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
