[Open-graphics] bootstrapping the video mode

[Nicolas Boulay]

That's the first step. After you have to deal with the fact : is it
more important to have a dedicated controler that could be tricky to
use, or general processing unit less specialised but more versatil so
easier to programm ?

For example, you could use the coprocesseur interface of the LEON to
add some specific instruction. If a 32 cpu is to big, 8 bits one could
do the job. Some ASM programm still exist for it.

2006/8/3, Timothy Miller <theosib at gmail.com>:
> On 8/3/06, Nicolas Boulay <nicolas.boulay at gmail.com> wrote:
> > Such a cpu is tiny compare to the reste of the GPU in terme of space.
> > It offer great flexibility and provide means to correct some hardware
> > bug and adding some feature that could be very complexe and slow in
> > pure hardware.
> >
>
> I'm thinking about returning to the nanocontroller idea for VGA (and
> saying so-what to the massive latency for VGA reads).  Some VGA stuff
> could possibly require specialized assist hardware, but the majority
> of it could be done in software.  This controller could run
> double-duty for a number of other purposes.
>
> We would give this processor access to graphics memory and some user
> I/O signals, at least.  VGA accesses would cause interrupts.  We could
> also give it access to the GPU and the DMA contoller.
>