GF100 (Fermi) previews and discussion

[sabot00]

As a dev it's simply interesting if nVidia holds to its words & lets Fermi run C++ naively.

 

[gamerk316]

As a dev it's simply interesting if nVidia holds to its words & lets Fermi run C++ naively.

As I understand it, they implemented the SDL libaries; I don't know about other extensions (MFC, etc). I'm more interested in the native Fortran, as I've got a ton of old code my company needs to run...

 

[xizorgetspeed]

Any further update on retail release? Or are we still hoping for mid to late march release.

 

[sabot00]

No updates.

 

[willmarth2]

When will the first cards come out?

 

[strangestranger]

What do you want me to use first, the chicken entrails or the tarot cards?

 

[Mousemonkey]

What do you want me to use first, the chicken entrails or the tarot cards?

Could you not use a lower life form than a chicken though? An MP perhaps or a traffic warden?

 

[strangestranger]

After what I have been doing to it recently it is practically begging to die anyway.

 

[Mousemonkey]

:lol: No comment!

 

[JAYDEEJOHN]

Maybe nVidia needs to do what ATI is doing:
In the past ATI would always try to accommodate new features and customer requests. But the R5xx changes meant that if a feature was going to push the schedule back, it wasn’t making it in. Recently Intel changed its design policy, stating that any feature that was going into the chip had to increase performance by 2% for every 1% increase in power consumption. ATI’s philosophy stated that any feature going into the chip couldn’t slip schedule. Prior to the R5xx generation ATI wasn’t really doing this well; serious delays within this family changed all of that. It really clamped down on feature creep, something that’s much worse in hardware than in software (bigger chips aren’t fun to debug or pay for).

http://anandtech.com/video/showdoc.aspx?i=3740&p=2

 

[witcherx]

Lol,, I wonder why everyone is goin gaga on fermi.... Its no more... You all will soon see it.. And i ll bet some Nvidia fanboy moderator will remove this post. haha. 😛

 

[witcherx]

http://anandtech.com/video/showdoc.aspx?i=3740&p=2

Yeah I jst read that very intresting. Nvidia is goin to Copy cat this and market as if its thier proprietory..
Fermi = CLOSED(.)

 

[Mousemonkey]

Lol,, I wonder why everyone is goin gaga on fermi.... Its no more... You all will soon see it.. And i ll bet some Nvidia fanboy moderator will remove this post. haha. 😛

Any chance of you breaking with ATi Troll tradition and modus operandi by providing factual evidence to back up your claims?

 

[witcherx]

Hey I know that what i posted is troll.. Just like to poke @ some of the Fanboys. But I have read that they are moving over from Fermi to some other brand.

 

[Mousemonkey]

Fermi is not a brand it's just a codename.

 

[RealityRush]

Hey I know that what i posted is troll.. Just like to poke @ some of the Fanboys. But I have read that they are moving over from Fermi to some other brand.

Bulls.h.i.t you have. And you better hope that there is a Fermi because otherwise there will basically be an ATI monopoly with ridiculous prices for a while, whether it is retailers doing it or ATI.....

 

[Dekasav]

I'm generally an AMD fan, and I support the banning of witcherx. I even loved "The Witcher."

I await Fermi so people will quit saying ATI overpriced the HD 5xxx series. Oh, and so I can see how the juicy new tech works out (new cores, those two new engines they're using, etc.)

 

[sabot00]

5850 - $299
GTX 280 - $349
GTX 285 - $389

 

[gamerk316]

^^ And? Frankly, based on what I've read on Fermi (specifically, how much easier it is to scale downward), I would expect lower prices for lower-tier offerings then NVIDIA has offered in the past. And if performance numbers are true, NVIDIA could easily offer the top tier models for ~$399, competitive on price/performance with the 5870/5970

 

[EXT64]

It will be interesting to see where they price their new cards, as they said they would try to price them more competitively from the start this time. In this economy and with the trouble both have been having, I don't think either wants to be giving their cards away. I wouldn't be surprised if the prices of both brands stay higher than we are hoping for.

 

[poul]

You might be right about the price/performance issue. But there is at least one but more, the performance per watt issue. Hemloch is Evergreen on the limmit, where is Fermi on the limmit? Loosing that one is going to be terrible, but if they win or even, they are okay.

 

[JAYDEEJOHN]

If they knew theyd be released last, then theyd know how much to price them at, which means little when they say itll be more competitively priced than the 650$ 280 that was 10-20% faster than the 300$ 4870.
The Fermi costs will be high, as their yields are terrible and their size is huge, and until theyre cut down below half size, they wont be very competitive price wise, as theyll still have to use a full chip.

 

[JAYDEEJOHN]

http://www.nvidia.com/content/PDF/fermi_white_papers/NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf

 

[JAYDEEJOHN]

Nvidia's Fermi GTX480 is broken and unfixable
Hot, slow, late and unmanufacturable
http://www.semiaccurate.com/2010/02/17/nvidias-fermigtx480-broken-and-unfixable/

Hope hes wrong this time

 

[RealityRush]

Nvidia's Fermi GTX480 is broken and unfixable
Hot, slow, late and unmanufacturable
http://www.semiaccurate.com/2010/02/17/nvidias-fermigtx480-broken-and-unfixable/

Hope hes wrong this time

Eh, questioning nVidia's engineers seems like folly to me. nVidia is run by some egotistical people, absolutely, but saying "they didn't do their homework" is retarded. I doubt that would be an issue with their experienced engineers.

I've always hoped Charlie was wrong though, because him being right equates to a lop-sided graphics industry that he seems to pine for >.<