If those were truly reports (eg: substantiated vs rumor), they'd have been backed up with some kind of proof vs sounding like more mere speculation. Let's be realistic here, you can't say the demo was run on a GT200 unless you know it was without sounding just as deceitful as you're accusing them of being.
No idea. I find it fascinating that you're getting so defensive over a passing comment. :) I don't know what was in that system, I don't think anyone aside from that person who built it really knows... or the bosses, at any rate. We're in no position to be guessing. Given that this is the discussion thread for GT300, I bought it up as it's been mentioned in other places. :)
In all of this what is perhaps most absurd though is despite it now being rather obvious Fermi and Tesla are aimed at HPC vs gaming, many including some of the more knowledgeable here are still clinging to the idea of using Fermi for gaming. Do you really think after what you've heard that any card with a Fermi is going to be anywhere near consumer grade affordable or well driver supported for games?
They're going to be based on the same silicon? Which would imply that at least to some level, a Fermi card could be used for gaming.
The drivers would be optimised for CAD/CAM/3D/GPGPU, rather than gaming, but I've seen people cross-flash workstation card BIOSes onto equivalent consumer cards for years because it's a cheap way of getting the more stable workstation-class drivers (and featureset). I'm sure it could be done in reverse, but there is no reason to (and plenty of reasons not to)...
How many times does it have to be said, JUNIPER is going to be the consumer level chip. Regardless of how long it actiually takes Fermi to hit the market, we may see a scaled down GPU with all the gaming power and none of the HPC power before that happens at a much lower price.
Juniper is the codename for ATi's baby Cypress chip, or the Radeon 5700 series cards. I'm a bit lost as to the relevance of that bit?
I tell ya man, I'm really getting sick of the angst here over nothing more than what is mostly speculation. I thought people on this forum were more intelligent than that. It just goes to show that even some of the smarter consumers lose their heads when they don't look at things from a business perspective. :roll:
What angst? I thought this was a discussion. Since what little information is in the public domain is mostly FUD (and the little that has been stated as 'true' by nVidia has a fair amount of healthy scepticism served with it) then this sort of "Oh, what if..." is normal.
What I am most impressed about is the way that here has been discussing it rationally, rather than the rabid fanboyism that I've seen in a lot of other places. Or, at least, I thought we were discussing it rationally until that last bit. As I said, it's an absolute joke seeing otherwise intelligent individuals getting so het up about this. We saw it on G80's release, and GT200's, and R600's, and RV770's... Core 2's, Prescotts, Phenoms', Phenom II's... etc etc etc... 'twill never end. And it's all the funnier because of that. ;)
I know a couple of chaps who would probably kill for that real-time ray-tracing, though. I think I know what a couple of grant applications in the new year will contain... 8)
...
...
whismerhill - thanks for that hareware.fr translation. I don't really remember enough about how nVidia clocks it's shaders to be able to comment on whether that 1.6GHz is conservative or not. The comparison against Cypress (Radeon 5870) is interesting, though - it's been seen before in both nVidia and ATi architectures that numerical advantages don't always equal actual performance advantages.
...
Unless something amazing crops up about GT300, I'm gonna sit back and watch how it develops. :)