NVIDIA GF100 & Friends speculation

[Ninjaprime]

Going back to my question a few pages back, is there any word on the final clocks of GTX 4x0 cards ?

GTX 470 appears to be 625/1250 with 800mhz mem, from leaks of people who have early cards. GTX 480 is still up in the air.

 

[Kaotik]

GTX 470 appears to be 625/1250 with 800mhz mem, from leaks of people who have early cards. GTX 480 is still up in the air.

Though the latest leak from czech, with screenshots, put 470 memories to 1000MHz instead of 800MHz

 

[onethreehill]

Zotac planning GeForce GTX 480 AMP! version
http://www.nordichardware.com/en/co...tac-planning-geforce-gtx-480-amp-version.html

 

[Silent_Buddha]

Though the latest leak from czech, with screenshots, put 470 memories to 1000MHz instead of 800MHz

It'll be interesting if that move puts it closer to 5870 in some benchmarks...

Regards,
SB

 

[onethreehill]

NVIDIA Explains Fermi GTX 470 and GTX 480 Delay
We redesigned GF100 from the ground up to deliver the best performance on DX11. This meant adding dedicated h/w engines in our GPU to accelerate key features like tessellation. We also made changes on the compute side that specifically benefit gamers like interactive ray-tracing and faster physics performance through things like support for concurrent kernels. Unfortunately all of these changes took longer than we originally anticipated and that’s why we are delayed. Do we wish we had GF100 today? Yes. However based on all the changes we made will GF100 be the best gaming GPU ever built. Absolutely.

http://news.softpedia.com/news/NVIDIA-Explains-Fermi-GTX-470-and-GTX-480-Delay-137157.shtml

 

[mczak]

Yes, x86 micro-ops can be changed without changing the ISA. But changing the micro-ops substantially requires a new microarchitecture, which Fermi is. The changes in Fermi's ISA were not done for cosmetic reasons. Nvidia didn't commit itself to writing a new compiler for Fermi just for fun, instead it was required due to a deep rethinking of what the processor should do.

Oh, I don't doubt they didn't do it just for fun. But since we don't know what the ISA looks like (or do we?) we have no idea how substantially it was changed. It might have been possible the encoding misses a (now) vital bit somewhere, and things needed to be readjusted just for that (not saying that's the case, just why an incompatible ISA doesn't mean it really has to be changed substantially).

The claims that Fermi is just a warmed over GT200 are ludicrous.

Yeah. If you really call it new architecture is probably still depending on the view, but it is certainly substantially different.

 

[Silent_Buddha]

http://news.softpedia.com/news/NVIDIA-Explains-Fermi-GTX-470-and-GTX-480-Delay-137157.shtml

PR fluff piece, considering it doesn't even mention one of the main reasons why it's so delayed. TSMC 40 nm woes.

Regards,
SB

 

[onethreehill]

http://www.tomshardware.com/news/palit-nvidia-geforce-fermi-gf100,9860.html

 

[Kowan]

Their box art looks like they are going for a Harley V-Twin/air cleaner look.

 

[Ailuros]

Stay tuned for the next exciting episode of the Time-to-Market and The-Rich-Feature,only here, on your favourite GPU soap opera source, B3D

SB: I think Fermi definitely has some Rampage tech. GigaPixel too. Oh, and it's pretty clear that the incredibly awesome never before seen utterly bombastic tessellation performance is due to them using Sage...think of it, that's why it's ~3 bln transistors!

*wears his mojo boots and kicks administrator*

 

[onethreehill]

Ready to ship?

http://forums.vr-zone.com/news-around-the-web/578723-inno3d-geforce-gtx-480-cards-ready-ship.html

 

[Lux_]

Specsfree box is a safe bet. The potential market already knows the specs by the time these boxes are on the shelves.

 

[eastmen]

and that is all the working gtx 480 and 470 that company will ever see......

Naaaa but kinda funny whats in that box 3 480s and 2 470s.

 

[igg]

Specsfree box is a safe bet. The potential market already knows the specs by the time these boxes are on the shelves.

I'm pretty sure the specs are on the back.

 

[eastmen]

http://www.fudzilla.com/content/view/18038/1/
Dual Fermi can be expected hopefully towards the end of Q2 2010 and the high thermal dissipation and complexity of cards are few reasons for this postponement. Nvidia would definitely like to have dual cards out, but it might take a little while before it happens.

A good news is that mainstream and entry level Fermi versions should be coming this summer, slightly delayed from its original plan, but for the Dual card, it’s not certain when should it happen. Nvidia is not telling much to us or its partners either.

End of q2 is what July ?

Also if Nvidia isn't shipping main stream fermi cards till summer , it looks like ati has plenty of time to make money off the $50-$300 market.

 

[Psycho]

Just seems like fudo trying to keep up his own dual-fermi idea, without anything behind it. I think you forgot this part of the quoute:

It looks like dual Fermi won’t be coming anytime soon. A few partners have said that at this time they are not aware that there will be a dual Fermi card

 

[rpg.314]

Just seems like fudo trying to keep up his own dual-fermi idea, without anything behind it. I think you forgot this part of the quoute:

IMHO, not gonna happen without a shrink.

 

[Florin]

So far we've seen box art from Gigabyte, Galaxy, Palit and inno3d, colorful, anything else?

How does this mesh with the rumour that there will be 3 larger OEMs and 1 smaller who will have cards available at the March launch date, and where are Evga and XFX in all of this?

 

[jaredpace]

So far we've seen box art from Gigabyte, Galaxy, Palit and inno3d, colorful, anything else?

evga

 

[neliz]

So far we've seen box art from Gigabyte, Galaxy, Palit and inno3d, colorful, anything else?

How does this mesh with the rumour that there will be 3 larger OEMs and 1 smaller who will have cards available at the March launch date, and where are Evga and XFX in all of this?

XFX won't have any cards. Inno3D doesn't do Europe as far as I know as well.