Since the list has been rather idle lately, I thought it might be wise to make use of this time to do some forward thinking about how we'd like this project to evolve in the future. Some of what I think we should discuss will influence nearer-term decisions, as well as set us up to handle contingencies as technologies evolve.
OGA is a design that many consider to be already a bit long in the tooth. The graphics market has moved on to hardware vertex processing and programmable fragment shaders. What's more, Microsoft has become obsessed with high-end graphics engines to the point that you will not be able to run Windows Vista without a very powerful graphics card. Fortunately for us, Vista is a long ways off, we don't care much about Windows, and the Linux community seems to be taking a much more practical approach to desktop graphics. The fact is, while OGA may be an older architecture, when it's finally produced, it will be done on the latest process technology, so it'll be very fast. And we've designed it looking ahead to the kinds of 3D graphics that is important for Linux desktops. At this point, the OGA feature set is high-end for embedded systems, low-end for games, and about right for desktop use. As sales volumes pick up and OGC prices come down, OGC will become a commodity product, useful for large deployments of Linux desktop systems. Because software support will never end, and the product line will have a long life, integrators will not be afraid to invest in OGC for what they sell. That all being said, some of all of the Linux community will shift over time to wanting to have programmable shaders and hardware vertex processing. With products like OGC1 funding us, we're going to want a piece of the game market. In the shorter term, I can't help but wonder if we couldn't produce a simpler design (probably which runs at a much higher clock rate) that is fully programmable. I personally will have to try not to get distracted by it, but there's no reason why the community couldn't attempt to best the OGA1 design by spec'ing out a programmable architecture. Until the next major OGD-related event, what do you say to spending some time discussing some different ideas? _______________________________________________ Open-graphics mailing list [email protected] http://lists.duskglow.com/mailman/listinfo/open-graphics List service provided by Duskglow Consulting, LLC (www.duskglow.com)
