thatdude90210
Regular
Saw someone mentioned that he's wrong about the A1 label, and that Nvidia uses the A0 for first silicon. So which is it?
Thanks a lot, I almost choked on a sandwich.
NVIDIA GF100 & Friends speculation
- Thread starter Arty
- Start date
If there was only one prototype, you TAPE the demo and show the prototype. I wouldn't waste your time. It seems more likely that what they have in-house isn't terribly photogenic at the moment.
-Dave
EDIT: Oh, I see, that's what you say earlier in that thread. Err, nm
What is written at Fudzilla is accurate
Fudo and i were both there with Drew Henry and Jason Paul (my company is AlienBabelTech [no links posted to there by me]; not Fudzilla)
- they said what Jensen showed "is a production mock-up"
However, they have working silicon of Fermi ... is in their testing setups 'black box', so it is not really "presentable" in a finished videocard
Who really cares if it was a "mock up" or not ?
- Fermi is real and according to the aforementioned Nvidia officials - "It will ship this year" (2009)
It's always funny to see that when pushed PR people grab for lies even when truth is more convenient ... kinda clarifies what PR really is.Who really cares if it was a "mock up" or not ?
PS. just for reference, it was Drew Henry which said that apoppin?
i am not following you.
i did not believe - at the time - what Jensen had in his hand was a "finished" videocard
When i asked that question, there was no hesitation whatsoever on the official's response that it was a mockup
it isn't like they are hiding something. Femi is working and they demoed by using it
EDIT: i think it was actually Jason Paul; but i need to go over my video
Did it?
recursive! :smile:
NVIDIA GF100 pre-release speculation
As I've alluded to in this thread, my bet is nominally = Cypress but 20% faster with PhysX or some other special conditions. Their marquee bench will be B:AA with PhysX and AA and, under those circumstances, they'll say X% faster than Cypress.
My prediction at least.
As I've alluded to in this thread, my bet is nominally = Cypress but 20% faster with PhysX or some other special conditions. Their marquee bench will be B:AA with PhysX and AA and, under those circumstances, they'll say X% faster than Cypress.
My prediction at least.
The 20-30% number has been going around the net since October (if not earlier.) It's not from people "connected to fermi", it's AMD's competitive analysis team and nv's own presentations.
IF some of these prices going around are realistic for the g104 ($500 bucks for a dual gpu verison ?) then surely the radeon 5870 is going to be much cheaper to make than the $380 they are currently charging for it.
So i don't see amd shying away from a price war in which they will surely win with nvidia.
How do you validly compare B:AA performance with PhysX unless they allow AMD to use GPU accelerated PhysX? Or are you saying that even with PhysX and all other settings the same, it will be 20% faster still? Therefore given PhysX load, it will actually be considerably faster without it, in which case wouldn't they use the faster value as a comparison? Unless somehow they now get PhysX processing for free?
http://www.youtube.com/watch?v=6RdIrY6NYrM looks like patched ver of Supersonic Sled demo, dude overs talk it's run on one card, also he show wireframe, boys body fully whyte so there good level of tesselation, environment tesselation is adapted and looks good. So if there 8x AA it's pretty fast for one card especially compare to relatively slow Unigine DX11 tess demo and Froblins
Similar threads
