[Arm-netbook] xilinx zynq-7000 800mhz ARM Dual-Core Cortex A9

[Gordan Bobic]

On 08/20/2011 12:12 PM, Luke Kenneth Casson Leighton wrote:
> On Sat, Aug 20, 2011 at 2:35 AM, Guillaume FORTAINE<gfortaine at live.com>  wrote:
>> Hello,
>>
>>> absolutely no graphics, whatsoever. none. nada. zip.
>>
>> http://wiki.opengraphics.org/tiki-index.php
>
>   ooo.  yes.  of course.  they're using the spartan XC3S4000, which is
> appx equivalent to 4 million gates (65k logic cells).  the 7030 is
> 125k logic cells (appx equivalent to 2 million gates).
>
>   and the advantage over the XC3S4000 is, it's in 28nm so it'll be
> smaller.  still a monster, but smaller.

The other thing to consider here is whether we actually need 3D 
acceleration on the ARM GPU at the moment. Sure, it's handy for 
phone/slate gaming, but that's a very limited use case. For server use 
we don't need a GPU at all (serial consile a-la SheevaPlug is 
sufficient), and for 99% of desktop use, you only need simple frame 
buffer, possibly with very basic acceleration just to get the Window 
manager performing well enough for LibreOffice. That covers all normal 
business use.

If you want to extend to a bit of entertainment use, then some DSP to 
get HD video playback is nice to have but for the large chunk of that 
use-case you are at Adobe's mercy WRT getting libflash.so ported.

So opengraphics are actually a pretty decent idea, but in the ideal 
world the ARM coupled GPU should be optimized for minimum power (Tegra2 
is pulling about 3W flat out, so with a basic 2D GPU you shouldn't be 
aiming for more than 2.5W at most). Whether opengraphics can achieve 
that - I have no idea. And then on top of that, assuming it is viable in 
terms of power draw, there needs to be an ARM licencee that is willing 
to go down this route for the GPU of their SoC - let's not forget we are 
talking here about a SoC that nobody has actually designed yet.

It's a nice pipe dream, but I'm not going to hold my breath for such a 
thing to actually happen.

Gordan