarding that topic and may or may
> > not relate to RTEMS. I think Sebastian has contributed a lot to this area
> > recently.
> >
> > You may also want to suggest building some simple multi-processor and/or
> > many-core systems that RTEMS currently supports, and how to simulate
> them.
> >
> > Thanks,
> > Hesham
> >
> > _______________________________________________
> > devel mailing list
> > devel at rtems.org
> > http://lists.rtems.org/mailman/listinfo/devel
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.rtems.org/pipermail/devel/attachments/20141027/9c1dff0a/attachment-0002.html>


More information about the devel mailing list