On 3/17/07, Carlo Salinari <[EMAIL PROTECTED]> wrote:
Timothy Normand Miller wrote:
> It won't be long before we'll have to design a nanocontroller for OGD1
> to manage VGA and DMA. I may be able to just go off and design one
> myself, but I think that many of you would fancy observing and
> participating in the design process, and with more brains on it, we'd
> do a better job.
Apart for the unquestionable fun-factor, why not considering one of the
many riscS at opencores? Some of them are already considered
production-quality (e.g. openrisc 1000). I also remember having seen a
free reduced-size implementation of sun's open niagara chip somewhere.
It could be worth a look.
I've had a look at some opencores stuff, and the quality varies
widely. Some stuff looks like it's been engineered well, while a lot
of it looks like it might work in simulation, but it's never been
tried for synthesis.
In any case, we're not looking for a general-purpose CPU. A toy 8-bit
processor would be insufficient for our needs, while a
production-quality 32-bit processor would be over-kill. At this time,
however, we're doing a needs analysis. Whatever my conception is now,
it's sure to change, so we'll see.
Also, it's been pointed out that we might be able to conform to an
existing ISA. You never want to start there, but if, in the end, we
can make it conform (same bitfields in the instructions, subset of the
instructions), then it'll be easier to adapt GCC to compile for us.
On the other hand, with only 512 words of program memory, we're
probably going to almost always use carefully-tuned assembly.
--
Timothy Normand Miller
http://www.cse.ohio-state.edu/~millerti
Favorite book: The Design of Everyday Things, Donald A. Norman, ISBN
0-465-06710-7
_______________________________________________
Open-graphics mailing list
[email protected]
http://lists.duskglow.com/mailman/listinfo/open-graphics
List service provided by Duskglow Consulting, LLC (www.duskglow.com)
