New Pi Quad Core

[Alan Cudmore]

RPI 2 should not be that bad:
I changed the peripheral register base in raspberrypi.h, changed the
compilation arch flags, commented out the mmu init call, and some samples
seem to work.

I ran ticker and paranoia

Alan


On Thu, Mar 5, 2015 at 7:42 PM, <alan.cudmore at gmail.com> wrote:

>  I think this will be possible. I just tried a few bare metal assembly
> demos on the Pi A+ and Pi2 and it looks like even without the published CPU
> datasheet, they have things figured out.
>
> For example: An assembly SMP NEON fractal demo:
>
> https://github.com/PeterLemon/RaspberryPi/tree/master/SMP/NEON/Fractal/Julia
>
> Another interesting thing: The same SD card firmware works for both the Pi
> and Pi2. The Pi2 boots kernel7.img, and the pi looks for kernel.img.
>
>
> Alan
>
>
> *From:* Joel Sherrill <joel.sherrill at oarcorp.com>
> *Sent:* ‎Thursday‎, ‎March‎ ‎5‎, ‎2015 ‎1‎:‎42‎ ‎PM
> *To:* rtems-devel at rtems.org <devel at rtems.org>, Alan Cudmore
> <alan.cudmore at gmail.com>
>
> Hi
>
> I am going to go back on what I said earlier. The online discussion
> seems to indicate that the BCM2836 has the same peripherals
> as the BCM2835 on the previous Pi Models. But they are at
> physical address 0x3F000000 rather than the 0x20000000.
> The CPU core is a different ARM level.
>
> Since people are having luck on the net and the source
> for Linux can always be consulted if there are specific
> register issues we can't figure out, I *THINK* that a
> BSP variant for this makes sense as a GSoC project.
>
> That would be an additional project to bring up the single
> core as step 1, support SMP and test drivers done on other
> single core Pi project. Maybe by the end of the summer ,
> both can be supported with the same driver set.
>
> --
> Joel Sherrill, Ph.D.             Director of Research & Development
> joel.sherrill at OARcorp.com        On-Line Applications Research
> Ask me about RTEMS: a free RTOS  Huntsville AL 35805
> Support Available                (256) 722-9985
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.rtems.org/pipermail/devel/attachments/20150305/ab4f98eb/attachment-0002.html>