Hi there!

Hi!

I have a weird idea, and I am not familiar enough with graphics hardware to 
decide
whether it's possible or not. So, the question is the following:

Is it possible to use one graphics chip-set to generate image
(ie. to render OpenGl, etc), and an other chip-set to output
the image to a physical output device?

To be more specific, if I add a pvr-350 to my box, then I will have
  - an integrated Intel 965G, which has some decent abilities, but no working 
tv-out, and
  - the ivtv chip on the PVR card, which has a nice TV-out, but no acceleration 
(except for XV)

I know that new video cards can do all kinds of off-screen rendering, so it 
might not
be impossible to use one chip-set to render the stuff, and then transfer the 
image
to the other card.

I have been told about a project called VirtualGL [1,2], which aims
to provide OpenGL capabilities to thin clients, by providing a 'fake' GLX 
extension
on the X server, doing the actual rendering on the server (remotely), and 
transferring
the image back to the xserver via the network.

I think the same thing could be done locally, using much more efficient image
transmission methods. (DMA?)

Is this physically possible?

If yes, how can this be done? Do I have to write a special driver
to "combine" the two devices, or can this be done from user-space?

If this would work, this could (at last for me) kind of remedy all weaknesses
of the PVR-350: coupling the power if the integrated chip-set with the ace video
quality of the PVR-350 would produce a very very nice solution for me.

What do you think?

   Kristof Csillag

[1] http://en.wikipedia.org/wiki/VirtualGL
[2] http://www.virtualgl.org/

_______________________________________________
ivtv-devel mailing list
[email protected]
http://ivtvdriver.org/mailman/listinfo/ivtv-devel

Reply via email to